MCPcopy Create free account

hub / github.com/crewAIInc/crewAI / functions

Functions19,482 in github.com/crewAIInc/crewAI

↓ 9 callersMethodload_pending_feedback
Load state and pending feedback context. Args: flow_uuid: Unique identifier for the flow instance Returns: T
lib/crewai/src/crewai/flow/persistence/sqlite.py:329
↓ 9 callersMethodmain
()
lib/crewai/tests/agents/test_agent.py:3158
↓ 9 callersMethodmark_completed
Mark a todo as completed by step number.
lib/crewai/src/crewai/utilities/planning_types.py:96
↓ 9 callersMethodon
Decorator to register an event handler for a specific event type. Handlers can accept 2 or 3 arguments: - ``(source, event)`` — s
lib/crewai/src/crewai/events/event_bus.py:245
↓ 9 callersFunctionparse_inputs_json
Parse a ``--inputs`` JSON object, exiting with a pointed error if invalid.
lib/cli/src/crewai_cli/input_prompt.py:25
↓ 9 callersFunctionprocess_guardrail
Process the guardrail for the agent output. Args: output: The output to validate with the guardrail guardrail: The guardrail to v
lib/crewai/src/crewai/utilities/guardrail.py:118
↓ 9 callersFunctionpush_event_scope
Push an event ID and type onto the scope stack.
lib/crewai/src/crewai/events/event_context.py:171
↓ 9 callersFunctionregister
Register a global hook for an interception point.
lib/crewai/src/crewai/hooks/dispatch.py:119
↓ 9 callersFunctionset_tui_mode
(enabled: bool)
lib/crewai/src/crewai/events/listeners/tracing/utils.py:81
↓ 9 callersFunctionstops_run_as
Count the run as stopped for REASON when the block raises, then re-raise.
lib/cli/src/crewai_cli/run_crew.py:887
↓ 9 callersMethodsummarize_messages
Compact a mutable conversation history to fit this model's context window.
lib/crewai/src/crewai/llms/base_llm.py:529
↓ 9 callersMethodsupports_stop_words
Check if the model supports stop words. Note: This method is only used by the litellm fallback path. Native providers override this m
lib/crewai/src/crewai/llm.py:2597
↓ 9 callersFunctionvalidate_audio
Validate an audio file against constraints. Args: file: The audio file to validate. constraints: Audio constraints to validate ag
lib/crewai-files/src/crewai_files/processing/validators.py:331
↓ 9 callersMethodvector_index_exists
Check an explicit index or the default name for the requested index type.
lib/crewai-tools/src/crewai_tools/tools/oracle_vector_search_tool/vector_search.py:675
↓ 8 callersMethod__init__
(self, toolkit: CodeInterpreterToolkit, **kwargs: Any)
lib/crewai-tools/src/crewai_tools/aws/bedrock/code_interpreter/code_interpreter_toolkit.py:388
↓ 8 callersFunction_agent
( llm: BaseLLM, tools: list[BaseTool] | None = None, max_rpm: int | None = None )
lib/crewai/tests/agents/test_empty_llm_response_retry.py:383
↓ 8 callersMethod_coerce_llm
Resolve a declared or live LLM the way a crew agent's ``llm`` resolves. ``create_llm`` is the shared helper the crew/agent declaration layer
lib/crewai/src/crewai/flow/conversational_mixin.py:1697
↓ 8 callersMethod_common_payload_refinement
Common payload refinement for all tools.
lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/base.py:284
↓ 8 callersMethod_create_mock_tool
(self, name, description)
lib/crewai-tools/tests/tools/tool_collection_test.py:20
↓ 8 callersFunction_crewai_dependency
(project_root: Path)
lib/cli/tests/test_create_crew.py:2237
↓ 8 callersFunction_crewai_dependency
(project_root: Path)
lib/cli/tests/test_create_flow.py:171
↓ 8 callersMethod_effective_routes
(self, router_config: RouterConfig | None = None)
lib/crewai/src/crewai/flow/conversational_mixin.py:1573
↓ 8 callersFunction_emit_llm_call
Emit one fake ``LLMCallCompletedEvent`` with ``current_flow_id`` pinned to ``flow_id``. Runs in a freshly-copied context so the value the bus
lib/crewai/tests/test_flow_usage_metrics.py:30
↓ 8 callersMethod_evaluate_if_one_is_waiting
Start the evaluation `crewai eval` opened this run for. The evaluation is the errand; the run was the prerequisite. It begins here, o
lib/cli/src/crewai_cli/crew_run_tui.py:1030
↓ 8 callersMethod_features
(self, bm: TraceBatchManager)
lib/crewai/tests/tracing/test_tracing.py:1620
↓ 8 callersMethod_finalize
(self, bm: TraceBatchManager, *, status_code: int = 200)
lib/crewai/tests/tracing/test_tracing.py:1599
↓ 8 callersMethod_flow
(state: dict[str, Any] | None)
lib/crewai/tests/test_flow_conversation.py:2787
↓ 8 callersMethod_get_client
Get or create the Gemini client.
