Method
This is a method of the OptimizationResult class in the models module.Percentage of tokens reduced.
Signature
Returns
The result of the operation.
Guide
Reference
- achat
- aexecute
- agent_id
- analyze_prompt
- arun
- astart
- auto_memory
- background
- chat
- chat_with_context
- checkpoints
- clean_json_output
- clear_history
- console
- context_manager
- delete_history
- delete_history_matching
- display_name
- ephemeral
- execute
- execute_tool
- execute_tool_async
- from_template
- generate_task
- get_available_tools
- get_history_size
- get_memory_context
- get_recommended_stage
- get_rules_context
- get_skills_prompt
- handoff_to
- handoff_to_async
- iter_stream
- launch
- llm_model
- output_style
- policy
- prune_history
- query
- rag
- rag_query
- retrieval_config
- retrieve
- rules_manager
- run
- run_autonomous
- session_id
- skill_manager
- start
- store_memory
- stream_emitter
- switch_model
- thinking_budget
- add_task
- aexecute_task
- append_to_state
- arun_all_tasks
- arun_task
- astart
- clean_json_output
- clear_state
- context_manager
- current_plan
- default_completion_checker
- delete_state
- display_token_usage
- execute_task
- get_agent_details
- get_all_state
- get_all_tasks_status
- get_detailed_token_report
- get_plan_markdown
- get_state
- get_task_details
- get_task_result
- get_task_status
- get_todo_markdown
- get_token_usage_summary
- has_state
- increment_state
- launch
- restore_session_state
- run
- run_all_tasks
- run_task
- save_output_to_file
- save_session_state
- set_state
- start
- todo_list
- update_plan_step_status
- update_state
- execute
- alisten
- asay
- aspeech
- atranscribe
- console
- listen
- litellm
- say
- speech
- transcribe
- Is Available | AI Agent
- Mark Error | AI Agent
- Mark Rate Limited | AI Agent
- reset | AI Agent
- astart
- start
- achat
- chat
- name
- rag
- run
- Channel ID | AI Agent
- Channel Type | AI Agent
- Is Channel Allowed | AI Agent
- Is User Allowed | AI Agent
- Is Webhook Mode | AI Agent
- command | AI Agent
- Command Args | AI Agent
- Is Command | AI Agent
- text | AI Agent
- channel | AI Agent
- content | AI Agent
- Message ID | AI Agent
- sender | AI Agent
- Bot User | AI Agent
- Delete Message | AI Agent
- Edit Message | AI Agent
- Get Agent | AI Agent
- Get Channel | AI Agent
- Get User | AI Agent
- Is Running | AI Agent
- On Command | AI Agent
- On Message | AI Agent
- platform | AI Agent
- Send Message | AI Agent
- Send Typing | AI Agent
- Set Agent | AI Agent
- start | AI Agent
- stop | AI Agent
- Is Bot | AI Agent
- User ID | AI Agent
- username | AI Agent
- Fixed Total | AI Agent
- Get Segment Budget | AI Agent
- History Budget | AI Agent
- usable | AI Agent
- SUPPORTED_CHUNKERS
- chunk
- chunker
- embedding_model
- aexecute
- agenerate
- console
- execute
- execute_code
- explain
- fix
- generate
- generate_code
- litellm
- refactor
- review
- aanalyze_codebase
- acreate_implementation_blueprint
- agenerate_prp
- analyze_codebase
- analyze_codebase_with_gitingest
- analyze_integration_points
- analyze_test_patterns
- build_implementation_blueprint
- compile_context_documentation
- create_implementation_blueprint
- create_quality_gates
- create_validation_framework
- execute_prp
- extract_implementation_patterns
- generate_comprehensive_prp
- generate_feature_prp
- generate_prp
- get_agent_interaction_summary
- log_debug
- perform_ast_analysis
- save_comprehensive_session_report
- save_markdown_output
- setup_logging
- setup_output_directories
- start
- For Recipe | AI Agent
- Add Segment | AI Agent
- Get Segment | AI Agent
- Set Segment | AI Agent
- total | AI Agent
- capture_llm_boundary
- emergency_truncate
- estimate_tokens
- get_history
- get_last_snapshot_hook
- get_resolved_config
- get_stats
- get_tool_budget
- process
- register_snapshot_callback
- reset
- set_tool_budget
- truncate_tool_output
- optimize | AI Agent
- Format For Prompt | AI Agent
- Has Citations | AI Agent
- From Config | AI Agent
- aresearch
- async_openai_client
- clarify
- follow_up
- gemini_client
- openai_client
- research
- rewrite_query
- Get All Sources | AI Agent
- Get Citation Text | AI Agent
- aembed
- aembed_batch
- asimilarity
- console
- embed
- embed_batch
