Compare commits

..

7 Commits

Author SHA1 Message Date
Alex
50c4b6e99f docs: add file upload to kickoff guide, clarify flow state population, all languages
- Added new "File Uploads" section to kickoff-crew.mdx with multipart,
  JSON URL, and separate upload + kickoff examples
- Clarified that file-typed fields in flow state schema signal the
  Platform UI to render file dropzones
- Updated flows.mdx File Inputs section to show state population pattern
- Updated files.mdx With Flows section with state schema example
- Applied all changes to en, ar, ko, pt-BR translations

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
f01f33de69 docs: translate file upload sections to pt-BR, ko, ar
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
8e59b27c93 docs: fix links + add file upload sections to all language versions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
53eb566e5c docs: address review comments — consistent field names, input_files key, cross-references
- Fix field name mismatch: use 'cover_image' in curl examples to match Python model
- Change 'inputFiles' to 'input_files' (snake_case) for Python API convention
- Add note that Option 3 is an alternative to multipart upload
- Add Platform API documentation reference for /files endpoint
- Add cross-reference from files.mdx to flows.mdx file inputs section

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
753b48f495 docs: Update file upload API to use unified /kickoff endpoint
The /kickoff endpoint now auto-detects content type:
- JSON body for normal kickoff
- multipart/form-data for file uploads

Removed references to separate /kickoff/multipart endpoint.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
1d34bed515 docs: Add API usage patterns for file uploads in flows
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
Alex
9ed3a3026b docs: Add file upload support documentation for flows
Document how to use crewai-files types in flow state for file uploads,
including CrewAI Platform integration with automatic file upload UI.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-04-22 03:32:49 -07:00
62 changed files with 996 additions and 5778 deletions

103
.github/workflows/import-time.yml vendored Normal file
View File

@@ -0,0 +1,103 @@
name: Import Time Guard
on:
pull_request:
paths:
- "lib/crewai/src/**"
- "lib/crewai/pyproject.toml"
- "pyproject.toml"
permissions:
contents: read
jobs:
import-time:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.12"]
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: astral-sh/setup-uv@v6
with:
version: "0.11.3"
enable-cache: true
- name: Install the project
run: uv sync --all-extras --no-dev
env:
UV_PYTHON: ${{ matrix.python-version }}
- name: Benchmark PR branch
id: pr
run: |
result=$(uv run python scripts/benchmark_import_time.py --runs 5 --json)
echo "result=$result" >> "$GITHUB_OUTPUT"
echo "pr_median=$(echo $result | python3 -c 'import sys,json; print(json.load(sys.stdin)["median_s"])')" >> "$GITHUB_OUTPUT"
echo "### PR Branch Import Time" >> "$GITHUB_STEP_SUMMARY"
echo "$result" | python3 -c "
import sys, json
d = json.load(sys.stdin)
print(f'- Median: {d[\"median_s\"]}s')
print(f'- Mean: {d[\"mean_s\"]}s ± {d[\"stdev_s\"]}s')
print(f'- Range: {d[\"min_s\"]}s {d[\"max_s\"]}s')
" >> "$GITHUB_STEP_SUMMARY"
env:
UV_PYTHON: ${{ matrix.python-version }}
- name: Checkout base branch
run: git checkout ${{ github.event.pull_request.base.sha }}
- name: Install base branch
run: uv sync --all-extras --no-dev
env:
UV_PYTHON: ${{ matrix.python-version }}
- name: Benchmark base branch
id: base
run: |
result=$(uv run python scripts/benchmark_import_time.py --runs 5 --json 2>/dev/null || echo '{"median_s": 0}')
echo "result=$result" >> "$GITHUB_OUTPUT"
echo "base_median=$(echo $result | python3 -c 'import sys,json; print(json.load(sys.stdin)["median_s"])')" >> "$GITHUB_OUTPUT"
echo "### Base Branch Import Time" >> "$GITHUB_STEP_SUMMARY"
echo "$result" | python3 -c "
import sys, json
d = json.load(sys.stdin)
if d.get('median_s', 0) > 0:
print(f'- Median: {d[\"median_s\"]}s')
else:
print('- Benchmark script not present on base branch (skip comparison)')
" >> "$GITHUB_STEP_SUMMARY"
env:
UV_PYTHON: ${{ matrix.python-version }}
- name: Compare and gate
run: |
pr_median=${{ steps.pr.outputs.pr_median }}
base_median=${{ steps.base.outputs.base_median }}
python3 -c "
pr = float('$pr_median')
base = float('$base_median')
if base <= 0:
print('⏭️ No base benchmark available — skipping comparison.')
exit(0)
change_pct = ((pr - base) / base) * 100
print(f'Base: {base:.3f}s')
print(f'PR: {pr:.3f}s')
print(f'Change: {change_pct:+.1f}%')
print()
if change_pct > 5:
print(f'❌ BLOCKED: Import time regressed by {change_pct:.1f}% (threshold: 5%)')
exit(1)
elif change_pct > 0:
print(f'⚠️ Slight regression ({change_pct:.1f}%) but within 5% threshold.')
else:
print(f'✅ Import time improved by {abs(change_pct):.1f}%')
"

View File

@@ -4,80 +4,6 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
icon: "clock"
mode: "wide"
---
<Update label="25 أبريل 2026">
## v1.14.3
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3)
## ما الذي تغير
### الميزات
- إضافة أحداث دورة الحياة لعمليات نقطة التحقق
- إضافة دعم لـ e2b
- الرجوع إلى DefaultAzureCredential عند عدم توفير مفتاح API في تكامل Azure
- إضافة دعم Bedrock V4
- إضافة أدوات Daytona sandbox لوظائف محسّنة
- إضافة دعم نقطة التحقق والتفرع للوكلاء المستقلين
### إصلاحات الأخطاء
- إصلاح execution_id ليكون منفصلًا عن state.id
- حل مشكلة إعادة تشغيل أحداث الطريقة المسجلة عند استئناف نقطة التحقق
- إصلاح تسلسل مراجع class initial_state كـ JSON schema
- الحفاظ على مهارات الوكلاء التي تحتوي على بيانات وصفية فقط
- تمرير أسماء @CrewBase الضمنية إلى أحداث الطاقم
- دمج بيانات التنفيذ عند تهيئة دفعة مكررة
- إصلاح تسلسل حقول مراجع class Task لنقاط التحقق
- التعامل مع نتيجة BaseModel في حلقة إعادة المحاولة guardrail
- الحفاظ على thought_signature في استدعاءات أدوات Gemini للبث
- إصدار task_started عند استئناف التفرع وإعادة تصميم واجهة المستخدم النصية لنقطة التحقق
- استخدام تواريخ مستقبلية في اختبارات تقليم نقطة التحقق لمنع الفشل المعتمد على الوقت
- إصلاح ترتيب التشغيل الجاف والتعامل مع الفرع القديم الذي تم التحقق منه في إصدار أدوات التطوير
- ترقية lxml إلى >=6.1.0 لرقعة الأمان
- رفع python-dotenv إلى >=1.2.2 لرقعة الأمان
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.3
- إضافة صفحة "بناء باستخدام الذكاء الاصطناعي" وتحديث التنقل لجميع اللغات
- إزالة الأسئلة الشائعة حول التسعير من صفحة البناء باستخدام الذكاء الاصطناعي عبر جميع المواقع
### الأداء
- تحسين MCP SDK وأنواع الأحداث لتقليل بدء التشغيل البارد بنسبة ~29%
### إعادة الهيكلة
- إعادة هيكلة مساعدي نقطة التحقق للقضاء على التكرار وتشديد تلميحات نوع الحالة
## المساهمون
@MatthiasHowellYopp, @akaKuruma, @alex-clawd, @github-actions[bot], @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha, @renatonitta
</Update>
<Update label="23 أبريل 2026">
## v1.14.3a3
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3a3)
## ما الذي تغير
### الميزات
- إضافة دعم لـ e2b
- تنفيذ التراجع إلى DefaultAzureCredential عند عدم توفير مفتاح API
### إصلاحات الأخطاء
- ترقية lxml إلى >=6.1.0 لمعالجة مشكلة الأمان GHSA-vfmq-68hx-4jfw
### الوثائق
- إزالة الأسئلة الشائعة حول التسعير من صفحة البناء باستخدام الذكاء الاصطناعي عبر جميع اللغات
### الأداء
- تحسين وقت بدء التشغيل البارد بنسبة ~29% من خلال التحميل الكسول لمجموعة أدوات MCP وأنواع الأحداث
## المساهمون
@alex-clawd, @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha
</Update>
<Update label="22 أبريل 2026">
## v1.14.3a2

View File

@@ -117,23 +117,35 @@ task = Task(
### مع التدفقات
مرر الملفات إلى التدفقات، والتي تنتقل تلقائيًا إلى الأطقم:
تعمل الحقول من نوع الملف (`File`، `ImageFile`، `PDFFile`) في مخطط حالة التدفق كإشارة لواجهة المنصة. عند النشر، تُعرض هذه الحقول كمناطق سحب وإفلات لرفع الملفات. يمكن أيضًا تمرير الملفات عبر `input_files` في API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile
from crewai_files import File, ImageFile
from pydantic import BaseModel
class AnalysisFlow(Flow):
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform UI
cover_image: ImageFile # Image-specific dropzone
title: str = ""
class AnalysisFlow(Flow[MyState]):
@start()
def analyze(self):
# Files are automatically populated in state
content = self.state.document.read()
return self.analysis_crew.kickoff()
flow = AnalysisFlow()
result = flow.kickoff(
input_files={"image": ImageFile(source="data.png")}
input_files={"document": File(source="report.pdf")}
)
```
<Note type="info" title="تكامل منصة CrewAI">
عند النشر على منصة CrewAI، تحصل الحقول من نوع الملف مثل `ImageFile` و `PDFFile` وغيرها في حالة التدفق تلقائيًا على واجهة رفع ملفات. يمكن للمستخدمين سحب وإفلات الملفات مباشرة في واجهة المنصة. يتم تخزين الملفات بشكل آمن وتمريرها إلى الوكلاء باستخدام تحسينات خاصة بالمزود (base64 مضمّن، أو واجهات برمجة لرفع الملفات، أو مراجع URL حسب المزود). للاطلاع على أمثلة استخدام API، راجع [مدخلات الملفات في التدفقات](/ar/concepts/flows#مدخلات-الملفات).
</Note>
### مع الوكلاء المستقلين
مرر الملفات مباشرة إلى تشغيل الوكيل:

View File

@@ -341,6 +341,90 @@ flow.kickoff()
من خلال توفير خيارات إدارة الحالة غير المهيكلة والمهيكلة، تمكّن تدفقات CrewAI المطورين من بناء سير عمل ذكاء اصطناعي مرن ومتين في آن واحد، ملبيةً مجموعة واسعة من متطلبات التطبيقات.
### مدخلات الملفات
عند استخدام الحالة المهيكلة، يمكنك تضمين حقول من نوع الملف باستخدام فئات من `crewai-files`. تعمل الحقول من نوع الملف في حالة التدفق كإشارة للمنصة — فهي تُعرض تلقائيًا كمناطق سحب وإفلات لرفع الملفات في واجهة علامة تبويب Run ويتم تعبئتها عند رفع الملفات عبر المنصة أو تمريرها عبر `input_files` في API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import File, ImageFile, PDFFile
from pydantic import BaseModel
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform
title: str = ""
class MyFlow(Flow[MyState]):
@start()
def process(self):
# File object is automatically populated in state
# when uploaded via Platform UI or passed via API
content = self.state.document.read()
print(f"Processing {self.state.title}: {len(content)} bytes")
return content
```
عند النشر على **منصة CrewAI**، تُعرض الحقول من نوع الملف (`File`، `ImageFile`، `PDFFile` من `crewai-files`) تلقائيًا كمناطق سحب وإفلات لرفع الملفات في واجهة المستخدم. يمكن للمستخدمين سحب وإفلات الملفات، والتي تُملأ بعد ذلك في حالة التدفق الخاص بك.
**بدء التشغيل مع الملفات عبر API:**
تكتشف نقطة النهاية `/kickoff` تنسيق الطلب تلقائيًا:
- **جسم JSON** ← بدء تشغيل عادي
- **multipart/form-data** ← رفع ملف + بدء تشغيل
يمكن لمستخدمي API أيضًا تمرير سلاسل URL مباشرة إلى الحقول من نوع الملف — يقوم Pydantic بتحويلها تلقائيًا.
### استخدام API
#### الخيار 1: بدء تشغيل multipart (موصى به)
أرسل الملفات مباشرة مع طلب بدء التشغيل:
```bash
# With files (multipart) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"company_name": "Einstein"}' \
-F 'cover_image=@/path/to/photo.jpg'
```
يتم تخزين الملفات تلقائيًا وتحويلها إلى كائنات `FileInput`. يتلقى الوكيل الملف مع تحسين خاص بالمزود (base64 مضمّن، أو API لرفع الملفات، أو مرجع URL حسب مزود LLM).
#### الخيار 2: بدء تشغيل JSON (بدون ملفات)
```bash
# Without files (JSON) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}}'
```
#### الخيار 3: رفع منفصل + بدء تشغيل
هذا بديل لرفع multipart عندما تحتاج إلى رفع الملفات بشكل منفصل عن طلب بدء التشغيل. ارفع الملفات أولاً، ثم أشِر إليها بواسطة URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/photo.jpg' \
-F 'field_name=cover_image'
# Returns: {"url": "https://...", "field_name": "cover_image"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}, "input_files": {"cover_image": "https://..."}}'
```
راجع وثائق Platform API للحصول على تفاصيل كاملة حول نقطة النهاية `/files`.
#### على منصة CrewAI
عند استخدام واجهة المنصة، تُعرض الحقول من نوع الملف تلقائيًا كمناطق سحب وإفلات للرفع. لا حاجة لاستدعاءات API — فقط أفلِت الملف وانقر على تشغيل.
## استمرارية التدفق
يتيح مزخرف @persist الاستمرارية التلقائية للحالة في تدفقات CrewAI، مما يسمح لك بالحفاظ على حالة التدفق عبر عمليات إعادة التشغيل أو تنفيذات سير العمل المختلفة. يمكن تطبيق هذا المزخرف على مستوى الفئة أو مستوى الدالة، مما يوفر مرونة في كيفية إدارة استمرارية الحالة.

View File

@@ -86,6 +86,60 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
رمز الحامل متاح في علامة تبويب Status في صفحة تفاصيل طاقمك.
## رفع الملفات
عندما يتضمن طاقمك أو تدفقك حقول حالة من نوع الملف (باستخدام `ImageFile` أو `PDFFile` أو `File` من `crewai-files`)، تُعرض هذه الحقول تلقائيًا كمناطق سحب وإفلات لرفع الملفات في واجهة علامة تبويب Run. يمكن للمستخدمين سحب وإفلات الملفات مباشرة، وتتولى المنصة التخزين والتسليم إلى وكلائك.
### بدء تشغيل Multipart (موصى به)
أرسل الملفات مباشرة مع طلب بدء التشغيل باستخدام `multipart/form-data`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"title": "Report"}' \
-F 'document=@/path/to/file.pdf'
```
يتم تخزين الملفات تلقائيًا وتحويلها إلى كائنات ملفات. يتلقى الوكيل الملف مع تحسين خاص بالمزود (base64 مضمّن، أو API لرفع الملفات، أو مرجع URL حسب مزود LLM).
### بدء تشغيل JSON مع عناوين URL للملفات
إذا كانت لديك ملفات مستضافة بالفعل على عناوين URL، مررها عبر `input_files`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"inputs": {"title": "Report"},
"input_files": {"document": "https://example.com/file.pdf"}
}'
```
### رفع منفصل + بدء تشغيل
ارفع الملفات أولاً، ثم أشِر إليها بواسطة URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/file.pdf' \
-F 'field_name=document'
# Returns: {"url": "https://...", "field_name": "document"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"title": "Report"}, "input_files": {"document": "https://..."}}'
```
<Note type="info">
يعمل رفع الملفات بنفس الطريقة لكل من الطواقم والتدفقات. عرّف حقول من نوع الملف في مخطط حالتك، وستتولى واجهة المنصة وAPI الرفع تلقائيًا.
</Note>
### التحقق من صحة الطاقم
قبل تنفيذ العمليات، يمكنك التحقق من أن طاقمك يعمل بشكل صحيح:

File diff suppressed because it is too large Load Diff

View File

@@ -4,80 +4,6 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="Apr 25, 2026">
## v1.14.3
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3)
## What's Changed
### Features
- Add lifecycle events for checkpoint operations
- Add support for e2b
- Fall back to DefaultAzureCredential when no API key is provided in Azure integration
- Add Bedrock V4 support
- Add Daytona sandbox tools for enhanced functionality
- Add checkpoint and fork support to standalone agents
### Bug Fixes
- Fix execution_id to be separate from state.id
- Resolve replay of recorded method events on checkpoint resume
- Fix serialization of initial_state class references as JSON schema
- Preserve metadata-only agent skills
- Propagate implicit @CrewBase names to crew events
- Merge execution metadata on duplicate batch initialization
- Fix serialization of Task class-reference fields for checkpointing
- Handle BaseModel result in guardrail retry loop
- Preserve thought_signature in Gemini streaming tool calls
- Emit task_started on fork resume and redesign checkpoint TUI
- Use future dates in checkpoint prune tests to prevent time-dependent failures
- Fix dry-run order and handle checked-out stale branch in devtools release
- Upgrade lxml to >=6.1.0 for security patch
- Bump python-dotenv to >=1.2.2 for security patch
### Documentation
- Update changelog and version for v1.14.3
- Add 'Build with AI' page and update navigation for all languages
- Remove pricing FAQ from build-with-ai page across all locales
### Performance
- Optimize MCP SDK and event types to reduce cold start by ~29%
### Refactoring
- Refactor checkpoint helpers to eliminate duplication and tighten state type hints
## Contributors
@MatthiasHowellYopp, @akaKuruma, @alex-clawd, @github-actions[bot], @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha, @renatonitta
</Update>
<Update label="Apr 23, 2026">
## v1.14.3a3
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3a3)
## What's Changed
### Features
- Add support for e2b
- Implement fallback to DefaultAzureCredential when no API key is provided
### Bug Fixes
- Upgrade lxml to >=6.1.0 to address security issue GHSA-vfmq-68hx-4jfw
### Documentation
- Remove pricing FAQ from build-with-ai page across all locales
### Performance
- Improve cold start time by ~29% through lazy-loading of MCP SDK and event types
## Contributors
@alex-clawd, @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha
</Update>
<Update label="Apr 22, 2026">
## v1.14.3a2

View File

@@ -117,23 +117,35 @@ task = Task(
### With Flows
Pass files to flows, which automatically inherit to crews:
File-typed fields (`File`, `ImageFile`, `PDFFile`) in your flow's state schema serve as the signal to the Platform UI. When deployed, these fields render as file upload dropzones. Files can also be passed via `input_files` in the API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile
from crewai_files import File, ImageFile
from pydantic import BaseModel
class AnalysisFlow(Flow):
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform UI
cover_image: ImageFile # Image-specific dropzone
title: str = ""
class AnalysisFlow(Flow[MyState]):
@start()
def analyze(self):
# Files are automatically populated in state
content = self.state.document.read()
return self.analysis_crew.kickoff()
flow = AnalysisFlow()
result = flow.kickoff(
input_files={"image": ImageFile(source="data.png")}
input_files={"document": File(source="report.pdf")}
)
```
<Note type="info" title="CrewAI Platform Integration">
When deployed on CrewAI Platform, `ImageFile`, `PDFFile`, and other file-typed fields in your flow state automatically get a file upload UI. Users can drag and drop files directly in the Platform interface. Files are stored securely and passed to agents using provider-specific optimizations (inline base64, file upload APIs, or URL references depending on the provider). For API usage examples, see [File Inputs in Flows](/concepts/flows#file-inputs).
</Note>
### With Standalone Agents
Pass files directly to agent kickoff:

View File

@@ -341,6 +341,90 @@ 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
When using structured state, you can include file-typed fields using classes from `crewai-files`. File-typed fields in your flow state serve as the signal to the Platform—they automatically render as file upload dropzones in the Run tab UI and get populated when files are uploaded via the Platform or passed via `input_files` in the API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import File, ImageFile, PDFFile
from pydantic import BaseModel
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform
title: str = ""
class MyFlow(Flow[MyState]):
@start()
def process(self):
# File object is automatically populated in state
# when uploaded via Platform UI or passed via API
content = self.state.document.read()
print(f"Processing {self.state.title}: {len(content)} bytes")
return content
```
When deployed on **CrewAI Platform**, file-typed fields (`File`, `ImageFile`, `PDFFile` from `crewai-files`) automatically render as file upload dropzones in the UI. Users can drag and drop files, which are then populated into your flow's state.
**Kicking off with files via API:**
The `/kickoff` endpoint auto-detects the request format:
- **JSON body** → normal kickoff
- **multipart/form-data** → file upload + kickoff
API users can also pass URL strings directly to file-typed fields—Pydantic coerces them automatically.
### API Usage
#### Option 1: Multipart kickoff (recommended)
Send files directly with the kickoff request:
```bash
# With files (multipart) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"company_name": "Einstein"}' \
-F 'cover_image=@/path/to/photo.jpg'
```
Files are automatically stored and converted to `FileInput` objects. The agent receives the file with provider-specific optimization (inline base64, file upload API, or URL reference depending on the LLM provider).
#### Option 2: JSON kickoff (no files)
```bash
# Without files (JSON) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}}'
```
#### Option 3: Separate upload + kickoff
This is an alternative to multipart upload when you need to upload files separately from the kickoff request. Upload files first, then reference them by URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/photo.jpg' \
-F 'field_name=cover_image'
# Returns: {"url": "https://...", "field_name": "cover_image"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}, "input_files": {"cover_image": "https://..."}}'
```
See the Platform API documentation for full `/files` endpoint details.
#### On CrewAI Platform
When using the Platform UI, file-typed fields automatically render as drag-and-drop upload zones. No API calls needed—just drop the file and click Run.
## 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

@@ -86,6 +86,60 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
Your bearer token is available on the Status tab of your crew's detail page.
## File Uploads
When your crew or flow includes file-typed state fields (using `ImageFile`, `PDFFile`, or `File` from `crewai-files`), these fields automatically render as file upload dropzones in the Run tab UI. Users can drag and drop files directly, and the Platform handles storage and delivery to your agents.
### Multipart Kickoff (Recommended)
Send files directly with the kickoff request using `multipart/form-data`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"title": "Report"}' \
-F 'document=@/path/to/file.pdf'
```
Files are automatically stored and converted to file objects. The agent receives the file with provider-specific optimization (inline base64, file upload API, or URL reference depending on the LLM provider).
### JSON Kickoff with File URLs
If you have files already hosted at URLs, pass them via `input_files`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"inputs": {"title": "Report"},
"input_files": {"document": "https://example.com/file.pdf"}
}'
```
### Separate Upload + Kickoff
Upload files first, then reference them by URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/file.pdf' \
-F 'field_name=document'
# Returns: {"url": "https://...", "field_name": "document"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"title": "Report"}, "input_files": {"document": "https://..."}}'
```
<Note type="info">
File uploads work the same way for both crews and flows. Define file-typed fields in your state schema, and the Platform UI and API will handle uploads automatically.
</Note>
### Checking Crew Health
Before executing operations, you can verify that your crew is running properly:

View File

@@ -4,80 +4,6 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
icon: "clock"
mode: "wide"
---
<Update label="2026년 4월 25일">
## v1.14.3
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3)
## 변경 사항
### 기능
- 체크포인트 작업을 위한 생명주기 이벤트 추가
- e2b 지원 추가
- Azure 통합에서 API 키가 제공되지 않을 경우 DefaultAzureCredential로 대체
- Bedrock V4 지원 추가
- 향상된 기능을 위한 Daytona 샌드박스 도구 추가
- 독립형 에이전트에 체크포인트 및 포크 지원 추가
### 버그 수정
- execution_id를 state.id와 분리되도록 수정
- 체크포인트 재개 시 기록된 메서드 이벤트 재생 문제 해결
- initial_state 클래스 참조의 JSON 스키마 직렬화 수정
- 메타데이터 전용 에이전트 기술 보존
- 암묵적인 @CrewBase 이름을 크루 이벤트로 전파
- 중복 배치 초기화 시 실행 메타데이터 병합
- 체크포인트를 위한 Task 클래스 참조 필드의 직렬화 수정
- 가드레일 재시도 루프에서 BaseModel 결과 처리
- Gemini 스트리밍 도구 호출에서 thought_signature 보존
- 포크 재개 시 task_started 방출 및 체크포인트 TUI 재설계
- 체크포인트 가지치기 테스트에서 미래 날짜 사용하여 시간 의존적 실패 방지
- 드라이 런 주문 수정 및 devtools 릴리스에서 체크아웃된 오래된 브랜치 처리
- 보안 패치를 위해 lxml을 >=6.1.0으로 업그레이드
- 보안 패치를 위해 python-dotenv를 >=1.2.2로 업그레이드
### 문서
- v1.14.3에 대한 변경 로그 및 버전 업데이트
- 'AI로 빌드하기' 페이지 추가 및 모든 언어에 대한 내비게이션 업데이트
- 모든 로케일에서 build-with-ai 페이지의 가격 FAQ 제거
### 성능
- MCP SDK 및 이벤트 유형 최적화하여 콜드 스타트를 약 29% 감소
### 리팩토링
- 중복 제거 및 상태 유형 힌트를 강화하기 위해 체크포인트 헬퍼 리팩토링
## 기여자
@MatthiasHowellYopp, @akaKuruma, @alex-clawd, @github-actions[bot], @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha, @renatonitta
</Update>
<Update label="2026년 4월 23일">
## v1.14.3a3
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3a3)
## 변경 사항
### 기능
- e2b 지원 추가
- API 키가 제공되지 않을 경우 DefaultAzureCredential로 대체 구현
### 버그 수정
- 보안 문제 GHSA-vfmq-68hx-4jfw를 해결하기 위해 lxml을 >=6.1.0으로 업그레이드
### 문서
- 모든 지역에서 build-with-ai 페이지의 가격 FAQ 제거
### 성능
- MCP SDK 및 이벤트 유형의 지연 로딩을 통해 콜드 스타트 시간을 약 29% 개선
## 기여자
@alex-clawd, @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha
</Update>
<Update label="2026년 4월 22일">
## v1.14.3a2

View File

@@ -117,23 +117,35 @@ task = Task(
### Flow와 함께
flow에 파일을 전달하면 자동으로 crew에 상속됩니다:
flow의 상태 스키마에 있는 파일 타입 필드(`File`, `ImageFile`, `PDFFile`)는 플랫폼 UI에 대한 신호 역할을 합니다. 배포 시 이러한 필드는 파일 업로드 드롭존으로 렌더링됩니다. 파일은 API에서 `input_files`를 통해서도 전달할 수 있습니다.
```python
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile
from crewai_files import File, ImageFile
from pydantic import BaseModel
class AnalysisFlow(Flow):
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform UI
cover_image: ImageFile # Image-specific dropzone
title: str = ""
class AnalysisFlow(Flow[MyState]):
@start()
def analyze(self):
# Files are automatically populated in state
content = self.state.document.read()
return self.analysis_crew.kickoff()
flow = AnalysisFlow()
result = flow.kickoff(
input_files={"image": ImageFile(source="data.png")}
input_files={"document": File(source="report.pdf")}
)
```
<Note type="info" title="CrewAI 플랫폼 통합">
CrewAI 플랫폼에 배포하면 flow 상태의 `ImageFile`, `PDFFile` 및 기타 파일 타입 필드가 자동으로 파일 업로드 UI를 갖게 됩니다. 사용자는 플랫폼 인터페이스에서 직접 파일을 드래그 앤 드롭할 수 있습니다. 파일은 안전하게 저장되고 프로바이더별 최적화(인라인 base64, 파일 업로드 API 또는 프로바이더에 따른 URL 참조)를 사용하여 에이전트에 전달됩니다. API 사용 예제는 [Flows의 파일 입력](/ko/concepts/flows#파일-입력)을 참조하세요.
</Note>
### 단독 에이전트와 함께
에이전트 킥오프에 직접 파일을 전달합니다:

View File

@@ -334,6 +334,90 @@ flow.kickoff()
CrewAI Flows는 비구조적 및 구조적 상태 관리 옵션을 모두 제공함으로써, 개발자들이 다양한 애플리케이션 요구 사항에 맞춰 유연하면서도 견고한 AI 워크플로를 구축할 수 있도록 지원합니다.
### 파일 입력
구조화된 상태를 사용할 때, `crewai-files`의 클래스를 사용하여 파일 타입 필드를 포함할 수 있습니다. flow 상태의 파일 타입 필드는 플랫폼에 대한 신호 역할을 합니다 — Run 탭 UI에서 자동으로 파일 업로드 드롭존으로 렌더링되며, 플랫폼을 통해 파일을 업로드하거나 API에서 `input_files`를 통해 전달할 때 자동으로 채워집니다.
```python
from crewai.flow.flow import Flow, start
from crewai_files import File, ImageFile, PDFFile
from pydantic import BaseModel
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform
title: str = ""
class MyFlow(Flow[MyState]):
@start()
def process(self):
# File object is automatically populated in state
# when uploaded via Platform UI or passed via API
content = self.state.document.read()
print(f"Processing {self.state.title}: {len(content)} bytes")
return content
```
**CrewAI 플랫폼**에 배포하면 파일 타입 필드(`crewai-files`의 `File`, `ImageFile`, `PDFFile`)가 UI에서 자동으로 파일 업로드 드롭존으로 렌더링됩니다. 사용자는 파일을 드래그 앤 드롭할 수 있으며, 해당 파일은 flow의 상태에 자동으로 채워집니다.
**API를 통한 파일 포함 시작:**
`/kickoff` 엔드포인트는 요청 형식을 자동으로 감지합니다:
- **JSON body** → 일반 kickoff
- **multipart/form-data** → 파일 업로드 + kickoff
API 사용자는 파일 타입 필드에 URL 문자열을 직접 전달할 수도 있습니다 — Pydantic이 자동으로 변환합니다.
### API 사용법
#### 옵션 1: Multipart kickoff (권장)
kickoff 요청과 함께 파일을 직접 전송합니다:
```bash
# With files (multipart) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"company_name": "Einstein"}' \
-F 'cover_image=@/path/to/photo.jpg'
```
파일은 자동으로 저장되고 `FileInput` 객체로 변환됩니다. 에이전트는 프로바이더별 최적화(LLM 프로바이더에 따라 인라인 base64, 파일 업로드 API 또는 URL 참조)와 함께 파일을 수신합니다.
#### 옵션 2: JSON kickoff (파일 없음)
```bash
# Without files (JSON) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}}'
```
#### 옵션 3: 분리된 업로드 + kickoff
kickoff 요청과 별도로 파일을 업로드해야 할 때 multipart 업로드의 대안입니다. 먼저 파일을 업로드한 다음 URL로 참조합니다:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/photo.jpg' \
-F 'field_name=cover_image'
# Returns: {"url": "https://...", "field_name": "cover_image"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}, "input_files": {"cover_image": "https://..."}}'
```
`/files` 엔드포인트에 대한 자세한 내용은 플랫폼 API 문서를 참조하세요.
#### CrewAI 플랫폼에서
플랫폼 UI를 사용할 때 파일 타입 필드는 자동으로 드래그 앤 드롭 업로드 영역으로 렌더링됩니다. API 호출이 필요 없습니다 — 파일을 드롭하고 실행을 클릭하면 됩니다.
## 플로우 지속성
@persist 데코레이터는 CrewAI 플로우에서 자동 상태 지속성을 활성화하여, 플로우 상태를 재시작이나 다른 워크플로우 실행 간에도 유지할 수 있도록 합니다. 이 데코레이터는 클래스 수준이나 메서드 수준 모두에 적용할 수 있어, 상태 지속성을 관리하는 데 유연성을 제공합니다.

View File

@@ -86,6 +86,60 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
베어러 토큰은 crew의 상세 페이지의 Status 탭에서 확인할 수 있습니다.
## 파일 업로드
crew나 flow에 파일 타입 상태 필드(`crewai-files`의 `ImageFile`, `PDFFile`, 또는 `File` 사용)가 포함되어 있으면, 이러한 필드는 Run 탭 UI에서 자동으로 파일 업로드 드롭존으로 렌더링됩니다. 사용자는 파일을 직접 드래그 앤 드롭할 수 있으며, 플랫폼이 저장 및 에이전트 전달을 처리합니다.
### Multipart Kickoff (권장)
`multipart/form-data`를 사용하여 kickoff 요청과 함께 파일을 직접 전송합니다:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"title": "Report"}' \
-F 'document=@/path/to/file.pdf'
```
파일은 자동으로 저장되고 파일 객체로 변환됩니다. 에이전트는 프로바이더별 최적화(LLM 프로바이더에 따라 인라인 base64, 파일 업로드 API 또는 URL 참조)와 함께 파일을 수신합니다.
### 파일 URL을 포함한 JSON Kickoff
이미 URL에 호스팅된 파일이 있다면 `input_files`를 통해 전달합니다:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"inputs": {"title": "Report"},
"input_files": {"document": "https://example.com/file.pdf"}
}'
```
### 분리된 업로드 + Kickoff
먼저 파일을 업로드한 다음 URL로 참조합니다:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/file.pdf' \
-F 'field_name=document'
# Returns: {"url": "https://...", "field_name": "document"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"title": "Report"}, "input_files": {"document": "https://..."}}'
```
<Note type="info">
파일 업로드는 crew와 flow 모두에서 동일하게 작동합니다. 상태 스키마에 파일 타입 필드를 정의하면 플랫폼 UI와 API가 자동으로 업로드를 처리합니다.
</Note>
### 크루 상태 확인
작업을 실행하기 전에 크루가 정상적으로 실행되고 있는지 확인할 수 있습니다:

View File

@@ -4,80 +4,6 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="25 abr 2026">
## v1.14.3
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3)
## O que Mudou
### Recursos
- Adicionar eventos de ciclo de vida para operações de checkpoint
- Adicionar suporte para e2b
- Reverter para DefaultAzureCredential quando nenhuma chave de API for fornecida na integração com o Azure
- Adicionar suporte ao Bedrock V4
- Adicionar ferramentas de sandbox Daytona para funcionalidade aprimorada
- Adicionar suporte a checkpoint e fork para agentes autônomos
### Correções de Bugs
- Corrigir execution_id para ser separado de state.id
- Resolver a reprodução de eventos de método gravados na retomada do checkpoint
- Corrigir a serialização de referências de classe initial_state como esquema JSON
- Preservar habilidades de agente somente de metadados
- Propagar nomes implícitos @CrewBase para eventos da equipe
- Mesclar metadados de execução na inicialização de lote duplicado
- Corrigir a serialização de campos de referência de classe Task para checkpointing
- Lidar com o resultado BaseModel no loop de retry do guardrail
- Preservar thought_signature em chamadas de ferramentas de streaming Gemini
- Emitir task_started na retomada do fork e redesenhar TUI de checkpoint
- Usar datas futuras em testes de poda de checkpoint para evitar falhas dependentes do tempo
- Corrigir a ordem de dry-run e lidar com branch obsoleta verificada na liberação do devtools
- Atualizar lxml para >=6.1.0 para patch de segurança
- Aumentar python-dotenv para >=1.2.2 para patch de segurança
### Documentação
- Atualizar changelog e versão para v1.14.3
- Adicionar página 'Construir com IA' e atualizar navegação para todos os idiomas
- Remover FAQ de preços da página construir-com-ia em todos os locais
### Desempenho
- Otimizar MCP SDK e tipos de eventos para reduzir o tempo de inicialização a frio em ~29%
### Refatoração
- Refatorar auxiliares de checkpoint para eliminar duplicação e apertar dicas de tipo de estado
## Contribuidores
@MatthiasHowellYopp, @akaKuruma, @alex-clawd, @github-actions[bot], @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha, @renatonitta
</Update>
<Update label="23 abr 2026">
## v1.14.3a3
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.3a3)
## O que Mudou
### Recursos
- Adicionar suporte para e2b
- Implementar fallback para DefaultAzureCredential quando nenhuma chave de API for fornecida
### Correções de Bugs
- Atualizar lxml para >=6.1.0 para resolver problema de segurança GHSA-vfmq-68hx-4jfw
### Documentação
- Remover FAQ de preços da página build-with-ai em todos os locais
### Desempenho
- Melhorar o tempo de inicialização a frio em ~29% através do carregamento preguiçoso do SDK MCP e tipos de eventos
## Contributors
@alex-clawd, @github-advanced-security[bot], @greysonlalonde, @iris-clawd, @lorenzejay, @mattatcha
</Update>
<Update label="22 abr 2026">
## v1.14.3a2

View File

@@ -117,23 +117,35 @@ task = Task(
### Com Flows
Passe arquivos para flows, que automaticamente herdam para crews:
Campos tipados como arquivo (`File`, `ImageFile`, `PDFFile`) no esquema de estado do seu flow servem como sinal para a interface da Plataforma. Quando implantado, esses campos são renderizados como zonas de upload de arquivos. Arquivos também podem ser passados via `input_files` na API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import ImageFile
from crewai_files import File, ImageFile
from pydantic import BaseModel
class AnalysisFlow(Flow):
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform UI
cover_image: ImageFile # Image-specific dropzone
title: str = ""
class AnalysisFlow(Flow[MyState]):
@start()
def analyze(self):
# Files are automatically populated in state
content = self.state.document.read()
return self.analysis_crew.kickoff()
flow = AnalysisFlow()
result = flow.kickoff(
input_files={"image": ImageFile(source="data.png")}
input_files={"document": File(source="report.pdf")}
)
```
<Note type="info" title="Integração com a Plataforma CrewAI">
Quando implantado na Plataforma CrewAI, campos tipados como arquivo como `ImageFile`, `PDFFile` e outros no estado do seu flow recebem automaticamente uma interface de upload de arquivos. Os usuários podem arrastar e soltar arquivos diretamente na interface da Plataforma. Os arquivos são armazenados de forma segura e passados para os agentes usando otimizações específicas do provedor (base64 inline, APIs de upload de arquivo ou referências por URL dependendo do provedor). Para exemplos de uso da API, consulte [Entradas de Arquivos em Flows](/pt-BR/concepts/flows#entradas-de-arquivos).
</Note>
### Com Agentes Standalone
Passe arquivos diretamente no kickoff do agente:

View File

@@ -173,6 +173,90 @@ Cada estado nos flows do CrewAI recebe automaticamente um identificador único (
Ao oferecer as duas opções de gerenciamento de estado, o CrewAI Flows permite que desenvolvedores criem fluxos de IA que sejam ao mesmo tempo flexíveis e robustos, atendendo a uma ampla variedade de requisitos de aplicação.
### Entradas de Arquivos
Ao usar estado estruturado, você pode incluir campos tipados como arquivo usando classes do `crewai-files`. Campos tipados como arquivo no estado do seu flow servem como sinal para a Plataforma — eles são renderizados automaticamente como zonas de upload de arquivos na aba Run da interface e são preenchidos quando arquivos são enviados via Plataforma ou passados via `input_files` na API.
```python
from crewai.flow.flow import Flow, start
from crewai_files import File, ImageFile, PDFFile
from pydantic import BaseModel
class MyState(BaseModel):
document: File # Renders as file dropzone in Platform
title: str = ""
class MyFlow(Flow[MyState]):
@start()
def process(self):
# File object is automatically populated in state
# when uploaded via Platform UI or passed via API
content = self.state.document.read()
print(f"Processing {self.state.title}: {len(content)} bytes")
return content
```
Quando implantado na **Plataforma CrewAI**, campos tipados como arquivo (`File`, `ImageFile`, `PDFFile` do `crewai-files`) são renderizados automaticamente como zonas de upload de arquivos na interface. Os usuários podem arrastar e soltar arquivos, que são então preenchidos no estado do seu flow.
**Iniciando com arquivos via API:**
O endpoint `/kickoff` detecta automaticamente o formato da requisição:
- **Corpo JSON** → kickoff normal
- **multipart/form-data** → upload de arquivo + kickoff
Usuários da API também podem passar strings de URL diretamente para campos tipados como arquivo — o Pydantic as converte automaticamente.
### Uso da API
#### Opção 1: Kickoff multipart (recomendado)
Envie arquivos diretamente com a requisição de kickoff:
```bash
# With files (multipart) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"company_name": "Einstein"}' \
-F 'cover_image=@/path/to/photo.jpg'
```
Os arquivos são armazenados automaticamente e convertidos em objetos `FileInput`. O agente recebe o arquivo com otimização específica do provedor (base64 inline, API de upload de arquivo ou referência por URL dependendo do provedor LLM).
#### Opção 2: Kickoff JSON (sem arquivos)
```bash
# Without files (JSON) — same endpoint
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}}'
```
#### Opção 3: Upload separado + kickoff
Esta é uma alternativa ao upload multipart quando você precisa fazer upload dos arquivos separadamente da requisição de kickoff. Faça o upload dos arquivos primeiro e depois referencie-os por URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/photo.jpg' \
-F 'field_name=cover_image'
# Returns: {"url": "https://...", "field_name": "cover_image"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"company_name": "Einstein"}, "input_files": {"cover_image": "https://..."}}'
```
Consulte a documentação da API da Plataforma para detalhes completos do endpoint `/files`.
#### Na Plataforma CrewAI
Ao usar a interface da Plataforma, campos tipados como arquivo são renderizados automaticamente como zonas de arrastar e soltar para upload. Nenhuma chamada de API é necessária — basta soltar o arquivo e clicar em Executar.
## Persistência de Flow
O decorador @persist permite a persistência automática do estado nos flows do CrewAI, garantindo que você mantenha o estado do flow entre reinicializações ou execuções diferentes do workflow. Esse decorador pode ser aplicado tanto ao nível de classe, quanto ao nível de método, oferecendo flexibilidade sobre como gerenciar a persistência do estado.

