Class: ClaudeAgentSDK::Client
- Inherits:
-
Object
- Object
- ClaudeAgentSDK::Client
- Defined in:
- lib/claude_agent_sdk.rb
Overview
Client for bidirectional, interactive conversations with Claude Code
This client provides full control over the conversation flow with support for streaming, hooks, permission callbacks, and dynamic message sending. The Client class always uses streaming mode for bidirectional communication.
Instance Attribute Summary collapse
-
#query_handler ⇒ Object
readonly
Returns the value of attribute query_handler.
Class Method Summary collapse
-
.open(prompt = nil, options: nil, transport_class: SubprocessCLITransport, transport_args: {}) ⇒ Object
Block-scoped Client lifecycle, mirroring Python's
async with ClaudeSDKClient() as clientand File.open ergonomics: connects, yields the client, and always disconnects (block exceptions propagate).
Instance Method Summary collapse
-
#connect(prompt = nil) ⇒ Object
Connect to Claude with optional initial prompt.
-
#disconnect ⇒ Object
Disconnect from Claude.
-
#get_context_usage ⇒ Hash
Get a breakdown of current context window usage by category.
-
#get_mcp_status ⇒ Hash
Get current MCP server connection status (only works with streaming mode).
-
#get_server_info ⇒ Hash
Get server initialization info including available commands and output styles.
-
#initialize(options: nil, transport_class: SubprocessCLITransport, transport_args: {}) ⇒ Client
constructor
A new instance of Client.
-
#interrupt ⇒ Object
Send interrupt signal.
-
#query(prompt, session_id: 'default') ⇒ Object
Send a query to Claude.
-
#receive_messages {|Message| ... } ⇒ Enumerator
Receive all messages from Claude.
-
#receive_response {|Message| ... } ⇒ Object
Receive messages until a ResultMessage is received.
-
#reconnect_mcp_server(server_name) ⇒ Object
Reconnect a failed MCP server.
-
#rewind_files(user_message_uuid) ⇒ Object
Rewind files to a previous checkpoint (v0.1.15+) Restores file state to what it was at the given user message Requires enable_file_checkpointing to be true in options.
-
#server_info ⇒ Hash?
Get server initialization info.
-
#set_model(model) ⇒ Object
Change the AI model during conversation.
-
#set_permission_mode(mode) ⇒ Object
Change permission mode during conversation.
-
#stop_task(task_id) ⇒ Object
Stop a running background task.
-
#toggle_mcp_server(server_name, enabled) ⇒ Object
Enable or disable an MCP server.
Constructor Details
#initialize(options: nil, transport_class: SubprocessCLITransport, transport_args: {}) ⇒ Client
Returns a new instance of Client.
613 614 615 616 617 618 619 620 621 |
# File 'lib/claude_agent_sdk.rb', line 613 def initialize(options: nil, transport_class: SubprocessCLITransport, transport_args: {}) @options = || ClaudeAgentOptions.new @transport_class = transport_class @transport_args = transport_args @transport = nil @query_handler = nil @connected = false @materialized = nil end |
Instance Attribute Details
#query_handler ⇒ Object (readonly)
Returns the value of attribute query_handler.
607 608 609 |
# File 'lib/claude_agent_sdk.rb', line 607 def query_handler @query_handler end |
Class Method Details
.open(prompt = nil, options: nil, transport_class: SubprocessCLITransport, transport_args: {}) ⇒ Object
In standalone (non-Async) use, break inside the block raises
LocalJumpError (teardown still runs) — return a value instead.
Block-scoped Client lifecycle, mirroring Python's
async with ClaudeSDKClient() as client and File.open ergonomics:
connects, yields the client, and always disconnects (block exceptions
propagate). Kernel#Sync runs inline inside an existing reactor and
creates one otherwise, so this works standalone too. Returns the
block's value.
638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 |
# File 'lib/claude_agent_sdk.rb', line 638 def self.open(prompt = nil, options: nil, transport_class: SubprocessCLITransport, transport_args: {}) raise ArgumentError, 'Client.open requires a block' unless block_given? Sync do client = new(options: , transport_class: transport_class, transport_args: transport_args) # connect failures self-clean via connect's rescue -> disconnect -> # raise, and disconnect is idempotent — no double-teardown. client.connect(prompt) begin yield client ensure client.disconnect end end end |
Instance Method Details
#connect(prompt = nil) ⇒ Object
Connect to Claude with optional initial prompt.
Client always uses streaming mode for bidirectional communication. If you pass a String, it will be sent as an initial user message after the connection is established. If you pass an Enumerator, it should yield JSONL messages (e.g., from ClaudeAgentSDK::Streaming.user_message); the stream is consumed in the BACKGROUND (connect returns immediately) and stdin closes when it is exhausted, so the stream is the session's input — a later #query after exhaustion will fail. Enumerator code runs on the reactor: use a producer Thread + Thread::Queue for blocking reads (Queue#pop is scheduler-aware). Stream errors are reported via Observer#on_error and logged, not raised out of connect.