- find_most_similar
- litellm
- similarity
- add_profile
- get_next_profile
- get_profile
- get_retry_delay
- list_profiles
- mark_failure
- mark_success
- on_failover
- remove_profile
- reset_all
- status
- Get Next Profile | AI Agent
- Mark Failure | AI Agent
- Mark Success | AI Agent
- display | AI Agent
- start | AI Agent
- stop | AI Agent
- Client ID | AI Agent
- close | AI Agent
- Connected At | AI Agent
- Is Connected | AI Agent
- receive | AI Agent
- send | AI Agent
- HTTP URL | AI Agent
- Is Secure | AI Agent
- Ws URL | AI Agent
- broadcast | AI Agent
- Close Session | AI Agent
- Create Session | AI Agent
- emit | AI Agent
- Get Agent | AI Agent
- Get Session | AI Agent
- health | AI Agent
- host | AI Agent
- Is Running | AI Agent
- List Agents | AI Agent
- List Sessions | AI Agent
- On Event | AI Agent
- port | AI Agent
- Register Agent | AI Agent
- start | AI Agent
- stop | AI Agent
- Unregister Agent | AI Agent
- Add Message | AI Agent
- Agent ID | AI Agent
- Client ID | AI Agent
- close | AI Agent
- Created At | AI Agent
- Get Messages | AI Agent
- Get State | AI Agent
- Is Active | AI Agent
- Last Activity | AI Agent
- Session ID | AI Agent
- Set State | AI Agent
- default_tool_description
- default_tool_name
- execute_async
- execute_programmatic
- to_tool_function
- tool_description
- tool_name
- matches | AI Agent
- Get Reason | AI Agent
- Is Blocking | AI Agent
- Should Stop | AI Agent
- clear
- disable_hook
- enable_hook
- enabled
- get_hooks
- has_hooks
- list_hooks
- on
- register
- register_command
- register_function
- set_global_timeout
- unregister
- allow | AI Agent
- ask | AI Agent
- block | AI Agent
- deny | AI Agent
- Is Allowed | AI Agent
- Is Denied | AI Agent
- aggregate_context
- execute
- execute_sync
- get_blocking_reason
- is_blocked
- registry
- achat
- aedit
- agenerate
- agenerate_image
- avariation
- chat
- edit
- generate
- generate_image
- litellm
- variation
- add
- chunker
- config
- delete
- delete_all
- get
- get_all
- get_corpus_stats
- history
- index
- markdown
- memory
- normalize_content
- reset
- search
- store
- update
- get_tools
- shutdown
- to_openai_tool
- call_tool
- run
- shutdown
- from_env
- merge
- build_context_for_task
- calculate_quality_metrics
- compute_quality_score
- delete_long_term
- delete_memories
- delete_memories_matching
- delete_memory
- delete_short_term
- finalize_task_output
- get_all_memories
- get_learn_context
- learn
- reset_all
- reset_entity_only
- reset_long_term
- reset_short_term
- reset_user_memory
- search
- search_entity
- search_long_term
- search_short_term
- search_user_memory
- search_with_quality
- store_entity
- store_long_term
- store_quality
- store_short_term
- store_user_memory
- execute
- execute_model_call
- execute_tool_call
- has_model_hooks
- has_tool_hooks
- run_after_model
- run_after_tool
- run_before_model
- run_before_tool
- add
- delete
- delete_all
- get
- get_all
- reset
- search
- update
- get_agent_manager
- get_agent_policy
- get_combined_stats
- get_session_cache
- prepare_handoff
- set_agent_policy
- aextract
- aread
- console
- extract
- litellm
- read
- close | AI Agent
- flush | AI Agent
- On LLM Call | AI Agent
- On Span End | AI Agent
- On Span Start | AI Agent
- On Tool Call | AI Agent
- On Trace End | AI Agent
- On Trace Start | AI Agent
- Reduction Percent | AI Agent
- Add Tool | AI Agent
- Clear Session Permissions | AI Agent
- Is Allowed | AI Agent
- Is Empty | AI Agent
- List Tools | AI Agent
- load | AI Agent
- Remove Tool | AI Agent
- save | AI Agent
- agent
- expand
- expand_basic
- expand_creative
- expand_detailed
- expand_structured
- add_abbreviation
- add_abbreviations
- agent
- rewrite
- rewrite_basic
- rewrite_contextual
- rewrite_hyde
- rewrite_multi_query
- rewrite_step_back
- rewrite_sub_queries
- Format Answer With Citations | AI Agent
- Has Citations | AI Agent
- aconnect
- adisconnect
- asend_audio
- asend_text
- connect
- console
- disconnect
- on_audio
- on_error
- on_message
- receive_loop
- send_audio
- send_text
- generous | AI Agent
- minimal | AI Agent
- standard | AI Agent
- Get Strategy | AI Agent
- Get Token Budget | AI Agent
- Should Retrieve | AI Agent
- To Knowledge Config | AI Agent
