Files
crewAI/lib/crewai/tests/project/test_crew_loader.py
João Moura bb477f8a91
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
JSON first crews (#6131)
* feat(cli): introduce JSON crew project support and TUI enhancements

- Added support for creating and running JSON-defined crew projects, allowing users to scaffold projects with a new `create_json_crew.py` file.
- Implemented a full-screen Textual TUI for crew execution in `crew_run_tui.py`, enhancing user interaction with a two-column layout.
- Updated `run_crew.py` to prioritize JSON crew projects and added daemon mode for running without TUI.
- Introduced interactive pickers in `tui_picker.py` for improved CLI prompts.
- Enhanced validation for JSON crew files in `validate.py` to ensure proper structure and agent definitions.
- Updated `.gitignore` to exclude demo and crewai directories.

* feat: update LLM model references to gpt-5.4-mini

- Changed default LLM model from gpt-4o-mini to gpt-5.4-mini across various files, including CLI options, JSON crew configurations, and agent definitions.
- Enhanced benchmark and human feedback functionalities to utilize the new model.
- Improved user interface elements in the TUI for better interaction and feedback during execution.
- Added support for new skills directory in JSON crew project creation.

* feat(benchmark): add crew-level benchmarking functionality

- Introduced a new `benchmark` command in the CLI for crew-level benchmarking, allowing users to specify agents, models, and timeout settings.
- Implemented `CrewBenchmarkCase` to handle crew-level benchmark cases with inputs and criteria.
- Enhanced the benchmark runner to support progress tracking and detailed reporting of results for multiple models.
- Added tests for loading crew benchmark cases and validating their structure.
- Updated existing benchmark functions to accommodate the new crew-level execution model.

* feat(cli): enhance JSON crew project functionality and TUI improvements

- Added optional agent-level guardrails and advanced options in JSON crew configurations to improve output validation and flexibility.
- Updated the TUI to better handle plan step statuses, including visual indicators for task completion and failure.
- Introduced methods for parsing and managing step observation events, ensuring accurate updates to task statuses during execution.
- Enhanced validation for JSON crew projects, ensuring proper structure and error handling for agent and task definitions.
- Added comprehensive tests for new features and validation logic, ensuring robustness in JSON crew project handling.

* refactor(cli): streamline JSON crew project handling and improve validation

- Refactored JSON crew project loading and validation logic to enhance clarity and maintainability.
- Introduced utility functions for finding JSON crew files, improving code reuse across modules.
- Removed deprecated benchmark functionality and associated tests to simplify the codebase.
- Updated CLI commands to utilize the new JSON project structure, ensuring compatibility with recent changes.
- Enhanced test coverage for JSON crew project features, ensuring robust validation and error handling.

* feat(cli): enhance activity log navigation and focus management

- Added functionality to focus on the activity log when navigating through log entries.
- Implemented refresh logic for the log panel to ensure updates are displayed correctly during navigation.
- Improved keyboard navigation for log entries, allowing users to expand and scroll through logs seamlessly.
- Added tests to verify the correct behavior of log navigation and focus management in the TUI.

* feat(cli): enhance JSON crew project interaction and input handling

- Introduced a new function to enable prompt line editing for better user experience during input prompts.
- Updated the JSON crew project wizards to show interpolation hints for dynamic values, improving user guidance.
- Enhanced the handling of missing input placeholders by prompting users for required values during crew setup.
- Refactored the crew run logic to ensure proper loading and preparation of JSON-defined crews, including runtime input management.
- Added tests to verify the correct behavior of new input handling features and JSON crew project interactions.

* feat(cli): improve crew project input prompts and event handling

- Enhanced the `_prompt_text` function to allow for configurable spacing before prompts, improving user experience during input collection.
- Updated the wizards for agent and task creation to utilize the new prompt configuration, ensuring a more compact and streamlined interaction.
- Introduced new plan step lifecycle events (`PlanStepStartedEvent`, `PlanStepCompletedEvent`) to better track the execution status of plan steps.
- Refactored the step executor to emit these events during the execution of tasks, improving observability and debugging capabilities.
- Added tests to verify the correct behavior of new prompt handling and event emissions during crew project execution.