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 |
# File 'lib/claude_agent_sdk.rb', line 668 def connect(prompt = nil) return if @connected raise ArgumentError, "prompt must be a String, an Enumerator, or nil (got #{prompt.class})" unless prompt.nil? || prompt.is_a?(String) || prompt.respond_to?(:each) # Validate and configure permission settings = @options if @options.can_use_tool # can_use_tool and permission_prompt_tool_name are mutually exclusive raise ArgumentError, 'can_use_tool callback cannot be used with permission_prompt_tool_name' if @options. # Set permission_prompt_tool_name to stdio for control protocol = @options.dup_with(permission_prompt_tool_name: 'stdio') end # Fail fast on invalid session_store combinations before spawning the CLI. # Configuration validation is a usage error, like the ArgumentErrors # above — deliberately outside the on_error notify scope. SessionStores.() # Resolve observers before the first failable runtime step so # connect-phase failures (including resume materialization) can be # notified via on_error. @resolved_observers = ClaudeAgentSDK.resolve_observers(@options.observers) # If anything from materialization onward fails, tear down (closes the # subprocess and removes the materialized temp config dir) before # surfacing the error, so a partial connect never leaks a temp dir # holding a credential copy. begin # Resume-from-store: materialize the session from the store into a # temp CLAUDE_CONFIG_DIR BEFORE spawn, then repoint options at it. # Inside the instrumented begin so store IO failures fire on_error # (matching the one-shot query() path) and disconnect cleans up. = materialize_resume() connect_inner(, prompt) rescue Exception => e # rubocop:disable Lint/RescueException # Pre-handshake failures (@connected still false) are notified here; # post-handshake String-prompt send failures were already notified by # the instrumented #query — the gate keeps on_error exactly-once. # (The enumerator branch streams in the background and cannot raise # out of connect.) No on_close follows for pre-handshake failures # (disconnect gates it on @connected): the session never opened. notify_error(e) if e.is_a?(StandardError) && !@connected # Tear down the partial connect, but never let a cleanup failure (e.g. a # custom transport whose #close raises) mask the original connect error. # Rescue Exception (not StandardError) so reactor cancellation # (Async::Stop < Exception) after materialize_resume set @materialized # still runs disconnect -> @materialized.cleanup, never leaking the temp # CLAUDE_CONFIG_DIR that holds the redacted .credentials.json copy. begin disconnect rescue StandardError => cleanup_error warn "Claude SDK: cleanup after failed connect raised: #{cleanup_error.}" end raise end end |
#disconnect ⇒ Object
Disconnect from Claude
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 |
# File 'lib/claude_agent_sdk.rb', line 904 def disconnect ClaudeAgentSDK.notify_observers(@resolved_observers || [], :on_close) if @connected # Tear down whatever exists — robust to a partial/failed connect, where # @connected is still false but a transport and/or materialized temp dir # were already created. #close on the query handler also closes the # transport (flushing the mirror batcher first); the extra @transport # close covers a failure before the query handler was built (idempotent). # # The nested ensures guarantee that even a raising close (e.g. a custom # transport whose #close raises) still runs the transport close, resets # state, and removes the materialized temp dir (which holds a redacted # .credentials.json copy) — so disconnect can never leave the client # half-open or leak the temp dir. The original error still propagates. # Keep a handle on the query handler past the nil-out below: whether the # mirror dropped batches is only final AFTER #close ran its last flush, # and the materialized-dir decision at the bottom needs to ask it. query_handler = @query_handler begin @query_handler&.close ensure @query_handler = nil begin @transport&.close ensure @transport = nil @connected = false # Remove the materialized resume temp dir AFTER the subprocess # exited — unless the mirror dropped batches: the store copy is then # incomplete and the temp dir holds the only copy of the dropped # turns, so it is preserved (scrubbed of credentials) with a warning # instead of deleted. if @materialized if query_handler&.mirror_batches_dropped? @materialized.preserve_transcripts else @materialized.cleanup end @materialized = nil end end end end |
#get_context_usage ⇒ Hash
Get a breakdown of current context window usage by category. Returns token counts per category (system prompt, tools, messages, etc.), total/max tokens, model info, MCP tools, memory files, and more.
