MCPcopy Create free account

hub / github.com/crewAIInc/crewAI / functions

Functions19,482 in github.com/crewAIInc/crewAI

Methodsync_step_2
(self)
lib/crewai/tests/test_flow.py:1679
Functionsynchronize_shared_probe_unlink
(path: Path, missing_ok: bool = False)
lib/crewai-core/tests/test_settings.py:27
Methodsynthesize_results
Deduplicate, composite-score, rank, and attach evidence gaps.
lib/crewai/src/crewai/memory/recall_flow.py:354
Functionsystem_message
Fixture providing a system message.
lib/crewai/tests/test_llm.py:530
Methodsystem_one
(self, state, questions, *, model=None)
lib/crewai/tests/test_jev_evaluation_runner.py:469
Functiontag
Create and push a version tag on main branch. Run this after the version bump PR has been merged. Automatically detects version from __versio
lib/devtools/src/crewai_devtools/cli.py:2223
Methodtake_left
(self)
lib/crewai/tests/test_flow_from_definition.py:270
Methodtake_right
(self)
lib/crewai/tests/test_flow_from_definition.py:274
Functiontask
Marks a method as a crew task. Args: meth: The method to mark. Returns: A wrapped method marked as a task with memoization.
lib/crewai/src/crewai/project/annotations.py:66
Methodtask_ended
(self, span, task, crew)
lib/crewai/tests/telemetry/test_task_failure_instrumentation.py:252
Methodtask_failed
(self, span, task, error_type=None)
lib/crewai/tests/telemetry/test_task_failure_instrumentation.py:247
Functiontask_output
()
lib/crewai/tests/test_task_guardrails.py:167
Functiontask_to_kickoff_adapter
( self: Any, task: Task, context: str | None, tools: list[Any] | None )
lib/crewai/src/crewai/lite_agent.py:163
Functiontaskoutput_guardrail
Returns a TaskOutput object.
lib/crewai/tests/test_task_guardrails.py:450
MethodtearDown
(self)
lib/crewai-tools/tests/tools/brightdata_serp_tool_test.py:47
MethodtearDown
(self)
lib/cli/tests/test_config.py:26
MethodtearDown
(self)
lib/cli/tests/test_config.py:160
MethodtearDown
Clean up temp directory.
lib/cli/tests/test_token_manager.py:157
MethodtearDown
(self)
lib/cli/tests/test_settings_command.py:27
MethodtearDown
(self)
lib/cli/tests/enterprise/test_main.py:26
MethodtearDown
(self)
lib/crewai/tests/cli/test_config.py:23
MethodtearDown
Clean up temp directory.
lib/crewai/tests/cli/test_token_manager.py:153
MethodtearDown
(self)
lib/crewai/tests/utilities/test_file_handler.py:20
MethodtearDown
(self)
lib/crewai/tests/utilities/test_training_handler.py:15
Methodteardown_class
Final cleanup after all tests in this class
lib/crewai/tests/tracing/test_tracing.py:486
Methodteardown_method
(self)
lib/crewai/tests/test_context.py:19
Methodteardown_method
Clean up after tests.
lib/crewai/tests/utilities/test_file_store.py:28
Methodteardown_method
Cleanup after each test method
lib/crewai/tests/tracing/test_tracing.py:471
Functiontelemetry
A Telemetry whose spans are captured instead of exported. The singleton is disabled in tests and never builds a provider, so both the gate an
lib/crewai-core/tests/test_telemetry_deploy.py:19
Functiontelemetry
Telemetry whose spans land in memory rather than being exported.
lib/crewai/tests/telemetry/test_crew_completed_span.py:38
Functiontelemetry_with_exporter
A fresh Telemetry whose provider exports into memory. Telemetry is a process-wide singleton that registers atexit and signal handlers on init
lib/crewai/tests/telemetry/test_tracer_isolation.py:39
Functiontemp_crew_project
()
lib/crewai/tests/cli/test_utils.py:186
Functiontemp_dir
()
lib/cli/tests/test_create_crew.py:46
Functiontemp_directory
()
lib/crewai-tools/tests/rag/test_directory_loader.py:11
Functiontemp_env
(monkeypatch)
lib/crewai-tools/tests/tools/test_file_writer_tool.py:15
Functiontemp_project
()
lib/crewai-tools/tests/test_optional_dependencies.py:9
Functiontemp_project_dir
Create a temporary directory for testing tool extraction.
