Class: Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow
- Inherits:
-
Internal::Type::BaseModel
- Object
- Internal::Type::BaseModel
- Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow
- Defined in:
- lib/telnyx/models/ai/assistant_update_params.rb
Defined Under Namespace
Instance Attribute Summary collapse
-
#edges ⇒ Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge>?
Directed transitions between nodes.
-
#nodes ⇒ Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool>
All nodes in the flow.
-
#start_node_id ⇒ String
ID of the node where the conversation begins.
Class Method Summary collapse
- .values ⇒ Array<Symbol>
- .variants ⇒ Array(Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool)
Instance Method Summary collapse
-
#initialize(nodes:, start_node_id:, edges: nil) ⇒ Object
constructor
Some parameter documentations has been truncated, see ConversationFlow for more details.
Methods inherited from Internal::Type::BaseModel
==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml
Methods included from Internal::Type::Converter
#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info
Methods included from Internal::Util::SorbetRuntimeSupport
#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type
Constructor Details
#initialize(nodes:, start_node_id:, edges: nil) ⇒ Object
Some parameter documentations has been truncated, see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow for more details.
Conversation flow as supplied by API clients (create / update).
A directed graph of ‘FlowNodeReq` connected by `FlowEdge`s. Validation enforces unique node/edge IDs, that `start_node_id` references a real node, and that every edge’s endpoints reference real nodes.
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 |
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 300 class ConversationFlow < Telnyx::Internal::Type::BaseModel # @!attribute nodes # All nodes in the flow. Must contain `start_node_id`. Each node is a prompt node # (`type: prompt`) or a tool node (`type: tool`). # # @return [Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool>] required :nodes, -> { Telnyx::Internal::Type::ArrayOf[union: Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node] } # @!attribute start_node_id # ID of the node where the conversation begins. # # @return [String] required :start_node_id, String # @!attribute edges # Directed transitions between nodes. May be empty for a single-node flow. # # @return [Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge>, nil] optional :edges, -> { Telnyx::Internal::Type::ArrayOf[Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge] } # @!method initialize(nodes:, start_node_id:, edges: nil) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow} for more details. # # Conversation flow as supplied by API clients (create / update). # # A directed graph of `FlowNodeReq` connected by `FlowEdge`s. Validation enforces # unique node/edge IDs, that `start_node_id` references a real node, and that # every edge's endpoints reference real nodes. # # @param nodes [Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool>] All nodes in the flow. Must contain `start_node_id`. Each node is a prompt node # # @param start_node_id [String] ID of the node where the conversation begins. # # @param edges [Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge>] Directed transitions between nodes. May be empty for a single-node flow. # One step in a conversation flow, as supplied by API clients. # # Each node carries the prompt, tool scope, and optional overrides for # model/voice/transcription. Unset overrides cascade from the assistant. module Node extend Telnyx::Internal::Type::Union discriminator :type # One step in a conversation flow, as supplied by API clients. # # Each node carries the prompt, tool scope, and optional overrides for # model/voice/transcription. Unset overrides cascade from the assistant. variant :prompt, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt } # A standalone tool step in a conversation flow, as supplied by clients. # # Unlike a prompt node, a tool node has no instructions or model — it # isn't an LLM turn. Reaching it deterministically runs one shared tool # (arguments filled from matching dynamic variables by name), then routes # on the result via outgoing `tool_result` edges. variant :tool, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Tool } class Prompt < Telnyx::Internal::Type::BaseModel # @!attribute id # Caller-supplied unique identifier for this node within the flow. # # @return [String] required :id, String # @!attribute instructions # Prompt that drives the LLM while this node is active. Required. # # @return [String] required :instructions, String # @!attribute external_llm # Override for `Assistant.external_llm` while this node is active. Use this to # route a node's turns to a different external LLM (different `model`, `base_url`, # credentials). Part of the LLM bundle — see `model` for cascade semantics. # Mutually exclusive with `model` on the node (a single LLM identity per node). # # @return [Telnyx::Models::AI::ExternalLlmReq, nil] optional :external_llm, -> { Telnyx::AI::ExternalLlmReq } # @!attribute instructions_mode # How `instructions` combine with the assistant-level instructions. `replace` # (default): the node's instructions are used alone. `append`: the node's # instructions are concatenated after the assistant's instructions. # # @return [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::InstructionsMode, nil] optional :instructions_mode, enum: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::InstructionsMode } # @!attribute llm_api_key_ref # Override for `Assistant.llm_api_key_ref` while this node is active. Part of the # LLM bundle — see `model` for cascade semantics. # # @return [String, nil] optional :llm_api_key_ref, String # @!attribute model # Override for `Assistant.model` while this node is active. Part of the LLM bundle # (`model` + `llm_api_key_ref` + `external_llm`): when any of the three is set on # the node, all three are taken from the node and the assistant-level LLM identity # is not consulted. When none of the three is set, the assistant's bundle cascades # unchanged. # # @return [String, nil] optional :model, String # @!attribute name # Optional human-readable label, displayed in authoring UIs. # # @return [String, nil] optional :name, String # @!attribute position # Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # by the runtime; round-trips so frontends can persist graph layout across # reloads. # # @return [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Position, nil] optional :position, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Position } # @!attribute shared_tool_ids # IDs of shared (org-level) tools available at this node. Knowledge bases are # attached the same way — via a shared retrieval tool. Tools not listed here are # not callable while this node is active. # # @return [Array<String>, nil] optional :shared_tool_ids, Telnyx::Internal::Type::ArrayOf[String] # @!attribute tools_mode # How `shared_tool_ids` combine with the assistant-level tool set. `replace` # (default): only the node's tools are callable. `append`: the node's tools are # added to the assistant's tools. Ignored when `shared_tool_ids` is null. # # @return [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::ToolsMode, nil] optional :tools_mode, enum: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::ToolsMode } # @!attribute transcription # Per-node transcription override (model/language/region). Unset fields cascade # from the assistant-level transcription. # # @return [Telnyx::Models::AI::TranscriptionSettings, nil] optional :transcription, -> { Telnyx::AI::TranscriptionSettings } # @!attribute type # Node kind discriminator. `prompt` (default) is an LLM-driven step; `tool` is a # standalone tool execution (see `ToolNodeReq`). # # @return [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Type, nil] optional :type, enum: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Type } # @!attribute voice_settings # Per-node voice override. Only fields set here override the assistant-level voice # settings; unset fields cascade. # # @return [Telnyx::Models::AI::VoiceSettings, nil] optional :voice_settings, -> { Telnyx::AI::VoiceSettings } # @!method initialize(id:, instructions:, external_llm: nil, instructions_mode: nil, llm_api_key_ref: nil, model: nil, name: nil, position: nil, shared_tool_ids: nil, tools_mode: nil, transcription: nil, type: nil, voice_settings: nil) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt} for # more details. # # One step in a conversation flow, as supplied by API clients. # # Each node carries the prompt, tool scope, and optional overrides for # model/voice/transcription. Unset overrides cascade from the assistant. # # @param id [String] Caller-supplied unique identifier for this node within the flow. # # @param instructions [String] Prompt that drives the LLM while this node is active. Required. # # @param external_llm [Telnyx::Models::AI::ExternalLlmReq] Override for `Assistant.external_llm` while this node is active. Use this to rou # # @param instructions_mode [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::InstructionsMode] How `instructions` combine with the assistant-level instructions. `replace` (def # # @param llm_api_key_ref [String] Override for `Assistant.llm_api_key_ref` while this node is active. Part of the # # @param model [String] Override for `Assistant.model` while this node is active. Part of the LLM bundle # # @param name [String] Optional human-readable label, displayed in authoring UIs. # # @param position [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Position] Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # # @param shared_tool_ids [Array<String>] IDs of shared (org-level) tools available at this node. Knowledge bases are atta # # @param tools_mode [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::ToolsMode] How `shared_tool_ids` combine with the assistant-level tool set. `replace` (defa # # @param transcription [Telnyx::Models::AI::TranscriptionSettings] Per-node transcription override (model/language/region). Unset fields cascade fr # # @param type [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt::Type] Node kind discriminator. `prompt` (default) is an LLM-driven step; `tool` is a s # # @param voice_settings [Telnyx::Models::AI::VoiceSettings] Per-node voice override. Only fields set here override the assistant-level voice # How `instructions` combine with the assistant-level instructions. `replace` # (default): the node's instructions are used alone. `append`: the node's # instructions are concatenated after the assistant's instructions. # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt#instructions_mode module InstructionsMode extend Telnyx::Internal::Type::Enum REPLACE = :replace APPEND = :append # @!method self.values # @return [Array<Symbol>] end # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt#position class Position < Telnyx::Internal::Type::BaseModel # @!attribute x # Horizontal coordinate in the authoring canvas. # # @return [Float] required :x, Float # @!attribute y_ # Vertical coordinate in the authoring canvas. # # @return [Float] required :y_, Float, api_name: :y # @!method initialize(x:, y_:) # Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # by the runtime; round-trips so frontends can persist graph layout across # reloads. # # @param x [Float] Horizontal coordinate in the authoring canvas. # # @param y_ [Float] Vertical coordinate in the authoring canvas. end # How `shared_tool_ids` combine with the assistant-level tool set. `replace` # (default): only the node's tools are callable. `append`: the node's tools are # added to the assistant's tools. Ignored when `shared_tool_ids` is null. # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt#tools_mode module ToolsMode extend Telnyx::Internal::Type::Enum REPLACE = :replace APPEND = :append # @!method self.values # @return [Array<Symbol>] end # Node kind discriminator. `prompt` (default) is an LLM-driven step; `tool` is a # standalone tool execution (see `ToolNodeReq`). # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt#type module Type extend Telnyx::Internal::Type::Enum PROMPT = :prompt # @!method self.values # @return [Array<Symbol>] end end class Tool < Telnyx::Internal::Type::BaseModel # @!attribute id # Caller-supplied unique identifier for this node within the flow. # # @return [String] required :id, String # @!attribute shared_tool_id # ID of the single shared (org-level) tool this node executes. When the flow # reaches this node the tool runs as a deliberate step (no LLM turn); its outgoing # `tool_result` edges then route on the outcome. Arguments are filled from the # conversation's dynamic variables by name — a dynamic variable whose name matches # one of the tool's parameters supplies that argument. Cross-validated against the # org's shared tools on write. # # @return [String] required :shared_tool_id, String # @!attribute name # Optional human-readable label, displayed in authoring UIs. # # @return [String, nil] optional :name, String # @!attribute position # Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # by the runtime; round-trips so frontends can persist graph layout across # reloads. # # @return [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Position, nil] optional :position, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Position } # @!attribute type # Node kind discriminator. Always `tool` for a tool node. # # @return [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Type, nil] optional :type, enum: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Type } # @!method initialize(id:, shared_tool_id:, name: nil, position: nil, type: nil) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool} for # more details. # # A standalone tool step in a conversation flow, as supplied by clients. # # Unlike a prompt node, a tool node has no instructions or model — it isn't an LLM # turn. Reaching it deterministically runs one shared tool (arguments filled from # matching dynamic variables by name), then routes on the result via outgoing # `tool_result` edges. # # @param id [String] Caller-supplied unique identifier for this node within the flow. # # @param shared_tool_id [String] ID of the single shared (org-level) tool this node executes. When the flow reach # # @param name [String] Optional human-readable label, displayed in authoring UIs. # # @param position [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Position] Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # # @param type [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool::Type] Node kind discriminator. Always `tool` for a tool node. # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool#position class Position < Telnyx::Internal::Type::BaseModel # @!attribute x # Horizontal coordinate in the authoring canvas. # # @return [Float] required :x, Float # @!attribute y_ # Vertical coordinate in the authoring canvas. # # @return [Float] required :y_, Float, api_name: :y # @!method initialize(x:, y_:) # Optional canvas coordinates used by authoring UIs to lay out the graph. Ignored # by the runtime; round-trips so frontends can persist graph layout across # reloads. # # @param x [Float] Horizontal coordinate in the authoring canvas. # # @param y_ [Float] Vertical coordinate in the authoring canvas. end # Node kind discriminator. Always `tool` for a tool node. # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool#type module Type extend Telnyx::Internal::Type::Enum TOOL = :tool # @!method self.values # @return [Array<Symbol>] end end # @!method self.variants # @return [Array(Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool)] end class Edge < Telnyx::Internal::Type::BaseModel # @!attribute id # Caller-supplied unique identifier for this edge within the flow. # # @return [String] required :id, String # @!attribute condition # Condition