* fix: refine json-first crew interactions

* fix: prioritize common json crew tools

* fix: make json crew more tools expandable

* fix: show json crew tools by category

* feat(memory): update default embedder to OpenAI text-embedding-3-large and enhance memory compatibility

- Changed the default embedding model for Memory to OpenAI text-embedding-3-large, which uses 3072-dimensional vectors.
- Added warnings regarding compatibility issues with existing local memory stores created with 1536-dimensional embeddings.
- Updated documentation to reflect the new default embedder and its configuration options.
- Enhanced the CLI and codebase to support the new embedding model across various components, ensuring a seamless transition for users.

* fix: address PR review feedback for JSON-first crews

Review blockers:
- Forward trained_agents_file to JSON crews: crewai run -f now exports
  CREWAI_TRAINED_AGENTS_FILE for the in-process JSON crew path
- Wizard agent picker: Esc/cancel now reprompts instead of silently
  assigning the first agent
- JSON tool resolution hard-fails: unknown tool names, missing custom
  tool files, and invalid custom tool modules raise JSONProjectError
  with actionable messages instead of warn-and-continue
- Embedding dimension mismatch: LanceDB and Qdrant Edge storages raise
  EmbeddingDimensionMismatchError with reset/pin guidance instead of
  silently zero-filling vectors or returning empty search results
- Custom tool code execution documented in loader docstring and the
  scaffolded project README

CI fixes:
- ruff format across lib/
- All 133 PR-introduced mypy errors fixed (llm.py lazy-litellm and
  cli.py lazy command shims now use TYPE_CHECKING imports; textual
  is_mounted misuse fixed; pick_many overloads; misc annotations)

Bot review comments:
- Empty except blocks now have explanatory comments or debug logging
- Removed unused _C_BG/_C_PANEL/_C_BORDER globals and redundant
  import re; tests use a single import style for create_json_crew

Tests: trained-agents propagation, wizard cancel, tool resolution
failures, and dimension mismatch guidance.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: address second round of PR review comments

Cursor Bugbot:
- Wizard agent slugs: strip to [a-z0-9_] and fall back to agent_<n> so
  symbol-only roles can't produce an empty agents/.jsonc filename
- Wizard task names: dedupe against prior task names and fall back to
  task_<n> for symbol-only descriptions

CodeRabbit:
- Agent.message(): import Task explicitly at runtime instead of relying
  on the namespace injection done by crewai/__init__
- Async executor: move the native-tools-unsupported fallback from
  _ainvoke_loop_react (self-recursion) to _ainvoke_loop_native_tools,
  mirroring the sync implementation
- StepExecutor downgrade: keep the in-step conversation and append the
  text-tooling instructions instead of rebuilding messages, so completed
  native tool calls are not re-executed
- crewai-files: extension-based MIME lookup now runs before byte
  sniffing so csv/xml types are not degraded to text/plain
- Memory storages: validate every record in a save() batch against a
  consistent embedding dimension (LanceDB previously checked only the
  first record); added mixed-batch tests
- _print_post_tui_summary now typed against CrewRunApp
- Docs: Azure OpenAI default embedder change called out in the memory
  migration warning and provider table

Code quality bots:
- Removed unused _C_YELLOW/_C_CYAN (crew_run_tui) and _GREEN (tui_picker)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(cli): accordion tool picker in JSON crew wizard

The flat tool list had grown to ~90 rows. The picker now shows:
- Common tools always visible at the top
- Every other category as a single expandable row with tool and
  selection counts (e.g. "Search & Research  (27 tools, 2 selected)")
- Expanding a category collapses the previously expanded one
- Selections persist across expand/collapse via new preselected
  support in pick_many; cursor follows the toggled category row

tui_picker gains preselected + initial_cursor options on pick_many,
and Esc in multi-select now confirms the current selection instead of
discarding it (required so collapsing can't silently drop choices).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(cli): remove --daemon flag from crewai run