View File

@@ -86,6 +86,60 @@ curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com
Seu bearer token está disponível na aba Status na página de detalhes do seu crew.
## Upload de Arquivos
Quando seu crew ou flow inclui campos de estado tipados como arquivo (usando `ImageFile`, `PDFFile` ou `File` do `crewai-files`), esses campos são renderizados automaticamente como zonas de upload de arquivos na aba Run da interface. Os usuários podem arrastar e soltar arquivos diretamente, e a Plataforma gerencia o armazenamento e entrega para seus agentes.
### Kickoff Multipart (Recomendado)
Envie arquivos diretamente com a requisição de kickoff usando `multipart/form-data`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'inputs={"title": "Report"}' \
-F 'document=@/path/to/file.pdf'
```
Os arquivos são armazenados automaticamente e convertidos em objetos de arquivo. O agente recebe o arquivo com otimização específica do provedor (base64 inline, API de upload de arquivo ou referência por URL dependendo do provedor LLM).
### Kickoff JSON com URLs de Arquivos
Se você já tem arquivos hospedados em URLs, passe-os via `input_files`:
```bash
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"inputs": {"title": "Report"},
"input_files": {"document": "https://example.com/file.pdf"}
}'
```
### Upload Separado + Kickoff
Faça upload dos arquivos primeiro e depois referencie-os por URL:
```bash
# Step 1: Upload
curl -X POST https://your-deployment.crewai.com/files \
-H 'Authorization: Bearer YOUR_TOKEN' \
-F 'file=@/path/to/file.pdf' \
-F 'field_name=document'
# Returns: {"url": "https://...", "field_name": "document"}
# Step 2: Kickoff with URL
curl -X POST https://your-deployment.crewai.com/kickoff \
-H 'Authorization: Bearer YOUR_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs": {"title": "Report"}, "input_files": {"document": "https://..."}}'
```
<Note type="info">
O upload de arquivos funciona da mesma forma tanto para crews quanto para flows. Defina campos tipados como arquivo no seu esquema de estado, e a interface da Plataforma e a API tratarão os uploads automaticamente.
</Note>
### Verificando o Status do Crew
Antes de executar operações, você pode verificar se seu crew está funcionando corretamente:

View File

@@ -152,4 +152,4 @@ __all__ = [
"wrap_file_source",
]
__version__ = "1.14.3"
__version__ = "1.14.3a2"

View File

@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
dependencies = [
"pytube~=15.0.0",
"requests>=2.33.0,<3",
"crewai==1.14.3",
"crewai==1.14.3a2",
"tiktoken~=0.8.0",
"beautifulsoup4~=4.13.4",
"python-docx~=1.2.0",
@@ -143,11 +143,6 @@ daytona = [
"daytona~=0.140.0",
]
e2b = [
"e2b~=2.20.0",
"e2b-code-interpreter~=2.6.0",
]
[tool.uv]
exclude-newer = "3 days"

View File

@@ -71,11 +71,6 @@ from crewai_tools.tools.directory_search_tool.directory_search_tool import (
DirectorySearchTool,
)
from crewai_tools.tools.docx_search_tool.docx_search_tool import DOCXSearchTool
from crewai_tools.tools.e2b_sandbox_tool import (
E2BExecTool,
E2BFileTool,
E2BPythonTool,
)
from crewai_tools.tools.exa_tools.exa_search_tool import EXASearchTool
from crewai_tools.tools.file_read_tool.file_read_tool import FileReadTool
from crewai_tools.tools.file_writer_tool.file_writer_tool import FileWriterTool
@@ -247,9 +242,6 @@ __all__ = [
"DaytonaPythonTool",
"DirectoryReadTool",
"DirectorySearchTool",
"E2BExecTool",
"E2BFileTool",
"E2BPythonTool",
"EXASearchTool",
"EnterpriseActionTool",
"FileCompressorTool",
@@ -321,4 +313,4 @@ __all__ = [
"ZapierActionTools",
]
__version__ = "1.14.3"
__version__ = "1.14.3a2"

View File

@@ -60,11 +60,6 @@ from crewai_tools.tools.directory_search_tool.directory_search_tool import (
DirectorySearchTool,
)
from crewai_tools.tools.docx_search_tool.docx_search_tool import DOCXSearchTool
from crewai_tools.tools.e2b_sandbox_tool import (
E2BExecTool,
E2BFileTool,
E2BPythonTool,
)
from crewai_tools.tools.exa_tools.exa_search_tool import EXASearchTool
from crewai_tools.tools.file_read_tool.file_read_tool import FileReadTool
from crewai_tools.tools.file_writer_tool.file_writer_tool import FileWriterTool
@@ -232,9 +227,6 @@ __all__ = [
"DaytonaPythonTool",
"DirectoryReadTool",
"DirectorySearchTool",
"E2BExecTool",
"E2BFileTool",
"E2BPythonTool",
"EXASearchTool",
"FileCompressorTool",
"FileReadTool",

View File

@@ -5,7 +5,6 @@ from crewai_tools.tools.daytona_sandbox_tool.daytona_python_tool import (
DaytonaPythonTool,
)
__all__ = [
"DaytonaBaseTool",
"DaytonaExecTool",

View File

@@ -1,120 +0,0 @@
# E2B Sandbox Tools
Run shell commands, execute Python, and manage files inside an [E2B](https://e2b.dev/) sandbox. E2B provides isolated, ephemeral VMs suitable for agent-driven code execution, with a Jupyter-style code interpreter for rich Python results.
Three tools are provided so you can pick what the agent actually needs:
- **`E2BExecTool`** — run a shell command (`sandbox.commands.run`).
- **`E2BPythonTool`** — run a Python cell in the E2B code interpreter (`sandbox.run_code`), returning stdout/stderr and rich results (charts, dataframes).
- **`E2BFileTool`** — read / write / list / delete files (`sandbox.files.*`).
## Installation
```shell
uv add "crewai-tools[e2b]"
# or
pip install "crewai-tools[e2b]"
```
Set the API key:
```shell
export E2B_API_KEY="..."
```
`E2B_DOMAIN` is also respected if set (for self-hosted or non-default deployments).
## Sandbox lifecycle
All three tools share the same lifecycle controls from `E2BBaseTool`:
| Mode | When the sandbox is created | When it is killed |
| --- | --- | --- |
| **Ephemeral** (default, `persistent=False`) | On every `_run` call | At the end of that same call |
| **Persistent** (`persistent=True`) | Lazily on first use | At process exit (via `atexit`), or manually via `tool.close()` |
| **Attach** (`sandbox_id="…"`) | Never — the tool attaches to an existing sandbox | Never — the tool will not kill a sandbox it did not create |
Ephemeral mode is the safe default: nothing leaks if the agent forgets to clean up. Use persistent mode when you want filesystem state or installed packages to carry across steps — this is typical when pairing `E2BFileTool` with `E2BExecTool`.
E2B sandboxes also auto-expire after an idle timeout. Tune it via `sandbox_timeout` (seconds, default `300`).
## Examples
### One-shot Python execution (ephemeral)
```python
from crewai_tools import E2BPythonTool
tool = E2BPythonTool()
result = tool.run(code="print(sum(range(10)))")
```
### Multi-step shell session (persistent)
```python
from crewai_tools import E2BExecTool, E2BFileTool
exec_tool = E2BExecTool(persistent=True)
file_tool = E2BFileTool(persistent=True)
# Each tool keeps its own persistent sandbox. If you need the *same* sandbox
# across two tools, create one tool, grab the sandbox id via
# `tool._persistent_sandbox.sandbox_id`, and pass it to the other via
# `sandbox_id=...`.
```
### Attach to an existing sandbox
```python
from crewai_tools import E2BExecTool
tool = E2BExecTool(sandbox_id="sbx_...")
```
### Custom create params
```python
tool = E2BExecTool(
persistent=True,
template="my-custom-template",
sandbox_timeout=600,
envs={"MY_FLAG": "1"},
metadata={"owner": "crewai-agent"},
)
```
## Tool arguments
### `E2BExecTool`
- `command: str` — shell command to run.
- `cwd: str | None` — working directory.
- `envs: dict[str, str] | None` — extra env vars for this command.
- `timeout: float | None` — seconds.
### `E2BPythonTool`
- `code: str` — source to execute.
- `language: str | None` — override kernel language (default: Python).
- `envs: dict[str, str] | None` — env vars for the run.
- `timeout: float | None` — seconds.
### `E2BFileTool`
- `action: "read" | "write" | "append" | "list" | "delete" | "mkdir" | "info" | "exists"`
- `path: str` — absolute path inside the sandbox.
- `content: str | None` — required for `append`; optional for `write`.
- `binary: bool` — if `True`, `content` is base64 on write / returned as base64 on read.
- `depth: int` — for `list`, how many levels to recurse (default 1).
## Security considerations
These tools hand the LLM arbitrary shell, Python, and filesystem access inside a remote VM. The threat model to keep in mind:
- **Prompt-injection is a code-execution vector.** If the agent ingests untrusted content (web pages, scraped documents, user-supplied files, emails, search results), a malicious instruction hidden in that content can coerce the agent into issuing commands to `E2BExecTool` / `E2BPythonTool`. Treat any pipeline that feeds untrusted text into an agent that also has these tools as equivalent to remote code execution — the LLM is the attacker's shell.
- **Ephemeral mode (the default) is the main blast-radius control.** A fresh sandbox is created per call and killed at the end, so injected commands cannot persist state, exfiltrate long-lived secrets, or build up tooling across turns. Leave `persistent=False` unless you have a concrete reason to change it.
- **Avoid this specific combination:**
- untrusted content in the agent's context, **plus**
- `persistent=True` or an explicit long-lived `sandbox_id`, **plus**
- a large `sandbox_timeout` or credentials/secrets seeded into the sandbox via `envs`.
That stack lets a single injection pivot into a long-running, credentialed shell that survives across turns. If you must run persistently, also keep `sandbox_timeout` short, scope `envs` to the minimum the task needs, and don't feed the same agent untrusted input.
- **Don't mount production credentials.** Anything you put into `envs`, `metadata`, or files written to the sandbox is reachable from the LLM. Use per-task scoped keys, not your personal API tokens.
- **E2B's VM isolation is the final backstop**, not a license to relax the above — isolation prevents escape to the host, but everything the sandbox can reach (the public internet, any service whose token you dropped in) is still fair game for an injected command.

View File

@@ -1,12 +0,0 @@
from crewai_tools.tools.e2b_sandbox_tool.e2b_base_tool import E2BBaseTool
from crewai_tools.tools.e2b_sandbox_tool.e2b_exec_tool import E2BExecTool
from crewai_tools.tools.e2b_sandbox_tool.e2b_file_tool import E2BFileTool
from crewai_tools.tools.e2b_sandbox_tool.e2b_python_tool import E2BPythonTool
__all__ = [
"E2BBaseTool",
"E2BExecTool",
"E2BFileTool",
"E2BPythonTool",
]

View File

@@ -1,197 +0,0 @@
from __future__ import annotations
import atexit
import logging
import os
import threading
from typing import Any, ClassVar
from crewai.tools import BaseTool, EnvVar
from pydantic import ConfigDict, Field, PrivateAttr, SecretStr
logger = logging.getLogger(__name__)
class E2BBaseTool(BaseTool):
"""Shared base for tools that act on an E2B sandbox.
Lifecycle modes:
- persistent=False (default): create a fresh sandbox per `_run` call and
kill it when the call returns. Safer and stateless — nothing leaks if
the agent forgets cleanup.
- persistent=True: lazily create a single sandbox on first use, cache it
on the instance, and register an atexit hook to kill it at process
exit. Cheaper across many calls and lets files/state carry over.
- sandbox_id=<existing>: attach to a sandbox the caller already owns.
Never killed by the tool.
"""
model_config = ConfigDict(arbitrary_types_allowed=True)
package_dependencies: list[str] = Field(default_factory=lambda: ["e2b"])
api_key: SecretStr | None = Field(
default_factory=lambda: (
SecretStr(val) if (val := os.getenv("E2B_API_KEY")) else None
),
description="E2B API key. Falls back to E2B_API_KEY env var.",
json_schema_extra={"required": False},
repr=False,
)
domain: str | None = Field(
default_factory=lambda: os.getenv("E2B_DOMAIN"),
description="E2B API domain override. Falls back to E2B_DOMAIN env var.",
json_schema_extra={"required": False},
)
template: str | None = Field(
default=None,
description=(
"Optional template/snapshot name or id to create the sandbox from. "
"Defaults to E2B's base template when omitted."
),
)
persistent: bool = Field(
default=False,
description=(
"If True, reuse one sandbox across all calls to this tool instance "
"and kill it at process exit. Default False creates and kills a "
"fresh sandbox per call."
),
)
sandbox_id: str | None = Field(
default=None,
description=(
"Attach to an existing sandbox by id instead of creating a new "
"one. The tool will never kill a sandbox it did not create."
),
)
sandbox_timeout: int = Field(
default=300,
description=(
"Idle timeout in seconds after which E2B auto-kills the sandbox. "
"Applied at create time and when attaching via sandbox_id."
),
)
envs: dict[str, str] | None = Field(
default=None,
description="Environment variables to set inside the sandbox at create time.",
)
metadata: dict[str, str] | None = Field(
default=None,
description="Metadata key-value pairs to attach to the sandbox at create time.",
)
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
EnvVar(
name="E2B_API_KEY",
description="API key for E2B sandbox service",
required=False,
),
EnvVar(
name="E2B_DOMAIN",
description="E2B API domain (optional)",
required=False,
),
]
)
_persistent_sandbox: Any | None = PrivateAttr(default=None)
_lock: threading.Lock = PrivateAttr(default_factory=threading.Lock)
_cleanup_registered: bool = PrivateAttr(default=False)
_sdk_cache: ClassVar[dict[str, Any]] = {}
@classmethod
def _import_sandbox_class(cls) -> Any:
"""Return the Sandbox class used by this tool.
Subclasses override this to swap in a different SDK (e.g. the code
interpreter sandbox). The default uses plain `e2b.Sandbox`.
"""
cached = cls._sdk_cache.get("e2b.Sandbox")
if cached is not None:
return cached
try:
from e2b import Sandbox # type: ignore[import-untyped]
except ImportError as exc:
raise ImportError(
"The 'e2b' package is required for E2B sandbox tools. "
"Install it with: uv add e2b (or) pip install e2b"
) from exc
cls._sdk_cache["e2b.Sandbox"] = Sandbox
return Sandbox
def _connect_kwargs(self) -> dict[str, Any]:
kwargs: dict[str, Any] = {}
if self.api_key is not None:
kwargs["api_key"] = self.api_key.get_secret_value()
if self.domain:
kwargs["domain"] = self.domain
if self.sandbox_timeout is not None:
kwargs["timeout"] = self.sandbox_timeout
return kwargs
def _create_kwargs(self) -> dict[str, Any]:
kwargs: dict[str, Any] = self._connect_kwargs()
if self.template is not None:
kwargs["template"] = self.template
if self.envs is not None:
kwargs["envs"] = self.envs
if self.metadata is not None:
kwargs["metadata"] = self.metadata
return kwargs
def _acquire_sandbox(self) -> tuple[Any, bool]:
"""Return (sandbox, should_kill_after_use)."""
sandbox_cls = self._import_sandbox_class()
if self.sandbox_id:
return (
sandbox_cls.connect(self.sandbox_id, **self._connect_kwargs()),
False,
)
if self.persistent:
with self._lock:
if self._persistent_sandbox is None:
self._persistent_sandbox = sandbox_cls.create(
**self._create_kwargs()
)
if not self._cleanup_registered:
atexit.register(self.close)
self._cleanup_registered = True
return self._persistent_sandbox, False
sandbox = sandbox_cls.create(**self._create_kwargs())
return sandbox, True
def _release_sandbox(self, sandbox: Any, should_kill: bool) -> None:
if not should_kill:
return
try:
sandbox.kill()
except Exception:
logger.debug(
"Best-effort sandbox cleanup failed after ephemeral use; "
"the sandbox may need manual termination.",
exc_info=True,
)
def close(self) -> None:
"""Kill the cached persistent sandbox if one exists."""
with self._lock:
sandbox = self._persistent_sandbox
self._persistent_sandbox = None
if sandbox is None:
return
try:
sandbox.kill()
except Exception:
logger.debug(
"Best-effort persistent sandbox cleanup failed at close(); "
"the sandbox may need manual termination.",
exc_info=True,
)

View File

@@ -1,62 +0,0 @@
from __future__ import annotations
from builtins import type as type_
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.tools.e2b_sandbox_tool.e2b_base_tool import E2BBaseTool
class E2BExecToolSchema(BaseModel):
command: str = Field(..., description="Shell command to execute in the sandbox.")
cwd: str | None = Field(
default=None,
description="Working directory to run the command in. Defaults to the sandbox home dir.",
)
envs: dict[str, str] | None = Field(
default=None,
description="Optional environment variables to set for this command.",
)
timeout: float | None = Field(
default=None,
description="Maximum seconds to wait for the command to finish.",
)
class E2BExecTool(E2BBaseTool):
"""Run a shell command inside an E2B sandbox."""
name: str = "E2B Sandbox Exec"
description: str = (
"Execute a shell command inside an E2B sandbox and return the exit "
"code, stdout, and stderr. Use this to run builds, package installs, "
"git operations, or any one-off shell command."
)
args_schema: type_[BaseModel] = E2BExecToolSchema
def _run(
self,
command: str,
cwd: str | None = None,
envs: dict[str, str] | None = None,
timeout: float | None = None,
) -> Any:
sandbox, should_kill = self._acquire_sandbox()
try:
run_kwargs: dict[str, Any] = {}
if cwd is not None:
run_kwargs["cwd"] = cwd
if envs is not None:
run_kwargs["envs"] = envs
if timeout is not None:
run_kwargs["timeout"] = timeout
result = sandbox.commands.run(command, **run_kwargs)
return {
"exit_code": getattr(result, "exit_code", None),
"stdout": getattr(result, "stdout", None),
"stderr": getattr(result, "stderr", None),
"error": getattr(result, "error", None),
}
finally:
self._release_sandbox(sandbox, should_kill)

View File

@@ -1,220 +0,0 @@
from __future__ import annotations
import base64
from builtins import type as type_
import logging
import posixpath
from typing import Any, Literal
from pydantic import BaseModel, Field, model_validator
from crewai_tools.tools.e2b_sandbox_tool.e2b_base_tool import E2BBaseTool
logger = logging.getLogger(__name__)
FileAction = Literal[
"read", "write", "append", "list", "delete", "mkdir", "info", "exists"
]
class E2BFileToolSchema(BaseModel):
action: FileAction = Field(
...,
description=(
"The filesystem action to perform: 'read' (returns file contents), "
"'write' (create or replace a file with content), 'append' (append "
"content to an existing file — use this for writing large files in "
"chunks to avoid hitting tool-call size limits), 'list' (lists a "
"directory), 'delete' (removes a file/dir), 'mkdir' (creates a "
"directory), 'info' (returns file metadata), 'exists' (returns a "
"boolean for whether the path exists)."
),
)
path: str = Field(..., description="Absolute path inside the sandbox.")
content: str | None = Field(
default=None,
description=(
"Content to write or append. If omitted for 'write', an empty file "
"is created. For files larger than a few KB, prefer one 'write' "
"with empty content followed by multiple 'append' calls of ~4KB "
"each to stay within tool-call payload limits."
),
)