that gates the transition. Discriminated by `type`: `llm`, # `expression`. # # @return [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Llm, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression] required :condition, union: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition } # @!attribute start_node_id # ID of the node this edge transitions away from. # # @return [String] required :start_node_id, String # @!attribute target # Destination of the transition. Discriminated by `type`: `node` (jump to another # node in this flow) or `assistant` (hand off to a different assistant). # # @return [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Node, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant] required :target, union: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Target } # @!method initialize(id:, condition:, start_node_id:, target:) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge} for more # details. # # Directed transition from one node to a target, gated by a condition. # # The target is either another node in the same flow (`NodeTarget`) or a different # assistant (`AssistantTarget`). Multiple edges may share a `start_node_id`; the # runtime evaluates them in the order they're declared and takes the first whose # condition is true. # # @param id [String] Caller-supplied unique identifier for this edge within the flow. # # @param condition [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Llm, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression] Condition that gates the transition. Discriminated by `type`: `llm`, `expression # # @param start_node_id [String] ID of the node this edge transitions away from. # # @param target [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Node, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant] Destination of the transition. Discriminated by `type`: `node` (jump to another # Condition that gates the transition. Discriminated by `type`: `llm`, # `expression`. # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge#condition module Condition extend Telnyx::Internal::Type::Union discriminator :type # Edge condition evaluated by the LLM from a natural-language prompt. # # The model is asked to judge the prompt against conversation context and # returns true/false. Use this for fuzzy intents that aren't expressible as # a deterministic expression (e.g. 'user wants to escalate to a human'). variant :llm, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Llm } # Edge condition evaluated as a deterministic expression AST. # # The expression is computed against runtime dynamic variables and must # evaluate to a boolean. Prefer this over `LLMCondition` when the rule is # a clean function of known variables — it's cheaper and predictable. variant :expression, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression } class Llm < Telnyx::Internal::Type::BaseModel # @!attribute prompt # Natural-language criterion the LLM judges as true/false. # # @return [String] required :prompt, String # @!attribute type # # @return [Symbol, :llm] required :type, const: :llm # @!method initialize(prompt:, type: :llm) # Edge condition evaluated by the LLM from a natural-language prompt. # # The model is asked to judge the prompt against conversation context and returns # true/false. Use this for fuzzy intents that aren't expressible as a # deterministic expression (e.g. 'user wants to escalate to a human'). # # @param prompt [String] Natural-language criterion the LLM judges as true/false. # # @param type [Symbol, :llm] end class Expression < Telnyx::Internal::Type::BaseModel # @!attribute expression # A node in a deterministic expression AST. Exactly one variant is selected by the # `type` discriminator. Terminal variants (`number_literal`, `string_literal`, # `bool_literal`, `variable`) bottom out the recursion; `arithmetic`, `bool_op`, # and `comparison` nest further sub-expressions. # # Extracted into a single named schema so the recursive union is defined once (was # previously inlined at every operand site). # # @return [Object, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::DynamicVariableExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::StringLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::NumberLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::BooleanLiteralExpression] required :expression, union: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression } # @!attribute type # # @return [Symbol, :expression] required :type, const: :expression # @!method initialize(expression:, type: :expression) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression} # for more details. # # Edge condition evaluated as a deterministic expression AST. # # The expression is computed against runtime dynamic variables and must evaluate # to a boolean. Prefer this over `LLMCondition` when the rule is a clean function # of known variables — it's cheaper and predictable. # # @param expression [Object, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::DynamicVariableExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::StringLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::NumberLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::BooleanLiteralExpression] A node in a deterministic expression AST. Exactly one variant is selected by the # # @param type [Symbol, :expression] # A node in a deterministic expression AST. Exactly one variant is selected by the # `type` discriminator. Terminal variants (`number_literal`, `string_literal`, # `bool_literal`, `variable`) bottom out the recursion; `arithmetic`, `bool_op`, # and `comparison` nest further sub-expressions. # # Extracted into a single named schema so the recursive union is defined once (was # previously inlined at every operand site). # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression#expression module Expression extend Telnyx::Internal::Type::Union variant Telnyx::Internal::Type::Unknown # Reference a dynamic variable by name. # # Resolved at runtime from the assistant's dynamic-variables context (see # `Assistant.dynamic_variables` and the dynamic-variables webhook). variant -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::DynamicVariableExpression } # Constant string value. variant -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::StringLiteralExpression } # Constant numeric value (float; integers are accepted and stored as float). variant -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::NumberLiteralExpression } # Constant boolean value. Useful for unconditional ('always') edges. variant -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::BooleanLiteralExpression } class DynamicVariableExpression < Telnyx::Internal::Type::BaseModel # @!attribute name # Variable name to look up in the runtime context. # # @return [String] required :name, String # @!attribute type # # @return [Symbol, :variable] required :type, const: :variable # @!method initialize(name:, type: :variable) # Reference a dynamic variable by name. # # Resolved at runtime from the assistant's dynamic-variables context (see # `Assistant.dynamic_variables` and the dynamic-variables webhook). # # @param name [String] Variable name to look up in the runtime context. # # @param type [Symbol, :variable] end class StringLiteralExpression < Telnyx::Internal::Type::BaseModel # @!attribute type # # @return [Symbol, :string_literal] required :type, const: :string_literal # @!attribute value # Literal string value. # # @return [String] required :value, String # @!method initialize(value:, type: :string_literal) # Constant string value. # # @param value [String] Literal string value. # # @param type [Symbol, :string_literal] end class NumberLiteralExpression < Telnyx::Internal::Type::BaseModel # @!attribute type # # @return [Symbol, :number_literal] required :type, const: :number_literal # @!attribute value # Literal numeric value. # # @return [Float] required :value, Float # @!method initialize(value:, type: :number_literal) # Constant numeric value (float; integers are accepted and stored as float). # # @param value [Float] Literal numeric value. # # @param type [Symbol, :number_literal] end class BooleanLiteralExpression < Telnyx::Internal::Type::BaseModel # @!attribute type # # @return [Symbol, :bool_literal] required :type, const: :bool_literal # @!attribute value # Literal boolean value. # # @return [Boolean] required :value, Telnyx::Internal::Type::Boolean # @!method initialize(value:, type: :bool_literal) # Constant boolean value. Useful for unconditional ('always') edges. # # @param value [Boolean] Literal boolean value. # # @param type [Symbol, :bool_literal] end # @!method self.variants # @return [Array(Object, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::DynamicVariableExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::StringLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::NumberLiteralExpression, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression::Expression::BooleanLiteralExpression)] end end # @!method self.variants # @return [Array(Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Llm, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Condition::Expression)] end # Destination of the transition. Discriminated by `type`: `node` (jump to another # node in this flow) or `assistant` (hand off to a different assistant). # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge#target module Target extend Telnyx::Internal::Type::Union discriminator :type # Edge target referencing another node within the same flow. # # The runtime transitions the active node to `node_id` and continues # processing within the current assistant's flow. variant :node, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Node } # Edge target referencing a different assistant. # # When the edge fires, the conversation hands off to `assistant_id`: the # active assistant on the conversation row is rewritten and the new # assistant's flow starts at its own `start_node_id`. The current turn's # LLM response is delivered to the user as-is; subsequent turns route # to the new assistant. variant :assistant, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant } class Node < Telnyx::Internal::Type::BaseModel # @!attribute node_id # ID of the node this edge transitions into. # # @return [String] required :node_id, String # @!attribute type # # @return [Symbol, :node] required :type, const: :node # @!method initialize(node_id:, type: :node) # Edge target referencing another node within the same flow. # # The runtime transitions the active node to `node_id` and continues processing # within the current assistant's flow. # # @param node_id [String] ID of