lib/crewai/tests/cli/test_utils.py:15
Functiontemp_tree
()
lib/cli/tests/test_utils.py:12
Functiontemplate
Browse and install project templates.
lib/cli/src/crewai_cli/cli.py:1183
Functiontemplate_add
[Deprecated: use `crewai create template`] Add a template to the current directory.
lib/cli/src/crewai_cli/cli.py:1203
Methodtemplate_installed_span
Records when a template is downloaded and installed. Args: template_name: Name of the template that was installed
lib/crewai/src/crewai/telemetry/telemetry.py:1366
Functiontemplate_list
List available templates and select one to install.
lib/cli/src/crewai_cli/cli.py:1188
Functionterminal_stdin
Prompt as a person at a terminal would be prompted.
lib/cli/tests/test_create_crew.py:1634
Functiontest
Test the crew and evaluate the results.
lib/cli/src/crewai_cli/cli.py:685
Functiontest
Test the crew execution and returns the results.
lib/cli/src/crewai_cli/templates/crew/main.py:51
Methodtest_401_fallback_ephemeral_also_fails
If ephemeral fallback also fails, trace_batch_id is cleared.
lib/crewai/tests/tracing/test_tracing.py:1403
Methodtest_401_non_ephemeral_falls_back_to_ephemeral
A 401 on the non-ephemeral endpoint should retry as ephemeral.
lib/crewai/tests/tracing/test_tracing.py:1299
Methodtest_401_on_ephemeral_does_not_recurse
A 401 on the ephemeral endpoint should NOT try to fall back again.
lib/crewai/tests/tracing/test_tracing.py:1374
Methodtest_403_non_ephemeral_falls_back_to_ephemeral
A 403 on the non-ephemeral endpoint should also fall back.
lib/crewai/tests/tracing/test_tracing.py:1337
Functiontest_429_rate_limited_exhausts_retries
Persistent RATE_LIMITED 429s exhaust retries and raise RuntimeError.
lib/crewai-tools/tests/tools/brave_search_tool_test.py:736
Functiontest_429_rate_limited_retries_then_succeeds
A transient RATE_LIMITED 429 is retried; success on the second attempt.
lib/crewai-tools/tests/tools/brave_search_tool_test.py:694
Functiontest_4xx_error_raises_with_api_detail
A 422 with a structured error body includes code and detail in the message.
lib/crewai-tools/tests/tools/brave_search_tool_test.py:496
Functiontest_5xx_is_retried
A 502 server error is retried; success on the second attempt.
lib/crewai-tools/tests/tools/brave_search_tool_test.py:718
Functiontest__setup_for_training
(researcher, writer)
lib/crewai/tests/test_crew.py:3039
Functiontest_a_401_to_a_request_without_a_login_offers_none
Only the login AMP rejected is offered again: an anonymous read was not one.
lib/cli/tests/experimental/test_eval_crew.py:2491
Methodtest_a_backslash_target_measures_the_root_workbook_calamine_would_read
( self, calamine_must_not_open )
lib/crewai-files/tests/spreadsheets/test_reading.py:746
Methodtest_a_backslash_target_reads_the_root_workbook_as_calamine_does
calamine takes the workbook folder up to the last "/" only, so a target of ``xl\\workbook.xml`` names the root ``workbook.xml``, not ``xl/``'s
lib/crewai-files/tests/spreadsheets/test_reading.py:738
Functiontest_a_bare_llm_call_in_a_flow_step_runs_on_the_mapped_model
The case roles cannot reach: a flow step's own `LLM(...).call()`.
lib/crewai/tests/test_llm_overlay.py:589
Functiontest_a_blank_credential_runs_untraced_too
The grant client refuses a blank credential in its constructor, with the same error a refused grant raises — so it must not fail the run either.
