Compare commits

..

2 Commits

Author SHA1 Message Date
Alex
d8ba5b823a docs: add file upload support documentation for flows
- Add 'File Inputs' section to flows.mdx documenting:
  - Using crewai-files types (ImageFile, PDFFile, etc.) in flow state
  - CrewAI Platform (AMP) automatic file upload dropzone rendering
  - API usage with URL string coercion via Pydantic
- Update files.mdx with:
  - Example of file types in flow state
  - Note about CrewAI Platform integration for flows

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-27 00:45:31 -07:00
Joao Moura
5a850a708b fix: preserve method return value as flow output for @human_feedback with emit
When a @human_feedback decorated method with emit= is the final method in a
flow (no downstream listeners triggered), the flow's final output was
incorrectly set to the collapsed outcome string (e.g., 'approved') instead
of the method's actual return value (e.g., a state dict).

Root cause: _process_feedback() returns the collapsed_outcome string when
emit is set, and this string was being stored as the method's result in
_method_outputs.

The fix:
1. In human_feedback.py: After _process_feedback, stash the real method_output
   on the flow instance as _human_feedback_method_output when emit is set.

2. In flow.py: After appending a method result to _method_outputs, check if
   _human_feedback_method_output is set. If so, replace the last entry with
   the stashed real output and clear the stash.

This ensures:
- Routing still works correctly (collapsed outcome used for @listen matching)
- The flow's final result is the actual method return value
- If downstream listeners execute, their results become the final output

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-25 22:51:44 -07:00
19 changed files with 106 additions and 2001 deletions

View File

@@ -4,29 +4,6 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
icon: "clock"
mode: "wide"
---
<Update label="25 مارس 2026">
## v1.12.2
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.12.2)
## ما الذي تغير
### الميزات
- إضافة مرحلة إصدار المؤسسات إلى إصدار أدوات المطورين
### إصلاحات الأخطاء
- الحفاظ على قيمة إرجاع الطريقة كإخراج تدفق لـ @human_feedback مع emit
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.12.1
- مراجعة سياسة الأمان وتعليمات الإبلاغ
## المساهمون
@alex-clawd, @greysonlalonde, @joaomdmoura, @theCyberTech
</Update>
<Update label="25 مارس 2026">
## v1.12.1

File diff suppressed because it is too large Load Diff

View File

@@ -4,29 +4,6 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="Mar 25, 2026">
## v1.12.2
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.12.2)
## What's Changed
### Features
- Add enterprise release phase to devtools release
### Bug Fixes
- Preserve method return value as flow output for @human_feedback with emit
### Documentation
- Update changelog and version for v1.12.1
- Revise security policy and reporting instructions
## Contributors
@alex-clawd, @greysonlalonde, @joaomdmoura, @theCyberTech
</Update>
<Update label="Mar 25, 2026">
## v1.12.1