the node this edge transitions into. # # @param type [Symbol, :node] end class Assistant < Telnyx::Internal::Type::BaseModel # @!attribute assistant_id # ID of the assistant the conversation transitions to. # # @return [String] required :assistant_id, String # @!attribute type # # @return [Symbol, :assistant] required :type, const: :assistant # @!attribute position # Optional canvas coordinates for rendering the target assistant as a node in # authoring UIs. Pure presentation — the runtime ignores it; round-trips so # frontends can persist graph layout across reloads. When multiple edges target # the same assistant, each edge's `position` is independent (frontends typically # use the first non-null one). # # @return [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::Position, nil] optional :position, -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::Position } # @!attribute voice_mode # Voice behavior when handing off to the target assistant, mirroring the handoff # tool's `voice_mode`. `unified` (default) keeps the current voice across the # handoff; `distinct` lets the target assistant speak with its own configured # voice. Only applies to assistant targets — node targets override voice via the # node's own `voice_settings`. # # @return [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::VoiceMode, nil] optional :voice_mode, enum: -> { Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::VoiceMode } # @!method initialize(assistant_id:, position: nil, voice_mode: nil, type: :assistant) # Some parameter documentations has been truncated, see # {Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant} # for more details. # # Edge target referencing a different assistant. # # When the edge fires, the conversation hands off to `assistant_id`: the active # assistant on the conversation row is rewritten and the new assistant's flow # starts at its own `start_node_id`. The current turn's LLM response is delivered # to the user as-is; subsequent turns route to the new assistant. # # @param assistant_id [String] ID of the assistant the conversation transitions to. # # @param position [Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::Position] Optional canvas coordinates for rendering the target assistant as a node in auth # # @param voice_mode [Symbol, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant::VoiceMode] Voice behavior when handing off to the target assistant, mirroring the handoff t # # @param type [Symbol, :assistant] # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant#position class Position < Telnyx::Internal::Type::BaseModel # @!attribute x # Horizontal coordinate in the authoring canvas. # # @return [Float] required :x, Float # @!attribute y_ # Vertical coordinate in the authoring canvas. # # @return [Float] required :y_, Float, api_name: :y # @!method initialize(x:, y_:) # Optional canvas coordinates for rendering the target assistant as a node in # authoring UIs. Pure presentation — the runtime ignores it; round-trips so # frontends can persist graph layout across reloads. When multiple edges target # the same assistant, each edge's `position` is independent (frontends typically # use the first non-null one). # # @param x [Float] Horizontal coordinate in the authoring canvas. # # @param y_ [Float] Vertical coordinate in the authoring canvas. end # Voice behavior when handing off to the target assistant, mirroring the handoff # tool's `voice_mode`. `unified` (default) keeps the current voice across the # handoff; `distinct` lets the target assistant speak with its own configured # voice. Only applies to assistant targets — node targets override voice via the # node's own `voice_settings`. # # @see Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant#voice_mode module VoiceMode extend Telnyx::Internal::Type::Enum UNIFIED = :unified DISTINCT = :distinct # @!method self.values # @return [Array<Symbol>] end end # @!method self.variants # @return [Array(Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Node, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge::Target::Assistant)] end end end |
Instance Attribute Details
#edges ⇒ Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Edge>?
Directed transitions between nodes. May be empty for a single-node flow.
319 320 |
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 319 optional :edges, -> { Telnyx::Internal::Type::ArrayOf[Telnyx::AI::AssistantUpdateParams::ConversationFlow::Edge] } |
#nodes ⇒ Array<Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool>
All nodes in the flow. Must contain ‘start_node_id`. Each node is a prompt node (`type: prompt`) or a tool node (`type: tool`).
306 307 |
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 306 required :nodes, -> { Telnyx::Internal::Type::ArrayOf[union: Telnyx::AI::AssistantUpdateParams::ConversationFlow::Node] } |
#start_node_id ⇒ String
ID of the node where the conversation begins.
313 |
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 313 required :start_node_id, String |
Class Method Details
.values ⇒ Array<Symbol>
|
|
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 657
|
.variants ⇒ Array(Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Prompt, Telnyx::Models::AI::AssistantUpdateParams::ConversationFlow::Node::Tool)
|
|
# File 'lib/telnyx/models/ai/assistant_update_params.rb', line 662
|