lib/crewai-files/src/crewai_files/uploaders/gemini.py:116
↓ 8 callersMethod_get_client_params
Get OpenAI client parameters.
lib/crewai/src/crewai/llms/providers/openai/completion.py:563
↓ 8 callersFunction_get_machine_id
Stable, privacy-preserving machine fingerprint (cross-platform).
lib/crewai/src/crewai/events/listeners/tracing/utils.py:235
↓ 8 callersFunction_is_cache_valid
Return True if the cache is less than 24 hours old.
lib/crewai-core/src/crewai_core/version.py:49
↓ 8 callersFunction_llm_stop_words_applied
Apply the executor's stop words to the LLM for the duration of one call. Uses :func:`crewai.llms.base_llm.call_stop_override` so the LLM's stop
lib/crewai/src/crewai/utilities/agent_utils.py:355
↓ 8 callersMethod_make_mcp_request
Make a JSON-RPC 2.0 MCP request to Agent Handler.
lib/crewai-tools/src/crewai_tools/tools/merge_agent_handler_tool/merge_agent_handler_tool.py:73
↓ 8 callersFunction_make_pyproject
( name: str = "my_crew", dependencies: Iterable[str] = ("crewai>=1.14.0",), *, hatchling: bool
lib/cli/tests/deploy/test_validate.py:29
↓ 8 callersMethod_oauth2_base_url
(self)
lib/crewai-core/src/crewai_core/auth/providers/keycloak.py:36
↓ 8 callersFunction_record
(dim: int, content: str = "test")
lib/crewai/tests/memory/test_dimension_mismatch.py:24
↓ 8 callersFunction_record_checkpoint_usage
Count a CLI action without recording checkpoint data or blocking execution.
lib/cli/src/crewai_cli/checkpoint_cli.py:16
↓ 8 callersMethod_rejects_reasoning_effort_with_tools
Whether a 400 is OpenAI refusing `reasoning_effort` alongside tools. GPT-5.6 applies a server-side `reasoning_effort` default and then reject
lib/crewai/src/crewai/llms/providers/openai/completion.py:2035
↓ 8 callersFunction_reregister_listener
Re-subscribe the global listener to the event bus. The repo-wide ``cleanup_event_handlers`` fixture clears every handler after each test, so
lib/crewai/tests/telemetry/test_flow_telemetry.py:31
↓ 8 callersMethod_resolve_route
Decide which class ``LLM(model, **kwargs)`` constructs, without building it. The routing ``__new__`` applies, in its priority order: ``custom
lib/crewai/src/crewai/llm.py:479
↓ 8 callersFunction_run_crew
( llm: ScriptedLLM, mode: str, tools: list[BaseTool] | None = None, max_rpm: int | None = None
lib/crewai/tests/agents/test_executor_structured_output_with_tools.py:152
↓ 8 callersMethod_save_to_memory
Save task result to unified memory (memory or crew._memory).
lib/crewai/src/crewai/agents/agent_builder/base_agent_executor.py:31
↓ 8 callersMethod_set_agent_params
(self, data: dict[str, Any])
lib/crewai/src/crewai/events/base_events.py:107
↓ 8 callersMethod_set_task_params
(self, data: dict[str, Any])
lib/crewai/src/crewai/events/base_events.py:101
↓ 8 callersFunction_success
(message: str, *, bold: bool = False, dim: bool = False)
lib/cli/src/crewai_cli/create_json_crew.py:357
↓ 8 callersFunction_task_for
(agent: Agent)
lib/crewai/tests/events/test_skill_usage_events.py:45
↓ 8 callersMethod_to_responses_input
Translate a chat-format message into Responses ``input`` items. Tool calling is expressed differently by the two APIs. Chat Completions
lib/crewai/src/crewai/llms/providers/openai/completion.py:1021
↓ 8 callersMethod_track_token_usage_internal
Track token usage internally in the LLM instance. Args: usage_data: Token usage data from the API response
lib/crewai/src/crewai/llms/base_llm.py:1212
↓ 8 callersMethod_validate_query
Validate the search query to ensure it's safe to execute. Only SELECT and SHOW statements are allowed for security reasons. Args:
lib/crewai-tools/src/crewai_tools/tools/singlestore_search_tool/singlestore_search_tool.py:356
↓ 8 callersMethodacall
Async call to Anthropic messages API. Args: messages: Input messages for the chat completion tools: List of tool/func
lib/crewai/src/crewai/llms/providers/anthropic/completion.py:552
↓ 8 callersMethodadd
Add content to the knowledge base.