The flag only affected JSON crew projects — classic and flow projects
ignored it entirely, which made the behavior inconsistent. Removed the
option, the daemon code path (_run_json_crew_daemon), and its helper
(_load_json_crew_with_inputs).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: update run command tests after --daemon removal

lib/crewai/tests/cli/test_run_crew.py still asserted the old
run_crew(trained_agents_file=..., daemon=False) call signature.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): exit codes, mid-run quit, async statuses, hyphen placeholders

Addresses the latest Bugbot review round:

- Failed JSON crew runs now exit non-zero (SystemExit(1)) so scripts
  and CI don't treat failures as success, mirroring the classic path
- Quitting the TUI mid-run now ends the process (os._exit(130));
  kickoff runs in a thread worker that cannot be force-cancelled, so
  letting the CLI return would leave LLM/tool work burning tokens in
  the background
- Sidebar task statuses are now async-safe: completion/failure events
  resolve the task's own row via identity instead of assuming the most
  recently started task, and starting a task no longer blanket-marks
  earlier active rows as done
- The runtime-input prompt regex now accepts hyphenated placeholder
  names ({my-topic}), matching kickoff's interpolation pattern

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: validation safety, custom tool sandboxing, TUI log integrity, memory error surfacing

- Deploy validation no longer executes project code: validation mode
  checks tool declarations structurally (well-formed entries, custom
  tool file exists) without importing or instantiating anything.
  custom:<name> resolution only happens on the actual run path.
- custom:<name> is constrained to [A-Za-z_][A-Za-z0-9_]* and the
  resolved path must stay inside the project's tools/ directory, so
  custom:../foo or absolute-path names cannot execute code outside it.
  Tool paths resolve relative to the crew project root, not cwd.
- TUI task logs are built from per-task state captured at task start
  (idx, description, agent, start time); an out-of-order completion
  takes its output from the event and no longer steals or resets the
  current task's streamed steps/output.
- EmbeddingDimensionMismatchError now inherits ValueError instead of
  RuntimeError so background saves surface it through
  MemorySaveFailedEvent instead of silently dropping the save; the
  shutdown catch in _background_encode_batch is narrowed to the
  "cannot schedule new futures" case.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): declared project type wins over crew.json presence

A flow project that also contains a crew.json(c) file now runs and
validates as the flow it declares in pyproject.toml instead of being
hijacked by the JSON crew path. Both crewai run (_has_json_crew) and
deploy validation (_is_json_crew) check tool.crewai.type; a missing or
unreadable pyproject still means a bare JSON crew project.

Also documents why StepObservationFailedEvent intentionally marks the
plan step "done": the event signals an observer failure, not a step
failure, and the executor continues past it.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(cli): type the declared_type locals so mypy stays clean

Comparing an Any-typed .get() chain returns Any, which tripped
no-any-return on the previous commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-14 04:19:48 -03:00