- To RAG Config | AI Agent
- All Queries | AI Agent
- Primary Query | AI Agent
- docker | AI Agent
- e2b | AI Agent
- subprocess | AI Agent
- cleanup | AI Agent
- execute | AI Agent
- Execute File | AI Agent
- Get Status | AI Agent
- Is Available | AI Agent
- List Files | AI Agent
- Read File | AI Agent
- reset | AI Agent
- Run Command | AI Agent
- Sandbox Type | AI Agent
- start | AI Agent
- stop | AI Agent
- Write File | AI Agent
- output | AI Agent
- success | AI Agent
- permissive | AI Agent
- standard | AI Agent
- strict | AI Agent
- Agent
- add_knowledge
- add_memory
- chat
- clear_memory
- create_agent
- get_context
- get_state
- increment_state
- knowledge
- memory
- restore_state
- save_state
- search_knowledge
- search_memory
- send_message
- set_state
- check_and_add
- clear
- get_stats
- execute_callback
- execute_callback_sync
- initialize_memory
- store_in_memory
- estimate | AI Agent
- Estimate Messages | AI Agent
- run | AI Agent
- acontent
- adownload
- agenerate
- alist
- aremix
- arun
- astart
- astatus
- await_completion
- console
- content
- download
- generate
- list
- remix
- run
- start
- status
- video_module
- wait_for_completion
- aanalyze
- acompare
- adescribe
- aextract_text
- analyze
- compare
- console
- describe
- extract_text
- litellm
- add_approval_requirement
- add_hook
- Adisplay Error | AI Agent
- Adisplay Generating | AI Agent
- Adisplay Instruction | AI Agent
- Adisplay Interaction | AI Agent
- Adisplay Self Reflection | AI Agent
- Adisplay Tool Call | AI Agent
- aembedding | AI Agent
- after_model
- after_tool
- before_model
- before_tool
- categorize_hooks
- Clean Triple Backticks | AI Agent
- Cleanup Telemetry Resources | AI Agent
- clear_approval_context
- configure_default_approvals
- console_approval_callback
- create_context_agent
- create_context_manager
- Create Retrieval Config | AI Agent
- deduplicate_topics
- Detect URL Scheme | AI Agent
- Disable Performance Mode | AI Agent
- Disable Telemetry | AI Agent
- Display Error | AI Agent
- Display Generating | AI Agent
- Display Instruction | AI Agent
- Display Interaction | AI Agent
- Display Reasoning Steps | AI Agent
- Display Self Reflection | AI Agent
- Display Tool Call | AI Agent
- Display Working Status | AI Agent
- embedding | AI Agent
- Enable Performance Mode | AI Agent
- Enable Telemetry | AI Agent
- encode_file_to_base64
- Execute Callback | AI Agent
- Execute Sync Callback | AI Agent
- Force Shutdown Telemetry | AI Agent
- Format Percent | AI Agent
- get_approval_callback
- get_default_registry
- Get Dimensions | AI Agent
- get_hook_type
- get_multimodal_message
- get_permission_allowlist
- get_risk_level
- Get Telemetry | AI Agent
- handoff
- keep_last_n_messages
- remove_all_tools
- remove_system_messages
- has_hook
- is_already_approved
- is_approval_required
- is_env_auto_approve
- is_middleware
- Is Numeric String | AI Agent
- Is Path Like | AI Agent
- Is Policy String | AI Agent
- is_yaml_approved
- Make Array Error | AI Agent
- Make Preset Error | AI Agent
- mark_approved
- Merge Config With Overrides | AI Agent
- Parse Policy String | AI Agent
- Parse URL To Config | AI Agent
- process_task_context
- process_video
- prompt_with_handoff_instructions
- Register Approval Callback | AI Agent
- Register Display Callback | AI Agent
- remove_approval_requirement
- remove_hook
- request_approval
- require_approval
- reset_yaml_approved_tools
- resolve | AI Agent
- Resolve Autonomy | AI Agent
- Resolve Batch | AI Agent
- Resolve Caching | AI Agent
- Resolve Context | AI Agent
- Resolve Execution | AI Agent
- Resolve Guardrail Policies | AI Agent
- Resolve Guardrails | AI Agent
- Resolve Hooks | AI Agent
- Resolve Knowledge | AI Agent
- Resolve Memory | AI Agent
- Resolve Output | AI Agent
- Resolve Planning | AI Agent
- Resolve Reflection | AI Agent
- Resolve Routing | AI Agent
- Resolve Skills | AI Agent
- Resolve Web | AI Agent
- set_approval_callback
- set_default_registry
- set_permission_allowlist
- set_yaml_approved_tools
- Suggest Similar | AI Agent
- trace
- Track Workflow | AI Agent
- wrap_model_call
- wrap_tool_call
Functions
Reduction Percent | AI Agent
reduction_percent: Percentage of tokens reduced.
⌘I