binary: bool = Field(
default=False,
description=(
"For 'write'/'append': treat content as base64 and upload raw "
"bytes. For 'read': return contents as base64 instead of decoded "
"utf-8."
),
)
depth: int = Field(
default=1,
description="For action='list': how many levels deep to recurse (default 1).",
)
@model_validator(mode="after")
def _validate_action_args(self) -> E2BFileToolSchema:
if self.action == "append" and self.content is None:
raise ValueError(
"action='append' requires 'content'. Pass the chunk to append "
"in the 'content' field."
)
return self
class E2BFileTool(E2BBaseTool):
"""Read, write, and manage files inside an E2B sandbox.
Notes:
- Most useful with `persistent=True` or an explicit `sandbox_id`. With
the default ephemeral mode, files disappear when this tool call
finishes.
"""
name: str = "E2B Sandbox Files"
description: str = (
"Perform filesystem operations inside an E2B sandbox: read a file, "
"write content to a path, append content to an existing file, list a "
"directory, delete a path, make a directory, fetch file metadata, or "
"check whether a path exists. For files larger than a few KB, create "
"the file with action='write' and empty content, then send the body "
"via multiple 'append' calls of ~4KB each to stay within tool-call "
"payload limits."
)
args_schema: type_[BaseModel] = E2BFileToolSchema
def _run(
self,
action: FileAction,
path: str,
content: str | None = None,
binary: bool = False,
depth: int = 1,
) -> Any:
sandbox, should_kill = self._acquire_sandbox()
try:
if action == "read":
return self._read(sandbox, path, binary=binary)
if action == "write":
return self._write(sandbox, path, content or "", binary=binary)
if action == "append":
return self._append(sandbox, path, content or "", binary=binary)
if action == "list":
return self._list(sandbox, path, depth=depth)
if action == "delete":
sandbox.files.remove(path)
return {"status": "deleted", "path": path}
if action == "mkdir":
created = sandbox.files.make_dir(path)
return {"status": "created", "path": path, "created": bool(created)}
if action == "info":
return self._info(sandbox, path)
if action == "exists":
return {"path": path, "exists": bool(sandbox.files.exists(path))}
raise ValueError(f"Unknown action: {action}")
finally:
self._release_sandbox(sandbox, should_kill)
def _read(self, sandbox: Any, path: str, *, binary: bool) -> dict[str, Any]:
if binary:
data: bytes = sandbox.files.read(path, format="bytes")
return {
"path": path,
"encoding": "base64",
"content": base64.b64encode(data).decode("ascii"),
}
try:
content: str = sandbox.files.read(path)
return {"path": path, "encoding": "utf-8", "content": content}
except UnicodeDecodeError:
data = sandbox.files.read(path, format="bytes")
return {
"path": path,
"encoding": "base64",
"content": base64.b64encode(data).decode("ascii"),
"note": "File was not valid utf-8; returned as base64.",
}
def _write(
self, sandbox: Any, path: str, content: str, *, binary: bool
) -> dict[str, Any]:
payload: str | bytes = base64.b64decode(content) if binary else content
self._ensure_parent_dir(sandbox, path)
sandbox.files.write(path, payload)
size = (
len(payload)
if isinstance(payload, (bytes, bytearray))
else len(payload.encode("utf-8"))
)
return {"status": "written", "path": path, "bytes": size}
def _append(
self, sandbox: Any, path: str, content: str, *, binary: bool
) -> dict[str, Any]:
chunk: bytes = base64.b64decode(content) if binary else content.encode("utf-8")
self._ensure_parent_dir(sandbox, path)
try:
existing: bytes = sandbox.files.read(path, format="bytes")
except Exception:
existing = b""
payload = existing + chunk
sandbox.files.write(path, payload)
return {
"status": "appended",
"path": path,
"appended_bytes": len(chunk),
"total_bytes": len(payload),
}
@staticmethod
def _ensure_parent_dir(sandbox: Any, path: str) -> None:
parent = posixpath.dirname(path)
if not parent or parent in ("/", "."):
return
try:
sandbox.files.make_dir(parent)
except Exception:
logger.debug(
"Best-effort parent-directory create failed for %s; "
"assuming it already exists and proceeding with the write.",
parent,
exc_info=True,
)
def _list(self, sandbox: Any, path: str, *, depth: int) -> dict[str, Any]:
entries = sandbox.files.list(path, depth=depth)
return {
"path": path,
"entries": [self._entry_to_dict(e) for e in entries],
}
def _info(self, sandbox: Any, path: str) -> dict[str, Any]:
return self._entry_to_dict(sandbox.files.get_info(path))
@staticmethod
def _entry_to_dict(entry: Any) -> dict[str, Any]:
fields = (
"name",
"path",
"type",
"size",
"mode",
"permissions",
"owner",
"group",
"modified_time",
"symlink_target",
)
result: dict[str, Any] = {}
for field in fields:
value = getattr(entry, field, None)
if value is not None and field == "modified_time":
result[field] = (
value.isoformat() if hasattr(value, "isoformat") else str(value)
)
else:
result[field] = value
return result

View File

@@ -1,133 +0,0 @@
from __future__ import annotations
from builtins import type as type_
from typing import Any, ClassVar
from pydantic import BaseModel, Field
from crewai_tools.tools.e2b_sandbox_tool.e2b_base_tool import E2BBaseTool
class E2BPythonToolSchema(BaseModel):
code: str = Field(
...,
description="Python source to execute inside the sandbox.",
)
language: str | None = Field(
default=None,
description=(
"Override the execution language (e.g. 'python', 'r', 'javascript'). "
"Defaults to Python when omitted."
),
)
envs: dict[str, str] | None = Field(
default=None,
description="Optional environment variables for the run.",
)
timeout: float | None = Field(
default=None,
description="Maximum seconds to wait for the code to finish.",
)
class E2BPythonTool(E2BBaseTool):
"""Run Python code inside an E2B code interpreter sandbox.
Uses `e2b_code_interpreter`, which runs cells in a persistent Jupyter-style
kernel so state (imports, variables) carries across calls when
`persistent=True`.
"""
name: str = "E2B Sandbox Python"
description: str = (
"Execute a block of Python code inside an E2B code interpreter sandbox "
"and return captured stdout, stderr, the final expression value, and "
"any rich results (charts, dataframes). Use this for data processing, "
"quick scripts, or analysis that should run in an isolated environment."
)
args_schema: type_[BaseModel] = E2BPythonToolSchema
package_dependencies: list[str] = Field(
default_factory=lambda: ["e2b_code_interpreter"],
)
_ci_cache: ClassVar[dict[str, Any]] = {}
@classmethod
def _import_sandbox_class(cls) -> Any:
cached = cls._ci_cache.get("Sandbox")
if cached is not None:
return cached
try:
from e2b_code_interpreter import Sandbox # type: ignore[import-untyped]
except ImportError as exc:
raise ImportError(
"The 'e2b_code_interpreter' package is required for the E2B "
"Python tool. Install it with: "
"uv add e2b-code-interpreter (or) "
"pip install e2b-code-interpreter"
) from exc
cls._ci_cache["Sandbox"] = Sandbox
return Sandbox
def _run(
self,
code: str,
language: str | None = None,
envs: dict[str, str] | None = None,
timeout: float | None = None,
) -> Any:
sandbox, should_kill = self._acquire_sandbox()
try:
run_kwargs: dict[str, Any] = {}
if language is not None:
run_kwargs["language"] = language
if envs is not None:
run_kwargs["envs"] = envs
if timeout is not None:
run_kwargs["timeout"] = timeout
execution = sandbox.run_code(code, **run_kwargs)
return self._serialize_execution(execution)
finally:
self._release_sandbox(sandbox, should_kill)
@staticmethod
def _serialize_execution(execution: Any) -> dict[str, Any]:
logs = getattr(execution, "logs", None)
error = getattr(execution, "error", None)
results = getattr(execution, "results", None) or []
return {
"text": getattr(execution, "text", None),
"stdout": list(getattr(logs, "stdout", []) or []) if logs else [],
"stderr": list(getattr(logs, "stderr", []) or []) if logs else [],
"error": (
{
"name": getattr(error, "name", None),
"value": getattr(error, "value", None),
"traceback": getattr(error, "traceback", None),
}
if error
else None
),
"results": [E2BPythonTool._serialize_result(r) for r in results],
"execution_count": getattr(execution, "execution_count", None),
}
@staticmethod
def _serialize_result(result: Any) -> dict[str, Any]:
fields = (
"text",
"html",
"markdown",
"svg",
"png",
"jpeg",
"pdf",
"latex",
"json",
"javascript",
"data",
"is_main_result",
"extra",
)
return {field: getattr(result, field, None) for field in fields}

View File

@@ -8734,668 +8734,6 @@
"type": "object"
}
},
{
"description": "Execute a shell command inside an E2B sandbox and return the exit code, stdout, and stderr. Use this to run builds, package installs, git operations, or any one-off shell command.",
"env_vars": [
{
"default": null,
"description": "API key for E2B sandbox service",
"name": "E2B_API_KEY",
"required": false
},
{
"default": null,
"description": "E2B API domain (optional)",
"name": "E2B_DOMAIN",
"required": false
}
],
"humanized_name": "E2B Sandbox Exec",
"init_params_schema": {
"$defs": {
"EnvVar": {
"properties": {
"default": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Default"
},
"description": {
"title": "Description",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"required": {
"default": true,
"title": "Required",
"type": "boolean"
}
},
"required": [
"name",
"description"
],
"title": "EnvVar",
"type": "object"
}
},
"description": "Run a shell command inside an E2B sandbox.",
"properties": {
"api_key": {
"anyOf": [
{
"format": "password",
"type": "string",
"writeOnly": true
},
{
"type": "null"
}
],
"description": "E2B API key. Falls back to E2B_API_KEY env var.",
"required": false,
"title": "Api Key"
},
"domain": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "E2B API domain override. Falls back to E2B_DOMAIN env var.",
"required": false,
"title": "Domain"
},
"envs": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Environment variables to set inside the sandbox at create time.",
"title": "Envs"
},
"metadata": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Metadata key-value pairs to attach to the sandbox at create time.",
"title": "Metadata"
},
"persistent": {
"default": false,
"description": "If True, reuse one sandbox across all calls to this tool instance and kill it at process exit. Default False creates and kills a fresh sandbox per call.",
"title": "Persistent",
"type": "boolean"
},
"sandbox_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Attach to an existing sandbox by id instead of creating a new one. The tool will never kill a sandbox it did not create.",
"title": "Sandbox Id"
},
"sandbox_timeout": {
"default": 300,
"description": "Idle timeout in seconds after which E2B auto-kills the sandbox. Applied at create time and when attaching via sandbox_id.",
"title": "Sandbox Timeout",
"type": "integer"
},
"template": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional template/snapshot name or id to create the sandbox from. Defaults to E2B's base template when omitted.",
"title": "Template"
}
},
"required": [],
"title": "E2BExecTool",
"type": "object"
},
"name": "E2BExecTool",
"package_dependencies": [
"e2b"
],
"run_params_schema": {
"properties": {
"command": {
"description": "Shell command to execute in the sandbox.",
"title": "Command",
"type": "string"
},
"cwd": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Working directory to run the command in. Defaults to the sandbox home dir.",
"title": "Cwd"
},
"envs": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional environment variables to set for this command.",
"title": "Envs"
},
"timeout": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Maximum seconds to wait for the command to finish.",
"title": "Timeout"
}
},
"required": [
"command"
],
"title": "E2BExecToolSchema",
"type": "object"
}
},
{
"description": "Perform filesystem operations inside an E2B sandbox: read a file, write content to a path, append content to an existing file, list a directory, delete a path, make a directory, fetch file metadata, or check whether a path exists. For files larger than a few KB, create the file with action='write' and empty content, then send the body via multiple 'append' calls of ~4KB each to stay within tool-call payload limits.",
"env_vars": [
{
"default": null,
"description": "API key for E2B sandbox service",
"name": "E2B_API_KEY",
"required": false
},
{
"default": null,
"description": "E2B API domain (optional)",
"name": "E2B_DOMAIN",
"required": false
}
],
"humanized_name": "E2B Sandbox Files",
"init_params_schema": {
"$defs": {
"EnvVar": {
"properties": {
"default": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Default"
},
"description": {
"title": "Description",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"required": {
"default": true,
"title": "Required",
"type": "boolean"
}
},
"required": [
"name",
"description"
],
"title": "EnvVar",
"type": "object"
}
},
"description": "Read, write, and manage files inside an E2B sandbox.\n\nNotes:\n - Most useful with `persistent=True` or an explicit `sandbox_id`. With\n the default ephemeral mode, files disappear when this tool call\n finishes.",
"properties": {
"api_key": {
"anyOf": [
{
"format": "password",
"type": "string",
"writeOnly": true
},
{
"type": "null"
}
],
"description": "E2B API key. Falls back to E2B_API_KEY env var.",
"required": false,
"title": "Api Key"
},
"domain": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "E2B API domain override. Falls back to E2B_DOMAIN env var.",
"required": false,
"title": "Domain"
},
"envs": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Environment variables to set inside the sandbox at create time.",
"title": "Envs"
},
"metadata": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Metadata key-value pairs to attach to the sandbox at create time.",
"title": "Metadata"
},
"persistent": {
"default": false,
"description": "If True, reuse one sandbox across all calls to this tool instance and kill it at process exit. Default False creates and kills a fresh sandbox per call.",
"title": "Persistent",
"type": "boolean"
},
"sandbox_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Attach to an existing sandbox by id instead of creating a new one. The tool will never kill a sandbox it did not create.",
"title": "Sandbox Id"
},
"sandbox_timeout": {
"default": 300,
"description": "Idle timeout in seconds after which E2B auto-kills the sandbox. Applied at create time and when attaching via sandbox_id.",
"title": "Sandbox Timeout",
"type": "integer"
},
"template": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional template/snapshot name or id to create the sandbox from. Defaults to E2B's base template when omitted.",
"title": "Template"
}
},
"required": [],
"title": "E2BFileTool",
"type": "object"
},
"name": "E2BFileTool",
"package_dependencies": [
"e2b"
],
"run_params_schema": {
"properties": {
"action": {
"description": "The filesystem action to perform: 'read' (returns file contents), 'write' (create or replace a file with content), 'append' (append content to an existing file \u2014 use this for writing large files in chunks to avoid hitting tool-call size limits), 'list' (lists a directory), 'delete' (removes a file/dir), 'mkdir' (creates a directory), 'info' (returns file metadata), 'exists' (returns a boolean for whether the path exists).",
"enum": [
"read",
"write",
"append",
"list",
"delete",
"mkdir",
"info",
"exists"
],
"title": "Action",
"type": "string"
},
"binary": {
"default": false,
"description": "For 'write'/'append': treat content as base64 and upload raw bytes. For 'read': return contents as base64 instead of decoded utf-8.",
"title": "Binary",
"type": "boolean"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Content to write or append. If omitted for 'write', an empty file is created. For files larger than a few KB, prefer one 'write' with empty content followed by multiple 'append' calls of ~4KB each to stay within tool-call payload limits.",
"title": "Content"
},
"depth": {
"default": 1,
"description": "For action='list': how many levels deep to recurse (default 1).",
"title": "Depth",
"type": "integer"
},
"path": {
"description": "Absolute path inside the sandbox.",
"title": "Path",
"type": "string"
}
},
"required": [
"action",
"path"
],
"title": "E2BFileToolSchema",
"type": "object"
}
},
{
"description": "Execute a block of Python code inside an E2B code interpreter sandbox and return captured stdout, stderr, the final expression value, and any rich results (charts, dataframes). Use this for data processing, quick scripts, or analysis that should run in an isolated environment.",
"env_vars": [
{
"default": null,
"description": "API key for E2B sandbox service",
"name": "E2B_API_KEY",
"required": false
},
{
"default": null,
"description": "E2B API domain (optional)",
"name": "E2B_DOMAIN",
"required": false
}
],
"humanized_name": "E2B Sandbox Python",
"init_params_schema": {
"$defs": {
"EnvVar": {
"properties": {
"default": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Default"
},
"description": {
"title": "Description",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"required": {
"default": true,
"title": "Required",
"type": "boolean"
}
},
"required": [
"name",
"description"
],
"title": "EnvVar",
"type": "object"
}
},
"description": "Run Python code inside an E2B code interpreter sandbox.\n\nUses `e2b_code_interpreter`, which runs cells in a persistent Jupyter-style\nkernel so state (imports, variables) carries across calls when\n`persistent=True`.",
"properties": {
"api_key": {
"anyOf": [
{
"format": "password",
"type": "string",
"writeOnly": true
},
{
"type": "null"
}
],
"description": "E2B API key. Falls back to E2B_API_KEY env var.",
"required": false,
"title": "Api Key"
},
"domain": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "E2B API domain override. Falls back to E2B_DOMAIN env var.",
"required": false,
"title": "Domain"
},
"envs": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Environment variables to set inside the sandbox at create time.",
"title": "Envs"
},
"metadata": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Metadata key-value pairs to attach to the sandbox at create time.",
"title": "Metadata"
},
"persistent": {
"default": false,
"description": "If True, reuse one sandbox across all calls to this tool instance and kill it at process exit. Default False creates and kills a fresh sandbox per call.",
"title": "Persistent",
"type": "boolean"
},
"sandbox_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Attach to an existing sandbox by id instead of creating a new one. The tool will never kill a sandbox it did not create.",
"title": "Sandbox Id"
},
"sandbox_timeout": {
"default": 300,
"description": "Idle timeout in seconds after which E2B auto-kills the sandbox. Applied at create time and when attaching via sandbox_id.",