425 lines
13 KiB
Python

"""Tests for crewai.project.crew_loader."""
from __future__ import annotations
import json
from pathlib import Path
import pytest
from crewai.llms.base_llm import BaseLLM
from crewai.project.json_loader import JSONProjectError, JSONProjectValidationError
from crewai.project.crew_loader import load_crew
def _write_agent(agents_dir: Path, name: str, **overrides) -> Path:
defn = {
"role": f"{name} role",
"goal": f"{name} goal",
"backstory": f"{name} backstory",
}
defn.update(overrides)
f = agents_dir / f"{name}.jsonc"
f.write_text(json.dumps(defn))
return f
def _write_crew(project_dir: Path, crew_def: dict) -> Path:
f = project_dir / "crew.jsonc"
f.write_text(json.dumps(crew_def))
return f
class TestLoadCrew:
def test_minimal_crew(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "researcher")
crew_def = {
"name": "test_crew",
"agents": ["researcher"],
"tasks": [
{
"name": "research",
"description": "Do research",
"expected_output": "Research findings",
"agent": "researcher",
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
crew, inputs = load_crew(crew_file)
assert crew.name == "test_crew"
assert len(crew.agents) == 1
assert len(crew.tasks) == 1
assert crew.tasks[0].description == "Do research"
assert inputs == {}
def test_crew_with_default_inputs(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "researcher")
crew_def = {
"name": "test_crew",
"agents": ["researcher"],
"tasks": [
{
"name": "research",
"description": "Research {topic}",
"expected_output": "Findings about {topic}",
"agent": "researcher",
}
],
"inputs": {"topic": "AI"},
}
crew_file = _write_crew(tmp_path, crew_def)
crew, inputs = load_crew(crew_file)
assert inputs == {"topic": "AI"}
def test_crew_with_multiple_agents(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "researcher")
_write_agent(agents_dir, "writer")
crew_def = {
"name": "multi_crew",
"agents": ["researcher", "writer"],
"tasks": [
{
"name": "research",
"description": "Do research",
"expected_output": "Findings",
"agent": "researcher",
},
{
"name": "write",
"description": "Write report",
"expected_output": "Report",
"agent": "writer",
"context": ["research"],
},
],
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
assert len(crew.agents) == 2
assert len(crew.tasks) == 2
# Second task should have context referencing first task
assert crew.tasks[1].context is not None
assert len(crew.tasks[1].context) == 1
def test_crew_hierarchical_process(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker")
crew_def = {
"name": "hier_crew",
"agents": ["worker"],
"tasks": [
{
"name": "work",
"description": "Do work",
"expected_output": "Work done",
"agent": "worker",
}
],
"process": "hierarchical",
"manager_llm": "openai/gpt-4o",
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
from crewai import Process
assert crew.process == Process.hierarchical
def test_crew_accepts_llm_config_objects(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker", llm="ollama/llama3")
crew_def = {
"name": "llm_config_crew",
"agents": ["worker"],
"tasks": [
{
"name": "work",
"description": "Do work",
"expected_output": "Work done",
"agent": "worker",
}
],
"process": "hierarchical",
"manager_llm": {
"model": "llama3",
"provider": "ollama",
"base_url": "http://localhost:11434",
},
"planning_llm": {
"model": "deepseek-chat",
"provider": "deepseek",
"api_key": "test-key",
},
"chat_llm": {
"model": "openrouter/anthropic/claude-3-opus",
"api_key": "test-key",
},
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
assert isinstance(crew.manager_llm, BaseLLM)
assert crew.manager_llm.model == "llama3"
assert crew.manager_llm.provider == "ollama"
assert crew.manager_llm.base_url == "http://localhost:11434/v1"
assert isinstance(crew.planning_llm, BaseLLM)
assert crew.planning_llm.model == "deepseek-chat"
assert crew.planning_llm.provider == "deepseek"
assert isinstance(crew.chat_llm, BaseLLM)
assert crew.chat_llm.model == "anthropic/claude-3-opus"
assert crew.chat_llm.provider == "openrouter"
def test_crew_accepts_public_crew_config_fields(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker")
crew_def = {
"name": "config_crew",
"agents": ["worker"],
"tasks": [
{
"name": "work",
"description": "Do work",
"expected_output": "Work done",
"agent": "worker",
}
],
"cache": False,
"max_rpm": 12,
"planning": True,
"planning_llm": "openai/gpt-4o-mini",