lib/crewai/tests/telemetry/test_trace_lifecycle.py:427
Methodtest_a_body_past_the_limit_stops_the_download
(self, monkeypatch)
lib/crewai-files/tests/spreadsheets/test_loading.py:213
Methodtest_a_body_that_arrives_before_the_deadline_is_returned
(self)
lib/crewai-tools/tests/url_read_tool_test.py:875
Methodtest_a_broken_archive_is_unreadable
(self)
lib/crewai-files/tests/spreadsheets/test_reading.py:119
Methodtest_a_calamine_failure_is_unreadable
(self, monkeypatch)
lib/crewai-files/tests/spreadsheets/test_reading.py:370
Methodtest_a_call
(self, server, provider, mode, stream)
lib/crewai/tests/llms/openai_compatible/test_openai_compatible.py:566
Methodtest_a_call_without_tools_keeps_its_reasoning
(self, monkeypatch)
lib/crewai/tests/llms/openai/test_tools_reasoning_effort_retry.py:383
Functiontest_a_caller_who_chose_litellm_keeps_it_when_the_declared_sdk_is_missing
( monkeypatch: pytest.MonkeyPatch, )
lib/crewai/tests/test_llm_overlay.py:873
Functiontest_a_caller_who_chose_litellm_keeps_litellm
()
lib/crewai/tests/utilities/test_create_llm_like.py:189
Functiontest_a_cap_the_caller_set_is_carried_even_when_the_class_does_not_emit_it
()
lib/crewai/tests/utilities/test_create_llm_like.py:66
Functiontest_a_change_outside_the_project_directory_leaves_the_zip_clean
In a monorepo the ZIP holds only the project directory, so a change elsewhere in the repository is not an uncommitted change in the ZIP.
lib/cli/tests/deploy/test_deploy_main.py:2282
Functiontest_a_change_since_the_last_traced_run_runs_the_crew_again
What the evaluation would grade is no longer what the project does: a coding agent that edits the crew and runs `crewai eval` gets its edit graded
lib/cli/tests/experimental/test_eval_crew.py:3378
Functiontest_a_character_reference_too_long_to_decode_is_left_alone
(downloads)
lib/crewai/tests/agents/test_agent_spreadsheets.py:1114
Functiontest_a_checkpoint_from_before_the_field_never_reads_its_plan
( downloads, monkeypatch, tmp_path )
lib/crewai/tests/agents/test_agent_spreadsheets.py:822
Functiontest_a_checkpoint_restore_is_not_counted_as_a_resume
Only a run restored from a human pause is marked resumed. ``_is_execution_resuming`` is also set by checkpoint restores that never paused for
lib/crewai/tests/telemetry/test_flow_telemetry.py:783
Functiontest_a_child_app_reads_the_note_off_the_token_file
In a child process there is no holder: the file the command wrote says it.
lib/cli/tests/test_crew_run_tui.py:564
Functiontest_a_child_process_run_reads_the_waiting_evaluation_off_its_environment
A project's crew runs through `uv run …`, so the app is in another process — the one thing that crosses is the environment the command passed
lib/cli/tests/test_crew_run_tui.py:664
Functiontest_a_class_the_running_process_cannot_reach_degrades_to_none_not_to_the_wrong_class
An unresolvable identity must lose only ``error_type``, never bind to something else. A locally defined class is unreachable by attribute lookup
lib/crewai/tests/telemetry/test_task_failure_instrumentation.py:594
Methodtest_a_client_params_base_url_marks_a_server_compatible
`client_params` win over the standard fields when the client is built.
