> ## Documentation Index > Fetch the complete documentation index at: https://docs.noxus.ai/llms.txt > Use this file to discover all available pages before exploring further. # Refresh Message ## OpenAPI ````yaml post /v1/conversations/{conversation_id}/messages/{message_id}/refresh openapi: 3.1.0 info: title: Noxus Backend description: >- Backend API for the Noxus Platform. More information can be found at https://docs.noxus.ai version: 1.1.0 servers: [] security: [] paths: /v1/conversations/{conversation_id}/messages/{message_id}/refresh: post: tags: - V1 - Conversations summary: Refresh Message operationId: refresh_message parameters: - name: conversation_id in: path required: true schema: type: string format: uuid title: Conversation Id - name: message_id in: path required: true schema: type: string title: Message Id - name: assistant_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Assistant Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SdkConversationWithMessages' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: SdkConversationWithMessages: properties: id: type: string format: uuid title: Id user_id: anyOf: - type: string format: uuid - type: 'null' title: User Id api_key_id: anyOf: - type: string format: uuid - type: 'null' title: Api Key Id name: anyOf: - type: string - type: 'null' title: Name created_at: type: string format: date-time title: Created At last_updated_at: type: string format: date-time title: Last Updated At etag: anyOf: - type: string - type: 'null' title: Etag settings: $ref: '#/components/schemas/CoWorkerSettings-Output' assistant_id: anyOf: - type: string format: uuid - type: 'null' title: Assistant Id status: $ref: '#/components/schemas/RunStatus' manual: type: boolean title: Manual default: false preview: type: boolean title: Preview default: false assistant_version_id: anyOf: - type: string format: uuid - type: 'null' title: Assistant Version Id chat_transport: anyOf: - type: string - type: 'null' title: Chat Transport channel_ref: anyOf: - additionalProperties: true type: object - type: 'null' title: Channel Ref deployment_id: anyOf: - type: string format: uuid - type: 'null' title: Deployment Id public_access_token: anyOf: - type: string - type: 'null' title: Public Access Token todos: items: additionalProperties: true type: object type: array title: Todos default: [] is_locked: type: boolean title: Is Locked default: false lock_message: anyOf: - type: string - type: 'null' title: Lock Message messages: items: $ref: '#/components/schemas/Message' type: array title: Messages vercel_messages: items: $ref: '#/components/schemas/UIMessage' type: array title: Vercel Messages default: [] type: object required: - id - user_id - api_key_id - name - created_at - last_updated_at - etag - settings - status - messages title: SdkConversationWithMessages description: >- ConversationWithMessages for the public SDK — strips TipTap from settings. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError CoWorkerSettings-Output: properties: pii_banner: type: string title: Pii Banner description: Information about PII anonymization default: '' accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false style: info type: banner tab: Model tool_mode: hidden visible: false pii_info: type: string title: Pii Info description: Information about PII anonymization default: '' accordion: Safety display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: Choose which PII types to anonymize. title: PII Anonymization Settings type: ui_text_display tab: Model tool_mode: hidden visible: false pii_lock: type: boolean title: Pii Lock description: Information about the guardrails default: false accordion: Safety display: col_align: start col_justify: end col_span: 2 icon: Unlock is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false toggledIcon: Lock tooltip: Lock PII settings so they cannot be changed type: toggle_button tab: Model tool_mode: hidden visible: false pii_anonimization: items: additionalProperties: type: string type: object type: array title: Pii Anonimization description: Preferred anonymization method for PII values. default: - value: PERSON label: Name - value: EMAIL_ADDRESS label: Email - value: PHONE_NUMBER label: Phone Number - value: CREDIT_CARD label: Credit Card accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Anonymize PII needs_confirmation: false show_optional_label: false type: multi_select values: - label: Person value: PERSON - label: Email Address value: EMAIL_ADDRESS - label: Phone Number value: PHONE_NUMBER - label: Credit Card value: CREDIT_CARD - label: Cryptocurrency value: CRYPTO - label: IP Address value: IP_ADDRESS - label: Date Time value: DATE_TIME - label: NRP value: NRP - label: Location value: LOCATION - label: Medical License value: MEDICAL_LICENSE - label: URL value: URL - label: IBAN Code value: IBAN_CODE rules: - config_source: pii_lock type: disabled_if value: true tab: Model tool_mode: hidden visible: false divider1: type: string title: Divider1 default: '' accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Model tool_mode: hidden visible: false guardrail_info: type: string title: Guardrail Info description: Information about the guardrails default: '' accordion: Safety display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: >- Set the strictness level of guardrails to ensure the AI model's behavior and responses remain safe and appropriate — from 'Off' (no protection) to 'High' (maximum protection). title: Guardrails type: ui_text_display tab: Model tool_mode: hidden guardrail_lock: type: boolean title: Guardrail Lock description: Locks the guardrails settings. default: false accordion: Safety display: col_align: start col_justify: end col_span: 2 icon: Unlock is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false toggledIcon: Lock tooltip: Lock guardrails settings so they cannot be changed type: toggle_button tab: Model tool_mode: hidden visible: false guardrail_latency_banner: type: string title: Guardrail Latency Banner description: '' default: '' accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: >- Each enabled guardrail makes its own LLM call before the model can reply. Expect noticeably slower responses while any of these are on. needs_confirmation: false show_optional_label: false style: warning title: Guardrails add response latency type: banner rules: - conds: - config_source: violence_and_hate type: visible_if_not value: 'Off' - config_source: sexual_content type: visible_if_not value: 'Off' - config_source: guns_and_weapons type: visible_if_not value: 'Off' - config_source: suicide type: visible_if_not value: 'Off' - config_source: crime type: visible_if_not value: 'Off' - config_source: toxicity type: visible_if_not value: 'Off' - config_source: bias type: visible_if_not value: 'Off' - config_source: profanity type: visible_if_not value: 'Off' - config_source: jailbreak type: visible_if value: true - config_source: prompt_injection type: visible_if value: true mode: or type: visible_if_group tab: Model tool_mode: hidden violence_and_hate: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a news agency — reporting on conflict zones is expected and should not be flagged. is_disabled: false is_subconfig: false label: Violence and Hate needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden sexual_content: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is an airline booking system — mentions of children traveling are normal and should not be flagged. is_disabled: false is_subconfig: false label: Sexual Content needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden guns_and_weapons: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a sporting goods store — discussion of hunting equipment is expected. is_disabled: false is_subconfig: false label: Guns and Illegal Weapons needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden suicide: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a mental health support platform — discussing symptoms is expected and should not be blocked. is_disabled: false is_subconfig: false label: Suicide and Self-Harm needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden crime: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a legal firm assistant — discussing criminal cases and charges is part of normal operation. is_disabled: false is_subconfig: false label: Crime and Criminal Planning needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden toxicity: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a gaming community moderator — competitive banter and trash talk is normal. is_disabled: false is_subconfig: false label: Toxicity needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden bias: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This assistant serves a diversity and inclusion team — discussing demographic differences is expected. is_disabled: false is_subconfig: false label: Bias needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden profanity: $ref: '#/components/schemas/GuardrailValue' default: value: 'Off' context: '' accordion: Safety display: accordion_label: Additional context col_span: 12 context_placeholder: >- E.g. This is a content moderation tool — quoting flagged content for review is expected. is_disabled: false is_subconfig: false label: Profanity needs_confirmation: false off_value: 'Off' show_optional_label: false type: guardrail_card values: - 'Off' - Low - Medium - High rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden guardrails_scan_output: type: boolean title: Guardrails Scan Output description: >- Scan the model's response with the same semantic guardrails applied to input. Catches sensitive content sourced from Knowledge Base documents or tools that the input scan cannot see. default: false accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Scan responses (output guardrails) needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden guardrails_output_mode: type: string enum: - post_stream - pre_stream title: Guardrails Output Mode description: >- How output guardrails are enforced. 'post_stream' streams the response in real-time and warns/clears after the fact. 'pre_stream' buffers the full response, validates it against guardrails, and only emits it if it passes. default: post_stream accordion: Safety display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: true is_subconfig: false label: Output guardrail mode needs_confirmation: false show_optional_label: false type: select values: - label: Post-stream (warn after response) value: post_stream - label: Pre-stream (validate before showing) value: pre_stream rules: - config_source: guardrail_lock type: disabled_if value: true - config_source: guardrails_scan_output type: visible_if value: true tab: Model tool_mode: hidden divider2: type: string title: Divider2 default: '' accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Model tool_mode: hidden guardrail_action: anyOf: - additionalProperties: type: string type: object - type: string title: Guardrail Action description: Choose the action to take when a guardrail is triggered. default: value: fail label: Fail/block run accordion: Safety display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: true is_subconfig: false label: Guardrail action needs_confirmation: false show_optional_label: false type: select values: - label: Fail/block run value: fail - label: Flag with warning but proceed value: flag rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden visible: false guardrail_action_replace: type: string title: Guardrail Action Replace default: '' accordion: Safety display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Replace with needs_confirmation: false number_of_lines: 1 placeholder: E.g. show_optional_label: false show_refresh: false type: text rules: - config_source: guardrail_action type: visible_if value: replace - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden visible: false guardrail_action_human: type: string title: Guardrail Action Human default: '' accordion: Safety display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: true label: Human task template needs_confirmation: false number_of_lines: 1 placeholder: E.g. show_optional_label: false show_refresh: false type: text rules: - config_source: guardrail_action type: visible_if value: human - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden visible: false block_after_violations: type: integer title: Block After Violations description: >- Block the chat after this many turns with guardrail violations. Set to 0 to never block (per-turn warnings still surface). default: 0 accordion: Safety display: col_span: 12 hide_number: false is_disabled: false is_subconfig: false label: Block chat after N violations max: 20 min: 0 needs_confirmation: false show_optional_label: false step: 1 tooltip: >- Once a conversation accumulates this many turns with any guardrail violation (flag or fail mode), the chat input locks. Set to 0 to disable. type: number_slider rules: - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden block_message: type: string title: Block Message description: Message shown to the user when the chat is locked. default: >- This conversation has been locked due to repeated safety violations. Please start a new conversation. accordion: Safety display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: true label: Block message needs_confirmation: false number_of_lines: 1 placeholder: >- This conversation has been locked due to repeated safety violations. show_optional_label: false show_refresh: false type: text rules: - config_source: block_after_violations type: visible_if_not value: 0 - config_source: guardrail_lock type: disabled_if value: true tab: Model tool_mode: hidden divider3: type: string title: Divider3 default: '' accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Model tool_mode: hidden visible: false prompt_defense: type: string title: Prompt Defense default: '' accordion: Safety display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: >- Configurations to ensure the model behaves as expected and is protected against attacks, like jailbreak or prompt injection. title: Prompt Defense type: ui_text_display tab: Model tool_mode: hidden prompt_lock: type: boolean title: Prompt Lock description: Locks the prompt defense settings default: false accordion: Safety display: col_align: start col_justify: end col_span: 2 icon: Unlock is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false toggledIcon: Lock tooltip: Lock prompt settings so they cannot be changed type: toggle_button tab: Model tool_mode: hidden visible: false jailbreak: type: boolean title: Jailbreak description: >- Prevents attempts to manipulate or "jailbreak" the model into ignoring safety rules or system instructions (e.g., prompts like "ignore previous instructions"). default: false accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Jailbreak needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: prompt_lock type: disabled_if value: true tab: Model tool_mode: hidden prompt_injection: type: boolean title: Prompt Injection description: >- Detects and blocks strategies where users attempt to get around restrictions indirectly (e.g., asking the model to 'pretend' or speak as a fictional character to evade policies). default: false accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Prompt Injection needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: prompt_lock type: disabled_if value: true tab: Model tool_mode: hidden context_leak: type: boolean title: Context Leak description: >- Prevents the model from unintentionally revealing internal context, instructions, or system messages that are not meant to be shared with the user. default: false accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Context Leak needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: prompt_lock type: disabled_if value: true tab: Model tool_mode: hidden visible: false auto_model_pick: type: boolean title: Auto Model Pick description: AI selects the optimal model for performance, cost savings or length default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Smart model selection needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Model tool_mode: hidden visible: false auto_model_preference: type: string title: Auto Model Preference default: cost display: can_wrap: true col_span: 12 endpoint: /models/llms is_disabled: false is_multi: false is_subconfig: true needs_confirmation: false show_optional_label: false type: select_chips values: - custom_fields: icon: gauge label: Performance value: performance - custom_fields: icon: dollar label: Cost value: cost - custom_fields: icon: text label: Length value: length optional: true tab: Model tool_mode: hidden visible: false model: items: type: string type: array title: Model description: Model configuration default: - preset:cost display: col_span: 12 default_preset: cost endpoint: /models/llms hide_disabled_models: true is_disabled: false is_subconfig: true label: Choose from our recommended models layout: side_by_side model_type: text needs_confirmation: false show_inline_presets: true show_optional_label: false show_presets: false type: model_select optional: true tab: Model tool_mode: hidden parameter_preset: type: string enum: - default - creative - precise - custom title: Parameter Preset description: >- Controls randomness, diversity, and repetition of the model's output. default: default accordion: Model Parameters display: button_size: sm button_variant: outline col_span: 12 is_disabled: false is_horizontal: true is_subconfig: false label: Model parameters preset needs_confirmation: false show_optional_label: false type: menu_select values: - description: Provider-recommended settings for general use icon: settings2 label: Default value: default - description: Higher randomness for diverse, imaginative outputs icon: sparkles label: Creative value: creative - description: Deterministic and focused for factual tasks icon: target label: Precise value: precise - description: Fine-tune each parameter manually icon: sliders-horizontal label: Custom value: custom rules: - target_fields: - temperature - top_p - top_k - presence_penalty - frequency_penalty type: sets_field_values value_map: creative: frequency_penalty: 0.3 presence_penalty: 0.3 temperature: 0.7 top_k: 40 top_p: 0.95 custom: {} default: {} precise: frequency_penalty: 0 presence_penalty: 0 temperature: 0 top_k: 5 top_p: 0.1 tab: Model tool_mode: hidden intro: type: string title: Intro default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: >- Fine-tune the selected model's behavior with advanced controls. Not all of the settings apply to all models. type: ui_text_display rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden basic_params_section: type: string title: Basic Params Section default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: >- Control the model's output length, randomness, and response time limits. title: Basic parameters type: ui_text_display rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden max_tokens: type: integer title: Max Tokens description: The maximum number of tokens per request default: 64000 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Max tokens max: 128000 min: 0 needs_confirmation: false show_optional_label: false step: 100 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden temperature: type: number title: Temperature description: The temperature of the model default: 0.7 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Temperature max: 1 min: 0 needs_confirmation: false show_optional_label: false step: 0.01 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden top_p: type: number title: Top P description: The top P of the model default: 1 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Top P max: 1 min: 0.01 needs_confirmation: false show_optional_label: false step: 0.01 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden top_k: type: integer title: Top K description: The top K of the model default: 40 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Top K max: 100 min: 1 needs_confirmation: false show_optional_label: false step: 1 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden timeout: type: number title: Timeout description: The base timeout of the model default: 120 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Timeout max: 600 min: 1 needs_confirmation: false show_optional_label: false step: 1 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden divider_7: type: string title: Divider 7 default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden penalty_section: type: string title: Penalty Section default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: >- Adjust penalties and stop sequences to control the model's generation. title: Generation control type: ui_text_display rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden presence_penalty: type: number title: Presence Penalty description: The presence penalty of the model default: 0.3 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Presence penalty max: 2 min: -2 needs_confirmation: false show_optional_label: false step: 0.1 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden frequency_penalty: type: number title: Frequency Penalty description: The frequency penalty of the model default: 0.6 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Frequency penalty max: 2 min: -2 needs_confirmation: false show_optional_label: false step: 0.1 type: number_slider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden stop_sequences: items: type: string type: array title: Stop Sequences description: >- The model will stop generating text when it encounters any of these stop sequences default: [] accordion: Model Parameters display: chips_are_closable: false col_span: 12 hide_toolbar: false is_disabled: false is_subconfig: false label: Stop sequences needs_confirmation: false show_optional_label: false type: chips_list_text rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden divider_8: type: string title: Divider 8 default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden reasoning_section: type: string title: Reasoning Section default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: >- Configure the model's reasoning capabilities and computational effort level. title: Model reasoning type: ui_text_display rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden enable_reasoning: type: boolean title: Enable Reasoning description: Whether to enable reasoning default: true accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: Enable reasoning needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden reasoning_effort: type: string title: Reasoning Effort description: The reasoning effort of the model default: Low accordion: Model Parameters display: col_span: 12 is_disabled: false is_horizontal: false is_subconfig: false label: Reasoning effort needs_confirmation: false show_optional_label: false type: enum_slider values: - low - medium - high rules: - conds: - config_source: parameter_preset type: visible_if value: custom - config_source: enable_reasoning type: visible_if value: true mode: and type: visible_if_group tab: Model tool_mode: hidden divider: type: string title: Divider default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider rules: - config_source: parameter_preset type: visible_if value: custom tab: Model tool_mode: hidden reliability_section: type: string title: Reliability Section default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: >- Configure retry behavior and fallback options for improved reliability. title: Reliability type: ui_text_display tab: Model tool_mode: hidden max_retries_per_model: type: integer title: Max Retries Per Model description: The maximum number of retries per model default: 3 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Max retries max: 5 min: 0 needs_confirmation: false show_optional_label: false step: 1 type: number_slider tab: Model tool_mode: hidden retry_on_status_codes: items: type: integer type: array title: Retry On Status Codes description: The status codes to retry on default: - 429 - 500 - 502 - 503 - 504 accordion: Model Parameters display: chips_are_closable: false col_span: 12 hide_toolbar: false is_disabled: false is_subconfig: false label: Retry on status codes needs_confirmation: false show_optional_label: false type: chips_list_text tab: Model tool_mode: hidden datacenter_fallback: type: boolean title: Datacenter Fallback description: >- Whether to fallback to a different datacenter of the same model if the current one is down default: true accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: Datacenter fallback needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Model tool_mode: hidden exclude_user_identity_from_prompt: type: boolean title: Exclude User Identity From Prompt description: >- Omit the user's name from the system prompt. Keeps the cached instruction prefix identical across users so it can be reused, and avoids sending user identity to the model. default: false accordion: Advanced display: col_span: 12 is_disabled: false is_subconfig: false label: Exclude user identity from prompt needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Prompt tool_mode: hidden enable_prompt_caching: type: boolean title: Enable Prompt Caching description: >- Cache the stable instruction prefix at the model provider to cut input cost and latency on repeated turns. Disable to send every request uncached. default: true accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: Prompt caching needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Model tool_mode: hidden protect_instructions_in_preview: type: boolean title: Protect Instructions In Preview description: >- Deployed conversations always keep the agent's system instructions, persona, tools, and configuration confidential. Turn this on to also protect them in the preview/dev page — otherwise the safeguard is dropped there so builders can inspect the agent they are configuring. default: false accordion: Safety display: col_span: 12 is_disabled: false is_subconfig: false label: Protect instructions in preview needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: prompt_lock type: disabled_if value: true tab: Model tool_mode: hidden agentflow_enabled: type: boolean title: Agentflow Enabled description: Whether to enable chat flow default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Enable chat flow needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false usage_limits_section: type: string title: Usage Limits Section default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false text: Set limits on resource usage to control costs and prevent overuse. title: Agent usage limits tooltip: Applies to each conversation. type: ui_text_display tab: Model tool_mode: hidden usage_limits_maximum_request: type: integer title: Usage Limits Maximum Request description: The maximum number of requests default: 1000 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Total Max Requests max: 10000 min: 0 needs_confirmation: false show_optional_label: false step: 50 tooltip: Applies to each conversation. type: number_slider tab: Model tool_mode: hidden usage_limits_maximum_tokens: type: integer title: Usage Limits Maximum Tokens description: The maximum number of tokens default: 2000000 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Total max tokens max: 2000000 min: 100 needs_confirmation: false show_optional_label: false step: 500 tooltip: Applies to each conversation. type: number_slider tab: Model tool_mode: hidden usage_limits_max_messages: type: integer title: Usage Limits Max Messages description: The maximum number of messages default: 100 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Total max messages max: 1000 min: 0 needs_confirmation: false show_optional_label: false step: 10 tooltip: Applies to each conversation. type: number_slider tab: Model tool_mode: hidden usage_limits_agent_timeout: type: integer title: Usage Limits Agent Timeout description: The maximum number of seconds the agent can run for default: 120 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Agent timeout max: 600 min: 0 needs_confirmation: false show_optional_label: false step: 1 tooltip: Applies to each message. type: number_slider tab: Model tool_mode: hidden divider_11: type: string title: Divider 11 default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Model tool_mode: hidden compaction_enabled: type: boolean title: Compaction Enabled description: >- Automatically summarize old messages when context limit is approached. default: true accordion: Compaction Settings display: col_span: 12 is_disabled: false is_subconfig: false label: Conversation compaction needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Model tool_mode: hidden compaction_strategy: type: string title: Compaction Strategy description: How to compact conversation history when it grows too long. default: auto accordion: Compaction Settings display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: false is_subconfig: false label: Compaction strategy needs_confirmation: false show_optional_label: false type: select values: - label: Auto (prefer provider-native) value: auto - label: Provider-native only value: provider - label: LLM summarization value: summarization rules: - config_source: compaction_enabled type: visible_if value: true tab: Model tool_mode: hidden compaction_threshold: type: number title: Compaction Threshold description: Fraction of context window that triggers compaction (0.01–0.95). default: 0.75 accordion: Compaction Settings display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Compaction threshold max: 0.95 min: 0.01 needs_confirmation: false show_optional_label: false step: 0.01 tooltip: >- When token usage reaches this fraction of the context window, older messages are summarized. type: number_slider rules: - conds: - config_source: compaction_enabled type: visible_if value: true - conds: - config_source: compaction_strategy type: visible_if value: auto - config_source: compaction_strategy type: visible_if value: summarization mode: or type: visible_if_group mode: and type: visible_if_group tab: Model tool_mode: hidden compaction_tool_enabled: type: boolean title: Compaction Tool Enabled description: Expose a tool that lets the agent request compaction manually. default: false accordion: Compaction Settings display: col_span: 12 is_disabled: false is_subconfig: false label: Compaction tool needs_confirmation: false show_optional_label: false toggle_position: right tooltip: >- When on, the agent can call `compact_conversation` to compact at will. type: toggle rules: - conds: - config_source: compaction_enabled type: visible_if value: true - conds: - config_source: compaction_strategy type: visible_if value: auto - config_source: compaction_strategy type: visible_if value: summarization mode: or type: visible_if_group mode: and type: visible_if_group tab: Model tool_mode: hidden tool_calling_section: type: string title: Tool Calling Section default: '' accordion: Model Parameters display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: Configure how the agent handles tool execution and function calls. title: Tool calling type: ui_text_display tab: Model tool_mode: hidden parallel_tool_calls: type: boolean title: Parallel Tool Calls description: Whether to allow the agent to call multiple tools at the same time. default: true accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: Parallel tool calls needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Model tool_mode: hidden tool_timeout: type: number title: Tool Timeout description: Maximum seconds a single tool call can run before timing out. default: 15 accordion: Model Parameters display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Tool timeout max: 300 min: 1 needs_confirmation: false show_optional_label: false step: 1 tooltip: Per-tool-call timeout. The model retries on timeout. type: number_slider tab: Model tool_mode: hidden visuals_section: type: string title: Visuals Section default: '' display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: >- Control what information is displayed to users during agent interactions. title: Visual preferences type: ui_text_display tab: Display tool_mode: hidden hide_reasoning: type: boolean title: Hide Reasoning description: Whether to hide the reasoning messages default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Hide reasoning messages needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: enable_reasoning type: visible_if value: true tab: Display tool_mode: hidden group_into_chain_of_thought: type: boolean title: Group Into Chain Of Thought description: Group reasoning and tool calls into a collapsible chain of thought default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Group into chain of thought needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Display tool_mode: hidden chain_of_thought_final_answer_only: type: boolean title: Chain Of Thought Final Answer Only description: >- The agent only responds at the end, keeping all intermediate messages in its chain of thought. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Only show the final answer needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: group_into_chain_of_thought type: visible_if value: true tab: Display tool_mode: hidden visible: false hide_workflow_progress: type: boolean title: Hide Workflow Progress description: Whether to hide the flow progress default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Hide flow progress needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Display tool_mode: hidden tool_display_preset: type: string title: Tool Display Preset description: Controls how tool executions are shown during conversations default: execution display: col_span: 12 cols: 3 is_disabled: false is_subconfig: false items: - description: Minimalist loading state. Best for end-users image: >- https://storage.googleapis.com/image-storage-spot-manual/tool-display/minimal.svg label: Minimal value: minimal - description: Step-by-step execution visibility image: >- https://storage.googleapis.com/image-storage-spot-manual/tool-display/execution.svg label: Execution value: execution - description: Tool inputs, outputs, and system trace image: >- https://storage.googleapis.com/image-storage-spot-manual/tool-display/trace.svg label: Trace value: tracing label: Tool display preset needs_confirmation: false show_optional_label: false type: card_select variant: preview tab: Display tool_mode: hidden minimal_caret_only: type: boolean title: Minimal Caret Only description: Show a loading message while the agent is working. default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enable loading message needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Display tool_mode: hidden minimal_tool_message: type: string title: Minimal Tool Message default: Thinking... display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Loading message max_length: 50 needs_confirmation: false number_of_lines: 1 placeholder: Thinking... show_optional_label: false show_refresh: false type: text rules: - config_source: minimal_caret_only type: visible_if value: true tab: Display tool_mode: hidden citation_style: type: string title: Citation Style description: How inline citation references are displayed default: text display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: false is_subconfig: false label: Citation style needs_confirmation: false show_optional_label: false type: select values: - label: Text (hostname / title) value: text - label: Numbered (1, 2, 3) value: numbered - label: Hidden value: hidden tab: Display tool_mode: hidden deduplicate_sources_by_url: type: boolean title: Deduplicate Sources By Url description: Group sources by unique URL in the sources panel default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Deduplicate sources by URL needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - conds: - config_source: citation_style type: visible_if value: text - config_source: citation_style type: visible_if value: numbered mode: or type: visible_if_group tab: Display tool_mode: hidden omit_citation_quotes: type: boolean title: Omit Citation Quotes description: Hide quoted text in citation bubbles, show only the URL default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Omit citation quotes needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - conds: - config_source: citation_style type: visible_if value: text - config_source: citation_style type: visible_if value: numbered mode: or type: visible_if_group tab: Display tool_mode: hidden show_source_images: type: boolean title: Show Source Images description: >- Show document page images presented by the agent expanded by default instead of collapsed behind the source images toggle default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Show source images by default needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Display tool_mode: hidden chat_input_placeholder: type: string title: Chat Input Placeholder default: Ask me anything... display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Chat input hint max_length: 50 needs_confirmation: false number_of_lines: 1 placeholder: Ask me anything... show_optional_label: false show_refresh: false type: text tab: Display tool_mode: hidden divider_visuals: type: string title: Divider Visuals default: '' display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Display tool_mode: hidden transport_show_tool_calls: type: boolean title: Transport Show Tool Calls default: false tab: Configuration tool_mode: hidden visible: false transport_show_sources: type: boolean title: Transport Show Sources default: true tab: Configuration tool_mode: hidden visible: false transport_show_thinking: type: boolean title: Transport Show Thinking default: false tab: Configuration tool_mode: hidden visible: false transport_allow_noop: type: boolean title: Transport Allow Noop default: false tab: Configuration tool_mode: hidden visible: false transport_thinking_text: type: string title: Transport Thinking Text default: '' tab: Configuration tool_mode: hidden visible: false conversation_title_section: type: string title: Conversation Title Section default: '' display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: Configure how the agent conversation title is displayed. title: Conversation title display type: ui_text_display tab: Display tool_mode: hidden agent_title_mode: type: string enum: - generate - first_message - last_message - custom title: Agent Title Mode description: >- Configure how the agent conversation titlte is displayed in the conversation history default: generate display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: true is_subconfig: false label: Title mode needs_confirmation: false show_optional_label: false type: select values: - label: Generate from first messages value: generate - label: Use first message value: first_message - label: Use last message value: last_message - label: Custom prompt value: custom tab: Display tool_mode: hidden agent_title_prompt: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: string title: Agent Title Prompt description: Custom instructions for the generated conversation title. default: '' display: col_span: 12 hide_toolbar: false is_disabled: false is_subconfig: false label: Title prompt needs_confirmation: false number_of_lines: 5 placeholder: >- Describe what the title should contain and the format it should follow. show_optional_label: false type: big_text rules: - config_source: agent_title_mode type: visible_if value: custom tab: Display tool_mode: hidden divider_conversation_title: type: string title: Divider Conversation Title default: '' display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider tab: Display tool_mode: hidden feedback_section: type: string title: Feedback Section default: '' display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: Customise the inline prompt shown when a user rates a response. title: Message feedback type: ui_text_display tab: Display tool_mode: hidden feedback_placeholder: type: string title: Feedback Placeholder description: Placeholder shown in the inline feedback box. default: Add details (optional) display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Feedback placeholder max_length: 140 needs_confirmation: false number_of_lines: 1 placeholder: Add details (optional) show_optional_label: false show_refresh: false type: text tab: Display tool_mode: hidden feedback_submit_label: type: string title: Feedback Submit Label default: Submit display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Submit button label max_length: 30 needs_confirmation: false number_of_lines: 1 placeholder: Submit show_optional_label: false show_refresh: false type: text tab: Display tool_mode: hidden feedback_cancel_label: type: string title: Feedback Cancel Label default: Cancel display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Cancel button label max_length: 30 needs_confirmation: false number_of_lines: 1 placeholder: Cancel show_optional_label: false show_refresh: false type: text tab: Display tool_mode: hidden agentflow_section: type: string title: Agentflow Section default: '' accordion: Model Parameters display: col_span: 10 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_optional_label: false small_text: Configure how the chat flow handles state transitions type: ui_text_display rules: - config_source: agentflow_enabled type: visible_if value: true tab: Display tool_mode: hidden hide_state_transitions: type: boolean title: Hide State Transitions description: Whether to hide the state transitions default: false accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: Hide state transitions needs_confirmation: false show_optional_label: false toggle_position: right type: toggle rules: - config_source: agentflow_enabled type: visible_if value: true tab: Display tool_mode: hidden divider_13: type: string title: Divider 13 default: '' accordion: Model Parameters display: col_span: 12 is_disabled: false is_subconfig: false label: '' needs_confirmation: false show_line: true show_optional_label: false spacing: 0 type: divider rules: - config_source: agentflow_enabled type: visible_if value: true tab: Display tool_mode: hidden agent_flow_id: anyOf: - type: string - type: 'null' title: Agent Flow Id description: The agent flow to use for the conversation display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Agent flow needs_confirmation: false number_of_lines: 1 placeholder: The agent flow to use for the conversation show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden visible: false is_coworker: type: boolean title: Is Coworker description: Whether the agent is a co-worker default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Is co-worker needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false preset_selector: anyOf: - type: string - type: 'null' title: Preset Selector description: Choose a preset to get started quickly. display: button_label: Choose preset button_size: default button_variant: outline col_span: 12 confirmation_message: >- Loading a preset will overwrite your persona, tone, instructions, and some model settings. Continue? is_disabled: false is_horizontal: true is_subconfig: false label: Quick start mixpanel_event: AGENT_PRESET_SELECTOR_CLICK needs_confirmation: true show_optional_label: false type: menu_select values: - description: Customer service agent for issue resolution label: Customer Operations value: customer_operations - description: Technical support specialist for troubleshooting label: IT Helpdesk value: it_helpdesk - description: Case management specialist for claims and workflows label: Case Management value: case_management rules: - target_fields: - persona - tone - extra_instructions - temperature - top_p - top_k - presence_penalty - frequency_penalty - parameter_preset - preset_selector type: sets_field_values value_map: case_management: extra_instructions: definition: content: - content: - text: >- - Review all case details thoroughly before proceeding type: text type: paragraph - content: - text: >- - Follow established procedures and compliance requirements type: text type: paragraph - content: - text: '- Document all actions and decisions clearly' type: text type: paragraph - content: - text: >- - Maintain accuracy and attention to detail throughout the process type: text type: paragraph type: doc isRaw: false text: >- - Review all case details thoroughly before proceeding - Follow established procedures and compliance requirements - Document all actions and decisions clearly - Maintain accuracy and attention to detail throughout the process frequency_penalty: 0.5 parameter_preset: custom persona: definition: content: - content: - text: >- You are a detail-oriented case management specialist with expertise in claims processing, case review, and regulatory compliance. You are methodical, thorough, and skilled at managing complex workflows while ensuring accuracy and adherence to procedures. type: text type: paragraph type: doc isRaw: false text: >- You are a detail-oriented case management specialist with expertise in claims processing, case review, and regulatory