"share_crew": False,
"output_log_file": "crew.log",
"tracing": False,
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
assert crew.cache is False
assert crew.max_rpm == 12
assert crew.planning is True
assert crew.planning_llm == "openai/gpt-4o-mini"
assert crew.output_log_file == "crew.log"
assert crew.tracing is False
def test_crew_with_output_file(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "writer")
crew_def = {
"name": "output_crew",
"agents": ["writer"],
"tasks": [
{
"name": "write",
"description": "Write something",
"expected_output": "Written content",
"agent": "writer",
"output_file": "output.md",
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
assert crew.tasks[0].output_file == "output.md"
def test_task_accepts_public_task_config_fields(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "writer")
schema = {
"title": "ReportOutput",
"type": "object",
"properties": {
"summary": {"type": "string"},
},
"required": ["summary"],
}
crew_def = {
"name": "task_config_crew",
"agents": ["writer"],
"tasks": [
{
"name": "write",
"description": "Write something",
"expected_output": "Written content",
"agent": "writer",
"output_json": schema,
"response_model": schema,
"create_directory": False,
"human_input": True,
"markdown": True,
"guardrail": "Return a summary field.",
"guardrail_max_retries": 1,
"allow_crewai_trigger_context": False,
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
task = crew.tasks[0]
assert task.output_json is not None
assert "summary" in task.output_json.model_fields
assert task.response_model is not None
assert task.create_directory is False
assert task.human_input is True
assert task.markdown is True
assert task.guardrail == "Return a summary field."
assert task.allow_crewai_trigger_context is False
def test_missing_agent_file_raises(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
crew_def = {
"name": "broken_crew",
"agents": ["nonexistent"],
"tasks": [],
}
crew_file = _write_crew(tmp_path, crew_def)
with pytest.raises(FileNotFoundError, match="nonexistent"):
load_crew(crew_file)
def test_task_references_unknown_agent_raises(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "researcher")
crew_def = {
"name": "bad_ref_crew",
"agents": ["researcher"],
"tasks": [
{
"name": "task1",
"description": "Do something",
"expected_output": "Something",
"agent": "unknown_agent",
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
with pytest.raises(JSONProjectError, match="unknown_agent"):
load_crew(crew_file)
def test_task_context_order_dependency(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker")
crew_def = {
"name": "order_crew",
"agents": ["worker"],
"tasks": [
{
"name": "task2",
"description": "Second task",
"expected_output": "Output",
"agent": "worker",
"context": ["task1"],
},
{
"name": "task1",
"description": "First task",
"expected_output": "Output",
"agent": "worker",
},
],
}
crew_file = _write_crew(tmp_path, crew_def)
with pytest.raises(JSONProjectError, match="task1"):
load_crew(crew_file)
def test_runtime_fields_are_rejected(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker")
crew_def = {
"name": "bad_runtime_crew",
"id": "00000000-0000-4000-8000-000000000000",
"agents": ["worker"],
"tasks": [
{
"name": "work",
"description": "Work",
"expected_output": "Done",
"agent": "worker",
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
with pytest.raises(JSONProjectValidationError, match="runtime-only"):
load_crew(crew_file)
def test_custom_agents_dir(self, tmp_path: Path):
custom_dir = tmp_path / "my_agents"
custom_dir.mkdir()
_write_agent(custom_dir, "analyst")
crew_def = {
"name": "custom_dir_crew",
"agents": ["analyst"],
"tasks": [
{
"name": "analyze",
"description": "Analyze data",
"expected_output": "Analysis",
"agent": "analyst",
}
],
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file, agents_dir=custom_dir)
assert len(crew.agents) == 1
def test_crew_verbose_and_memory_flags(self, tmp_path: Path):
agents_dir = tmp_path / "agents"
agents_dir.mkdir()
_write_agent(agents_dir, "worker")
crew_def = {
"name": "flags_crew",
"agents": ["worker"],
"tasks": [
{
"name": "work",
"description": "Work",
"expected_output": "Done",
"agent": "worker",
}
],
"verbose": True,
"memory": True,
}
crew_file = _write_crew(tmp_path, crew_def)
crew, _ = load_crew(crew_file)
assert crew.verbose is True