lib/crewai-tools/src/crewai_tools/tools/rag/rag_tool.py:99
↓ 8 callersMethodappend_agent_result
Record an agent result, optionally making it visible to the user.
lib/crewai/src/crewai/flow/conversational_mixin.py:857
↓ 8 callersFunctionassert_counted_every_row
(text: str)
lib/crewai/tests/agents/test_agent_spreadsheets.py:184
↓ 8 callersFunctionbuild_env_with_all_tool_credentials
Return ``os.environ`` augmented with UV_INDEX_* credentials for every private index referenced under ``[tool.uv.sources]`` in ``pyproject.toml``.
lib/crewai-core/src/crewai_core/tool_credentials.py:35
↓ 8 callersFunctioncheck_repeated_tool_call
Track a streak of identical tool calls and warn the agent before it is stopped. A call extends the streak only when its tool, arguments and resul
lib/crewai/src/crewai/utilities/agent_utils.py:1999
↓ 8 callersFunctionchunk_text
Split a text file into chunks of maximum character count. Yields chunks one at a time to minimize memory usage. Args: file: The text
lib/crewai-files/src/crewai_files/processing/transformers.py:227
↓ 8 callersFunctioncleanup_temp_file
(path)
lib/crewai-tools/tests/rag/test_text_loaders.py:22
↓ 8 callersFunctioncollect_live_decisions
Ask Jev for each record that has no recorded decision or error. Opt-in: the caller supplies a client built with their own credentials, and re
scripts/jev_evaluation_runner.py:357
↓ 8 callersMethodcount
(self, *filters)
lib/crewai-files/tests/spreadsheets/test_answers.py:289
↓ 8 callersMethodcreate_crew_deployment_span
Records creating a new crew deployment (``crewai deploy create``). Also emits ``deploy:created`` so that deployments are countable from the
lib/crewai-core/src/crewai_core/telemetry.py:452
↓ 8 callersFunctioncreate_llm_like
Build ``model`` configured like ``base``. The instance is built through :class:`LLM`, so provider routing and every setting derived from the
lib/crewai/src/crewai/utilities/llm_utils.py:189
↓ 8 callersMethodcreate_test_tool
( self, client: IntegrationsClient | None = None )
lib/crewai-tools/tests/tools/crewai_platform_tools/test_crewai_platform_action_tool.py:38
↓ 8 callersFunctioncreate_validated_connection
Open a TCP socket to *host* after validating and pinning the peer IP.
lib/crewai-tools/src/crewai_tools/security/ssrf_adapter.py:76
↓ 8 callersFunctioncrewai_extras_for_model
Return the crewai extras, besides ``tools``, a project needs to run ``model``. That is the provider's extra from ``PROVIDER_EXTRAS``, plus ``lite
lib/cli/src/crewai_cli/constants.py:266
↓ 8 callersMethodcursor
(self)
lib/crewai/tests/rag/embeddings/test_oracle_provider.py:70
↓ 8 callersFunctiondetect_content_type
Detect MIME type from file content. Uses python-magic if available for accurate content-based detection, falls back to mimetypes module using
lib/crewai-files/src/crewai_files/core/sources.py:125
↓ 8 callersFunctionenforce_rpm_limit
Enforce the requests per minute (RPM) limit if applicable. Args: request_within_rpm_limit: Function to enforce RPM limit.
lib/crewai/src/crewai/utilities/agent_utils.py:463
↓ 8 callersFunctionerror_for_status
Build the exception matching an HTTP status. Args: status_code: HTTP status the server responded with. detail: Optional underlyin
lib/crewai/src/crewai/mcp/exceptions.py:103
↓ 8 callersMethodevaluate
(self, agent, task, execution_trace, final_output)
lib/crewai/tests/experimental/evaluation/test_agent_evaluator.py:239
↓ 8 callersMethodexec_module
(self, module: ModuleType)
lib/crewai/src/crewai/cli/__init__.py:39
↓ 8 callersMethodexport
(self, spans: Any)
lib/crewai/tests/telemetry/test_tracer_isolation.py:28
↓ 8 callersMethodfirst
(self, event_type: type[BaseEvent])
lib/crewai/tests/events/test_event_ordering.py:44
↓ 8 callersFunctionforce_additional_properties_false
Force additionalProperties=false on all object-type dicts recursively. OpenAI strict mode requires all objects to have additionalProperties=false
lib/crewai/src/crewai/utilities/pydantic_schema_utils.py:183
↓ 8 callersFunctionformat_skill_context
Format skill information for agent prompt injection. At METADATA level: returns name and description only. At INSTRUCTIONS level or above: re
lib/crewai/src/crewai/skills/loader.py:293
↓ 8 callersFunctiongenerate_filename
Generate a UUID-based filename with extension from content type. Args: content_type: MIME type to derive extension from. Returns:
lib/crewai-files/src/crewai_files/core/sources.py:110
↓ 8 callersMethodget_context_window_size
(self)
lib/crewai/tests/llms/test_context_window.py:363
↓ 8 callersFunctionget_crew_context
Get the current crew context from OpenTelemetry baggage. Returns: CrewContext instance containing crew context information, or None if no
lib/crewai/src/crewai/utilities/crew/crew_context.py:10
↓ 8 callersFunctionget_current_parent_id
Get the current parent event ID from the stack.