View File

@@ -134,6 +134,29 @@ result = flow.kickoff(
)
```
You can also define file types directly in your flow state for structured file handling:
```python
from pydantic import BaseModel
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile, PDFFile
class DocumentState(BaseModel):
document: PDFFile
cover_image: ImageFile
title: str = ""
class DocumentFlow(Flow[DocumentState]):
@start()
def process(self):
content = self.state.document.read()
return {"processed": True}
```
<Note type="info" title="CrewAI Platform Integration">
When deploying flows to the CrewAI Platform (AMP), file fields in your state automatically render as file upload dropzones in the UI. For API usage, you can pass URL strings directly and Pydantic coerces them to file objects automatically. See [Flows - File Inputs](/en/concepts/flows#file-inputs) for details.
</Note>
### With Standalone Agents
Pass files directly to agent kickoff:

View File

@@ -341,6 +341,69 @@ flow.kickoff()
By providing both unstructured and structured state management options, CrewAI Flows empowers developers to build AI workflows that are both flexible and robust, catering to a wide range of application requirements.
## File Inputs
Flows support file inputs through the `crewai-files` package, enabling you to build workflows that process images, PDFs, and other file types. When you use file types like `ImageFile` or `PDFFile` in your flow state, they integrate seamlessly with both local development and the CrewAI Platform.
<Note type="info" title="Optional Dependency">
File support requires the optional `crewai-files` package. Install it with:
```bash
uv add 'crewai[file-processing]'
```
</Note>
### Using File Types in Flow State
You can include file types directly in your structured flow state:
```python
from pydantic import BaseModel
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile, PDFFile
class DocumentProcessingState(BaseModel):
document: PDFFile # Renders as file upload in CrewAI Platform
cover_image: ImageFile # Renders as image upload
title: str = "" # Renders as text input
class DocumentFlow(Flow[DocumentProcessingState]):
@start()
def process_document(self):
# Access the file - works with URLs, paths, or uploaded files
content = self.state.document.read()
# Or pass to an agent with VisionTool, etc.
return {"processed": True}
```
### CrewAI Platform Integration
When you deploy a flow to the CrewAI Platform (AMP), file fields in your state automatically render as file upload dropzones in the UI. This makes it easy to build user-facing applications that accept file uploads without any additional frontend work.
| State Field Type | Platform UI Rendering |
|:-----------------|:----------------------|
| `ImageFile` | Image upload dropzone |
| `PDFFile` | PDF upload dropzone |
| `AudioFile` | Audio upload dropzone |
| `VideoFile` | Video upload dropzone |
| `TextFile` | Text file upload dropzone |
| `str`, `int`, etc. | Standard form inputs |
### API Usage
When calling your flow via API, you can pass URL strings directly for file fields. Pydantic automatically coerces URLs into the appropriate file type:
```python
# API request body - URLs are automatically converted to file objects
{
"document": "https://example.com/report.pdf",
"cover_image": "https://example.com/cover.png",
"title": "Q4 Report"
}
```
For more details on file types, sources, and provider support, see the [Files documentation](/en/concepts/files).
## Flow Persistence
The @persist decorator enables automatic state persistence in CrewAI Flows, allowing you to maintain flow state across restarts or different workflow executions. This decorator can be applied at either the class level or method level, providing flexibility in how you manage state persistence.

View File

@@ -4,29 +4,6 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
icon: "clock"
mode: "wide"
---
<Update label="2026년 3월 25일">
## v1.12.2
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.12.2)
## 변경 사항
### 기능
- devtools 릴리스에 기업 릴리스 단계 추가
### 버그 수정
- @human_feedback과 함께 emit을 사용할 때 메서드 반환 값을 흐름 출력으로 유지
### 문서
- v1.12.1에 대한 변경 로그 및 버전 업데이트
- 보안 정책 및 보고 지침 수정
## 기여자
@alex-clawd, @greysonlalonde, @joaomdmoura, @theCyberTech
</Update>
<Update label="2026년 3월 25일">
## v1.12.1

View File

@@ -4,29 +4,6 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="25 mar 2026">
## v1.12.2
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.12.2)
## O que Mudou
### Recursos
- Adicionar fase de lançamento empresarial ao lançamento do devtools
### Correções de Bugs
- Preservar o valor de retorno do método como saída de fluxo para @human_feedback com emit
### Documentação
- Atualizar changelog e versão para v1.12.1
- Revisar política de segurança e instruções de relatório
## Contributors
@alex-clawd, @greysonlalonde, @joaomdmoura, @theCyberTech
</Update>
<Update label="25 mar 2026">
## v1.12.1

View File

@@ -152,4 +152,4 @@ __all__ = [
"wrap_file_source",
]
__version__ = "1.12.2"
__version__ = "1.12.1"

View File