884 885 886 887 |
# File 'lib/claude_agent_sdk.rb', line 884 def get_context_usage raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.get_context_usage end |
#get_mcp_status ⇒ Hash
Get current MCP server connection status (only works with streaming mode)
891 892 893 894 |
# File 'lib/claude_agent_sdk.rb', line 891 def get_mcp_status raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.get_mcp_status end |
#get_server_info ⇒ Hash
Get server initialization info including available commands and output styles
898 899 900 901 |
# File 'lib/claude_agent_sdk.rb', line 898 def get_server_info raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected server_info end |
#interrupt ⇒ Object
Send interrupt signal
824 825 826 827 |
# File 'lib/claude_agent_sdk.rb', line 824 def interrupt raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.interrupt end |
#query(prompt, session_id: 'default') ⇒ Object
Send a query to Claude
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 |
# File 'lib/claude_agent_sdk.rb', line 737 def query(prompt, session_id: 'default') raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected # A bare Hash responds to #each and would silently iterate [key, value] # pairs (Python's async-for over a dict raises TypeError). raise ArgumentError, 'prompt must be a String or an Enumerable of message Hashes/JSONL Strings (got Hash)' if prompt.is_a?(Hash) begin if prompt.is_a?(String) ClaudeAgentSDK.notify_observers(@resolved_observers, :on_user_prompt, prompt) = { type: 'user', message: { role: 'user', content: prompt }, parent_tool_use_id: nil, session_id: session_id } writeln(JSON.generate()) elsif prompt.respond_to?(:each) # Inline iteration on the caller, Python client.py parity — NOT # Query#stream_input, whose ensure always ends input after # exhaustion (correct for connect-time sole-input streams, fatal # for a mid-session query). Blocks until the iterable is exhausted, # identical to Python's async-for. (prompt, session_id) else raise ArgumentError, "prompt must be a String or respond to #each (got #{prompt.class})" end rescue StandardError => e notify_error(e) raise end end |
#receive_messages {|Message| ... } ⇒ Enumerator
#next/#peek either raise FiberError or hang depending on message timing, and can kill the session's read loop, leaving the client unusable; iterate with a block or each-driven Enumerable methods (#first, #take) inside the Async block instead.
Receive all messages from Claude
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 |
# File 'lib/claude_agent_sdk.rb', line 776 def (&block) return enum_for(:receive_messages) unless block raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected begin @query_handler. do |data| = MessageParser.parse(data) next unless ClaudeAgentSDK.notify_observers(@resolved_observers, :on_message, ) signal = FiberBoundary.invoke_iteration(block, ) break signal.value if signal.is_a?(FiberBoundary::Break) end rescue StandardError => e notify_error(e) raise end end |
#receive_response {|Message| ... } ⇒ Object
Receive messages until a ResultMessage is received
798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 |
# File 'lib/claude_agent_sdk.rb', line 798 def receive_response(&block) return enum_for(:receive_response) unless block raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected # Keep loop control on the same fiber as the underlying dequeue: both # the SDK's ResultMessage break and the user's translated break happen # here, never inside the FiberBoundary hop (break in a proc on a # foreign thread raises LocalJumpError). begin @query_handler. do |data| = MessageParser.parse(data) next unless ClaudeAgentSDK.notify_observers(@resolved_observers, :on_message, ) signal = FiberBoundary.invoke_iteration(block, ) break signal.value if signal.is_a?(FiberBoundary::Break) break if .is_a?(ResultMessage) end rescue StandardError => e notify_error(e) raise end end |
#reconnect_mcp_server(server_name) ⇒ Object
Reconnect a failed MCP server
845 846 847 848 |
# File 'lib/claude_agent_sdk.rb', line 845 def reconnect_mcp_server(server_name) raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.reconnect_mcp_server(server_name) end |
#rewind_files(user_message_uuid) ⇒ Object
Rewind files to a previous checkpoint (v0.1.15+) Restores file state to what it was at the given user message Requires enable_file_checkpointing to be true in options
869 870 871 872 |
# File 'lib/claude_agent_sdk.rb', line 869 def rewind_files() raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.rewind_files() end |
#server_info ⇒ Hash?
Get server initialization info
876 877 878 |
# File 'lib/claude_agent_sdk.rb', line 876 def server_info @query_handler&.instance_variable_get(:@initialization_result) end |
#set_model(model) ⇒ Object
Change the AI model during conversation
838 839 840 841 |
# File 'lib/claude_agent_sdk.rb', line 838 def set_model(model) raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.set_model(model) end |
#set_permission_mode(mode) ⇒ Object
Change permission mode during conversation
831 832 833 834 |
# File 'lib/claude_agent_sdk.rb', line 831 def (mode) raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.(mode) end |
#stop_task(task_id) ⇒ Object
Stop a running background task
860 861 862 863 |
# File 'lib/claude_agent_sdk.rb', line 860 def stop_task(task_id) raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.stop_task(task_id) end |
#toggle_mcp_server(server_name, enabled) ⇒ Object
Enable or disable an MCP server
853 854 855 856 |
# File 'lib/claude_agent_sdk.rb', line 853 def toggle_mcp_server(server_name, enabled) raise CLIConnectionError, 'Not connected. Call connect() first' unless @connected @query_handler.toggle_mcp_server(server_name, enabled) end |