lib/crewai/tests/llms/openai/test_reasoning_effort_forwarding.py:472
Functiontest_a_code_flow_step_kicking_off_an_agent
(downloads)
lib/crewai/tests/agents/test_agent_spreadsheets.py:413
Functiontest_a_column_never_mixes_per_run_and_totals
(deployed, monkeypatch, capsys)
lib/cli/tests/experimental/test_eval_crew.py:1773
Methodtest_a_column_with_many_values_counts_them
(self)
lib/crewai-files/tests/spreadsheets/test_answers.py:92
Functiontest_a_comparison_leaves_its_criteria_behind_when_the_project_has_none
(deployed, monkeypatch, capsys)
lib/cli/tests/experimental/test_eval_crew.py:2162
Functiontest_a_comparison_never_overwrites_the_projects_criteria
(deployed, monkeypatch, capsys)
lib/cli/tests/experimental/test_eval_crew.py:2174
Functiontest_a_comparison_prints_its_brief_only_when_nobody_is_watching
(deployed, monkeypatch, capsys, watching)
lib/cli/tests/experimental/test_eval_crew.py:2297
Methodtest_a_compatible_server_is_not_remembered
Its later calls still start on chat completions, as `api` asks.
lib/crewai/tests/llms/openai/test_tools_reasoning_effort_retry.py:612
Methodtest_a_complaint_about_the_value_surfaces_and_is_not_remembered
The server takes the parameter; the value is the caller's mistake.
lib/crewai/tests/llms/openai/test_reasoning_effort_forwarding.py:587
Functiontest_a_concurrent_run_cannot_send_the_command_after_the_wrong_one
The record is the project's last finish, which another run can replace while this app is open. The app's own marker is what settles it.
lib/cli/tests/experimental/test_eval_crew.py:1441
Functiontest_a_config_too_large_to_be_criteria_is_left_behind
A file that AMP would refuse is not uploaded, and the run is still graded.
lib/cli/tests/experimental/test_eval_crew.py:1277
Functiontest_a_configured_definition_that_does_not_exist
( project, usage, pyproject, kind )
lib/cli/tests/test_run_usage.py:279
Functiontest_a_connection_made_after_the_deadline_passed_is_cut
As the next redirect hop can be: the timer has already run when it connects.
lib/crewai-tools/tests/utilities/test_safe_requests.py:805
Functiontest_a_conversation_ending_on_a_tool_result_keeps_its_order
The tool pair answers the question, so it must not precede it. Splicing every non-request turn before the prompt hoisted a trailing tool call
lib/crewai/tests/agents/test_agent_kickoff_message_history.py:151
Functiontest_a_conversation_over_the_bound_keeps_its_ends_and_names_the_cut
The repeated conversation on an LLM call is where a large tool result would otherwise be copied into every later call: past the bound its middle
lib/crewai/tests/telemetry/test_span_attribute_bound.py:222
Methodtest_a_conversation_state_subclass_is_not_composed_twice
(self)
lib/crewai/tests/test_flow_conversation.py:2834
Functiontest_a_conversation_with_no_user_message_still_has_a_request
Nothing to select, so the last message stands in as it always has.
lib/crewai/tests/agents/test_agent_kickoff_message_history.py:138
Functiontest_a_conversational_flow_without_a_terminal
(project, usage, monkeypatch)
lib/cli/tests/test_run_usage.py:950
Functiontest_a_conversational_turn_is_marked
Each turn is its own kickoff, but a session reports one completion. Without the marker those spans run many-to-one against Flow Completed and
lib/crewai/tests/telemetry/test_flow_telemetry.py:810
Functiontest_a_copied_task_never_reads_its_plan
(downloads, monkeypatch)
lib/crewai/tests/agents/test_agent_spreadsheets.py:873
Functiontest_a_coworker_never_fetches_a_url_the_manager_model_wrote
(downloads)
lib/crewai/tests/agents/test_agent_spreadsheets.py:647
Functiontest_a_coworker_reads_a_spreadsheet_the_crews_input_gave
(downloads)
lib/crewai/tests/agents/test_agent_spreadsheets.py:618
Functiontest_a_coworker_reads_a_url_from_the_crews_input_past_the_cap
(downloads)
lib/crewai/tests/agents/test_agent_spreadsheets.py:631
Methodtest_a_crafted_name_is_cut_to_excels_length_and_cannot_close_its_quotes
(self)
lib/crewai-files/tests/spreadsheets/test_answers.py:142
← previousnext →10,001–10,100 of 19,482, ranked by callers