@@ -11,7 +11,7 @@ dependencies = [
"pytube~=15.0.0",
"requests~=2.32.5",
"docker~=7.1.0",
"crewai==1.12.2",
"crewai==1.12.1",
"tiktoken~=0.8.0",
"beautifulsoup4~=4.13.4",
"python-docx~=1.2.0",

View File

@@ -309,4 +309,4 @@ __all__ = [
"ZapierActionTools",
]
__version__ = "1.12.2"
__version__ = "1.12.1"

View File

@@ -54,7 +54,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
[project.optional-dependencies]
tools = [
"crewai-tools==1.12.2",
"crewai-tools==1.12.1",
]
embeddings = [
"tiktoken~=0.8.0"

View File

@@ -42,7 +42,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
_suppress_pydantic_deprecation_warnings()
__version__ = "1.12.2"
__version__ = "1.12.1"
_telemetry_submitted = False

View File

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
authors = [{ name = "Your Name", email = "you@example.com" }]
requires-python = ">=3.10,<3.14"
dependencies = [
"crewai[tools]==1.12.2"
"crewai[tools]==1.12.1"
]
[project.scripts]

View File

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
authors = [{ name = "Your Name", email = "you@example.com" }]
requires-python = ">=3.10,<3.14"
dependencies = [
"crewai[tools]==1.12.2"
"crewai[tools]==1.12.1"
]
[project.scripts]

View File

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
readme = "README.md"
requires-python = ">=3.10,<3.14"
dependencies = [
"crewai[tools]==1.12.2"
"crewai[tools]==1.12.1"
]
[tool.crewai]

View File

@@ -883,9 +883,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
self.human_feedback_history: list[HumanFeedbackResult] = []
self.last_human_feedback: HumanFeedbackResult | None = None
self._pending_feedback_context: PendingFeedbackContext | None = None
# Per-method stash for real @human_feedback output (keyed by method name)
# Used to decouple routing outcome from method return value when emit is set
self._human_feedback_method_outputs: dict[str, Any] = {}
self._human_feedback_method_output: Any = None # Stashed real output from @human_feedback with emit
self.suppress_flow_events: bool = suppress_flow_events
# User input history (for self.ask())
@@ -2297,12 +2295,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
# For @human_feedback methods with emit, the result is the collapsed outcome
# (e.g., "approved") used for routing. But we want the actual method output
# to be the stored result (for final flow output). Replace the last entry
# if a stashed output exists. Dict-based stash is concurrency-safe and
# handles None return values (presence in dict = stashed, not value).
if method_name in self._human_feedback_method_outputs:
self._method_outputs[-1] = self._human_feedback_method_outputs.pop(
method_name
)
# if a stashed output exists.
if self._human_feedback_method_output is not None:
self._method_outputs[-1] = self._human_feedback_method_output
self._human_feedback_method_output = None
self._method_execution_counts[method_name] = (
self._method_execution_counts.get(method_name, 0) + 1

View File

@@ -594,9 +594,8 @@ def human_feedback(
# Stash the real method output for final flow result when emit is set
# (result is the collapsed outcome string for routing, but we want to
# preserve the actual method output as the flow's final result)
# Uses per-method dict for concurrency safety and to handle None returns
if emit:
self._human_feedback_method_outputs[func.__name__] = method_output
self._human_feedback_method_output = method_output
return result
@@ -625,9 +624,8 @@ def human_feedback(
# Stash the real method output for final flow result when emit is set
# (result is the collapsed outcome string for routing, but we want to
# preserve the actual method output as the flow's final result)
# Uses per-method dict for concurrency safety and to handle None returns
if emit:
self._human_feedback_method_outputs[func.__name__] = method_output
self._human_feedback_method_output = method_output
return result

View File

@@ -726,31 +726,3 @@ class TestHumanFeedbackFinalOutputPreservation:
# _method_outputs should contain the real output
assert len(flow._method_outputs) == 1
assert flow._method_outputs[0] == {"data": "real output"}
@patch("builtins.input", return_value="looks good")
@patch("builtins.print")
def test_none_return_value_is_preserved(self, mock_print, mock_input):
"""A method returning None should preserve None as flow output, not the outcome string."""
class NoneReturnFlow(Flow):
@start()
@human_feedback(
message="Review:",
emit=["approved", "rejected"],
llm="gpt-4o-mini",
)
def process(self):
# Method does work but returns None (implicit)
pass
flow = NoneReturnFlow()
with (
patch.object(flow, "_request_human_feedback", return_value=""),
patch.object(flow, "_collapse_to_outcome", return_value="approved"),
):
result = flow.kickoff()
# Final output should be None (the method's real return), not "approved"
assert result is None, f"Expected None, got {result!r}"
assert flow.last_human_feedback.outcome == "approved"

View File

@@ -1,3 +1,3 @@
"""CrewAI development tools."""
__version__ = "1.12.2"
__version__ = "1.12.1"