"title": "Sandbox Timeout",
"type": "integer"
},
"template": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional template/snapshot name or id to create the sandbox from. Defaults to E2B's base template when omitted.",
"title": "Template"
}
},
"required": [],
"title": "E2BPythonTool",
"type": "object"
},
"name": "E2BPythonTool",
"package_dependencies": [
"e2b_code_interpreter"
],
"run_params_schema": {
"properties": {
"code": {
"description": "Python source to execute inside the sandbox.",
"title": "Code",
"type": "string"
},
"envs": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional environment variables for the run.",
"title": "Envs"
},
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Override the execution language (e.g. 'python', 'r', 'javascript'). Defaults to Python when omitted.",
"title": "Language"
},
"timeout": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Maximum seconds to wait for the code to finish.",
"title": "Timeout"
}
},
"required": [
"code"
],
"title": "E2BPythonToolSchema",
"type": "object"
}
},
{
"description": "Search the internet using Exa",
"env_vars": [

View File

@@ -55,7 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
[project.optional-dependencies]
tools = [
"crewai-tools==1.14.3",
"crewai-tools==1.14.3a2",
]
embeddings = [
"tiktoken~=0.8.0"
@@ -84,7 +84,7 @@ voyageai = [
"voyageai~=0.3.5",
]
litellm = [
"litellm~=1.83.7",
"litellm~=1.83.0",
]
bedrock = [
"boto3~=1.42.79",
@@ -94,7 +94,6 @@ google-genai = [
]
azure-ai-inference = [
"azure-ai-inference~=1.0.0b9",
"azure-identity>=1.17.0,<2",
]
anthropic = [
"anthropic~=0.73.0",

View File

@@ -13,7 +13,6 @@ from crewai.crews.crew_output import CrewOutput
from crewai.flow.flow import Flow
from crewai.knowledge.knowledge import Knowledge
from crewai.llm import LLM
from crewai.llm_result import LLMResult, ToolCallRecord
from crewai.llms.base_llm import BaseLLM
from crewai.process import Process
from crewai.state.checkpoint_config import CheckpointConfig # noqa: F401
@@ -49,7 +48,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
_suppress_pydantic_deprecation_warnings()
__version__ = "1.14.3"
__version__ = "1.14.3a2"
_LAZY_IMPORTS: dict[str, tuple[str, str]] = {
"Memory": ("crewai.memory.unified_memory", "Memory"),
@@ -196,13 +195,11 @@ __all__ = [
"Flow",
"Knowledge",
"LLMGuardrail",
"LLMResult",
"Memory",
"PlanningConfig",
"Process",
"RuntimeState",
"Task",
"TaskOutput",
"ToolCallRecord",
"__version__",
]

View File

@@ -394,17 +394,15 @@ class Agent(BaseAgent):
self,
resolved_crew_skills: list[SkillModel] | None = None,
) -> None:
"""Resolve skill paths while preserving explicit disclosure levels.
"""Resolve skill paths and activate skills to INSTRUCTIONS level.
Path entries trigger discovery and activation because directory-based
skills opt into eager loading. Pre-loaded Skill objects keep their
current disclosure level so callers can attach METADATA-only skills and
progressively activate them later. Crew-level skills are merged in with
event emission so observability is consistent regardless of origin.
Path entries trigger discovery and activation. Pre-loaded Skill objects
below INSTRUCTIONS level are activated. Crew-level skills are merged in
with event emission so observability is consistent regardless of origin.
Args:
resolved_crew_skills: Pre-resolved crew skills. When provided,
avoids redundant discovery per agent.
resolved_crew_skills: Pre-resolved crew skills (already discovered
and activated). When provided, avoids redundant discovery per agent.
"""
from crewai.crew import Crew
@@ -445,7 +443,8 @@ class Agent(BaseAgent):
elif isinstance(item, SkillModel):
if item.name not in seen:
seen.add(item.name)
if item.disclosure_level >= INSTRUCTIONS:
activated = activate_skill(item, source=self)
if activated is item and item.disclosure_level >= INSTRUCTIONS:
crewai_event_bus.emit(
self,
event=SkillActivatedEvent(
@@ -455,7 +454,7 @@ class Agent(BaseAgent):
disclosure_level=item.disclosure_level,
),
)
resolved.append(item)
resolved.append(activated)
self.skills = resolved if resolved else None

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]==1.14.3"
"crewai[tools]==1.14.3a2"
]
[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]==1.14.3"
"crewai[tools]==1.14.3a2"
]
[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]==1.14.3"
"crewai[tools]==1.14.3a2"
]
[tool.crewai]

View File

@@ -21,7 +21,6 @@ from crewai.events.depends import Depends
from crewai.events.event_bus import crewai_event_bus
from crewai.events.handler_graph import CircularDependencyError
if TYPE_CHECKING:
from crewai.events.types.agent_events import (
AgentEvaluationCompletedEvent,
@@ -34,20 +33,6 @@ if TYPE_CHECKING:
LiteAgentExecutionErrorEvent,
LiteAgentExecutionStartedEvent,
)
from crewai.events.types.checkpoint_events import (
CheckpointBaseEvent,
CheckpointCompletedEvent,
CheckpointFailedEvent,
CheckpointForkBaseEvent,
CheckpointForkCompletedEvent,
CheckpointForkStartedEvent,
CheckpointPrunedEvent,
CheckpointRestoreBaseEvent,
CheckpointRestoreCompletedEvent,
CheckpointRestoreFailedEvent,
CheckpointRestoreStartedEvent,
CheckpointStartedEvent,
)
from crewai.events.types.crew_events import (
CrewKickoffCompletedEvent,
CrewKickoffFailedEvent,
@@ -156,19 +141,6 @@ _LAZY_EVENT_MAPPING: dict[str, str] = {
"LiteAgentExecutionCompletedEvent": "crewai.events.types.agent_events",
"LiteAgentExecutionErrorEvent": "crewai.events.types.agent_events",
"LiteAgentExecutionStartedEvent": "crewai.events.types.agent_events",
# checkpoint_events
"CheckpointBaseEvent": "crewai.events.types.checkpoint_events",
"CheckpointCompletedEvent": "crewai.events.types.checkpoint_events",
"CheckpointFailedEvent": "crewai.events.types.checkpoint_events",
"CheckpointForkBaseEvent": "crewai.events.types.checkpoint_events",
"CheckpointForkCompletedEvent": "crewai.events.types.checkpoint_events",
"CheckpointForkStartedEvent": "crewai.events.types.checkpoint_events",
"CheckpointPrunedEvent": "crewai.events.types.checkpoint_events",
"CheckpointRestoreBaseEvent": "crewai.events.types.checkpoint_events",
"CheckpointRestoreCompletedEvent": "crewai.events.types.checkpoint_events",
"CheckpointRestoreFailedEvent": "crewai.events.types.checkpoint_events",
"CheckpointRestoreStartedEvent": "crewai.events.types.checkpoint_events",
"CheckpointStartedEvent": "crewai.events.types.checkpoint_events",
# crew_events
"CrewKickoffCompletedEvent": "crewai.events.types.crew_events",
"CrewKickoffFailedEvent": "crewai.events.types.crew_events",
@@ -293,18 +265,6 @@ __all__ = [
"AgentReasoningFailedEvent",
"AgentReasoningStartedEvent",
"BaseEventListener",
"CheckpointBaseEvent",
"CheckpointCompletedEvent",
"CheckpointFailedEvent",
"CheckpointForkBaseEvent",
"CheckpointForkCompletedEvent",
"CheckpointForkStartedEvent",
"CheckpointPrunedEvent",
"CheckpointRestoreBaseEvent",
"CheckpointRestoreCompletedEvent",
"CheckpointRestoreFailedEvent",
"CheckpointRestoreStartedEvent",
"CheckpointStartedEvent",
"CircularDependencyError",
"CrewKickoffCompletedEvent",
"CrewKickoffFailedEvent",

View File

@@ -64,22 +64,6 @@ P = ParamSpec("P")
R = TypeVar("R")
_replaying: contextvars.ContextVar[bool] = contextvars.ContextVar(
"crewai_event_replaying", default=False
)
def is_replaying() -> bool:
"""Return True if the current context is dispatching a replayed event.
Listeners with side effects (checkpoint writes, external API calls that
should not be repeated) should early-return when this is true. Listeners
whose purpose is reconstructing timeline state (trace batch, console
formatter) should ignore the flag and process replayed events normally.
"""
return _replaying.get()
class CrewAIEventsBus:
"""Singleton event bus for handling events in CrewAI.
@@ -277,11 +261,6 @@ class CrewAIEventsBus:
self._runtime_state = state
self._registered_entity_ids = {id(e) for e in state.root}
@property
def runtime_state(self) -> RuntimeState | None:
"""The RuntimeState currently attached to the bus, if any."""
return self._runtime_state
def register_entity(self, entity: Any) -> None:
"""Add an entity to the RuntimeState, creating it if needed.
@@ -589,87 +568,6 @@ class CrewAIEventsBus:
return None
async def _acall_handlers_replaying(
self,
source: Any,
event: BaseEvent,
handlers: AsyncHandlerSet,
) -> None:
"""Call async handlers with the replaying flag set on the loop thread."""
token = _replaying.set(True)
try:
await self._acall_handlers(source, event, handlers)
finally:
_replaying.reset(token)
async def _emit_with_dependencies_replaying(
self, source: Any, event: BaseEvent
) -> None:
"""Dependency-aware dispatch with the replaying flag set."""
token = _replaying.set(True)
try:
await self._emit_with_dependencies(source, event)
finally:
_replaying.reset(token)
def replay(self, source: Any, event: BaseEvent) -> Future[None] | None:
"""Dispatch a previously-recorded event without mutating its fields.
Unlike :meth:`emit`, this does not run ``_prepare_event`` (so stored
event ids and ``emission_sequence`` are preserved) and does not
re-record the event. Listeners can call :func:`is_replaying` to
opt out of side-effectful processing.
Args:
source: The emitting object.
event: The previously-recorded event to dispatch.
Returns:
Future that completes when handlers finish, or None if no handlers.
"""
event_type = type(event)
with self._rwlock.r_locked():
if self._shutting_down:
return None
has_dependencies = event_type in self._handler_dependencies
sync_handlers = self._sync_handlers.get(event_type, frozenset())
async_handlers = self._async_handlers.get(event_type, frozenset())
if not sync_handlers and not async_handlers:
return None
self._ensure_executor_initialized()
self._has_pending_events = True
token = _replaying.set(True)
try:
if has_dependencies:
return self._track_future(
asyncio.run_coroutine_threadsafe(
self._emit_with_dependencies_replaying(source, event),
self._loop,
)
)
if sync_handlers:
ctx = contextvars.copy_context()
sync_future = self._sync_executor.submit(
ctx.run, self._call_handlers, source, event, sync_handlers
)
self._track_future(sync_future)
if not async_handlers:
return sync_future
return self._track_future(
asyncio.run_coroutine_threadsafe(
self._acall_handlers_replaying(source, event, async_handlers),
self._loop,
)
)
finally:
_replaying.reset(token)
def flush(self, timeout: float | None = 30.0) -> bool:
"""Block until all pending event handlers complete.

View File

@@ -30,17 +30,6 @@ from crewai.events.types.agent_events import (
AgentExecutionStartedEvent,
LiteAgentExecutionCompletedEvent,
)
from crewai.events.types.checkpoint_events import (
CheckpointCompletedEvent,
CheckpointFailedEvent,
CheckpointForkCompletedEvent,
CheckpointForkStartedEvent,
CheckpointPrunedEvent,
CheckpointRestoreCompletedEvent,
CheckpointRestoreFailedEvent,
CheckpointRestoreStartedEvent,
CheckpointStartedEvent,
)
from crewai.events.types.crew_events import (
CrewKickoffCompletedEvent,
CrewKickoffFailedEvent,
@@ -194,13 +183,4 @@ EventTypes = (
| MCPToolExecutionCompletedEvent
| MCPToolExecutionFailedEvent
| MCPConfigFetchFailedEvent
| CheckpointStartedEvent
| CheckpointCompletedEvent
| CheckpointFailedEvent
| CheckpointForkStartedEvent
| CheckpointForkCompletedEvent
| CheckpointRestoreStartedEvent
| CheckpointRestoreCompletedEvent
| CheckpointRestoreFailedEvent
| CheckpointPrunedEvent
)

View File

@@ -1,97 +0,0 @@
"""Event family for automatic state checkpointing and forking."""
from typing import Literal
from crewai.events.base_events import BaseEvent
class CheckpointBaseEvent(BaseEvent):
"""Base event for checkpoint lifecycle operations."""
type: str
location: str
provider: str
trigger: str | None = None
branch: str | None = None
parent_id: str | None = None
class CheckpointStartedEvent(CheckpointBaseEvent):
"""Event emitted immediately before a checkpoint is written."""
type: Literal["checkpoint_started"] = "checkpoint_started"
class CheckpointCompletedEvent(CheckpointBaseEvent):
"""Event emitted when a checkpoint has been written successfully."""
type: Literal["checkpoint_completed"] = "checkpoint_completed"
checkpoint_id: str
duration_ms: float
class CheckpointFailedEvent(CheckpointBaseEvent):
"""Event emitted when a checkpoint write fails."""
type: Literal["checkpoint_failed"] = "checkpoint_failed"
error: str
class CheckpointPrunedEvent(CheckpointBaseEvent):
"""Event emitted after pruning old checkpoints from a branch."""
type: Literal["checkpoint_pruned"] = "checkpoint_pruned"
removed_count: int
max_checkpoints: int
class CheckpointForkBaseEvent(BaseEvent):
"""Base event for fork lifecycle operations on a RuntimeState."""
type: str
branch: str
parent_branch: str | None = None
parent_checkpoint_id: str | None = None
class CheckpointForkStartedEvent(CheckpointForkBaseEvent):
"""Event emitted immediately before a fork relabels the branch."""
type: Literal["checkpoint_fork_started"] = "checkpoint_fork_started"
class CheckpointForkCompletedEvent(CheckpointForkBaseEvent):
"""Event emitted after a fork has established the new branch."""
type: Literal["checkpoint_fork_completed"] = "checkpoint_fork_completed"
class CheckpointRestoreBaseEvent(BaseEvent):
"""Base event for checkpoint restore lifecycle operations."""
type: str
location: str
provider: str | None = None
class CheckpointRestoreStartedEvent(CheckpointRestoreBaseEvent):
"""Event emitted immediately before a checkpoint restore begins."""
type: Literal["checkpoint_restore_started"] = "checkpoint_restore_started"
class CheckpointRestoreCompletedEvent(CheckpointRestoreBaseEvent):
"""Event emitted when a checkpoint has been restored successfully."""
type: Literal["checkpoint_restore_completed"] = "checkpoint_restore_completed"
checkpoint_id: str
branch: str | None = None
parent_id: str | None = None
duration_ms: float
class CheckpointRestoreFailedEvent(CheckpointRestoreBaseEvent):
"""Event emitted when a checkpoint restore fails."""
type: Literal["checkpoint_restore_failed"] = "checkpoint_restore_failed"
error: str

View File

@@ -45,7 +45,6 @@ from pydantic import (
BeforeValidator,
ConfigDict,
Field,
PlainSerializer,
PrivateAttr,
SerializeAsAny,
ValidationError,
@@ -59,7 +58,6 @@ from crewai.events.event_bus import crewai_event_bus
from crewai.events.event_context import (
get_current_parent_id,
reset_last_event_id,
restore_event_scope,
triggered_by_scope,
)
from crewai.events.listeners.tracing.trace_listener import (
@@ -159,37 +157,6 @@ def _resolve_persistence(value: Any) -> Any:
return value
_INITIAL_STATE_CLASS_MARKER = "__crewai_pydantic_class_schema__"
def _serialize_initial_state(value: Any) -> Any:
"""Make ``initial_state`` safe for JSON checkpoint serialization.
``BaseModel`` class refs are emitted as their JSON schema under a sentinel
marker key so deserialization can round-trip them back to a class.
``BaseModel`` instances are dumped to JSON (round-trip as plain dicts,
which ``_create_initial_state`` accepts). Bare ``type`` values that are
not ``BaseModel`` subclasses (e.g. ``dict``) are dropped since they
can't be represented in JSON.
"""
if isinstance(value, type):
if issubclass(value, BaseModel):
return {_INITIAL_STATE_CLASS_MARKER: value.model_json_schema()}
return None
if isinstance(value, BaseModel):
return value.model_dump(mode="json")
return value
def _deserialize_initial_state(value: Any) -> Any:
"""Rehydrate a class ref serialized by :func:`_serialize_initial_state`."""
if isinstance(value, dict) and _INITIAL_STATE_CLASS_MARKER in value:
from crewai.utilities.pydantic_schema_utils import create_model_from_schema
return create_model_from_schema(value[_INITIAL_STATE_CLASS_MARKER])
return value
class FlowState(BaseModel):
"""Base model for all flow states, ensuring each state has a unique ID."""
@@ -941,11 +908,7 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
entity_type: Literal["flow"] = "flow"
initial_state: Annotated[ # type: ignore[type-arg]
type[BaseModel] | type[dict] | dict[str, Any] | BaseModel | None,
BeforeValidator(_deserialize_initial_state),
PlainSerializer(_serialize_initial_state, return_type=Any, when_used="json"),
] = Field(default=None)
initial_state: Any = Field(default=None)
name: str | None = Field(default=None)
tracing: bool | None = Field(default=None)
stream: bool = Field(default=False)
@@ -1017,18 +980,13 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
A Flow instance on the new branch. Call kickoff() to run.
"""
flow = cls.from_checkpoint(config)
state = crewai_event_bus.runtime_state
state = crewai_event_bus._runtime_state
if state is None:
raise RuntimeError(
"Cannot fork: no runtime state on the event bus. "
"Ensure from_checkpoint() succeeded before calling fork()."
)
state.fork(branch)
new_id = str(uuid4())
if isinstance(flow._state, dict):
flow._state["id"] = new_id
else:
object.__setattr__(flow._state, "id", new_id)
return flow
checkpoint_completed_methods: set[str] | None = Field(default=None)
@@ -1050,8 +1008,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
}
if self.checkpoint_state is not None:
self._restore_state(self.checkpoint_state)
restore_event_scope(())
reset_last_event_id()
_methods: dict[FlowMethodName, FlowMethod[Any, Any]] = PrivateAttr(
default_factory=dict
@@ -1074,7 +1030,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
_human_feedback_method_outputs: dict[str, Any] = PrivateAttr(default_factory=dict)
_input_history: list[InputHistoryEntry] = PrivateAttr(default_factory=list)
_state: Any = PrivateAttr(default=None)
_execution_id: str = PrivateAttr(default_factory=lambda: str(uuid4()))
def __class_getitem__(cls: type[Flow[T]], item: type[T]) -> type[Flow[T]]: # type: ignore[override]
class _FlowGeneric(cls): # type: ignore[valid-type,misc]
@@ -1865,27 +1820,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
except (AttributeError, TypeError):
return "" # Safely handle any unexpected attribute access issues
@property
def execution_id(self) -> str:
"""Stable identifier for this flow execution.
Separate from ``flow_id`` / ``state.id``, which consumers may
override via ``kickoff(inputs={"id": ...})`` to resume a persisted
flow. ``execution_id`` is never affected by ``inputs`` and stays
stable for the lifetime of a single run, so it is the correct key
for telemetry, tracing, and any external correlation that must
uniquely identify a single execution even when callers pass an
``id`` in ``inputs``.
Defaults to a fresh ``uuid4`` per ``Flow`` instance; assign to
override when an outer system already has an execution identity.
"""
return self._execution_id
@execution_id.setter
def execution_id(self, value: str) -> None:
self._execution_id = value
def _initialize_state(self, inputs: dict[str, Any]) -> None:
"""Initialize or update flow state with new inputs.
@@ -2199,9 +2133,9 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