lib/crewai/src/crewai/events/event_context.py:62
↓ 8 callersFunctionget_project_id
Return ``[tool.crewai].project_id`` if the project has one. Read-only and safe to call from library code: it never creates or modifies anythi
lib/crewai-core/src/crewai_core/project.py:302
↓ 8 callersMethodget_scope_info
Get information about a scope. Args: scope: The scope path. Returns: ScopeInfo with record count, categories
lib/crewai/src/crewai/memory/storage/backend.py:135
↓ 8 callersMethodget_token
Return the access token if valid and not expired, else None.
lib/crewai-core/src/crewai_core/token_manager.py:65
↓ 8 callersFunctionget_tool_call_events
Extract tool call streaming events from mock emit calls.
lib/crewai/tests/llms/test_tool_call_streaming.py:55
↓ 8 callersFunctionget_tool_names
Get the sanitized names of the tools. Args: tools: List of tools to get names from. Returns: Comma-separated string of sanit
lib/crewai/src/crewai/utilities/agent_utils.py:210
↓ 8 callersFunctionget_triggering_event_id
Get the ID of the event that triggered the current execution. Returns: The event_id of the triggering event, or None if not in a triggere
lib/crewai/src/crewai/events/event_context.py:100
↓ 8 callersMethodhandle_llm_stream_chunk
Handle LLM stream chunk event - display streaming text in a panel. Args: accumulated_text: All text accumulated so far.
lib/crewai/src/crewai/events/utils/console_formatter.py:583
↓ 8 callersMethodinterrupt
Fence exactly this reply; never cancel a job or abort a provider. Repeated valid requests are idempotent. Completed generated text is
lib/crewai/src/crewai/experimental/flow_turns.py:173
↓ 8 callersMethodis_expired
Check if this cached upload has expired.
lib/crewai-files/src/crewai_files/cache/upload_cache.py:48
↓ 8 callersFunctionload_skill
Load one skill input into Skill objects. Accepts a pre-loaded Skill object, skill search path, inline SKILL.md string, or '@org/name' registr
lib/crewai/src/crewai/skills/loader.py:154
↓ 8 callersMethodlogin
(self)
lib/cli/src/crewai_cli/tools/main.py:228
↓ 8 callersFunctionnormalize_scope_path
Normalize a scope path by removing double slashes and ensuring proper format. Args: path: The raw scope path (e.g. '/crew/MyCrewName//age
lib/crewai/src/crewai/memory/utils.py:39
↓ 8 callersFunctionoutcome_of
(record, **thresholds)
lib/crewai/tests/test_jev_evaluation_runner.py:134
↓ 8 callersFunctionparse_registry_ref
Parse '@org/skill-name' into (org, name), ignoring any version pin. Retained for backwards compatibility. Use :func:`parse_skill_ref` to read
lib/crewai/src/crewai/skills/registry.py:95
↓ 8 callersMethodprepare
(self)
lib/crewai/tests/telemetry/test_conversation_spans.py:154
↓ 8 callersMethodprocess
Process a single file according to constraints and its mode mode. Args: file: The file to process. Returns:
lib/crewai-files/src/crewai_files/processing/processor.py:110
↓ 8 callersFunctionproject_config
(root: Path, definition: str | None = None)
lib/crewai-core/tests/test_agent_project_entrypoint.py:8
↓ 8 callersMethodpublish_tool
( self, handle: str, is_public: bool, version: str, description: str |
lib/crewai-core/src/crewai_core/plus_api.py:379
↓ 8 callersFunctionread_toml
(*args: Any, **kwargs: Any)
lib/cli/src/crewai_cli/run_crew.py:154
↓ 8 callersMethodrequest_human_input
Request human input during LLM hook execution. This method pauses live console updates, displays a prompt to the user, waits for thei
lib/crewai/src/crewai/hooks/llm_hooks.py:116
↓ 8 callersFunctionresolve_refs
Recursively resolve all local $refs in the given JSON Schema using $defs as the source. This is needed because Pydantic generates $ref-based sche
lib/crewai/src/crewai/utilities/pydantic_schema_utils.py:101
↓ 8 callersFunctionrestore_tool
(data: dict[str, object])
lib/crewai/tests/tools/test_deserialization_guard.py:29
← previousnext →601–700 of 19,482, ranked by callers