Files
crewAI/lib/cli/src/crewai_cli/tui_picker.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

420 lines
12 KiB
Python

"""Arrow-key interactive pickers for CLI prompts."""
from __future__ import annotations
from contextlib import suppress
import sys
from typing import overload
import click
# CrewAI brand: primary=#FF5A50 (coral), teal=#1F7982
_CORAL = "\033[38;2;255;90;80m" # #FF5A50
_TEAL = "\033[38;2;31;121;130m" # #1F7982
_BOLD = "\033[1m"
_DIM = "\033[2m"
_RESET = "\033[0m"
_HIDE_CURSOR = "\033[?25l"
_SHOW_CURSOR = "\033[?25h"
def _is_interactive() -> bool:
try:
return sys.stdin.isatty() and sys.stdout.isatty()
except Exception:
return False
def _read_key() -> str:
if sys.platform == "win32":
import msvcrt
ch = msvcrt.getwch()
if ch in ("\x00", "\xe0"):
ch2 = msvcrt.getwch()
return {"H": "up", "P": "down"}.get(ch2, "")
if ch == "\r":
return "enter"
if ch == " ":
return "space"
if ch == "\x03":
raise KeyboardInterrupt
return ch
import termios
import tty
fd = sys.stdin.fileno()
old = termios.tcgetattr(fd)
try:
tty.setcbreak(fd)
ch = sys.stdin.read(1)
if ch == "\x1b":
seq = sys.stdin.read(2)
if seq == "[A":
return "up"
if seq == "[B":
return "down"
return "esc"
if ch in ("\r", "\n"):
return "enter"
if ch == " ":
return "space"
if ch == "\x03":
raise KeyboardInterrupt
return ch
finally:
termios.tcsetattr(fd, termios.TCSADRAIN, old)
def _clear_lines(n: int) -> None:
sys.stdout.write(f"\033[{n}A")
for _ in range(n):
sys.stdout.write("\033[2K\n")
sys.stdout.write(f"\033[{n}A")
sys.stdout.flush()
def _draw_single(labels: list[str], cursor: int, *, clear: bool = False) -> None:
total = len(labels)
if clear:
sys.stdout.write(f"\033[{total}A")
for i, label in enumerate(labels):
if i == cursor:
sys.stdout.write(f"\033[2K {_CORAL}{_RESET} {_BOLD}{label}{_RESET}\n")
else:
sys.stdout.write(f"\033[2K {label}\n")
sys.stdout.flush()
def _draw_multi(
labels: list[str],
cursor: int,
selected: set[int],
*,
action_indices: set[int] | None = None,
separator_indices: set[int] | None = None,
clear: bool = False,
) -> None:
action_indices = action_indices or set()
separator_indices = separator_indices or set()
hint_text = "↑↓ navigate, space toggle, enter confirm"
if action_indices:
hint_text = "↑↓ navigate, space toggle, enter confirm, ▸ rows expand/collapse"
hint = f" {_DIM}{hint_text}{_RESET}"
total = len(labels) + 1
if clear:
sys.stdout.write(f"\033[{total}A")
sys.stdout.write(f"\033[2K{hint}\n")
for i, label in enumerate(labels):
if i in separator_indices:
sys.stdout.write(f"\033[2K {_TEAL}{label}{_RESET}\n")
continue
if i in action_indices:
check = " "
elif i in selected:
check = f"{_CORAL}[x]{_RESET}"
else:
check = "[ ]"
arrow = f"{_CORAL}{_RESET} " if i == cursor else " "
bold = f"{_BOLD}{label}{_RESET}" if i == cursor else label
sys.stdout.write(f"\033[2K {arrow}{check} {bold}\n")
sys.stdout.flush()
def _arrow_select_one(labels: list[str]) -> int:
cursor = 0
total = len(labels)
sys.stdout.write(_HIDE_CURSOR)
sys.stdout.flush()
try:
_draw_single(labels, cursor)
while True:
key = _read_key()
if key == "up" and cursor > 0:
cursor -= 1
_draw_single(labels, cursor, clear=True)
elif key == "down" and cursor < total - 1:
cursor += 1
_draw_single(labels, cursor, clear=True)
elif key == "enter":
_clear_lines(total)
return cursor
elif key in ("esc", "q"):
_clear_lines(total)
return -1
finally:
sys.stdout.write(_SHOW_CURSOR)
sys.stdout.flush()
def _arrow_select_multi(
labels: list[str],
*,
action_indices: set[int] | None = None,
separator_indices: set[int] | None = None,
preselected: set[int] | None = None,
initial_cursor: int | None = None,
) -> tuple[list[int], int | None]:
total = len(labels)
selected: set[int] = set(preselected or ())
action_indices = action_indices or set()
separator_indices = separator_indices or set()
if initial_cursor is not None and 0 <= initial_cursor < total:
cursor = initial_cursor
else:
cursor = _first_selectable_index(total, separator_indices)
sys.stdout.write(_HIDE_CURSOR)
sys.stdout.flush()
try:
_draw_multi(
labels,
cursor,
selected,
action_indices=action_indices,
separator_indices=separator_indices,
)
while True:
key = _read_key()
if key == "up":
cursor = _next_selectable_index(cursor, -1, total, separator_indices)
_draw_multi(
labels,
cursor,
selected,
action_indices=action_indices,
separator_indices=separator_indices,
clear=True,
)
elif key == "down":
cursor = _next_selectable_index(cursor, 1, total, separator_indices)
_draw_multi(
labels,
cursor,
selected,
action_indices=action_indices,
separator_indices=separator_indices,
clear=True,
)
elif key == "space":
if cursor in action_indices:
_clear_lines(total + 1)
return sorted(selected), cursor
selected ^= {cursor}
_draw_multi(
labels,
cursor,
selected,
action_indices=action_indices,
separator_indices=separator_indices,
clear=True,
)
elif key == "enter":
_clear_lines(total + 1)
if cursor in action_indices:
return sorted(selected), cursor
return sorted(selected), None
elif key in ("esc", "q"):
_clear_lines(total + 1)
return sorted(selected), None
finally:
sys.stdout.write(_SHOW_CURSOR)
sys.stdout.flush()
def _numbered_select(labels: list[str]) -> int:
for idx, label in enumerate(labels, 1):
click.echo(f" {idx}. {label}")
click.echo()
while True:
choice = click.prompt(" Select", type=str, default="1")
if choice.lower() == "q":
return -1
try:
num = int(choice)
if 1 <= num <= len(labels):
return num - 1
except ValueError:
# Non-numeric input falls through to the shared error message.
pass
click.secho(f" Invalid choice. Enter 1-{len(labels)}.", fg="red")
def _numbered_select_multi(
labels: list[str],
*,
action_indices: set[int] | None = None,
separator_indices: set[int] | None = None,
preselected: set[int] | None = None,
) -> tuple[list[int], int | None]:
action_indices = action_indices or set()
separator_indices = separator_indices or set()
numbered_indices: list[int] = []
for idx, label in enumerate(labels):
if idx in separator_indices:
click.secho(f" {label}", fg="cyan")
continue
numbered_indices.append(idx)
click.echo(f" {len(numbered_indices)}. {label}")
click.echo()
raw = click.prompt(
" Select (comma-separated numbers, or empty to skip)",
default="",
show_default=False,
)
if not raw.strip():
return sorted(preselected or ()), None
indices: list[int] = list(preselected or ())
for part in raw.split(","):
with suppress(ValueError):
num = int(part.strip())
if 1 <= num <= len(numbered_indices):
idx = numbered_indices[num - 1]
if idx in action_indices:
return sorted(set(indices)), idx
indices.append(idx)
return sorted(set(indices)), None
def _first_selectable_index(total: int, separator_indices: set[int]) -> int:
for idx in range(total):
if idx not in separator_indices:
return idx
return 0
def _next_selectable_index(
cursor: int,
direction: int,
total: int,
separator_indices: set[int],
) -> int:
next_cursor = cursor + direction
while 0 <= next_cursor < total:
if next_cursor not in separator_indices:
return next_cursor
next_cursor += direction
return cursor
# ── Public API ──────────────────────────────────────────────────
def pick(title: str, options: list[tuple[str, str]]) -> str | None:
"""Arrow-key single-select picker.
Args:
title: Header text.
options: List of ``(value, description)`` tuples.
Returns:
The *value* of the selected option, or ``None`` if cancelled.
"""
labels = [f"{value:<12s} {desc}" for value, desc in options]
click.echo()
click.secho(f" {title}", fg="cyan", bold=True)
click.echo()
if _is_interactive():
try:
idx = _arrow_select_one(labels)
except Exception:
idx = _numbered_select(labels)
else:
idx = _numbered_select(labels)
if idx < 0:
return None
value, _desc = options[idx]
click.secho(f"{value}", fg="green")
return value
def pick_one(title: str, labels: list[str]) -> int:
"""Arrow-key single-select from plain labels.
Returns:
Selected index, or ``-1`` if cancelled.
"""
click.echo()
click.secho(f" {title}", fg="cyan")
if _is_interactive():
try:
return _arrow_select_one(labels)
except Exception:
return _numbered_select(labels)
return _numbered_select(labels)
@overload
def pick_many(
title: str,
labels: list[str],
*,
separator_indices: set[int] | None = None,
preselected: set[int] | None = None,
initial_cursor: int | None = None,
) -> list[int]: ...
@overload
def pick_many(
title: str,
labels: list[str],
*,
action_indices: set[int],
separator_indices: set[int] | None = None,
preselected: set[int] | None = None,
initial_cursor: int | None = None,
) -> tuple[list[int], int | None]: ...
def pick_many(
title: str,
labels: list[str],
*,
action_indices: set[int] | None = None,
separator_indices: set[int] | None = None,
preselected: set[int] | None = None,
initial_cursor: int | None = None,
) -> list[int] | tuple[list[int], int | None]:
"""Arrow-key multi-select with checkboxes.
Returns:
Sorted list of selected indices, or ``(indices, action_index)`` when
``action_indices`` is provided.
"""
click.echo()
click.secho(f" {title}", fg="cyan")
if _is_interactive():
try:
selected, action = _arrow_select_multi(
labels,
action_indices=action_indices,
separator_indices=separator_indices,
preselected=preselected,
initial_cursor=initial_cursor,
)
except Exception:
selected, action = _numbered_select_multi(
labels,
action_indices=action_indices,
separator_indices=separator_indices,
preselected=preselected,
)
else:
selected, action = _numbered_select_multi(
labels,
action_indices=action_indices,
separator_indices=separator_indices,
preselected=preselected,
)
if action_indices is None:
return selected
return selected, action