compliance. You are methodical, thorough, and skilled at managing complex workflows while ensuring accuracy and adherence to procedures. presence_penalty: 0.3 temperature: 0.2 tone: definition: content: - content: - text: >- Maintain a formal and professional tone at all times. Use precise, business-appropriate language. Be respectful and maintain clear boundaries in all interactions. type: text type: paragraph type: doc isRaw: false text: >- Maintain a formal and professional tone at all times. Use precise, business-appropriate language. Be respectful and maintain clear boundaries in all interactions. top_k: 25 top_p: 0.85 customer_operations: extra_instructions: definition: content: - content: - text: >- - Always confirm customer details before taking action type: text type: paragraph - content: - text: '- Provide concise step-by-step guidance' type: text type: paragraph - content: - text: '- Escalate complex cases politely when needed' type: text type: paragraph - content: - text: >- - Maintain empathy and professionalism in all interactions type: text type: paragraph type: doc isRaw: false text: |- - Always confirm customer details before taking action - Provide concise step-by-step guidance - Escalate complex cases politely when needed - Maintain empathy and professionalism in all interactions frequency_penalty: 0.6 parameter_preset: custom persona: definition: content: - content: - text: >- You are a knowledgeable and empathetic customer operations agent who helps users resolve issues quickly and clearly. You have deep expertise in customer service best practices, issue resolution, and maintaining positive customer relationships. type: text type: paragraph type: doc isRaw: false text: >- You are a knowledgeable and empathetic customer operations agent who helps users resolve issues quickly and clearly. You have deep expertise in customer service best practices, issue resolution, and maintaining positive customer relationships. presence_penalty: 0.4 temperature: 0.2 tone: definition: content: - content: - text: >- Be professional yet personable. Provide clear and engaging communication. Exercise good judgment in matching tone to context. type: text type: paragraph type: doc isRaw: false text: >- Be professional yet personable. Provide clear and engaging communication. Exercise good judgment in matching tone to context. top_k: 20 top_p: 0.85 it_helpdesk: extra_instructions: definition: content: - content: - text: >- - Gather system information and error details first type: text type: paragraph - content: - text: >- - Provide step-by-step troubleshooting instructions type: text type: paragraph - content: - text: '- Explain technical concepts in simple terms' type: text type: paragraph - content: - text: '- Document solutions for future reference' type: text type: paragraph type: doc isRaw: false text: |- - Gather system information and error details first - Provide step-by-step troubleshooting instructions - Explain technical concepts in simple terms - Document solutions for future reference frequency_penalty: 0.7 parameter_preset: custom persona: definition: content: - content: - text: >- You are an experienced IT helpdesk support specialist with comprehensive knowledge of technical troubleshooting, common software and hardware issues, and system administration. You excel at translating complex technical concepts into simple, actionable guidance. type: text type: paragraph type: doc isRaw: false text: >- You are an experienced IT helpdesk support specialist with comprehensive knowledge of technical troubleshooting, common software and hardware issues, and system administration. You excel at translating complex technical concepts into simple, actionable guidance. presence_penalty: 0.3 temperature: 0.2 tone: definition: content: - content: - text: >- Be professional yet personable. Provide clear and engaging communication. Exercise good judgment in matching tone to context. type: text type: paragraph type: doc isRaw: false text: >- Be professional yet personable. Provide clear and engaging communication. Exercise good judgment in matching tone to context. top_k: 25 top_p: 0.85 tab: Prompt tool_mode: hidden visible: false introductory_message: anyOf: - items: $ref: '#/components/schemas/NoxusTipTapDocument-Output' type: array - type: 'null' title: Introductory Message description: The introductory message to use for the conversation. display: col_span: 12 connector_name: '' hide_chip_options: false hide_toolbar: false is_disabled: false is_simple_text: false is_subconfig: false label: Introductory message needs_confirmation: false no_space_on_insert: false number_of_lines: 5 placeholder: Hello, how can I help you today? show_optional_label: false type: rich_text_variables rules: - config_source: is_coworker type: visible_if value: true tab: Prompt tool_mode: hidden persona: anyOf: - items: $ref: '#/components/schemas/NoxusTipTapDocument-Output' type: array - type: 'null' title: Persona description: >- Describe who the co-worker is — their background, role, or point of view. display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Agent persona defining the AI's character, background, role, and point of view heuristic_types: - clarity - specificity - roleplaying improver_context: >- This is an AGENT PERSONA definition — a description of who the AI agent is. The output must read as a natural character description, NOT a structured task prompt. Do NOT include output format specs, JSON schemas, edge case sections, or task-type templates. Focus on: identity, background, personality traits, expertise, and point of view. Keep it concise (2-4 short paragraphs max). Write in second person ('You are...'). Be specific about the character but avoid copying any real or copyrighted personas. improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Persona needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Prompt tool_mode: hidden tone: anyOf: - items: $ref: '#/components/schemas/NoxusTipTapDocument-Output' type: array - type: 'null' title: Tone description: >- Define how the co-worker should communicate — its voice, attitude, and style. display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Agent tone and communication style defining voice, attitude, and writing style heuristic_types: - clarity - specificity - roleplaying improver_context: >- This is an AGENT TONE & STYLE definition — how the AI agent should communicate. The output must be a concise set of voice and style guidelines, NOT a structured task prompt. Do NOT include output format specs, JSON schemas, edge case sections, or task-type templates. Focus on: communication style, vocabulary level, formality, pacing, and attitude. Keep it concise (a short list of guidelines or 1-2 paragraphs max). Use direct instructions ('Use short sentences', 'Be encouraging', etc.). improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Tone & style needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Prompt tool_mode: hidden extra_instructions: anyOf: - items: $ref: '#/components/schemas/NoxusTipTapDocument-Output' type: array - type: 'null' title: Extra Instructions description: >- Provide specific rules, goals, or context to guide the co-worker's behavior. display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Agent behavior instructions providing specific rules, goals, and operational guidelines heuristic_types: - clarity - specificity - actionability - task_breakdown improver_context: >- This is an AGENT BEHAVIOR INSTRUCTIONS field — specific rules and guidelines for the agent. The output must be a concise set of behavioral rules, NOT a generic task prompt template. Do NOT include output format specs, JSON schemas, edge case sections, or task-type templates. Focus on: do/don't rules, goals, boundaries, and operational guidelines. Keep it concise and actionable. Use bullet points or numbered rules. improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Instructions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Prompt tool_mode: hidden tools: items: oneOf: - $ref: '#/components/schemas/WebResearchSettings-Output' - $ref: '#/components/schemas/NoxusQaSettings-Output' - $ref: '#/components/schemas/KnowledgeBaseSelectorSettings-Output' - $ref: '#/components/schemas/KnowledgeBaseQaSettings-Output' - $ref: '#/components/schemas/WorkflowSettings-Output' - $ref: '#/components/schemas/AttachFileSettings' - $ref: '#/components/schemas/FlowTransitionSettings-Output' - $ref: '#/components/schemas/ChatflowSettings-Output' - $ref: '#/components/schemas/ChatflowExtractionSettings-Output' - $ref: '#/components/schemas/HumanInTheLoopSettings-Output' - $ref: '#/components/schemas/ChatflowTransitionSettings' - $ref: '#/components/schemas/AgentToolSettings-Output' - $ref: '#/components/schemas/MemorySettings-Output' - $ref: '#/components/schemas/ActionToolSettings-Output' - $ref: '#/components/schemas/ExcelSettings-Output' - $ref: '#/components/schemas/DocxSettings-Output' - $ref: '#/components/schemas/FileSystemSettings-Output' - $ref: '#/components/schemas/FileSettings-Output' - $ref: '#/components/schemas/TodoSettings-Output' - $ref: '#/components/schemas/SandboxSettings-Output' - $ref: '#/components/schemas/ScheduleToolSettings-Output' - $ref: '#/components/schemas/SubAgentSettings-Output' - $ref: '#/components/schemas/CodeExecutionSettings-Output' - $ref: '#/components/schemas/AgentMemorySettings-Output' - $ref: '#/components/schemas/CreateFilesSettings-Output' - $ref: '#/components/schemas/DocumentationSettings-Output' - $ref: '#/components/schemas/ImageGenerationSettings-Output' discriminator: propertyName: type mapping: action: $ref: '#/components/schemas/ActionToolSettings-Output' agent_memory: $ref: '#/components/schemas/AgentMemorySettings-Output' agent_tool: $ref: '#/components/schemas/AgentToolSettings-Output' attach_file: $ref: '#/components/schemas/AttachFileSettings' chatflow: $ref: '#/components/schemas/ChatflowSettings-Output' chatflow_extraction: $ref: '#/components/schemas/ChatflowExtractionSettings-Output' chatflow_transition: $ref: '#/components/schemas/ChatflowTransitionSettings' code_execution: $ref: '#/components/schemas/CodeExecutionSettings-Output' create_files: $ref: '#/components/schemas/CreateFilesSettings-Output' documentation: $ref: '#/components/schemas/DocumentationSettings-Output' docx: $ref: '#/components/schemas/DocxSettings-Output' excel: $ref: '#/components/schemas/ExcelSettings-Output' files: $ref: '#/components/schemas/FileSettings-Output' filesystem: $ref: '#/components/schemas/FileSystemSettings-Output' flow_transition: $ref: '#/components/schemas/FlowTransitionSettings-Output' human_in_the_loop: $ref: '#/components/schemas/HumanInTheLoopSettings-Output' image_generation: $ref: '#/components/schemas/ImageGenerationSettings-Output' kb_qa: $ref: '#/components/schemas/KnowledgeBaseQaSettings-Output' kb_selector: $ref: '#/components/schemas/KnowledgeBaseSelectorSettings-Output' memory: $ref: '#/components/schemas/MemorySettings-Output' noxus_qa: $ref: '#/components/schemas/NoxusQaSettings-Output' sandbox: $ref: '#/components/schemas/SandboxSettings-Output' schedule_tool: $ref: '#/components/schemas/ScheduleToolSettings-Output' subagent: $ref: '#/components/schemas/SubAgentSettings-Output' todos: $ref: '#/components/schemas/TodoSettings-Output' web_research: $ref: '#/components/schemas/WebResearchSettings-Output' workflow: $ref: '#/components/schemas/WorkflowSettings-Output' type: array title: Tools default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Tools needs_confirmation: false show_optional_label: false show_sections: [] type: tools_select tab: Configuration tool_mode: hidden visible: false mcp_servers: items: $ref: '#/components/schemas/MCPServerBinding' type: array title: Mcp Servers description: Workspace MCP credentials this agent can call tools on. default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: MCP needs_confirmation: false show_optional_label: false type: mcp_credential_select order: 50 tab: Actions tool_mode: hidden skills_enabled: type: boolean title: Skills Enabled description: Extend agent capabilities with markdown-based skill packages. default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Skills needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Knowledge tool_mode: hidden visible: false convert_unsupported_files_to_text: type: boolean title: Convert Unsupported Files To Text description: >- When an attached file's type can't be sent to the model as a native attachment (e.g. JSON, CSV, XML, Markdown), inline its text content into the prompt instead of failing the run. PDFs and images are always sent as attachments. default: true accordion: Advanced display: col_span: 12 is_disabled: false is_subconfig: false label: Convert unsupported files to text needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Prompt tool_mode: hidden skills: items: $ref: '#/components/schemas/SkillConfig' type: array title: Skills default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Skills needs_confirmation: false show_optional_label: false type: skills_list tab: Knowledge tool_mode: hidden subagents_enabled: type: boolean title: Subagents Enabled description: Delegate tasks to specialized subagents for parallel execution. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Subagents needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Actions tool_mode: hidden visible: false subagents: items: $ref: '#/components/schemas/SubAgentDefinition' type: array title: Subagents default: [] accordion: Subagent options display: col_span: 12 is_disabled: false is_subconfig: false label: Subagents needs_confirmation: false show_optional_label: false type: subagents_list tab: Actions tool_mode: hidden subagents_instructions: anyOf: - items: $ref: '#/components/schemas/NoxusTipTapDocument-Output' type: array - type: 'null' title: Subagents Instructions description: Tell the co-worker when to hand work to a subagent. accordion: Subagent options display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: false improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: When to delegate needs_confirmation: false number_of_lines: 4 placeholder: >- e.g. Delegate research that needs more than a few searches. Keep drafting and formatting for yourself. show_optional_label: false type: rich_text_variables_ai rules: - config_source: subagents_enabled type: visible_if value: true tab: Actions tool_mode: hidden subagents_model: items: type: string type: array title: Subagents Model description: >- Model the subagents run on. Specialists that pick their own model override this; an empty selection falls back to the agent's model. default: - preset:cost accordion: Subagent options display: col_span: 12 default_preset: cost endpoint: /models/llms hide_disabled_models: true is_disabled: false is_subconfig: false label: Subagent model layout: side_by_side model_limit: 3 model_type: text needs_confirmation: false show_inline_presets: true show_optional_label: false show_presets: true type: model_select optional: true rules: - config_source: subagents_enabled type: visible_if value: true tab: Actions tool_mode: hidden guidelines_enabled: type: boolean title: Guidelines Enabled description: Enable behavioral guidelines that shape how the agent responds. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Enable Guidelines needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Prompt tool_mode: hidden visible: false guidelines: items: $ref: '#/components/schemas/GuidelineConfig' type: array title: Guidelines default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Guidelines needs_confirmation: false show_optional_label: false type: guidelines_list tab: Prompt tool_mode: hidden glossary: items: $ref: '#/components/schemas/GlossaryTermConfig' type: array title: Glossary default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Glossary needs_confirmation: false show_optional_label: false type: glossary_list tab: Prompt tool_mode: hidden memories: items: $ref: '#/components/schemas/AgentMemoryEntry' type: array title: Memories description: Persistent memory across all conversations default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Agent Memory needs_confirmation: false show_optional_label: false type: agent_memory_field tab: Knowledge tool_mode: hidden hidden_tools: items: type: string type: array title: Hidden Tools description: Tool calls that never appear in the chat activity feed. default: - todos_read_todos - todos_add_todo - todos_write_todos - todos_update_todo_status - todos_remove_todo display: col_span: 12 is_disabled: false is_subconfig: false label: Hidden tools needs_confirmation: false show_optional_label: false tooltip: Toggled-on tools never appear in the chat activity feed. type: tool_select tab: Display tool_mode: hidden visible: false deployment_custom_instructions: anyOf: - type: string - type: 'null' title: Deployment Custom Instructions display: col_span: 12 is_disabled: false is_subconfig: false label: deployment_custom_instructions needs_confirmation: false show_optional_label: false type: config_dynamic_text tab: Configuration tool_mode: hidden visible: false workflows: items: $ref: '#/components/schemas/WorkflowSettings-Output' type: array title: Workflows description: Workflows the agent can run default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Workflows needs_confirmation: false show_optional_label: false type: workflows_field order: 10 tab: Actions tool_mode: hidden knowledge_bases: items: $ref: '#/components/schemas/KnowledgeBaseQaSettings-Output' type: array title: Knowledge Bases description: Knowledge bases the agent can search default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Knowledge Bases needs_confirmation: false show_optional_label: false type: knowledge_bases_field tab: Knowledge tool_mode: hidden agent_files: items: $ref: '#/components/schemas/AgentFileConfig-Output' type: array title: Agent Files description: >- Files pre-loaded into every conversation. Each is added to the session (readable via the file tools) with its context shown to the agent. default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Files needs_confirmation: false show_optional_label: false type: files_field order: 10 tab: Knowledge tool_mode: hidden databases: items: $ref: '#/components/schemas/AgentDatabaseConfig-Output' type: array title: Databases description: >- SQL databases the agent can query read-only. Each references a database credential; access is deferred, so the agent connects only when a query is needed. default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Databases needs_confirmation: false show_optional_label: false type: databases_field order: 20 tab: Knowledge tool_mode: hidden tables: items: $ref: '#/components/schemas/AgentTableConfig-Output' type: array title: Tables description: >- The workspace tables this agent can use. Add context for each so the agent knows what it holds and when to use it. default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Tables needs_confirmation: false show_optional_label: false type: tables_field order: 21 tab: Knowledge tool_mode: hidden coworkers: items: $ref: '#/components/schemas/AgentToolSettings-Output' type: array title: Coworkers description: Co-workers the agent can call default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Co-workers needs_confirmation: false show_optional_label: false type: coworkers_field order: 20 tab: Actions tool_mode: hidden base_tools: items: oneOf: - $ref: '#/components/schemas/WebResearchSettings-Output' - $ref: '#/components/schemas/HumanInTheLoopSettings-Output' - $ref: '#/components/schemas/MemorySettings-Output' - $ref: '#/components/schemas/AttachFileSettings' - $ref: '#/components/schemas/FileSystemSettings-Output' - $ref: '#/components/schemas/FileSettings-Output' - $ref: '#/components/schemas/CodeExecutionSettings-Output' - $ref: '#/components/schemas/ExcelSettings-Output' - $ref: '#/components/schemas/DocxSettings-Output' - $ref: '#/components/schemas/NoxusQaSettings-Output' - $ref: '#/components/schemas/KnowledgeBaseSelectorSettings-Output' - $ref: '#/components/schemas/TodoSettings-Output' - $ref: '#/components/schemas/SandboxSettings-Output' - $ref: '#/components/schemas/ScheduleToolSettings-Output' - $ref: '#/components/schemas/SubAgentSettings-Output' - $ref: '#/components/schemas/AgentMemorySettings-Output' - $ref: '#/components/schemas/CreateFilesSettings-Output' - $ref: '#/components/schemas/DocumentationSettings-Output' - $ref: '#/components/schemas/ImageGenerationSettings-Output' discriminator: propertyName: type mapping: agent_memory: $ref: '#/components/schemas/AgentMemorySettings-Output' attach_file: $ref: '#/components/schemas/AttachFileSettings' code_execution: $ref: '#/components/schemas/CodeExecutionSettings-Output' create_files: $ref: '#/components/schemas/CreateFilesSettings-Output' documentation: $ref: '#/components/schemas/DocumentationSettings-Output' docx: $ref: '#/components/schemas/DocxSettings-Output' excel: $ref: '#/components/schemas/ExcelSettings-Output' files: $ref: '#/components/schemas/FileSettings-Output' filesystem: $ref: '#/components/schemas/FileSystemSettings-Output' human_in_the_loop: $ref: '#/components/schemas/HumanInTheLoopSettings-Output' image_generation: $ref: '#/components/schemas/ImageGenerationSettings-Output' kb_selector: $ref: '#/components/schemas/KnowledgeBaseSelectorSettings-Output' memory: $ref: '#/components/schemas/MemorySettings-Output' noxus_qa: $ref: '#/components/schemas/NoxusQaSettings-Output' sandbox: $ref: '#/components/schemas/SandboxSettings-Output' schedule_tool: $ref: '#/components/schemas/ScheduleToolSettings-Output' subagent: $ref: '#/components/schemas/SubAgentSettings-Output' todos: $ref: '#/components/schemas/TodoSettings-Output' web_research: $ref: '#/components/schemas/WebResearchSettings-Output' type: array title: Base Tools description: Quick action tools the agent can use default: - title: Human in the Loop description: Human in the Loop category: QuickAction enabled: false tool_display_icon: PersonStanding tool_display_message_start: Escalating to human operator... tool_display_message_end: Escalated to human operator requires_approval: false visible: true icon: PersonStanding bg_color: blue.50 icon_color: blue.500 chatflow_usable: true deprecated: false type: human_in_the_loop has_timeout: false handover_message: You are now talking to the co-worker. - title: Web Research description: Search the web for information category: QuickAction enabled: false tool_display_icon: Globe tool_display_message_start: Searching the web... tool_display_message_end: Searched the web requires_approval: false visible: true icon: Globe bg_color: '#D1FADF' icon_color: '#027A48' chatflow_usable: true deprecated: false type: web_research - title: Files description: Attach, generate, and work with files. category: QuickAction enabled: false tool_display_icon: Files tool_display_message_start: Working with files... tool_display_message_end: Done requires_approval: false visible: true icon: Files bg_color: '#EFF6FF' icon_color: '#2B7FFF' chatflow_usable: true deprecated: false type: files allow_html_graphs: true show_inline: true custom_author_name: false author_name: '' enable_python_sandbox: false enable_formula_eval: false experimental: false - title: Memory description: Persistent memory during a single conversation category: QuickAction enabled: false tool_display_icon: Brain tool_display_message_start: Accessing memory... tool_display_message_end: Memory operation complete requires_approval: false visible: true icon: Brain bg_color: '#f5f3ff' icon_color: '#8e51ff' chatflow_usable: true deprecated: false type: memory - title: File System description: Access and read files in the current session category: QuickAction enabled: true tool_display_icon: FolderOpen tool_display_message_start: Accessing file system... tool_display_message_end: File system operation complete requires_approval: false visible: false icon: FolderOpen bg_color: '#fef3c7' icon_color: '#f59e0b' chatflow_usable: true deprecated: false type: filesystem - title: Code Execution description: Run Python code in a sandboxed environment category: QuickAction enabled: false tool_display_icon: Terminal tool_display_message_start: Running code... tool_display_message_end: Code executed requires_approval: false visible: true icon: Terminal bg_color: '#fef9c3' icon_color: '#ca8a04' chatflow_usable: true deprecated: false type: code_execution timeout: 60 - title: Agent Memory description: Persistent memory across all conversations category: QuickAction enabled: false tool_display_icon: BookOpen tool_display_message_start: Accessing agent memory... tool_display_message_end: Memory operation complete requires_approval: false visible: false icon: BookOpen bg_color: '#fef3c7' icon_color: '#d97706' chatflow_usable: true deprecated: false type: agent_memory - title: Documentation description: Search and read Noxus platform documentation category: QuickAction enabled: false tool_display_icon: BookOpen tool_display_message_start: Searching documentation... tool_display_message_end: Documentation found requires_approval: false visible: true icon: BookOpen bg_color: '#EFF6FF' icon_color: '#2B7FFF' chatflow_usable: true deprecated: false type: documentation - title: Task Tracking description: Track and manage tasks during the conversation category: QuickAction enabled: false tool_display_icon: ListTodo tool_display_message_start: Managing tasks... tool_display_message_end: Tasks updated requires_approval: false visible: true icon: ListTodo bg_color: '#f0fdf4' icon_color: '#16a34a' chatflow_usable: true deprecated: false type: todos enable_subtasks: false - title: Image Generation description: Generate images from text prompts, shown inline in the chat. category: QuickAction enabled: false tool_display_icon: ImagePlus tool_display_message_start: Generating image... tool_display_message_end: Image generated requires_approval: false visible: true icon: ImagePlus bg_color: '#FDF4FF' icon_color: '#C026D3' chatflow_usable: true deprecated: false type: image_generation display: col_span: 12 is_disabled: false is_subconfig: false label: Tools needs_confirmation: false show_optional_label: false type: base_tools_field order: 80 tab: Actions tool_mode: hidden actions: items: $ref: '#/components/schemas/ActionToolSettings-Output' type: array title: Actions description: Action nodes the agent can execute default: [] display: col_span: 12 is_disabled: false is_subconfig: false label: Actions needs_confirmation: false show_optional_label: false type: actions_field order: 40 tab: Actions tool_mode: hidden chatflow_tools: items: oneOf: - $ref: '#/components/schemas/FlowTransitionSettings-Output' - $ref: '#/components/schemas/ChatflowSettings-Output' - $ref: '#/components/schemas/ChatflowExtractionSettings-Output' - $ref: '#/components/schemas/ChatflowTransitionSettings' discriminator: propertyName: type mapping: chatflow: $ref: '#/components/schemas/ChatflowSettings-Output' chatflow_extraction: $ref: '#/components/schemas/ChatflowExtractionSettings-Output' chatflow_transition: $ref: '#/components/schemas/ChatflowTransitionSettings' flow_transition: $ref: '#/components/schemas/FlowTransitionSettings-Output' type: array title: Chatflow Tools default: [] tab: Configuration tool_mode: hidden visible: false insights_enabled: type: boolean title: Insights Enabled description: Enable conversation analysis and insights dashboard. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Enable Insights needs_confirmation: false show_optional_label: false toggle_position: left type: toggle tab: Insights tool_mode: hidden insights_csat_enabled: type: boolean title: Insights Csat Enabled description: >- Collect customer satisfaction (CSAT) ratings at end of conversations. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Enable CSAT needs_confirmation: false show_optional_label: false toggle_position: left type: toggle rules: - config_source: insights_enabled type: visible_if value: true tab: Insights tool_mode: hidden insights_csat_sampling_rate: type: number title: Insights Csat Sampling Rate description: >- Fraction of conversations that get a CSAT prompt (1.0 = every conversation). default: 1 display: col_span: 12 hide_number: false is_disabled: false is_subconfig: false label: CSAT Sampling Rate max: 1 min: 0 needs_confirmation: false show_optional_label: false step: 0.05 type: number_slider rules: - conds: - config_source: insights_enabled type: visible_if value: true - config_source: insights_csat_enabled type: visible_if value: true mode: and type: visible_if_group tab: Insights tool_mode: hidden insights_csat_agent_tool_enabled: type: boolean title: Insights Csat Agent Tool Enabled description: Let the agent decide when to show the CSAT form via a tool call. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Agent Feedback Tool needs_confirmation: false show_optional_label: false toggle_position: left type: toggle rules: - conds: - config_source: insights_enabled type: visible_if value: true - config_source: insights_csat_enabled type: visible_if value: true mode: and type: visible_if_group tab: Insights tool_mode: hidden insights_csat_agent_tool_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: string title: Insights Csat Agent Tool Instructions description: >- Custom instructions for when the agent should request customer feedback. default: '' display: col_span: 12 hide_toolbar: false is_disabled: false is_subconfig: false label: Feedback Tool Instructions needs_confirmation: false number_of_lines: 5 placeholder: >- e.g. Ask for feedback once the customer confirms their issue is solved. Never ask during troubleshooting. show_optional_label: false type: big_text rules: - conds: - config_source: insights_enabled type: visible_if value: true - config_source: insights_csat_enabled type: visible_if value: true - config_source: insights_csat_agent_tool_enabled type: visible_if value: true mode: and type: visible_if_group tab: Insights tool_mode: hidden insights_csat_auto_enabled: type: boolean title: Insights Csat Auto Enabled description: >- Automatically show the CSAT form at the end of an agent turn (rule-based, no tool call). Independent of the agent feedback tool. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Automatic Feedback Request needs_confirmation: false show_optional_label: false toggle_position: left type: toggle rules: - conds: - config_source: insights_enabled type: visible_if value: true - config_source: insights_csat_enabled type: visible_if value: true mode: and type: visible_if_group tab: Insights tool_mode: hidden insights_csat_auto_min_messages: type: integer title: Insights Csat Auto Min Messages description: >- Only auto-request feedback once the user has sent at least this many messages. default: 2 display: col_span: 12 is_disabled: false is_subconfig: false label: Minimum user messages before auto request needs_confirmation: false show_optional_label: false type: number rules: - conds: - config_source: insights_enabled type: visible_if value: true - config_source: insights_csat_enabled type: visible_if value: true - config_source: insights_csat_auto_enabled type: visible_if value: true mode: and type: visible_if_group tab: Insights tool_mode: hidden insights_custom_definitions: items: $ref: '#/components/schemas/CustomInsightDefinition' type: array title: Insights Custom Definitions description: User-defined situations to detect in each conversation. default: [] tab: Insights tool_mode: hidden visible: false tool_grant_scope: type: string enum: - workspace - user title: Tool Grant Scope description: >- Whether 'Always Allow' tool grants apply to all workspace users or only the granting user default: workspace display: col_span: 12 icons: false is_clearable: false is_disabled: false is_horizontal: false is_searchable: true is_subconfig: false label: Tool Grant Scope needs_confirmation: false show_optional_label: false type: select values: - label: Workspace value: workspace - label: Per User value: user order: 70 tab: Actions tool_mode: hidden type: object title: CoWorkerSettings RunStatus: type: string enum: - queued - running - failed - completed - stopped - awaiting_human_feedback title: RunStatus Message: properties: id: type: string format: uuid title: Id created_at: type: string format: date-time title: Created At message_parts: items: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/ToolCallMessage' - $ref: '#/components/schemas/ToolCalledMessage' - $ref: '#/components/schemas/ToolCalledMessageEnd' - $ref: '#/components/schemas/MessageEnd' - $ref: '#/components/schemas/MarkdownMessage' - $ref: '#/components/schemas/AudioReferenceMessage' - $ref: '#/components/schemas/ImageReferenceMessage' - $ref: '#/components/schemas/VideoReferenceMessage' - $ref: '#/components/schemas/DocumentReferenceMessage' - $ref: '#/components/schemas/WebReferenceMessage' - $ref: '#/components/schemas/ImageCarouselMessage' - $ref: '#/components/schemas/SourceReferenceMessage' - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/ErrorMessage' - $ref: '#/components/schemas/WarningMessage' - $ref: '#/components/schemas/InfoMessage' - $ref: '#/components/schemas/SuccessMessage' - $ref: '#/components/schemas/SetConversationTitle' - $ref: '#/components/schemas/InternalToolResultMessage' - $ref: '#/components/schemas/YoutubeReferenceMessage' - $ref: '#/components/schemas/StateTransitionMessage' - $ref: '#/components/schemas/ChatflowExtractionMessage' - $ref: '#/components/schemas/ConversationEndMessage' - $ref: '#/components/schemas/HumanInTheLoopMessage' - $ref: '#/components/schemas/MemoryMessage' - $ref: '#/components/schemas/KBContextMessage' - $ref: '#/components/schemas/WebpageContextMessage' - $ref: '#/components/schemas/HumanInTheLoopAssignedMessage' - $ref: '#/components/schemas/ThinkingMessage' - $ref: '#/components/schemas/ThinkingEndedMessage' - $ref: '#/components/schemas/ClearConversationStreamMessage' - $ref: '#/components/schemas/WorkflowRunningMessage' - $ref: '#/components/schemas/ChatflowTransitionMessage' - $ref: '#/components/schemas/PresentedFileMessage' discriminator: propertyName: type mapping: audio: $ref: '#/components/schemas/AudioReferenceMessage' chatflow_extraction: $ref: '#/components/schemas/ChatflowExtractionMessage' chatflow_transition: $ref: '#/components/schemas/ChatflowTransitionMessage' clear_conversation_stream: $ref: '#/components/schemas/ClearConversationStreamMessage' conversation_end: $ref: '#/components/schemas/ConversationEndMessage' document: $ref: '#/components/schemas/DocumentReferenceMessage' error: $ref: '#/components/schemas/ErrorMessage' human_in_the_loop: $ref: '#/components/schemas/HumanInTheLoopMessage' human_in_the_loop_assigned: $ref: '#/components/schemas/HumanInTheLoopAssignedMessage' image: $ref: '#/components/schemas/ImageReferenceMessage' image_carousel: $ref: '#/components/schemas/ImageCarouselMessage' info: $ref: '#/components/schemas/InfoMessage' kb_context: $ref: '#/components/schemas/KBContextMessage' markdown: $ref: '#/components/schemas/MarkdownMessage' memory: $ref: '#/components/schemas/MemoryMessage' message_end: $ref: '#/components/schemas/MessageEnd' presented_file: $ref: '#/components/schemas/PresentedFileMessage' set_conversation_title: $ref: '#/components/schemas/SetConversationTitle' source_reference: $ref: '#/components/schemas/SourceReferenceMessage' state_transition: $ref: '#/components/schemas/StateTransitionMessage' success: $ref: '#/components/schemas/SuccessMessage' system: $ref: '#/components/schemas/SystemMessage' thinking: $ref: '#/components/schemas/ThinkingMessage' thinking_ended: $ref: '#/components/schemas/ThinkingEndedMessage' tool_call: $ref: '#/components/schemas/ToolCallMessage' tool_called: $ref: '#/components/schemas/ToolCalledMessage' tool_called_end: $ref: '#/components/schemas/ToolCalledMessageEnd' tool_result: $ref: '#/components/schemas/InternalToolResultMessage' user: $ref: '#/components/schemas/UserMessage' video: $ref: '#/components/schemas/VideoReferenceMessage' warning: $ref: '#/components/schemas/WarningMessage' web_reference: $ref: '#/components/schemas/WebReferenceMessage' webpage_context: $ref: '#/components/schemas/WebpageContextMessage' workflow_running: $ref: '#/components/schemas/WorkflowRunningMessage' youtube_reference: $ref: '#/components/schemas/YoutubeReferenceMessage' type: array title: Message Parts pydantic_message_parts: items: oneOf: - $ref: '#/components/schemas/ModelRequest' - $ref: '#/components/schemas/ModelResponse' discriminator: propertyName: kind mapping: request: $ref: '#/components/schemas/ModelRequest' response: $ref: '#/components/schemas/ModelResponse' type: array title: Pydantic Message Parts is_positive: anyOf: - type: boolean - type: 'null' title: Is Positive feedback_meta: anyOf: - $ref: '#/components/schemas/FeedbackMeta' - type: 'null' sender_ref: anyOf: - $ref: '#/components/schemas/SenderRefSchema' - type: 'null' type: object required: - id - created_at - message_parts - pydantic_message_parts - is_positive title: Message UIMessage: properties: id: type: string title: Id role: type: string enum: - system - user - assistant title: Role metadata: anyOf: - {} - type: 'null' title: Metadata parts: items: anyOf: - $ref: '#/components/schemas/TextUIPart' - $ref: '#/components/schemas/ReasoningUIPart' - $ref: '#/components/schemas/ToolInputStreamingPart' - $ref: '#/components/schemas/ToolInputAvailablePart' - $ref: '#/components/schemas/ToolOutputAvailablePart' - $ref: '#/components/schemas/ToolOutputErrorPart' - $ref: '#/components/schemas/ToolApprovalRequestedPart' - $ref: '#/components/schemas/ToolApprovalRespondedPart' - $ref: '#/components/schemas/ToolOutputDeniedPart' - $ref: '#/components/schemas/DynamicToolInputStreamingPart' - $ref: '#/components/schemas/DynamicToolInputAvailablePart' - $ref: '#/components/schemas/DynamicToolOutputAvailablePart' - $ref: '#/components/schemas/DynamicToolOutputErrorPart' - $ref: '#/components/schemas/DynamicToolApprovalRequestedPart' - $ref: '#/components/schemas/DynamicToolApprovalRespondedPart' - $ref: '#/components/schemas/DynamicToolOutputDeniedPart' - $ref: '#/components/schemas/SourceUrlUIPart' - $ref: '#/components/schemas/SourceDocumentUIPart' - $ref: '#/components/schemas/FileUIPart' - $ref: '#/components/schemas/DataUIPart' - $ref: '#/components/schemas/StepStartUIPart' type: array title: Parts additionalProperties: false type: object required: - id - role - parts title: UIMessage description: A message as displayed in the UI by Vercel AI Elements. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError GuardrailValue: properties: value: type: string title: Value default: 'Off' context: type: string title: Context default: '' type: object title: GuardrailValue NoxusTipTapDocument-Output: properties: text: type: string title: Text definition: $ref: '#/components/schemas/TiptapDocument-Output' type: object required: - text title: NoxusTipTapDocument WebResearchSettings-Output: properties: title: type: string title: Title default: Web Research description: type: string title: Description default: Search the web for information category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon default: Globe tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Searching the web... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the web search starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Searched the web col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the web search completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Globe bg_color: type: string title: Bg Color default: '#D1FADF' icon_color: type: string title: Icon Color default: '#027A48' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: web_research title: Type default: web_research type: object title: WebResearchSettings NoxusQaSettings-Output: properties: title: type: string title: Title default: Noxus Q&A description: type: string title: Description default: Noxus Q&A category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Bot tool_display_message_start: type: string title: Tool Display Message Start default: Noxus Q&A tool_display_message_end: type: string title: Tool Display Message End default: Noxus Q&A complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Bot bg_color: type: string title: Bg Color default: '#EFF6FF' icon_color: type: string title: Icon Color default: '#2B7FFF' chatflow_usable: type: boolean title: Chatflow Usable default: false deprecated: type: boolean title: Deprecated default: true type: type: string const: noxus_qa title: Type default: noxus_qa type: object title: NoxusQaSettings KnowledgeBaseSelectorSettings-Output: properties: title: type: string title: Title default: KB Selector description: type: string title: Description default: Allows the user to select a knowledge base for your co-worker category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon default: Search tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Searching knowledge base... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the knowledge base search starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Knowledge base search complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the knowledge base search completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Folder bg_color: type: string title: Bg Color default: '#FEF9C2' icon_color: type: string title: Icon Color default: '#894B00' chatflow_usable: type: boolean title: Chatflow Usable default: false deprecated: type: boolean title: Deprecated default: true type: type: string const: kb_selector title: Type default: kb_selector type: object title: KnowledgeBaseSelectorSettings description: >- Tool that allows the user to select a knowledge base to answer questions about KnowledgeBaseQaSettings-Output: properties: title: type: string title: Title default: Knowledge Base Q&A tab: Configuration tool_mode: hidden visible: false description: type: string title: Description default: Answer questions about the knowledge base tab: Configuration tool_mode: hidden visible: false category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Knowledge tab: Configuration tool_mode: hidden visible: false enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon default: Search tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Searching knowledge base... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the knowledge base search starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Knowledge base search complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the knowledge base search completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: kb_qa title: Type default: kb_qa tab: Configuration tool_mode: hidden visible: false kb_id: type: string format: uuid title: Kb Id tab: Configuration tool_mode: hidden visible: false advanced_search: type: boolean title: Advanced Search default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Advanced search tools needs_confirmation: false show_optional_label: false toggle_position: right tooltip: >- The agent chooses the best search method (overrides the KB configured retrieval method). type: toggle tab: Configuration tool_mode: hidden private: type: boolean title: Private default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Private knowledge base needs_confirmation: false show_optional_label: false toggle_position: right tooltip: The agent won’t cite this knowledge base as a source. type: toggle tab: Configuration tool_mode: hidden enable_browse_tools: type: boolean title: Enable Browse Tools default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enable File system tools needs_confirmation: false show_optional_label: false toggle_position: right tooltip: >- Enable kb_tree and kb_ls tools for navigating the knowledge base file system. type: toggle tab: Configuration tool_mode: hidden include_tree_in_instructions: type: boolean title: Include Tree In Instructions default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Include File system structure in instructions needs_confirmation: false show_optional_label: false toggle_position: right tooltip: >- Inline this KB's folder tree into the system prompt every turn. Saves the agent a kb_tree round-trip but increases prompt size — keep depth low for large KBs. type: toggle rules: - config_source: enable_browse_tools type: visible_if value: true tab: Configuration tool_mode: hidden tree_depth_in_instructions: type: integer title: Tree Depth In Instructions default: 3 display: col_span: 12 hide_number: true is_disabled: false is_subconfig: false label: Tree depth in instructions max: 10 min: 1 needs_confirmation: false show_optional_label: false step: 1 tooltip: How many folder levels to include (1-10). type: number_slider rules: - config_source: enable_browse_tools type: visible_if value: true - config_source: include_tree_in_instructions type: visible_if value: true tab: Configuration tool_mode: hidden link_references_to_noxus_file: type: boolean title: Link References To Noxus File default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Link references to the file in Noxus needs_confirmation: false show_optional_label: false toggle_position: right tooltip: >- Point citations at the copy stored in Noxus instead of the document's original source (e.g. Google Drive). Use when users may not have access to the source location. type: toggle tab: Configuration tool_mode: hidden type: object required: - kb_id title: KnowledgeBaseQaSettings description: >- Tool that allows the user to answer questions about a specific pre-selected knowledge base WorkflowSettings-Output: properties: title: type: string title: Title default: Workflow Runner tab: Configuration tool_mode: hidden visible: false description: type: string title: Description default: Run a workflow tab: Configuration tool_mode: hidden visible: false category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Flows tab: Configuration tool_mode: hidden visible: false enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Running a workflow col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the workflow starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Workflow run complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the workflow finishes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: workflow title: Type default: workflow tab: Configuration tool_mode: hidden visible: false workflow_id: type: string format: uuid title: Workflow Id description: >- The ID of the workflow to run. Comes unselected, and should be selected by the user. tab: Configuration tool_mode: hidden visible: false inputs_descriptions: additionalProperties: type: string type: object title: Inputs Descriptions description: A dictionary of input names to descriptions. tab: Configuration tool_mode: hidden visible: false version_id: anyOf: - type: string - type: 'null' title: Version Id description: >- The ID of the version of the workflow to run. Comes unselected, and should be selected by the user. tab: Configuration tool_mode: hidden visible: false type: object required: - workflow_id title: WorkflowSettings AttachFileSettings: properties: title: type: string title: Title default: Add Files description: type: string title: Description default: >- Allows the user to add files to the conversation for the agent to access. category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: true tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start description: The message to display to the user when the tool is called. default: Running tool... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End description: The message to display to the user when the tool completes. default: Tool complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - type: string - type: 'null' title: Extra Instructions requires_approval: type: boolean title: Requires Approval default: false visible: type: boolean title: Visible default: false icon: type: string title: Icon default: Paperclip bg_color: type: string title: Bg Color default: '#EFF6FF' icon_color: type: string title: Icon Color default: '#2B7FFF' chatflow_usable: type: boolean title: Chatflow Usable default: false deprecated: type: boolean title: Deprecated default: true type: type: string const: attach_file title: Type default: attach_file type: object title: AttachFileSettings FlowTransitionSettings-Output: properties: title: type: string title: Title default: Flow Transition description: type: string title: Description default: Transition to a different flow category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Chatflow enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start description: The message to display to the user when the tool is called. default: Running tool... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End description: The message to display to the user when the tool completes. default: Tool complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: flow_transition title: Type default: flow_transition transition: $ref: '#/components/schemas/Transition' description: The transition to make type: object required: - transition title: FlowTransitionSettings ChatflowSettings-Output: properties: title: type: string title: Title default: Chatflow description: type: string title: Description default: Chatflow category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Chatflow enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start description: The message to display to the user when the tool is called. default: Running tool... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End description: The message to display to the user when the tool completes. default: Tool complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: chatflow title: Type default: chatflow chatflow_instructions: type: string title: Chatflow Instructions description: The instructions for the chatflow chatflow_criteria: anyOf: - type: string - type: 'null' title: Chatflow Criteria description: The criteria for the chatflow mode: type: string enum: - choose_path - extract - response title: Mode type: object required: - chatflow_instructions - chatflow_criteria - mode title: ChatflowSettings ChatflowExtractionSettings-Output: properties: title: type: string title: Title default: Chatflow Extraction description: type: string title: Description default: Extract data in a chatflow category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Chatflow enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start description: The message to display to the user when the tool is called. default: Running tool... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End description: The message to display to the user when the tool completes. default: Tool complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: chatflow_extraction title: Type default: chatflow_extraction response_format: title: Response Format description: The transition to make type: object required: - response_format title: ChatflowExtractionSettings HumanInTheLoopSettings-Output: properties: title: type: string title: Title default: Human in the Loop description: type: string title: Description default: Human in the Loop category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: PersonStanding tool_display_message_start: type: string title: Tool Display Message Start default: Escalating to human operator... tool_display_message_end: type: string title: Tool Display Message End default: Escalated to human operator extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: PersonStanding bg_color: type: string title: Bg Color default: blue.50 icon_color: type: string title: Icon Color default: blue.500 chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: human_in_the_loop title: Type default: human_in_the_loop has_timeout: type: boolean title: Has Timeout default: false timeout: anyOf: - type: integer - type: 'null' title: Timeout handover_message: type: string title: Handover Message default: You are now talking to the co-worker. type: object title: HumanInTheLoopSettings ChatflowTransitionSettings: properties: title: type: string title: Title default: Chatflow Transition tab: Configuration tool_mode: hidden visible: false description: type: string title: Description default: Transition to a different chatflow state tab: Configuration tool_mode: hidden visible: false category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Chatflow tab: Configuration tool_mode: hidden visible: false enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon description: The lucide icon to display for this tool default: Cog tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start description: The message to display to the user when the tool is called. default: Running tool... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool starts. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End description: The message to display to the user when the tool completes. default: Tool complete col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when the tool completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - type: string - type: 'null' title: Extra Instructions description: The condition for the chat flow to proceed out of this node. default: You are done when the user has confirmed that you can proceed. display: class_name: h-[10rem] col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: true label: Transition criteria needs_confirmation: false number_of_lines: 5 placeholder: >- E.g. You are done when the user has confirmed that you can proceed. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: chatflow_transition title: Type default: chatflow_transition tab: Configuration tool_mode: hidden visible: false transition_key: type: string title: Transition Key description: >- A unique name that identifies the transition and maps to an output of the node. display: class_name: h-[1rem] col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Transition name needs_confirmation: false number_of_lines: 1 placeholder: A name for the transition show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden type: object required: - transition_key title: ChatflowTransitionSettings AgentToolSettings-Output: properties: title: type: string title: Title default: Agent Tool tab: Configuration tool_mode: hidden visible: false description: type: string title: Description default: Call another co-worker tab: Configuration tool_mode: hidden visible: false category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Agents tab: Configuration tool_mode: hidden visible: false enabled: type: boolean title: Enabled description: Whether the tool is enabled default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Enabled needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false tool_display_icon: type: string title: Tool Display Icon default: Bot tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Calling co-worker col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when calling the co-worker. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Co-worker responded col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed after the co-worker responds. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: agent_tool title: Type default: agent_tool tab: Configuration tool_mode: hidden visible: false agent_id: type: string format: uuid title: Agent Id description: >- The ID of the agent to call. Comes unselected, and should be selected by the user. tab: Configuration tool_mode: hidden visible: false max_clarification_turns: type: integer title: Max Clarification Turns description: >- How many times this co-worker can ask follow-up questions before giving a final answer. Set to 0 to require an immediate response with no back-and-forth. default: 2 display: col_span: 12 hide_number: false is_disabled: false is_subconfig: false label: Follow-up questions allowed max: 10 min: 0 needs_confirmation: false show_optional_label: false step: 1 type: number_slider tab: Configuration tool_mode: hidden type: object required: - agent_id title: AgentToolSettings MemorySettings-Output: properties: title: type: string title: Title default: Memory description: type: string title: Description default: Persistent memory during a single conversation category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Brain tool_display_message_start: type: string title: Tool Display Message Start default: Accessing memory... tool_display_message_end: type: string title: Tool Display Message End default: Memory operation complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Brain bg_color: type: string title: Bg Color default: '#f5f3ff' icon_color: type: string title: Icon Color default: '#8e51ff' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: memory title: Type default: memory type: object title: MemorySettings ActionToolSettings-Output: properties: title: type: string title: Title default: Actions description: type: string title: Description default: Execute workflow actions category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category default: Actions enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Zap tool_display_message_start: type: string title: Tool Display Message Start default: Running action... tool_display_message_end: type: string title: Tool Display Message End default: Action complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: type: string const: action title: Type default: action icon: type: string title: Icon default: Zap bg_color: type: string title: Bg Color default: '#FEF3C7' icon_color: type: string title: Icon Color default: '#F59E0B' node_name: type: string title: Node Name description: The name of the node/action to execute tool_config: anyOf: - $ref: '#/components/schemas/ActionToolConfig' - type: 'null' type: object required: - node_name title: ActionToolSettings ExcelSettings-Output: properties: title: type: string title: Title default: Excel description: type: string title: Description default: Read, analyze, and modify Excel spreadsheets category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: true tool_display_icon: type: string title: Tool Display Icon default: FileSpreadsheet tool_display_message_start: type: string title: Tool Display Message Start default: Analyzing spreadsheet... tool_display_message_end: type: string title: Tool Display Message End default: Spreadsheet analysis complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: FileSpreadsheet bg_color: type: string title: Bg Color default: '#dcfce7' icon_color: type: string title: Icon Color default: '#16a34a' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated default: true type: type: string const: excel title: Type default: excel enable_python_sandbox: type: boolean title: Enable Python Sandbox default: false enable_formula_eval: type: boolean title: Enable Formula Eval default: false experimental: type: boolean title: Experimental default: false type: object title: ExcelSettings DocxSettings-Output: properties: title: type: string title: Title default: Word Document description: type: string title: Description default: Read, edit, and comment on Word (.docx) files using track changes. category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: true tool_display_icon: type: string title: Tool Display Icon default: FileText tool_display_message_start: type: string title: Tool Display Message Start default: Editing Word document... tool_display_message_end: type: string title: Tool Display Message End default: Word document edit complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: FileText bg_color: type: string title: Bg Color default: '#dbeafe' icon_color: type: string title: Icon Color default: '#2563eb' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated default: true type: type: string const: docx title: Type default: docx author_name: type: string title: Author Name description: Author shown on track-change revisions and comments. default: Docx Agent display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Track-change author needs_confirmation: false number_of_lines: 1 placeholder: Docx Agent show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden type: object title: DocxSettings FileSystemSettings-Output: properties: title: type: string title: Title default: File System description: type: string title: Description default: Access and read files in the current session category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: true tool_display_icon: type: string title: Tool Display Icon default: FolderOpen tool_display_message_start: type: string title: Tool Display Message Start default: Accessing file system... tool_display_message_end: type: string title: Tool Display Message End default: File system operation complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: FolderOpen bg_color: type: string title: Bg Color default: '#fef3c7' icon_color: type: string title: Icon Color default: '#f59e0b' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: filesystem title: Type default: filesystem type: object title: FileSystemSettings FileSettings-Output: properties: title: type: string title: Title default: Files description: type: string title: Description default: Attach, generate, and work with files. category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Files tool_display_message_start: type: string title: Tool Display Message Start default: Working with files... tool_display_message_end: type: string title: Tool Display Message End default: Done extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Files bg_color: type: string title: Bg Color default: '#EFF6FF' icon_color: type: string title: Icon Color default: '#2B7FFF' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: files title: Type default: files allow_html_graphs: type: boolean title: Allow Html Graphs description: >- Instruct the agent to use self-contained HTML (Plotly, Chart.js, ...) when generating charts and visualizations. default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Use HTML for charts needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden show_inline: type: boolean title: Show Inline description: Render HTML and images directly in the chat instead of as a card. default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Render artifacts inline needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden custom_author_name: type: boolean title: Custom Author Name description: >- Use a custom author for track-change revisions and comments. When off, the agent's name is used. default: false accordion: Word documents (.docx) display: col_span: 12 is_disabled: false is_subconfig: false label: Custom track-change author needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden author_name: type: string title: Author Name description: >- Author shown on track-change revisions and comments. Defaults to the agent's name when left unset. default: '' accordion: Word documents (.docx) display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Track-change author needs_confirmation: false number_of_lines: 1 placeholder: The agent's name show_optional_label: false show_refresh: false type: text rules: - config_source: custom_author_name type: visible_if value: true tab: Configuration tool_mode: hidden enable_python_sandbox: type: boolean title: Enable Python Sandbox description: Run pandas/Python over the workbook in the sandbox. default: false accordion: Spreadsheets (Excel) display: col_span: 12 is_disabled: false is_subconfig: false label: Python sandbox needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false enable_formula_eval: type: boolean title: Enable Formula Eval description: Evaluate spreadsheet formulas via the formulas library. default: false accordion: Spreadsheets (Excel) display: col_span: 12 is_disabled: false is_subconfig: false label: Formula evaluation needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false experimental: type: boolean title: Experimental description: Enable every experimental spreadsheet tool above. default: false accordion: Spreadsheets (Excel) display: col_span: 12 is_disabled: false is_subconfig: false label: All experimental spreadsheet tools needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: object title: FileSettings description: >- Unified file capability for the agent. One master toggle that, when on, lets the user attach files and lets the agent generate + present them (``create_file``, ``present_file``, ``sandbox_publish_file``). Word (.docx) and Excel editing are offered on-demand whenever a matching file is in the session — no separate toggles. The always-on session-file reader (``list_files``/``read_file``) is a separate, hidden capability (``FileSystemSettings``) and is unaffected. TodoSettings-Output: properties: title: type: string title: Title default: Task Tracking description: type: string title: Description default: Track and manage tasks during the conversation category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: ListTodo tool_display_message_start: type: string title: Tool Display Message Start default: Managing tasks... tool_display_message_end: type: string title: Tool Display Message End default: Tasks updated extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: ListTodo bg_color: type: string title: Bg Color default: '#f0fdf4' icon_color: type: string title: Icon Color default: '#16a34a' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: todos title: Type default: todos enable_subtasks: type: boolean title: Enable Subtasks description: Enable subtask hierarchy and dependency features default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Enable Subtasks needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false type: object title: TodoSettings description: |- Settings for the task tracking toolset. Wraps pydantic-ai-todo's create_todo_toolset() with Noxus settings. Todos are persisted in conversation.memory["todos"]. SandboxSettings-Output: properties: title: type: string title: Title default: Sandbox description: type: string title: Description default: File operations and command execution in isolated sandbox category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Terminal tool_display_message_start: type: string title: Tool Display Message Start default: Working in sandbox... tool_display_message_end: type: string title: Tool Display Message End default: Command complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Terminal bg_color: type: string title: Bg Color default: '#fef3c7' icon_color: type: string title: Icon Color default: '#d97706' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: sandbox title: Type default: sandbox persistent: type: boolean title: Persistent description: Keep sandbox running permanently (no idle timeout) default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Keep Running needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden include_execute: type: boolean title: Include Execute description: Include shell command execution tool default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Shell Execution needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden require_write_approval: type: boolean title: Require Write Approval description: Require user approval for file write/edit operations default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Approve Writes needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden require_execute_approval: type: boolean title: Require Execute Approval description: Require user approval for shell command execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Approve Execution needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden type: object title: SandboxSettings description: >- Settings for the sandbox console toolset. Wraps pydantic-ai-backend's create_console_toolset() with Noxus settings. Provides file operations (ls, read, write, edit, glob, grep) and optional shell execution in an isolated sandbox environment. ScheduleToolSettings-Output: properties: title: type: string title: Title default: Periodic Tasks description: type: string title: Description default: Create periodic tasks that call this agent on a schedule category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Clock tool_display_message_start: type: string title: Tool Display Message Start default: Managing schedule... tool_display_message_end: type: string title: Tool Display Message End default: Schedule updated extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Clock bg_color: type: string title: Bg Color default: '#eff6ff' icon_color: type: string title: Icon Color default: '#2563eb' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: schedule_tool title: Type default: schedule_tool type: object title: ScheduleToolSettings SubAgentSettings-Output: properties: title: type: string title: Title default: Task Delegation description: type: string title: Description default: Delegate tasks to specialized subagents category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: true tool_display_icon: type: string title: Tool Display Icon default: Users tool_display_message_start: type: string title: Tool Display Message Start default: Delegating task... tool_display_message_end: type: string title: Tool Display Message End default: Task delegated extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: Users bg_color: type: string title: Bg Color default: '#f0f9ff' icon_color: type: string title: Icon Color default: '#0284c7' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: subagent title: Type default: subagent subagents: items: $ref: '#/components/schemas/SubAgentDefinition' type: array title: Subagents default: [] type: object title: SubAgentSettings description: >- Settings for the subagent task delegation toolset. The roster and the delegation guidance live on the agent settings (``subagents``, ``subagents_instructions``); this variant only carries the tool's chat display. CodeExecutionSettings-Output: properties: title: type: string title: Title default: Code Execution description: type: string title: Description default: Run Python code in a sandboxed environment category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: Terminal tool_display_message_start: type: string title: Tool Display Message Start default: Running code... tool_display_message_end: type: string title: Tool Display Message End default: Code executed extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: Terminal bg_color: type: string title: Bg Color default: '#fef9c3' icon_color: type: string title: Icon Color default: '#ca8a04' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: code_execution title: Type default: code_execution timeout: type: integer title: Timeout description: Maximum execution time in seconds default: 60 display: col_span: 12 hide_number: false is_disabled: false is_subconfig: false label: Timeout (seconds) max: 300 min: 10 needs_confirmation: false show_optional_label: false step: 10 type: number_slider tab: Configuration tool_mode: hidden type: object title: CodeExecutionSettings AgentMemorySettings-Output: properties: title: type: string title: Title default: Agent Memory description: type: string title: Description default: Persistent memory across all conversations category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: BookOpen tool_display_message_start: type: string title: Tool Display Message Start default: Accessing agent memory... tool_display_message_end: type: string title: Tool Display Message End default: Memory operation complete extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: BookOpen bg_color: type: string title: Bg Color default: '#fef3c7' icon_color: type: string title: Icon Color default: '#d97706' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: agent_memory title: Type default: agent_memory type: object title: AgentMemorySettings description: |- Settings for the persistent agent memory toolset. Memories are stored in assistant.definition["memories"] JSONB and persist across all conversations with this agent. CreateFilesSettings-Output: properties: title: type: string title: Title default: Create Files description: type: string title: Description default: Generate files and surface them in the chat. category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: FileInput tool_display_message_start: type: string title: Tool Display Message Start default: Working with files... tool_display_message_end: type: string title: Tool Display Message End default: Done extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible default: false icon: type: string title: Icon default: FileInput bg_color: type: string title: Bg Color default: '#EFF6FF' icon_color: type: string title: Icon Color default: '#2B7FFF' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated default: true type: type: string const: create_files title: Type default: create_files allow_html_graphs: type: boolean title: Allow Html Graphs description: >- Instruct the agent to use self-contained HTML (Plotly, Chart.js, ...) when generating charts and visualizations. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Use HTML for charts needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden show_inline: type: boolean title: Show Inline description: Render HTML and images directly in the chat instead of as a card. default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Render artifacts inline needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden type: object title: CreateFilesSettings description: >- Unified setting for the file creation + presentation tools. Enables ``create_file`` (generate text/markdown/html/json/csv/code into the session) and ``present_file`` (surface a session file as a preview/download card in the chat). They share one toggle because they're useless apart — creating a file the user can't see is dead weight, and presenting nothing is a no-op. DocumentationSettings-Output: properties: title: type: string title: Title default: Documentation description: type: string title: Description default: Search and read Noxus platform documentation category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: BookOpen tab: Configuration tool_mode: hidden visible: false tool_display_message_start: type: string title: Tool Display Message Start default: Searching documentation... col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: Start message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when searching docs. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden tool_display_message_end: type: string title: Tool Display Message End default: Documentation found col_span: 6 display: col_span: 12 is_code: false is_disabled: false is_subconfig: false is_textarea: false label: End message needs_confirmation: false number_of_lines: 1 placeholder: Message displayed when search completes. show_optional_label: false show_refresh: false type: text tab: Configuration tool_mode: hidden extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: BookOpen bg_color: type: string title: Bg Color default: '#EFF6FF' icon_color: type: string title: Icon Color default: '#2B7FFF' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: documentation title: Type default: documentation type: object title: DocumentationSettings ImageGenerationSettings-Output: properties: title: type: string title: Title default: Image Generation description: type: string title: Description default: Generate images from text prompts, shown inline in the chat. category: type: string enum: - QuickAction - Flows - Knowledge - Actions - MCP - Chatflow - Agents title: Category description: The category of the tool default: QuickAction enabled: type: boolean title: Enabled default: false tool_display_icon: type: string title: Tool Display Icon default: ImagePlus tool_display_message_start: type: string title: Tool Display Message Start default: Generating image... tool_display_message_end: type: string title: Tool Display Message End default: Image generated extra_instructions: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' description: Any extra instructions for the tool display: allow_reference_mentions: false col_span: 12 connector_name: '' enable_heuristics: true heuristic_context: >- Tool execution conditions specifying when and how the agent should use this tool heuristic_types: - clarity - specificity - actionability improver_prompt: PromptImproverPromptV2 is_disabled: false is_subconfig: false label: Execution Conditions needs_confirmation: false number_of_lines: 5 show_optional_label: false type: rich_text_variables_ai tab: Configuration tool_mode: hidden requires_approval: type: boolean title: Requires Approval description: Whether tool calls require user approval before execution default: false display: col_span: 12 is_disabled: false is_subconfig: false label: Require Approval needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: type: boolean title: Visible description: Whether the tool is visible default: true display: col_span: 12 is_disabled: false is_subconfig: false label: Visible needs_confirmation: false show_optional_label: false toggle_position: right type: toggle tab: Configuration tool_mode: hidden visible: false icon: type: string title: Icon default: ImagePlus bg_color: type: string title: Bg Color default: '#FDF4FF' icon_color: type: string title: Icon Color default: '#C026D3' chatflow_usable: type: boolean title: Chatflow Usable description: Whether the tool is usable in a chatflow default: true deprecated: type: boolean title: Deprecated description: >- Whether this tool type is deprecated and should be hidden from the UI default: false type: type: string const: image_generation title: Type default: image_generation type: object title: ImageGenerationSettings description: |- Image generation quick action. When on, the agent can generate images from text prompts with any image-generation-capable model in the registry; results are surfaced inline in the chat. MCPServerBinding: properties: credential_id: type: string format: uuid title: Credential Id enabled: type: boolean title: Enabled default: true selected_tools: anyOf: - items: type: string type: array - type: 'null' title: Selected Tools type: object required: - credential_id title: MCPServerBinding description: >- Per-agent binding to a workspace MCP credential. ``selected_tools=None`` means "every tool the server exposes minus the credential's ``disabled_tools``" — new server tools flow through without a re-probe. An explicit list is a per-agent allowlist narrowed further by the workspace denials. SkillConfig: properties: name: type: string title: Name description: type: string title: Description default: '' tags: items: type: string type: array title: Tags version: type: string title: Version default: 1.0.0 author: type: string title: Author default: '' instructions: type: string title: Instructions default: '' enabled: type: boolean title: Enabled default: true resources: additionalProperties: type: string type: object title: Resources type: object required: - name title: SkillConfig description: |- Full skill definition stored in agent settings. Skills are markdown-based instruction packages that extend agent capabilities. Stored directly in the agent's ``definition`` JSONB column — no separate table or migration needed. SubAgentDefinition: properties: name: type: string title: Name description: type: string title: Description instructions: type: string title: Instructions model: items: type: string type: array title: Model default: [] enabled: type: boolean title: Enabled default: true type: object required: - name - description - instructions title: SubAgentDefinition description: Single subagent config from frontend. GuidelineConfig: properties: id: type: string title: Id condition: type: string title: Condition action: type: string title: Action priority: type: string title: Priority default: NORMAL tags: items: type: string type: array title: Tags enabled: type: boolean title: Enabled default: true tool_association: anyOf: - $ref: '#/components/schemas/ToolAssociationConfig' - type: 'null' tool_associations: items: $ref: '#/components/schemas/ToolAssociationConfig' type: array title: Tool Associations type: object required: - id - condition - action title: GuidelineConfig description: A single When/Then behavioral guideline stored in agent settings. GlossaryTermConfig: properties: term: type: string title: Term definition: type: string title: Definition synonyms: items: type: string type: array title: Synonyms type: object required: - term - definition title: GlossaryTermConfig description: A glossary term definition stored in agent settings. AgentMemoryEntry: properties: id: type: string title: Id content: type: string title: Content category: type: string title: Category default: general created_at: type: string title: Created At default: '' updated_at: type: string title: Updated At default: '' type: object required: - id - content title: AgentMemoryEntry description: A single persistent memory entry stored in agent settings. AgentFileConfig-Output: properties: file: $ref: '#/components/schemas/File-Output' context: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' enabled: type: boolean title: Enabled default: true delimiter: anyOf: - type: string - type: 'null' title: Delimiter type: object required: - file title: AgentFileConfig description: >- A file pre-loaded into every conversation of an agent, with context. Stored directly in the agent's ``definition`` JSONB column. The file is uploaded in the agent settings (``file.uri`` is a ``spot://`` reference); ``context`` is shown to the agent so it knows what the file is and when to read it via the always-on session-file tools. AgentDatabaseConfig-Output: properties: credential_id: type: string format: uuid title: Credential Id context: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' enabled: type: boolean title: Enabled default: true selected_tables: anyOf: - items: type: string type: array - type: 'null' title: Selected Tables max_rows: type: integer maximum: 10000 minimum: 1 title: Max Rows default: 100 query_timeout_seconds: type: integer maximum: 300 minimum: 1 title: Query Timeout Seconds default: 30 type: object required: - credential_id title: AgentDatabaseConfig description: |- A SQL database, referenced by stored credential id, the agent can query read-only. ``selected_tables=None`` means every table is visible. AgentTableConfig-Output: properties: table_id: type: string format: uuid title: Table Id context: anyOf: - $ref: '#/components/schemas/NoxusTipTapDocument-Output' - type: 'null' enabled: type: boolean title: Enabled default: true read_only: type: boolean title: Read Only default: true max_rows: type: integer maximum: 10000 minimum: 1 title: Max Rows default: 100 query_timeout_seconds: type: integer maximum: 300 minimum: 1 title: Query Timeout Seconds default: 30 type: object required: - table_id title: AgentTableConfig description: >- A single workspace custom table the agent can query read-only, with its own context and limits. Queries run as the workspace's read-only tenant role and are restricted to this table. CustomInsightDefinition: properties: name: type: string maxLength: 200 title: Name prompt: type: string maxLength: 2000 title: Prompt scope: type: string enum: - all - resolved - unresolved - escalated - abandoned - rated-high - rated-low title: Scope default: all type: object required: - name - prompt title: CustomInsightDefinition description: A user-defined situation to detect in a conversation (binary). UserMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: user timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: user title: Type default: user content: type: string title: Content default: '' tool: anyOf: - type: string enum: - kb_qa - web_research - workflow - list_workflows - run_integration - noxus_qa - human_in_the_loop - type: string - type: 'null' title: Tool kb_id: anyOf: - type: string - type: 'null' title: Kb Id workflow_id: anyOf: - type: string - type: 'null' title: Workflow Id files: anyOf: - items: $ref: '#/components/schemas/ConversationFile' type: array - type: 'null' title: Files model_selection: anyOf: - items: type: string type: array - type: string - type: 'null' title: Model Selection images: anyOf: - items: type: string type: array - type: 'null' title: Images refresh_message: type: boolean title: Refresh Message default: false new_chat: type: boolean title: New Chat default: false type: object title: UserMessage ToolCallMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: function timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id tool_type: anyOf: - type: string enum: - kb_qa - web_research - workflow - list_workflows - run_integration - noxus_qa - human_in_the_loop - type: string title: Tool Type type: type: string const: tool_call title: Type default: tool_call display_message_start: type: string title: Display Message Start default: Running tool... display_message_end: type: string title: Display Message End default: Tool finished running icon: type: string title: Icon default: Cog run_id: anyOf: - type: string - type: 'null' title: Run Id type: object required: - tool_type title: ToolCallMessage ToolCalledMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: function timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id tool_type: anyOf: - type: string enum: - kb_qa - web_research - workflow - list_workflows - run_integration - noxus_qa - human_in_the_loop - type: string title: Tool Type type: type: string const: tool_called title: Type default: tool_called content: type: string title: Content type: object required: - tool_type - content title: ToolCalledMessage ToolCalledMessageEnd: properties: role: $ref: '#/components/schemas/MessageRole' default: function timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id tool_type: anyOf: - type: string enum: - kb_qa - web_research - workflow - list_workflows - run_integration - noxus_qa - human_in_the_loop - type: string title: Tool Type type: type: string const: tool_called_end title: Type default: tool_called_end content: type: string title: Content type: object required: - tool_type - content title: ToolCalledMessageEnd MessageEnd: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: message_end title: Type default: message_end content: type: string title: Content default: '' pydantic_messages: anyOf: - {} - type: 'null' title: Pydantic Messages noxus_messages: anyOf: - items: $ref: '#/components/schemas/BaseMessage' type: array - type: 'null' title: Noxus Messages type: object title: MessageEnd MarkdownMessage: properties: role: $ref: '#/components/schemas/MessageRole' timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: markdown title: Type default: markdown content: type: string title: Content default: '' type: object required: - role title: MarkdownMessage AudioReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id kb_id: anyOf: - type: string format: uuid - type: 'null' title: Kb Id doc_id: anyOf: - type: string format: uuid - type: 'null' title: Doc Id file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id file_name: anyOf: - type: string - type: 'null' title: File Name from_timestamp: type: string format: duration title: From Timestamp to_timestamp: type: string format: duration title: To Timestamp type: type: string const: audio title: Type default: audio type: object required: - from_timestamp - to_timestamp title: AudioReferenceMessage ImageReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id kb_id: anyOf: - type: string format: uuid - type: 'null' title: Kb Id doc_id: anyOf: - type: string format: uuid - type: 'null' title: Doc Id file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id file_name: anyOf: - type: string - type: 'null' title: File Name type: type: string const: image title: Type default: image type: object title: ImageReferenceMessage VideoReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id kb_id: anyOf: - type: string format: uuid - type: 'null' title: Kb Id doc_id: anyOf: - type: string format: uuid - type: 'null' title: Doc Id file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id file_name: anyOf: - type: string - type: 'null' title: File Name from_timestamp: type: string format: duration title: From Timestamp to_timestamp: type: string format: duration title: To Timestamp type: type: string const: video title: Type default: video type: object required: - from_timestamp - to_timestamp title: VideoReferenceMessage DocumentReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id kb_id: anyOf: - type: string format: uuid - type: 'null' title: Kb Id doc_id: anyOf: - type: string format: uuid - type: 'null' title: Doc Id file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id file_name: anyOf: - type: string - type: 'null' title: File Name type: type: string const: document title: Type default: document quote: type: string title: Quote page_label: type: string title: Page Label ref_num: type: integer title: Ref Num content_type: anyOf: - type: string - type: 'null' title: Content Type url: anyOf: - type: string - type: 'null' title: Url type: object required: - quote - page_label - ref_num title: DocumentReferenceMessage WebReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: web_reference title: Type default: web_reference quote: type: string title: Quote title: type: string title: Title ref_label: type: string title: Ref Label url: type: string title: Url image_url: anyOf: - type: string - type: 'null' title: Image Url type: object required: - quote - title - ref_label - url title: WebReferenceMessage ImageCarouselMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: image_carousel title: Type default: image_carousel images: items: anyOf: - $ref: '#/components/schemas/ImageReferenceMessage' - $ref: '#/components/schemas/DocumentReferenceMessage' type: array title: Images type: object required: - images title: ImageCarouselMessage SourceReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: source_reference title: Type default: source_reference references: items: anyOf: - $ref: '#/components/schemas/DocumentReferenceMessage' - $ref: '#/components/schemas/WebReferenceMessage' - $ref: '#/components/schemas/YoutubeReferenceMessage' type: array title: References type: object required: - references title: SourceReferenceMessage SystemMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: system timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: system title: Type default: system content: type: string title: Content default: '' type: object title: SystemMessage ErrorMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id content: type: string title: Content show_to_user: type: boolean title: Show To User default: true close_delay: anyOf: - type: integer - type: 'null' title: Close Delay type: type: string const: error title: Type default: error error_type: anyOf: - type: string - type: 'null' title: Error Type type: object required: - content title: ErrorMessage WarningMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id content: type: string title: Content show_to_user: type: boolean title: Show To User default: true close_delay: anyOf: - type: integer - type: 'null' title: Close Delay type: type: string const: warning title: Type default: warning warning_type: anyOf: - type: string - type: 'null' title: Warning Type type: object required: - content title: WarningMessage InfoMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id content: type: string title: Content show_to_user: type: boolean title: Show To User default: true close_delay: anyOf: - type: integer - type: 'null' title: Close Delay type: type: string const: info title: Type default: info type: object required: - content title: InfoMessage SuccessMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id content: type: string title: Content show_to_user: type: boolean title: Show To User default: true close_delay: anyOf: - type: integer - type: 'null' title: Close Delay type: type: string const: success title: Type default: success type: object required: - content title: SuccessMessage SetConversationTitle: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: set_conversation_title title: Type default: set_conversation_title content: type: string title: Content type: object required: - content title: SetConversationTitle InternalToolResultMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: function timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id tool_type: anyOf: - type: string enum: - kb_qa - web_research - workflow - list_workflows - run_integration - noxus_qa - human_in_the_loop - type: string title: Tool Type type: type: string const: tool_result title: Type default: tool_result content: type: string title: Content type: object required: - tool_type - content title: InternalToolResultMessage YoutubeReferenceMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: youtube_reference title: Type default: youtube_reference url: type: string title: Url type: object required: - url title: YoutubeReferenceMessage StateTransitionMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: state_transition title: Type default: state_transition data: additionalProperties: true type: object title: Data next_state_key: type: string title: Next State Key type: object required: - data - next_state_key title: StateTransitionMessage ChatflowExtractionMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: chatflow_extraction title: Type default: chatflow_extraction data: additionalProperties: true type: object title: Data type: object required: - data title: ChatflowExtractionMessage ConversationEndMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: conversation_end title: Type default: conversation_end type: object title: ConversationEndMessage HumanInTheLoopMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: human_in_the_loop title: Type default: human_in_the_loop title: type: string title: Title description: type: string title: Description reason: type: string title: Reason priority: type: string enum: - low - medium - high - critical title: Priority type: object required: - title - description - reason - priority title: HumanInTheLoopMessage MemoryMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: memory title: Type default: memory content: additionalProperties: true type: object title: Content type: object required: - content title: MemoryMessage KBContextMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: kb_context title: Type default: kb_context context: $ref: '#/components/schemas/QAContext' type: object required: - context title: KBContextMessage WebpageContextMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: webpage_context title: Type default: webpage_context context: $ref: '#/components/schemas/WebpageContext' type: object required: - context title: WebpageContextMessage HumanInTheLoopAssignedMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: human_in_the_loop_assigned title: Type default: human_in_the_loop_assigned assigned_to: type: string format: uuid title: Assigned To type: object required: - assigned_to title: HumanInTheLoopAssignedMessage ThinkingMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: assistant timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: thinking title: Type default: thinking content: type: string title: Content default: '' type: object title: ThinkingMessage ThinkingEndedMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: thinking_ended title: Type default: thinking_ended seconds_duration: type: integer title: Seconds Duration type: object required: - seconds_duration title: ThinkingEndedMessage ClearConversationStreamMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: clear_conversation_stream title: Type default: clear_conversation_stream content: type: string title: Content default: '' type: object title: ClearConversationStreamMessage WorkflowRunningMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: workflow_running title: Type default: workflow_running workflow_id: type: string title: Workflow Id run_id: type: string title: Run Id display_message_start: type: string title: Display Message Start default: Running workflow... display_message_end: type: string title: Display Message End default: Workflow finished running type: object required: - workflow_id - run_id title: WorkflowRunningMessage ChatflowTransitionMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: chatflow_transition title: Type default: chatflow_transition content: type: string title: Content type: object required: - content title: ChatflowTransitionMessage PresentedFileMessage: properties: role: $ref: '#/components/schemas/MessageRole' default: noxus timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: type: string const: presented_file title: Type default: presented_file file_id: type: string title: File Id name: type: string title: Name content_type: type: string title: Content Type url: type: string title: Url size: anyOf: - type: integer - type: 'null' title: Size caption: anyOf: - type: string - type: 'null' title: Caption show_inline: type: boolean title: Show Inline default: false source_image: type: boolean title: Source Image default: false type: object required: - file_id - name - content_type - url title: PresentedFileMessage description: >- Persisted record of a file the agent surfaced via ``present_file``. Lives alongside the assistant message in ``Message.message_parts_`` so the file widget survives conversation reload and so the data chunk does not need to round-trip through the FE (which causes 422s on the next turn). ModelRequest: properties: parts: items: oneOf: - $ref: '#/components/schemas/SystemPromptPart' - $ref: '#/components/schemas/UserPromptPart' - $ref: '#/components/schemas/ToolSearchReturnPart' - $ref: '#/components/schemas/LoadCapabilityReturnPart' - $ref: '#/components/schemas/ToolReturnPart' - $ref: '#/components/schemas/RetryPromptPart' type: array title: Parts timestamp: anyOf: - type: string format: date-time - type: 'null' title: Timestamp instructions: anyOf: - type: string - type: 'null' title: Instructions kind: type: string const: request title: Kind default: request run_id: anyOf: - type: string - type: 'null' title: Run Id conversation_id: anyOf: - type: string - type: 'null' title: Conversation Id metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata state: type: string enum: - complete - interrupted title: State default: complete type: object required: - parts title: ModelRequest ModelResponse: properties: parts: items: oneOf: - $ref: '#/components/schemas/TextPart' - $ref: '#/components/schemas/ToolSearchCallPart' - $ref: '#/components/schemas/LoadCapabilityCallPart' - $ref: '#/components/schemas/ToolCallPart' - $ref: '#/components/schemas/NativeToolSearchCallPart' - $ref: '#/components/schemas/NativeToolCallPart' - $ref: '#/components/schemas/NativeToolSearchReturnPart' - $ref: '#/components/schemas/NativeToolReturnPart' - $ref: '#/components/schemas/ThinkingPart' - $ref: '#/components/schemas/CompactionPart' - $ref: '#/components/schemas/FilePart' type: array title: Parts usage: $ref: '#/components/schemas/RequestUsage' model_name: anyOf: - type: string - type: 'null' title: Model Name timestamp: type: string format: date-time title: Timestamp kind: type: string const: response title: Kind default: response provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_url: anyOf: - type: string - type: 'null' title: Provider Url provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details provider_response_id: anyOf: - type: string - type: 'null' title: Provider Response Id finish_reason: anyOf: - type: string enum: - stop - length - content_filter - tool_call - error - type: 'null' title: Finish Reason run_id: anyOf: - type: string - type: 'null' title: Run Id conversation_id: anyOf: - type: string - type: 'null' title: Conversation Id metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata state: type: string enum: - complete - incomplete - suspended - interrupted title: State default: complete type: object required: - parts title: ModelResponse FeedbackMeta: properties: feedback_reason: anyOf: - type: string - type: 'null' title: Feedback Reason comment: anyOf: - type: string - type: 'null' title: Comment type: object title: FeedbackMeta SenderRefSchema: properties: type: type: string title: Type default: external user_id: anyOf: - type: string format: uuid - type: 'null' title: User Id agent_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Id external_participant: anyOf: - additionalProperties: true type: object - type: 'null' title: External Participant type: object title: SenderRefSchema description: External participant identity on a message. TextUIPart: properties: type: type: string const: text title: Type default: text text: type: string title: Text state: anyOf: - type: string enum: - streaming - done - type: 'null' title: State providerMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Providermetadata additionalProperties: false type: object required: - text title: TextUIPart description: A text part of a message. ReasoningUIPart: properties: type: type: string const: reasoning title: Type default: reasoning text: type: string title: Text state: anyOf: - type: string enum: - streaming - done - type: 'null' title: State providerMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Providermetadata additionalProperties: false type: object required: - text title: ReasoningUIPart description: A reasoning part of a message. ToolInputStreamingPart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: input-streaming title: State default: input-streaming input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolInputStreamingPart description: Tool part in input-streaming state. ToolInputAvailablePart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: input-available title: State default: input-available input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolInputAvailablePart description: Tool part in input-available state. ToolOutputAvailablePart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-available title: State default: output-available input: anyOf: - {} - type: 'null' title: Input output: anyOf: - {} - type: 'null' title: Output providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata preliminary: anyOf: - type: boolean - type: 'null' title: Preliminary approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolOutputAvailablePart description: Tool part in output-available state. ToolOutputErrorPart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-error title: State default: output-error input: anyOf: - {} - type: 'null' title: Input rawInput: anyOf: - {} - type: 'null' title: Rawinput errorText: type: string title: Errortext providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId - errorText title: ToolOutputErrorPart description: Tool part in output-error state. ToolApprovalRequestedPart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: approval-requested title: State default: approval-requested input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolApprovalRequestedPart description: Tool part in approval-requested state (awaiting user decision). ToolApprovalRespondedPart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: approval-responded title: State default: approval-responded input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolApprovalRespondedPart description: >- Tool part in approval-responded state (user approved/denied, execution pending). ToolOutputDeniedPart: properties: type: type: string pattern: ^tool- title: Type toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-denied title: State default: output-denied input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - type - toolCallId title: ToolOutputDeniedPart description: Tool part in output-denied state (tool was denied, terminal state). DynamicToolInputStreamingPart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: input-streaming title: State default: input-streaming input: anyOf: - {} - type: 'null' title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId title: DynamicToolInputStreamingPart description: Dynamic tool part in input-streaming state. DynamicToolInputAvailablePart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: input-available title: State default: input-available input: title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input title: DynamicToolInputAvailablePart description: Dynamic tool part in input-available state. DynamicToolOutputAvailablePart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-available title: State default: output-available input: title: Input output: title: Output providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata preliminary: anyOf: - type: boolean - type: 'null' title: Preliminary approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input - output title: DynamicToolOutputAvailablePart description: Dynamic tool part in output-available state. DynamicToolOutputErrorPart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-error title: State default: output-error input: title: Input errorText: type: string title: Errortext providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input - errorText title: DynamicToolOutputErrorPart description: Dynamic tool part in output-error state. DynamicToolApprovalRequestedPart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: approval-requested title: State default: approval-requested input: title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input title: DynamicToolApprovalRequestedPart description: Dynamic tool part in approval-requested state (awaiting user decision). DynamicToolApprovalRespondedPart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: approval-responded title: State default: approval-responded input: title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input title: DynamicToolApprovalRespondedPart description: >- Dynamic tool part in approval-responded state (user approved/denied, execution pending). DynamicToolOutputDeniedPart: properties: type: type: string const: dynamic-tool title: Type default: dynamic-tool toolName: type: string title: Toolname toolCallId: type: string title: Toolcallid title: anyOf: - type: string - type: 'null' title: Title state: type: string const: output-denied title: State default: output-denied input: title: Input providerExecuted: anyOf: - type: boolean - type: 'null' title: Providerexecuted callProviderMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Callprovidermetadata approval: anyOf: - $ref: '#/components/schemas/ToolApprovalRequested' - $ref: '#/components/schemas/ToolApprovalResponded' - type: 'null' title: Approval additionalProperties: false type: object required: - toolName - toolCallId - input title: DynamicToolOutputDeniedPart description: >- Dynamic tool part in output-denied state (tool was denied, terminal state). SourceUrlUIPart: properties: type: type: string const: source-url title: Type default: source-url sourceId: type: string title: Sourceid url: type: string title: Url title: anyOf: - type: string - type: 'null' title: Title providerMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Providermetadata additionalProperties: false type: object required: - sourceId - url title: SourceUrlUIPart description: A source part of a message. SourceDocumentUIPart: properties: type: type: string const: source-document title: Type default: source-document sourceId: type: string title: Sourceid mediaType: type: string title: Mediatype title: type: string title: Title filename: anyOf: - type: string - type: 'null' title: Filename providerMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Providermetadata additionalProperties: false type: object required: - sourceId - mediaType - title title: SourceDocumentUIPart description: A document source part of a message. FileUIPart: properties: type: type: string const: file title: Type default: file mediaType: type: string title: Mediatype filename: anyOf: - type: string - type: 'null' title: Filename url: type: string title: Url providerMetadata: anyOf: - additionalProperties: additionalProperties: true type: object type: object - type: 'null' title: Providermetadata additionalProperties: false type: object required: - mediaType - url title: FileUIPart description: A file part of a message. DataUIPart: properties: type: type: string pattern: ^data- title: Type id: anyOf: - type: string - type: 'null' title: Id data: title: Data additionalProperties: false type: object required: - type - data title: DataUIPart description: Data part with dynamic type based on data name. StepStartUIPart: properties: type: type: string const: step-start title: Type default: step-start additionalProperties: false type: object title: StepStartUIPart description: A step boundary part of a message. TiptapDocument-Output: properties: type: type: string title: Type default: doc content: items: $ref: '#/components/schemas/Node-Output' type: array title: Content default: [] type: object title: TiptapDocument Transition: properties: node_label: type: string title: Node Label transition_key: anyOf: - type: string - type: 'null' title: Transition Key transition_criteria: type: string title: Transition Criteria type: object required: - node_label - transition_criteria title: Transition ActionToolConfig: properties: config_overrides: additionalProperties: true type: object title: Config Overrides input_overrides: additionalProperties: true type: object title: Input Overrides exposed_configs: items: type: string type: array title: Exposed Configs exposed_inputs: items: type: string type: array title: Exposed Inputs type: object title: ActionToolConfig description: >- Configuration for hardcoded values and exposed parameters in action tools. For each config parameter or input connector, you either: 1. Hardcode it (store value in overrides, don't expose to LLM) 2. Expose it to LLM (add to exposed list, LLM provides value) ToolAssociationConfig: properties: tool_names: items: type: string type: array title: Tool Names mode: type: string title: Mode default: PREFER type: object title: ToolAssociationConfig description: Tool enforcement configuration for a guideline. File-Output: properties: id: anyOf: - type: string - type: 'null' title: Id uri: type: string title: Uri name: type: string title: Name content_type: type: string title: Content Type default: text/plain size: anyOf: - type: integer - type: 'null' title: Size content_metadata: anyOf: - oneOf: - $ref: '#/components/schemas/PdfMetadata' - $ref: '#/components/schemas/SpreadsheetMetadata' - $ref: '#/components/schemas/TabularMetadata' discriminator: propertyName: kind mapping: pdf: $ref: '#/components/schemas/PdfMetadata' spreadsheet: $ref: '#/components/schemas/SpreadsheetMetadata' tabular: $ref: '#/components/schemas/TabularMetadata' - type: 'null' title: Content Metadata source_type: $ref: '#/components/schemas/SourceType' default: Document source_metadata: anyOf: - $ref: '#/components/schemas/SourceMetadata' - additionalProperties: true type: object - type: 'null' title: Source Metadata additionalProperties: true type: object required: - uri - name title: File MessageRole: type: string enum: - system - user - assistant - function - noxus - controller title: MessageRole ConversationFile: properties: id: anyOf: - type: string format: uuid - type: 'null' title: Id name: type: string title: Name size: anyOf: - type: integer - type: 'null' title: Size type: anyOf: - type: string - type: 'null' title: Type status: type: string enum: - pending - success - error title: Status url: anyOf: - type: string - type: 'null' title: Url b64_content: anyOf: - type: string - type: 'null' title: B64 Content type: object required: - id - name - size - type - status - url title: ConversationFile BaseMessage: properties: role: $ref: '#/components/schemas/MessageRole' timestamp: type: string format: date-time title: Timestamp model: type: string title: Model trace_id: anyOf: - type: string - type: 'null' title: Trace Id message_id: anyOf: - type: string - type: 'null' title: Message Id span_id: anyOf: - type: string - type: 'null' title: Span Id type: object required: - role title: BaseMessage QAContext: properties: file_name: type: string title: File Name doc_id: anyOf: - type: string - type: 'null' title: Doc Id node_id: anyOf: - type: string - type: 'null' title: Node Id path: anyOf: - type: string - type: 'null' title: Path page_num: anyOf: - type: integer - type: string - type: 'null' title: Page Num context: type: string title: Context type: object required: - file_name - context title: QAContext WebpageContext: properties: url: type: string title: Url context: type: string title: Context type: object required: - url - context title: WebpageContext SystemPromptPart: properties: content: type: string title: Content timestamp: type: string format: date-time title: Timestamp dynamic_ref: anyOf: - type: string - type: 'null' title: Dynamic Ref part_kind: type: string const: system-prompt title: Part Kind default: system-prompt type: object required: - content title: SystemPromptPart UserPromptPart: properties: content: anyOf: - type: string - items: anyOf: - type: string - $ref: '#/components/schemas/TextContent' - oneOf: - $ref: '#/components/schemas/ImageUrl' - $ref: '#/components/schemas/AudioUrl' - $ref: '#/components/schemas/DocumentUrl' - $ref: '#/components/schemas/VideoUrl' - $ref: '#/components/schemas/BinaryContent' - $ref: '#/components/schemas/UploadedFile' discriminator: propertyName: kind mapping: audio-url: $ref: '#/components/schemas/AudioUrl' binary: $ref: '#/components/schemas/BinaryContent' document-url: $ref: '#/components/schemas/DocumentUrl' image-url: $ref: '#/components/schemas/ImageUrl' uploaded-file: $ref: '#/components/schemas/UploadedFile' video-url: $ref: '#/components/schemas/VideoUrl' - $ref: '#/components/schemas/CachePoint' type: array title: Content timestamp: type: string format: date-time title: Timestamp part_kind: type: string const: user-prompt title: Part Kind default: user-prompt type: object required: - content title: UserPromptPart ToolSearchReturnPart: properties: tool_name: type: string const: search_tools title: Tool Name default: search_tools tool_call_id: type: string title: Tool Call Id tool_kind: type: string const: tool-search title: Tool Kind default: tool-search content: $ref: '#/components/schemas/ToolSearchReturnContent' metadata: title: Metadata timestamp: type: string format: date-time title: Timestamp outcome: type: string enum: - success - failed - denied - interrupted title: Outcome default: success part_kind: type: string const: tool-return title: Part Kind default: tool-return type: object required: - content title: ToolSearchReturnPart LoadCapabilityReturnPart: properties: tool_call_id: type: string title: Tool Call Id tool_name: type: string const: load_capability title: Tool Name default: load_capability content: $ref: '#/components/schemas/LoadCapabilityReturn' tool_kind: type: string const: capability-load title: Tool Kind default: capability-load metadata: title: Metadata timestamp: type: string format: date-time title: Timestamp outcome: type: string enum: - success - failed - denied - interrupted title: Outcome default: success part_kind: type: string const: tool-return title: Part Kind default: tool-return type: object required: - content title: LoadCapabilityReturnPart ToolReturnPart: properties: tool_name: type: string title: Tool Name content: $ref: '#/components/schemas/ToolReturnContent' tool_call_id: type: string title: Tool Call Id tool_kind: anyOf: - type: string enum: - tool-search - capability-load - type: 'null' title: Tool Kind metadata: title: Metadata timestamp: type: string format: date-time title: Timestamp outcome: type: string enum: - success - failed - denied - interrupted title: Outcome default: success part_kind: type: string const: tool-return title: Part Kind default: tool-return type: object required: - tool_name - content title: ToolReturnPart RetryPromptPart: properties: content: anyOf: - items: $ref: '#/components/schemas/ErrorDetails' type: array - type: string title: Content tool_name: anyOf: - type: string - type: 'null' title: Tool Name tool_call_id: type: string title: Tool Call Id timestamp: type: string format: date-time title: Timestamp part_kind: type: string const: retry-prompt title: Part Kind default: retry-prompt type: object required: - content title: RetryPromptPart TextPart: properties: content: type: string title: Content id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: text title: Part Kind default: text type: object required: - content title: TextPart ToolSearchCallPart: properties: tool_name: type: string const: search_tools title: Tool Name default: search_tools args: anyOf: - type: string - $ref: '#/components/schemas/ToolSearchArgs' - type: 'null' title: Args tool_call_id: type: string title: Tool Call Id tool_kind: type: string const: tool-search title: Tool Kind default: tool-search id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: tool-call title: Part Kind default: tool-call type: object title: ToolSearchCallPart LoadCapabilityCallPart: properties: tool_call_id: type: string title: Tool Call Id tool_name: type: string const: load_capability title: Tool Name default: load_capability args: anyOf: - type: string - $ref: '#/components/schemas/LoadCapabilityArgs' - type: 'null' title: Args tool_kind: type: string const: capability-load title: Tool Kind default: capability-load id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: tool-call title: Part Kind default: tool-call type: object title: LoadCapabilityCallPart ToolCallPart: properties: tool_name: type: string title: Tool Name args: anyOf: - type: string - additionalProperties: true type: object - type: 'null' title: Args tool_call_id: type: string title: Tool Call Id tool_kind: anyOf: - type: string enum: - tool-search - capability-load - type: 'null' title: Tool Kind id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: tool-call title: Part Kind default: tool-call type: object required: - tool_name title: ToolCallPart NativeToolSearchCallPart: properties: tool_name: type: string const: tool_search title: Tool Name default: tool_search args: anyOf: - type: string - $ref: '#/components/schemas/ToolSearchArgs' - type: 'null' title: Args tool_call_id: type: string title: Tool Call Id tool_kind: type: string const: tool-search title: Tool Kind default: tool-search id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: builtin-tool-call title: Part Kind default: builtin-tool-call type: object title: NativeToolSearchCallPart NativeToolCallPart: properties: tool_name: type: string title: Tool Name args: anyOf: - type: string - additionalProperties: true type: object - type: 'null' title: Args tool_call_id: type: string title: Tool Call Id tool_kind: anyOf: - type: string enum: - tool-search - capability-load - type: 'null' title: Tool Kind id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: builtin-tool-call title: Part Kind default: builtin-tool-call type: object required: - tool_name title: NativeToolCallPart NativeToolSearchReturnPart: properties: tool_name: type: string const: tool_search title: Tool Name default: tool_search tool_call_id: type: string title: Tool Call Id tool_kind: type: string const: tool-search title: Tool Kind default: tool-search content: $ref: '#/components/schemas/ToolSearchReturnContent' metadata: title: Metadata timestamp: type: string format: date-time title: Timestamp outcome: type: string enum: - success - failed - denied - interrupted title: Outcome default: success provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: builtin-tool-return title: Part Kind default: builtin-tool-return type: object required: - content title: NativeToolSearchReturnPart NativeToolReturnPart: properties: tool_name: type: string title: Tool Name content: $ref: '#/components/schemas/ToolReturnContent' tool_call_id: type: string title: Tool Call Id tool_kind: anyOf: - type: string enum: - tool-search - capability-load - type: 'null' title: Tool Kind metadata: title: Metadata timestamp: type: string format: date-time title: Timestamp outcome: type: string enum: - success - failed - denied - interrupted title: Outcome default: success provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: builtin-tool-return title: Part Kind default: builtin-tool-return type: object required: - tool_name - content title: NativeToolReturnPart ThinkingPart: properties: content: type: string title: Content id: anyOf: - type: string - type: 'null' title: Id signature: anyOf: - type: string - type: 'null' title: Signature provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: thinking title: Part Kind default: thinking type: object required: - content title: ThinkingPart CompactionPart: properties: content: anyOf: - type: string - type: 'null' title: Content id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: compaction title: Part Kind default: compaction type: object title: CompactionPart FilePart: properties: content: $ref: '#/components/schemas/BinaryContent' id: anyOf: - type: string - type: 'null' title: Id provider_name: anyOf: - type: string - type: 'null' title: Provider Name provider_details: anyOf: - additionalProperties: true type: object - type: 'null' title: Provider Details part_kind: type: string const: file title: Part Kind default: file type: object required: - content title: FilePart RequestUsage: properties: input_tokens: type: integer title: Input Tokens default: 0 cache_write_tokens: type: integer title: Cache Write Tokens default: 0 cache_read_tokens: type: integer title: Cache Read Tokens default: 0 output_tokens: type: integer title: Output Tokens default: 0 input_audio_tokens: type: integer title: Input Audio Tokens default: 0 cache_audio_read_tokens: type: integer title: Cache Audio Read Tokens default: 0 output_audio_tokens: type: integer title: Output Audio Tokens default: 0 details: additionalProperties: type: integer type: object title: Details type: object title: RequestUsage ToolApprovalRequested: properties: id: type: string title: Id additionalProperties: false type: object required: - id title: ToolApprovalRequested description: Tool approval in requested state (awaiting user response). ToolApprovalResponded: properties: id: type: string title: Id approved: type: boolean title: Approved reason: anyOf: - type: string - type: 'null' title: Reason additionalProperties: false type: object required: - id - approved title: ToolApprovalResponded description: Tool approval in responded state (user has approved or denied). Node-Output: properties: type: type: string title: Type attrs: anyOf: - additionalProperties: true type: object - type: 'null' title: Attrs content: anyOf: - items: $ref: '#/components/schemas/Node-Output' type: array - type: 'null' title: Content marks: anyOf: - items: $ref: '#/components/schemas/Mark' type: array - type: 'null' title: Marks text: anyOf: - type: string - type: 'null' title: Text type: object required: - type title: Node PdfMetadata: properties: kind: type: string const: pdf title: Kind default: pdf page_count: type: integer title: Page Count type: object required: - page_count title: PdfMetadata description: Structural metadata for a PDF file. SpreadsheetMetadata: properties: kind: type: string const: spreadsheet title: Kind default: spreadsheet sheets: items: $ref: '#/components/schemas/SheetInfo' type: array title: Sheets type: object required: - sheets title: SpreadsheetMetadata description: Structural metadata for a spreadsheet (Excel) file. TabularMetadata: properties: kind: type: string const: tabular title: Kind default: tabular row_count: type: integer title: Row Count column_count: type: integer title: Column Count type: object required: - row_count - column_count title: TabularMetadata description: Structural metadata for a delimited-text (CSV/TSV) file. SourceType: type: string enum: - Document - Google Drive - Notion - Website - OneDrive - Slack - Linear - Github - Teams - Sharepoint - ServiceNow - Custom title: SourceType SourceMetadata: properties: rel_path: anyOf: - type: string - type: 'null' title: Rel Path external_id: anyOf: - type: string - type: 'null' title: External Id file_created_date: anyOf: - type: string - type: 'null' title: File Created Date file_modified_date: anyOf: - type: string - type: 'null' title: File Modified Date original_url: anyOf: - type: string - type: 'null' title: Original Url source_label: anyOf: - type: string - type: 'null' title: Source Label source_image: anyOf: - type: string - type: 'null' title: Source Image additionalProperties: true type: object title: SourceMetadata description: |- Base class for source metadata across different source types. ``external_id`` is the source's stable id for this item (Drive file id, OneDrive item id, URL for websites, etc.). Datasource ``download_file`` implementations stamp it explicitly, and the DB materialisation trigger projects it onto ``KnowledgeBaseDocument.m_source_external_id`` — which is the join key the KB sync engine uses to find existing docs by their source id. TextContent: properties: content: type: string title: Content metadata: title: Metadata kind: type: string const: text-content title: Kind default: text-content type: object required: - content title: TextContent ImageUrl: properties: url: type: string title: Url force_download: anyOf: - type: boolean - type: string const: allow-local title: Force Download default: false vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: image-url title: Kind default: image-url media_type: type: string title: Media Type description: >- Return the media type of the file, based on the URL or the provided `media_type`. readOnly: true identifier: type: string title: Identifier description: >- The identifier of the file, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `FileUrl`. This identifier is only automatically passed to the model when the `FileUrl` is returned by a tool. If you're passing the `FileUrl` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `FileUrl`. It's also included in inline-text delimiters for providers that require inlining text documents, so the model can distinguish multiple files. readOnly: true type: object required: - url - media_type - identifier title: ImageUrl description: A URL to an image. AudioUrl: properties: url: type: string title: Url force_download: anyOf: - type: boolean - type: string const: allow-local title: Force Download default: false vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: audio-url title: Kind default: audio-url media_type: type: string title: Media Type description: >- Return the media type of the file, based on the URL or the provided `media_type`. readOnly: true identifier: type: string title: Identifier description: >- The identifier of the file, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `FileUrl`. This identifier is only automatically passed to the model when the `FileUrl` is returned by a tool. If you're passing the `FileUrl` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `FileUrl`. It's also included in inline-text delimiters for providers that require inlining text documents, so the model can distinguish multiple files. readOnly: true type: object required: - url - media_type - identifier title: AudioUrl description: A URL to an audio file. DocumentUrl: properties: url: type: string title: Url force_download: anyOf: - type: boolean - type: string const: allow-local title: Force Download default: false vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: document-url title: Kind default: document-url media_type: type: string title: Media Type description: >- Return the media type of the file, based on the URL or the provided `media_type`. readOnly: true identifier: type: string title: Identifier description: >- The identifier of the file, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `FileUrl`. This identifier is only automatically passed to the model when the `FileUrl` is returned by a tool. If you're passing the `FileUrl` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `FileUrl`. It's also included in inline-text delimiters for providers that require inlining text documents, so the model can distinguish multiple files. readOnly: true type: object required: - url - media_type - identifier title: DocumentUrl description: The URL of the document. VideoUrl: properties: url: type: string title: Url force_download: anyOf: - type: boolean - type: string const: allow-local title: Force Download default: false vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: video-url title: Kind default: video-url media_type: type: string title: Media Type description: >- Return the media type of the file, based on the URL or the provided `media_type`. readOnly: true identifier: type: string title: Identifier description: >- The identifier of the file, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `FileUrl`. This identifier is only automatically passed to the model when the `FileUrl` is returned by a tool. If you're passing the `FileUrl` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `FileUrl`. It's also included in inline-text delimiters for providers that require inlining text documents, so the model can distinguish multiple files. readOnly: true type: object required: - url - media_type - identifier title: VideoUrl description: A URL to a video. BinaryContent: properties: data: type: string contentEncoding: base64 contentMediaType: application/octet-stream title: Data format: binary media_type: anyOf: - type: string enum: - audio/wav - audio/mpeg - audio/ogg - audio/flac - audio/aiff - audio/aac - type: string enum: - image/jpeg - image/png - image/gif - image/webp - type: string enum: - application/pdf - text/plain - text/csv - >- application/vnd.openxmlformats-officedocument.wordprocessingml.document - >- application/vnd.openxmlformats-officedocument.spreadsheetml.sheet - text/html - text/markdown - application/msword - application/vnd.ms-excel - type: string title: Media Type vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: binary title: Kind default: binary identifier: type: string title: Identifier description: >- Identifier for the binary content, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `BinaryContent`. This identifier is only automatically passed to the model when the `BinaryContent` is returned by a tool. If you're passing the `BinaryContent` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `BinaryContent`. It's also included in inline-text delimiters for providers that require inlining text documents, so the model can distinguish multiple files. readOnly: true type: object required: - data - media_type - identifier title: BinaryContent description: Binary content, e.g. an audio or image file. UploadedFile: properties: file_id: type: string title: File Id provider_name: type: string enum: - anthropic - openai - google - google-cloud - google-gla - google-vertex - bedrock - xai title: Provider Name vendor_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Vendor Metadata kind: type: string const: uploaded-file title: Kind default: uploaded-file media_type: type: string title: Media Type description: >- Return the media type of the file, inferred from `file_id` if not explicitly provided. Note: Inference relies on the file extension in `file_id`. For opaque file IDs (e.g., `'file-abc123'`), the media type will default to `'application/octet-stream'`. Inference relies on Python's `mimetypes` module, whose results may vary across platforms. Required by some providers (e.g., Bedrock) for certain file types. readOnly: true identifier: type: string title: Identifier description: >- The identifier of the file, such as a unique ID. This identifier can be provided to the model in a message to allow it to refer to this file in a tool call argument, and the tool can look up the file in question by iterating over the message history and finding the matching `UploadedFile`. This identifier is only automatically passed to the model when the `UploadedFile` is returned by a tool. If you're passing the `UploadedFile` as a user message, it's up to you to include a separate text part with the identifier, e.g. "This is file :" preceding the `UploadedFile`. readOnly: true type: object required: - file_id - provider_name - media_type - identifier title: UploadedFile description: >- A reference to a file uploaded to a provider's file storage by ID. This allows referencing files that have been uploaded via provider-specific file APIs rather than providing the file content directly. Supported by: - [`AnthropicModel`][pydantic_ai.models.anthropic.AnthropicModel] - [`OpenAIChatModel`][pydantic_ai.models.openai.OpenAIChatModel] - [`OpenAIResponsesModel`][pydantic_ai.models.openai.OpenAIResponsesModel] - [`BedrockConverseModel`][pydantic_ai.models.bedrock.BedrockConverseModel] - [`GoogleModel`][pydantic_ai.models.google.GoogleModel] (Gemini API: [Files API](https://ai.google.dev/gemini-api/docs/files) URIs, Google Cloud: GCS `gs://` URIs) - [`XaiModel`][pydantic_ai.models.xai.XaiModel] CachePoint: properties: kind: type: string const: cache-point title: Kind default: cache-point ttl: type: string enum: - 5m - 1h title: Ttl default: 5m type: object title: CachePoint ToolSearchReturnContent: properties: discovered_tools: items: $ref: '#/components/schemas/ToolSearchMatch' type: array title: Discovered Tools message: type: string title: Message type: object required: - discovered_tools title: ToolSearchReturnContent description: >- Typed return value of the framework-managed tool-search builtin. Carried on [`NativeToolSearchReturnPart.content`][pydantic_ai.messages.NativeToolSearchReturnPart.content] (native server-side path) and [`ToolSearchReturnPart.content`][pydantic_ai.messages.ToolSearchReturnPart.content] (local-fallback path) as the canonical cross-provider shape. LoadCapabilityReturn: properties: instructions: type: string title: Instructions type: object title: LoadCapabilityReturn description: Typed return value for the `load_capability` tool. ToolReturnContent: oneOf: - {} - additionalProperties: $ref: '#/components/schemas/ToolReturnContent' type: object - items: $ref: '#/components/schemas/ToolReturnContent' type: array ErrorDetails: properties: type: type: string title: Type loc: items: anyOf: - type: integer - type: string type: array title: Loc msg: type: string title: Msg input: title: Input ctx: additionalProperties: true type: object title: Ctx url: type: string title: Url type: object required: - type - loc - msg - input title: ErrorDetails ToolSearchArgs: properties: queries: items: type: string type: array title: Queries type: object required: - queries title: ToolSearchArgs description: >- Typed arguments for a tool-search call. Carried on [`NativeToolSearchCallPart.args`][pydantic_ai.messages.NativeToolSearchCallPart.args] (native server-side path) and [`ToolSearchCallPart.args`][pydantic_ai.messages.ToolSearchCallPart.args] (local-fallback path) as the canonical cross-provider shape. Each adapter normalizes its provider's wire format into this shape on parse, and rebuilds the wire format from this shape on emit. LoadCapabilityArgs: properties: id: type: string title: Id description: The id of the capability to load. type: object required: - id title: LoadCapabilityArgs description: Typed arguments for a `load_capability` tool call. Mark: properties: type: type: string title: Type attrs: anyOf: - additionalProperties: true type: object - type: 'null' title: Attrs type: object required: - type title: Mark SheetInfo: properties: name: type: string title: Name dimensions: type: string title: Dimensions type: object required: - name - dimensions title: SheetInfo description: Per-worksheet metadata for a spreadsheet file. ToolSearchMatch: properties: name: type: string title: Name type: object required: - name title: ToolSearchMatch description: A single match in a tool-search result. securitySchemes: APIKeyHeader: type: apiKey in: header name: X-API-Key ````