flow_id_token = None
request_id_token = None
if current_flow_id.get() is None:
flow_id_token = current_flow_id.set(self.execution_id)
flow_id_token = current_flow_id.set(self.flow_id)
if current_flow_request_id.get() is None:
request_id_token = current_flow_request_id.set(self.execution_id)
request_id_token = current_flow_request_id.set(self.flow_id)
try:
# Reset flow state for fresh execution unless restoring from persistence
@@ -2280,9 +2214,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
if inputs is not None and "id" not in inputs:
self._initialize_state(inputs)
if self._is_execution_resuming:
await self._replay_recorded_events()
try:
# Determine which start methods to execute at kickoff
# Conditional start methods (with __trigger_methods__) are only triggered by their conditions
@@ -2430,44 +2361,6 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
"""
return await self.kickoff_async(inputs, input_files, from_checkpoint)
async def _replay_recorded_events(self) -> None:
"""Dispatch recorded ``MethodExecution*`` events from the event record."""
state = crewai_event_bus.runtime_state
if state is None:
return
record = state.event_record
if len(record) == 0:
return
replayable = (
MethodExecutionStartedEvent,
MethodExecutionFinishedEvent,
MethodExecutionFailedEvent,
)
flow_name = self.name or self.__class__.__name__
nodes = sorted(
(
n
for n in record.all_nodes()
if isinstance(n.event, replayable)
and n.event.flow_name == flow_name
and n.event.method_name in self._completed_methods
),
key=lambda n: n.event.emission_sequence or 0,
)
for node in nodes:
future = crewai_event_bus.replay(self, node.event)
if future is not None:
try:
await asyncio.wrap_future(future)
except Exception:
logger.warning(
"Replayed event handler failed: %s",
node.event.type,
exc_info=True,
)
async def _execute_start_method(self, start_method_name: FlowMethodName) -> None:
"""Executes a flow's start method and its triggered listeners.

View File

@@ -32,11 +32,6 @@ from crewai.events.types.tool_usage_events import (
ToolUsageFinishedEvent,
ToolUsageStartedEvent,
)
from crewai.llm_result import (
LLMResult,
ToolCallRecord,
estimate_cost_usd as _estimate_cost_usd,
)
from crewai.llms.base_llm import (
BaseLLM,
JsonResponseFormat,
@@ -1704,7 +1699,6 @@ class LLM(BaseLLM):
from_task: Task | None = None,
from_agent: BaseAgent | None = None,
response_model: type[BaseModel] | None = None,
max_iterations: int = 10,
) -> str | Any:
"""High-level LLM call method.
@@ -1722,250 +1716,16 @@ class LLM(BaseLLM):
from_task: Optional Task that invoked the LLM
from_agent: Optional Agent that invoked the LLM
response_model: Optional Model that contains a pydantic response model.
max_iterations: Maximum number of tool-loop iterations (default 10).
Only used when both ``tools`` and ``available_functions``
are provided.
Returns:
Union[str, LLMResult, Any]:
- ``str`` when called without tools (backwards compatible).
- ``LLMResult`` when called with tools and available_functions.
- ``Any`` when a tool call returns a non-string result in legacy mode.
Union[str, Any]: Either a text response from the LLM (str) or
the result of a tool function call (Any).
Raises:
TypeError: If messages format is invalid
ValueError: If response format is not supported
LLMContextLengthExceededError: If input exceeds model's context limit
"""
# When tools AND available_functions are both provided, use the tool loop
# which returns an LLMResult with structured metadata.
if tools and available_functions:
return self._call_with_tool_loop(
messages=messages,
tools=tools,
callbacks=callbacks,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
response_model=response_model,
max_iterations=max_iterations,
)
# Original single-shot path — returns str (backwards compatible).
return self._call_single(
messages=messages,
tools=tools,
callbacks=callbacks,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
response_model=response_model,
)
def _call_with_tool_loop(
self,
messages: str | list[LLMMessage],
tools: list[dict[str, BaseTool]],
callbacks: list[Any] | None,
available_functions: dict[str, Any],
from_task: Task | None,
from_agent: BaseAgent | None,
response_model: type[BaseModel] | None,
max_iterations: int,
) -> LLMResult:
"""Run an LLM tool loop, returning a structured LLMResult.
Keeps calling the model until it stops requesting tool calls or
``max_iterations`` is reached.
"""
from crewai.types.usage_metrics import UsageMetrics
if isinstance(messages, str):
messages = [{"role": "user", "content": messages}]
# Work on a mutable copy so we can append assistant/tool messages.
conversation: list[dict[str, Any]] = list(messages) # type: ignore[arg-type]
result = LLMResult(
text="",
tool_calls=[],
usage=UsageMetrics(),
cost_usd=0.0,
iterations=0,
)
for iteration in range(max_iterations):
# Call the model WITHOUT available_functions so the internal
# handler returns tool_calls as-is instead of executing them.
raw = self._call_single(
messages=conversation, # type: ignore[arg-type]
tools=tools,
callbacks=callbacks,
available_functions=None, # Don't let inner layer execute
from_task=from_task,
from_agent=from_agent,
response_model=response_model,
)
result.iterations = iteration + 1
# Accumulate usage from this iteration
self._accumulate_usage(result)
# If we got a string back, the model is done (no tool calls).
if isinstance(raw, str):
result.text = raw
break
# If we got tool_calls (list), execute them and feed results back.
if isinstance(raw, list):
# Append assistant message with tool calls to conversation
assistant_msg: dict[str, Any] = {
"role": "assistant",
"content": None,
"tool_calls": [
{
"id": getattr(tc, "id", f"call_{i}"),
"type": "function",
"function": {
"name": getattr(tc.function, "name", "")
if hasattr(tc, "function")
else "",
"arguments": getattr(tc.function, "arguments", "{}")
if hasattr(tc, "function")
else "{}",
},
}
for i, tc in enumerate(raw)
],
}
conversation.append(assistant_msg)
# Execute each tool call
for tc in raw:
func_name = sanitize_tool_name(
getattr(tc.function, "name", "")
if hasattr(tc, "function")
else ""
)
func_args_str = (
getattr(tc.function, "arguments", "{}")
if hasattr(tc, "function")
else "{}"
)
tool_call_id = getattr(tc, "id", f"call_{func_name}")
try:
func_args = json.loads(func_args_str)
except (json.JSONDecodeError, TypeError):
func_args = {}
record = ToolCallRecord(
name=func_name,
input=func_args,
)
if func_name in available_functions:
t0 = datetime.now()
started_at = t0
crewai_event_bus.emit(
self,
event=ToolUsageStartedEvent(
tool_name=func_name,
tool_args=func_args,
from_agent=from_agent,
from_task=from_task,
),
)
try:
fn = available_functions[func_name]
tool_output = fn(**func_args)
t1 = datetime.now()
record.output = (
str(tool_output) if tool_output is not None else ""
)
record.duration_ms = (t1 - t0).total_seconds() * 1000
crewai_event_bus.emit(
self,
event=ToolUsageFinishedEvent(
output=tool_output,
tool_name=func_name,
tool_args=func_args,
started_at=started_at,
finished_at=t1,
from_task=from_task,
from_agent=from_agent,
),
)
except Exception as e:
t1 = datetime.now()
record.output = f"Error: {e}"
record.duration_ms = (t1 - t0).total_seconds() * 1000
record.is_error = True
crewai_event_bus.emit(
self,
event=ToolUsageErrorEvent(
tool_name=func_name,
tool_args=func_args,
error=str(e),
from_task=from_task,
from_agent=from_agent,
),
)
else:
record.output = f"Error: unknown function '{func_name}'"
record.is_error = True
result.tool_calls.append(record)
# Append tool result message for the model
conversation.append(
{
"role": "tool",
"tool_call_id": tool_call_id,
"content": record.output,
}
)
else:
# Unexpected return type — treat as final text
result.text = str(raw)
break
else:
# max_iterations exhausted — use last text or empty
if not result.text and result.tool_calls:
result.text = (
f"Max iterations ({max_iterations}) reached. "
f"Last tool: {result.tool_calls[-1].name}"
)
# Estimate cost
result.cost_usd = _estimate_cost_usd(
self.model,
result.usage.prompt_tokens,
result.usage.completion_tokens,
)
return result
def _accumulate_usage(self, result: LLMResult) -> None:
"""Pull token counts from the internal tracker into the LLMResult."""
tracker = getattr(self, "_token_usage", None)
if tracker and isinstance(tracker, dict):
result.usage.prompt_tokens = tracker.get("prompt_tokens", 0)
result.usage.completion_tokens = tracker.get("completion_tokens", 0)
result.usage.total_tokens = tracker.get("total_tokens", 0)
result.usage.successful_requests += 1
def _call_single(
self,
messages: str | list[LLMMessage],
tools: list[dict[str, BaseTool]] | None = None,
callbacks: list[Any] | None = None,
available_functions: dict[str, Any] | None = None,
from_task: Task | None = None,
from_agent: BaseAgent | None = None,
response_model: type[BaseModel] | None = None,
) -> str | Any:
"""Single-shot LLM call (original call() logic)."""
with llm_call_context() as call_id:
crewai_event_bus.emit(
self,
@@ -2059,7 +1819,7 @@ class LLM(BaseLLM):
logging.info("Retrying LLM call without the unsupported 'stop'")
return self._call_single(
return self.call(
messages,
tools=tools,
callbacks=callbacks,

View File

@@ -1,112 +0,0 @@
"""Structured result types for LLM.call() with tool loop support.
When LLM.call() is invoked with tools and available_functions, it returns
an LLMResult instead of a plain string. This preserves backwards compatibility:
calls without tools still return str.
"""
from __future__ import annotations
from typing import Any
from pydantic import BaseModel, Field
from crewai.types.usage_metrics import UsageMetrics
class ToolCallRecord(BaseModel):
"""Record of a single tool call executed during an LLM tool loop.
Attributes:
name: The tool function name.
input: The arguments passed to the tool.
output: The string result returned by the tool.
duration_ms: Wall-clock time for the tool execution in milliseconds.
is_error: Whether the tool call raised an exception.
"""
name: str
input: dict[str, Any] = Field(default_factory=dict)
output: str = ""
duration_ms: float = 0.0
is_error: bool = False
class LLMResult(BaseModel):
"""Structured result from LLM.call() when tools are used.
Attributes:
text: The final text response from the model.
tool_calls: Ordered list of every tool call made during the loop.
usage: Aggregated token usage across all iterations.
cost_usd: Estimated cost in USD based on model pricing.
iterations: Number of LLM round-trips in the tool loop.
"""
text: str = ""
tool_calls: list[ToolCallRecord] = Field(default_factory=list)
usage: UsageMetrics = Field(default_factory=UsageMetrics)
cost_usd: float = 0.0
iterations: int = 0
# ---------------------------------------------------------------------------
# Simple cost estimation
# ---------------------------------------------------------------------------
# USD per 1M tokens. Covers major models. Inspired by Iris's pricing table.
PRICING: dict[str, dict[str, float]] = {
# Anthropic
"claude-opus-4-7": {"in": 5.00, "out": 25.00},
"claude-sonnet-4-6": {"in": 3.00, "out": 15.00},
"claude-sonnet-4-5": {"in": 3.00, "out": 15.00},
"claude-haiku-4-5": {"in": 1.00, "out": 5.00},
# OpenAI
"gpt-4o": {"in": 2.50, "out": 10.00},
"gpt-4o-mini": {"in": 0.15, "out": 0.60},
"gpt-4.1": {"in": 2.00, "out": 8.00},
"gpt-4.1-mini": {"in": 0.40, "out": 1.60},
"gpt-4.1-nano": {"in": 0.10, "out": 0.40},
"o1": {"in": 15.00, "out": 60.00},
"o1-mini": {"in": 3.00, "out": 12.00},
"o3": {"in": 2.00, "out": 8.00},
"o3-mini": {"in": 1.10, "out": 4.40},
"gpt-5": {"in": 1.25, "out": 10.00},
# Google Gemini
"gemini-2.5-pro": {"in": 1.25, "out": 10.00},
"gemini-2.5-flash": {"in": 0.30, "out": 2.50},
"gemini-2.0-flash": {"in": 0.10, "out": 0.40},
}
def _lookup_pricing(model: str) -> dict[str, float] | None:
"""Resolve a model name to its pricing row.
Handles provider prefixes (``anthropic/claude-sonnet-4-6``) and partial
matches (``claude-sonnet-4-6-20250514`` → ``claude-sonnet-4-6``).
"""
if not model:
return None
# Exact match
if model in PRICING:
return PRICING[model]
# Strip provider prefix
if "/" in model:
suffix = model.rsplit("/", 1)[1]
if suffix in PRICING:
return PRICING[suffix]
model = suffix
# Prefix / partial match
for key in PRICING:
if model.startswith(key) or key.startswith(model):
return PRICING[key]
return None
def estimate_cost_usd(model: str, prompt_tokens: int, completion_tokens: int) -> float:
"""Estimate the cost in USD for a given model and token counts."""
pricing = _lookup_pricing(model)
if not pricing:
return 0.0
return (
prompt_tokens * pricing["in"] + completion_tokens * pricing["out"]
) / 1_000_000

View File

@@ -183,6 +183,11 @@ class AzureCompletion(BaseLLM):
AzureCompletion._is_azure_openai_endpoint(self.endpoint)
)
if not self.api_key:
raise ValueError(
"Azure API key is required. Set AZURE_API_KEY environment "
"variable or pass api_key parameter."
)
if not self.endpoint:
raise ValueError(
"Azure endpoint is required. Set AZURE_ENDPOINT environment "
@@ -190,39 +195,12 @@ class AzureCompletion(BaseLLM):
)
client_kwargs: dict[str, Any] = {
"endpoint": self.endpoint,
"credential": self._resolve_credential(),
"credential": AzureKeyCredential(self.api_key),
}
if self.api_version:
client_kwargs["api_version"] = self.api_version
return client_kwargs
def _resolve_credential(self) -> Any:
"""Return an Azure credential, preferring the API key when set.
Without an API key, fall back to ``DefaultAzureCredential`` from
``azure-identity``. That chain auto-detects the standard keyless
paths the customer's environment may provide — OIDC Workload
Identity Federation (``AZURE_FEDERATED_TOKEN_FILE`` +
``AZURE_TENANT_ID`` + ``AZURE_CLIENT_ID``), Managed Identity on
AKS/Azure VMs, environment-configured service principals, and
developer tools like the Azure CLI. Installing ``azure-identity``
is what enables these paths; without it we raise the existing
API-key error.
"""
if self.api_key:
return AzureKeyCredential(self.api_key)
try:
from azure.identity import DefaultAzureCredential
except ImportError:
raise ValueError(
"Azure API key is required when azure-identity is not "
"installed. Set AZURE_API_KEY, or install azure-identity "
'for keyless auth: uv add "crewai[azure-ai-inference]"'
) from None
return DefaultAzureCredential()
def _get_sync_client(self) -> Any:
if self._client is None:
self._client = self._build_sync_client()

View File

@@ -27,7 +27,6 @@ from crewai.mcp.filters import (
create_static_tool_filter,
)
if TYPE_CHECKING:
from crewai.mcp.client import MCPClient
from crewai.mcp.tool_resolver import MCPToolResolver

View File

@@ -10,22 +10,12 @@ from __future__ import annotations
import json
import logging
import threading
import time
from typing import Any
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.crew import Crew
from crewai.events.base_events import BaseEvent
from crewai.events.event_bus import CrewAIEventsBus, crewai_event_bus, is_replaying
from crewai.events.types.checkpoint_events import (
CheckpointBaseEvent,
CheckpointCompletedEvent,
CheckpointFailedEvent,
CheckpointForkBaseEvent,
CheckpointPrunedEvent,
CheckpointRestoreBaseEvent,
CheckpointStartedEvent,
)
from crewai.events.event_bus import CrewAIEventsBus, crewai_event_bus
from crewai.flow.flow import Flow
from crewai.state.checkpoint_config import CheckpointConfig
from crewai.state.runtime import RuntimeState, _prepare_entities
@@ -63,26 +53,12 @@ def _resolve(value: CheckpointConfig | bool | None) -> CheckpointConfig | None |
if isinstance(value, CheckpointConfig):
_ensure_handlers_registered()
return value
if value:
if value is True:
_ensure_handlers_registered()
return CheckpointConfig()
if value is False:
return _SENTINEL
return None
def _resolve_from_agent(agent: BaseAgent) -> CheckpointConfig | None:
"""Resolve a checkpoint config starting from an agent, walking to its crew."""
result = _resolve(agent.checkpoint)
if isinstance(result, CheckpointConfig):
return result
if result is _SENTINEL:
return None
crew = agent.crew
if isinstance(crew, Crew):
crew_result = _resolve(crew.checkpoint)
return crew_result if isinstance(crew_result, CheckpointConfig) else None
return None
return None # None = inherit
def _find_checkpoint(source: Any) -> CheckpointConfig | None:
@@ -101,11 +77,28 @@ def _find_checkpoint(source: Any) -> CheckpointConfig | None:
result = _resolve(source.checkpoint)
return result if isinstance(result, CheckpointConfig) else None
if isinstance(source, BaseAgent):
return _resolve_from_agent(source)
result = _resolve(source.checkpoint)
if isinstance(result, CheckpointConfig):
return result
if result is _SENTINEL:
return None
crew = source.crew
if isinstance(crew, Crew):
result = _resolve(crew.checkpoint)
return result if isinstance(result, CheckpointConfig) else None
return None
if isinstance(source, Task):
agent = source.agent
if isinstance(agent, BaseAgent):
return _resolve_from_agent(agent)
result = _resolve(agent.checkpoint)
if isinstance(result, CheckpointConfig):
return result
if result is _SENTINEL:
return None
crew = agent.crew
if isinstance(crew, Crew):
result = _resolve(crew.checkpoint)
return result if isinstance(result, CheckpointConfig) else None
return None
return None
@@ -114,106 +107,27 @@ def _do_checkpoint(
state: RuntimeState, cfg: CheckpointConfig, event: BaseEvent | None = None
) -> None:
"""Write a checkpoint and prune old ones if configured."""
provider_name: str = type(cfg.provider).__name__
trigger: str | None = event.type if event is not None else None
context: dict[str, Any] = {
"task_id": event.task_id if event is not None else None,
"task_name": event.task_name if event is not None else None,
"agent_id": event.agent_id if event is not None else None,
"agent_role": event.agent_role if event is not None else None,
}
parent_id_snapshot: str | None = state._parent_id
branch_snapshot: str = state._branch
crewai_event_bus.emit(
cfg,
CheckpointStartedEvent(
location=cfg.location,
provider=provider_name,
trigger=trigger,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
**context,
),
_prepare_entities(state.root)
payload = state.model_dump(mode="json")
if event is not None:
payload["trigger"] = event.type
data = json.dumps(payload)
location = cfg.provider.checkpoint(
data,
cfg.location,
parent_id=state._parent_id,
branch=state._branch,
)
state._chain_lineage(cfg.provider, location)
start: float = time.perf_counter()
try:
_prepare_entities(state.root)
payload = state.model_dump(mode="json")
if event is not None:
payload["trigger"] = event.type
data = json.dumps(payload)
location = cfg.provider.checkpoint(
data,
cfg.location,
parent_id=parent_id_snapshot,
branch=branch_snapshot,
)
state._chain_lineage(cfg.provider, location)
checkpoint_id: str = cfg.provider.extract_id(location)
except Exception as exc:
crewai_event_bus.emit(
cfg,
CheckpointFailedEvent(
location=cfg.location,
provider=provider_name,
trigger=trigger,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
error=str(exc),
**context,
),
)
raise
duration_ms: float = (time.perf_counter() - start) * 1000.0
checkpoint_id: str = cfg.provider.extract_id(location)
msg: str = (
f"Checkpoint saved. Resume with: crewai checkpoint resume {checkpoint_id}"
)
logger.info(msg)
crewai_event_bus.emit(
cfg,
CheckpointCompletedEvent(
location=location,
provider=provider_name,
trigger=trigger,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
checkpoint_id=checkpoint_id,
duration_ms=duration_ms,
**context,
),
)
if cfg.max_checkpoints is not None:
try:
removed_count: int = cfg.provider.prune(
cfg.location, cfg.max_checkpoints, branch=branch_snapshot
)
except Exception:
logger.warning(
"Checkpoint prune failed for %s (branch=%s)",
cfg.location,
branch_snapshot,
exc_info=True,
)
return
crewai_event_bus.emit(
cfg,
CheckpointPrunedEvent(
location=cfg.location,
provider=provider_name,
trigger=trigger,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
removed_count=removed_count,
max_checkpoints=cfg.max_checkpoints,
**context,
),
)
cfg.provider.prune(cfg.location, cfg.max_checkpoints, branch=state._branch)
def _should_checkpoint(source: Any, event: BaseEvent) -> CheckpointConfig | None:
@@ -228,13 +142,6 @@ def _should_checkpoint(source: Any, event: BaseEvent) -> CheckpointConfig | None
def _on_any_event(source: Any, event: BaseEvent, state: Any) -> None:
"""Sync handler registered on every event class."""
if is_replaying():
return
if isinstance(
event,
(CheckpointBaseEvent, CheckpointForkBaseEvent, CheckpointRestoreBaseEvent),
):
return
cfg = _should_checkpoint(source, event)
if cfg is None:
return
@@ -254,8 +161,7 @@ def _register_all_handlers(event_bus: CrewAIEventsBus) -> None:
seen: set[type] = set()
def _collect(cls: type[BaseEvent]) -> None:
subclasses: list[type[BaseEvent]] = cls.__subclasses__()
for sub in subclasses:
for sub in cls.__subclasses__():
if sub not in seen:
seen.add(sub)
type_field = sub.model_fields.get("type")

View File

@@ -39,8 +39,7 @@ def _build_event_type_map() -> None:
"""Populate _event_type_map from all BaseEvent subclasses."""
def _collect(cls: type[BaseEvent]) -> None:
subclasses: list[type[BaseEvent]] = cls.__subclasses__()
for sub in subclasses:
for sub in cls.__subclasses__():
type_field = sub.model_fields.get("type")
if type_field and type_field.default:
_event_type_map[type_field.default] = sub
@@ -197,21 +196,6 @@ class EventRecord(BaseModel):
node for node in self.nodes.values() if not node.neighbors("parent")
]
def all_nodes(self) -> list[EventNode]:
"""Return a snapshot of every node under the read lock.
Returns:
A list copy of the current nodes, safe to iterate without holding
the lock.
"""
with self._lock.r_locked():
return list(self.nodes.values())
def clear(self) -> None:
"""Remove all nodes from the record under the write lock."""
with self._lock.w_locked():
self.nodes.clear()
def __len__(self) -> int:
with self._lock.r_locked():
return len(self.nodes)

View File

@@ -61,16 +61,13 @@ class BaseProvider(BaseModel, ABC):
...
@abstractmethod
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> int:
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> None:
"""Remove old checkpoints, keeping at most *max_keep* per branch.
Args:
location: The storage destination passed to ``checkpoint``.
max_keep: Maximum number of checkpoints to retain.
branch: Only prune checkpoints on this branch.
Returns:
The number of checkpoints removed.
"""
...

View File

@@ -95,20 +95,17 @@ class JsonProvider(BaseProvider):
await f.write(data)
return str(file_path)
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> int:
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> None:
"""Remove oldest checkpoint files beyond *max_keep* on a branch."""
_safe_branch(location, branch)
branch_dir = os.path.join(location, branch)
pattern = os.path.join(branch_dir, "*.json")
files = sorted(glob.glob(pattern), key=os.path.getmtime)
removed = 0
for path in files if max_keep == 0 else files[:-max_keep]:
try:
os.remove(path)
removed += 1
except OSError: # noqa: PERF203
logger.debug("Failed to remove %s", path, exc_info=True)
return removed
def extract_id(self, location: str) -> str:
"""Extract the checkpoint ID from a file path.

View File

@@ -111,13 +111,11 @@ class SqliteProvider(BaseProvider):
await db.commit()
return f"{location}#{checkpoint_id}"
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> int:
def prune(self, location: str, max_keep: int, *, branch: str = "main") -> None:
"""Remove oldest checkpoint rows beyond *max_keep* on a branch."""
with sqlite3.connect(location) as conn:
cursor = conn.execute(_PRUNE, (branch, branch, max_keep))
removed: int = cursor.rowcount
conn.execute(_PRUNE, (branch, branch, max_keep))
conn.commit()
return max(removed, 0)
def extract_id(self, location: str) -> str:
"""Extract the checkpoint ID from a ``db_path#id`` string."""

View File

@@ -10,7 +10,6 @@ via ``RuntimeState.model_rebuild()``.
from __future__ import annotations
import logging
import time
from typing import TYPE_CHECKING, Any
import uuid
@@ -24,17 +23,6 @@ from pydantic import (
)
from crewai.context import capture_execution_context
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.checkpoint_events import (
CheckpointCompletedEvent,
CheckpointFailedEvent,
CheckpointForkCompletedEvent,
CheckpointForkStartedEvent,
CheckpointRestoreCompletedEvent,
CheckpointRestoreFailedEvent,
CheckpointRestoreStartedEvent,
CheckpointStartedEvent,
)
from crewai.state.checkpoint_config import CheckpointConfig
from crewai.state.event_record import EventRecord
from crewai.state.provider.core import BaseProvider
@@ -101,7 +89,7 @@ def _migrate(data: dict[str, Any]) -> dict[str, Any]:
"""
raw = data.get("crewai_version")
current = Version(get_crewai_version())
stored = Version(raw) if isinstance(raw, str) and raw else Version("0.0.0")
stored = Version(raw) if raw else Version("0.0.0")
if raw is None:
logger.warning("Checkpoint has no crewai_version — treating as 0.0.0")
@@ -171,63 +159,6 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
self._checkpoint_id = provider.extract_id(location)
self._parent_id = self._checkpoint_id
def _begin_checkpoint(self, location: str) -> tuple[str, str | None, str, float]:
"""Emit the start event and return the invariant context for a checkpoint."""
provider_name: str = type(self._provider).__name__
parent_id_snapshot: str | None = self._parent_id
branch_snapshot: str = self._branch
crewai_event_bus.emit(
self,
CheckpointStartedEvent(
location=location,
provider=provider_name,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
),
)
return provider_name, parent_id_snapshot, branch_snapshot, time.perf_counter()
def _emit_checkpoint_failed(
self,
location: str,
provider_name: str,
branch_snapshot: str,
parent_id_snapshot: str | None,
exc: Exception,
) -> None:
"""Emit the failure event for a checkpoint write."""
crewai_event_bus.emit(
self,
CheckpointFailedEvent(
location=location,
provider=provider_name,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
error=str(exc),
),
)
def _emit_checkpoint_completed(
self,
result: str,
provider_name: str,
branch_snapshot: str,
parent_id_snapshot: str | None,
start: float,
) -> None:
"""Emit the completion event for a successful checkpoint write."""
crewai_event_bus.emit(
self,
CheckpointCompletedEvent(
location=result,
provider=provider_name,
branch=branch_snapshot,
parent_id=parent_id_snapshot,
checkpoint_id=self._provider.extract_id(result),
duration_ms=(time.perf_counter() - start) * 1000.0,
),
)
def checkpoint(self, location: str) -> str:
"""Write a checkpoint.
@@ -238,27 +169,14 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
Returns:
A location identifier for the saved checkpoint.
"""
provider_name, parent_id_snapshot, branch_snapshot, start = (
self._begin_checkpoint(location)
)
try:
_prepare_entities(self.root)
result = self._provider.checkpoint(
self.model_dump_json(),
location,
parent_id=parent_id_snapshot,
branch=branch_snapshot,
)
self._chain_lineage(self._provider, result)
except Exception as exc:
self._emit_checkpoint_failed(
location, provider_name, branch_snapshot, parent_id_snapshot, exc
)
raise
self._emit_checkpoint_completed(
result, provider_name, branch_snapshot, parent_id_snapshot, start
_prepare_entities(self.root)
result = self._provider.checkpoint(
self.model_dump_json(),
location,
parent_id=self._parent_id,
branch=self._branch,
)
self._chain_lineage(self._provider, result)
return result
async def acheckpoint(self, location: str) -> str:
@@ -271,27 +189,14 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
Returns:
A location identifier for the saved checkpoint.
"""
provider_name, parent_id_snapshot, branch_snapshot, start = (
self._begin_checkpoint(location)
)
try:
_prepare_entities(self.root)
result = await self._provider.acheckpoint(
self.model_dump_json(),
location,
parent_id=parent_id_snapshot,
branch=branch_snapshot,
)
self._chain_lineage(self._provider, result)
except Exception as exc:
self._emit_checkpoint_failed(
location, provider_name, branch_snapshot, parent_id_snapshot, exc
)
raise
self._emit_checkpoint_completed(
result, provider_name, branch_snapshot, parent_id_snapshot, start
_prepare_entities(self.root)
result = await self._provider.acheckpoint(
self.model_dump_json(),
location,
parent_id=self._parent_id,
branch=self._branch,
)
self._chain_lineage(self._provider, result)
return result
def fork(self, branch: str | None = None) -> None:
@@ -306,32 +211,11 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
times without collisions.
"""
if branch:
new_branch = branch
self._branch = branch
elif self._checkpoint_id:
new_branch = f"fork/{self._checkpoint_id}_{uuid.uuid4().hex[:6]}"
self._branch = f"fork/{self._checkpoint_id}_{uuid.uuid4().hex[:6]}"
else:
new_branch = f"fork/{uuid.uuid4().hex[:8]}"
parent_branch: str | None = self._branch
parent_checkpoint_id: str | None = self._checkpoint_id
crewai_event_bus.emit(
self,
CheckpointForkStartedEvent(
branch=new_branch,
parent_branch=parent_branch,
parent_checkpoint_id=parent_checkpoint_id,
),
)
self._branch = new_branch
crewai_event_bus.emit(
self,
CheckpointForkCompletedEvent(
branch=new_branch,
parent_branch=parent_branch,
parent_checkpoint_id=parent_checkpoint_id,
),
)
self._branch = f"fork/{uuid.uuid4().hex[:8]}"
@classmethod
def from_checkpoint(cls, config: CheckpointConfig, **kwargs: Any) -> RuntimeState:
@@ -349,41 +233,13 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
if config.restore_from is None:
raise ValueError("CheckpointConfig.restore_from must be set")
location = str(config.restore_from)
crewai_event_bus.emit(config, CheckpointRestoreStartedEvent(location=location))
start: float = time.perf_counter()
provider_name: str | None = None
try:
provider = detect_provider(location)
provider_name = type(provider).__name__
raw = provider.from_checkpoint(location)
state = cls.model_validate_json(raw, **kwargs)
state._provider = provider
checkpoint_id = provider.extract_id(location)
state._checkpoint_id = checkpoint_id
state._parent_id = checkpoint_id
except Exception as exc:
crewai_event_bus.emit(
config,
CheckpointRestoreFailedEvent(
location=location,
provider=provider_name,
error=str(exc),
),
)
raise
crewai_event_bus.emit(
config,
CheckpointRestoreCompletedEvent(
location=location,
provider=provider_name,
checkpoint_id=checkpoint_id,
branch=state._branch,
parent_id=state._parent_id,
duration_ms=(time.perf_counter() - start) * 1000.0,
),
)
provider = detect_provider(location)
raw = provider.from_checkpoint(location)
state = cls.model_validate_json(raw, **kwargs)
state._provider = provider
checkpoint_id = provider.extract_id(location)
state._checkpoint_id = checkpoint_id
state._parent_id = checkpoint_id
return state
@classmethod
@@ -404,41 +260,13 @@ class RuntimeState(RootModel): # type: ignore[type-arg]
if config.restore_from is None:
raise ValueError("CheckpointConfig.restore_from must be set")
location = str(config.restore_from)
crewai_event_bus.emit(config, CheckpointRestoreStartedEvent(location=location))
start: float = time.perf_counter()
provider_name: str | None = None
try:
provider = detect_provider(location)
provider_name = type(provider).__name__
raw = await provider.afrom_checkpoint(location)
state = cls.model_validate_json(raw, **kwargs)
state._provider = provider
checkpoint_id = provider.extract_id(location)
state._checkpoint_id = checkpoint_id
state._parent_id = checkpoint_id
except Exception as exc:
crewai_event_bus.emit(
config,
CheckpointRestoreFailedEvent(
location=location,
provider=provider_name,
error=str(exc),
),
)
raise
crewai_event_bus.emit(
config,
CheckpointRestoreCompletedEvent(
location=location,
provider=provider_name,
checkpoint_id=checkpoint_id,
branch=state._branch,
parent_id=state._parent_id,
duration_ms=(time.perf_counter() - start) * 1000.0,
),
)
provider = detect_provider(location)
raw = await provider.afrom_checkpoint(location)
state = cls.model_validate_json(raw, **kwargs)
state._provider = provider
checkpoint_id = provider.extract_id(location)
state._checkpoint_id = checkpoint_id
state._parent_id = checkpoint_id
return state

View File

@@ -1,165 +0,0 @@
"""Tests for event bus replay dispatch and is_replaying flag."""
from __future__ import annotations
from typing import Any
from unittest.mock import patch
from crewai.events.event_bus import _replaying, crewai_event_bus, is_replaying
from crewai.events.types.flow_events import (
MethodExecutionFinishedEvent,
MethodExecutionStartedEvent,
)
def _make_started(method: str, event_id: str, sequence: int) -> MethodExecutionStartedEvent:
"""Build a MethodExecutionStartedEvent with explicit ids/sequence."""
ev = MethodExecutionStartedEvent(
method_name=method,
flow_name="F",
params={},
state={},
)
ev.event_id = event_id
ev.emission_sequence = sequence
return ev
class TestReplayPreservesFields:
"""replay() must not overwrite event_id, parent_event_id, or emission_sequence."""
def test_preserves_ids_and_sequence(self) -> None:
captured: list[MethodExecutionStartedEvent] = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(MethodExecutionStartedEvent)
def _capture(_: Any, event: MethodExecutionStartedEvent) -> None:
captured.append(event)
ev = _make_started("outline", "orig-id-1", 42)
ev.parent_event_id = "parent-abc"
future = crewai_event_bus.replay(object(), ev)
if future is not None:
future.result(timeout=5.0)
assert len(captured) == 1
assert captured[0].event_id == "orig-id-1"
assert captured[0].parent_event_id == "parent-abc"
assert captured[0].emission_sequence == 42
class TestIsReplayingFlag:
"""is_replaying() must be True inside handlers dispatched via replay()."""
def test_flag_true_during_replay(self) -> None:
seen: list[bool] = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(MethodExecutionStartedEvent)
def _capture(_: Any, __: MethodExecutionStartedEvent) -> None:
seen.append(is_replaying())
ev = _make_started("m", "id-1", 1)
future = crewai_event_bus.replay(object(), ev)
if future is not None:
future.result(timeout=5.0)
assert seen == [True]
assert is_replaying() is False
def test_flag_false_during_emit(self) -> None:
seen: list[bool] = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(MethodExecutionStartedEvent)
def _capture(_: Any, __: MethodExecutionStartedEvent) -> None:
seen.append(is_replaying())
ev = _make_started("m", "id-1", 1)
future = crewai_event_bus.emit(object(), ev)
if future is not None:
future.result(timeout=5.0)
assert seen == [False]
class TestCheckpointListenerOptsOut:
"""CheckpointListener must early-return during replay."""
def test_checkpoint_not_written_on_replay(self) -> None:
from crewai.state.checkpoint_config import CheckpointConfig
from crewai.state.checkpoint_listener import _on_any_event
class FlowLike:
entity_type = "flow"
checkpoint = CheckpointConfig(trigger_all=True)
ev = _make_started("m", "id-1", 1)
with patch("crewai.state.checkpoint_listener._do_checkpoint") as do_cp:
token = _replaying.set(True)
try:
_on_any_event(FlowLike(), ev, state=None)
finally:
_replaying.reset(token)
assert do_cp.call_count == 0
class TestFlowResumeReplaysEvents:
"""End-to-end: a resumed flow emits MethodExecution* events for completed methods."""
def test_resume_dispatches_completed_method_events(self, tmp_path) -> None:
from crewai.flow.flow import Flow, listen, start
from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
db_path = tmp_path / "flows.db"
persistence = SQLiteFlowPersistence(str(db_path))
class ThreeStepFlow(Flow[dict]):
@start()
def step_a(self) -> str:
return "a"
@listen(step_a)
def step_b(self) -> str:
return "b"
@listen(step_b)
def step_c(self) -> str:
return "c"
if crewai_event_bus.runtime_state is not None:
crewai_event_bus.runtime_state.event_record.clear()
flow1 = ThreeStepFlow(persistence=persistence)
flow1.kickoff()
flow_id = flow1.state["id"]
captured_started: list[str] = []
captured_finished: list[str] = []
flow2 = ThreeStepFlow(persistence=persistence)
flow2._completed_methods = {"step_a", "step_b"}
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(MethodExecutionStartedEvent)
def _cs(_: Any, event: MethodExecutionStartedEvent) -> None:
captured_started.append(event.method_name)
@crewai_event_bus.on(MethodExecutionFinishedEvent)
def _cf(_: Any, event: MethodExecutionFinishedEvent) -> None:
captured_finished.append(event.method_name)
flow2.kickoff(inputs={"id": flow_id})
assert captured_started.count("step_a") == 1
assert captured_started.count("step_b") == 1
assert captured_started.count("step_c") == 1
assert captured_finished.count("step_a") == 1
assert captured_finished.count("step_b") == 1
assert captured_finished.count("step_c") == 1

View File

@@ -389,41 +389,17 @@ def test_azure_raises_error_when_endpoint_missing():
llm._get_sync_client()
def test_azure_raises_error_when_api_key_missing_without_azure_identity():
"""Without an API key AND without ``azure-identity`` installed,
def test_azure_raises_error_when_api_key_missing():
"""Credentials are validated lazily: construction succeeds, first
client build raises the descriptive error."""
from crewai.llms.providers.azure.completion import AzureCompletion
with patch.dict(os.environ, {}, clear=True):
with patch.dict("sys.modules", {"azure.identity": None}):
llm = AzureCompletion(
model="gpt-4", endpoint="https://test.openai.azure.com"
)
with pytest.raises(ValueError, match="Azure API key is required"):
llm._get_sync_client()
def test_azure_uses_default_credential_when_api_key_missing():
"""With ``azure-identity`` installed, a missing API key falls back to
``DefaultAzureCredential`` instead of raising. This is the path that
enables keyless auth (OIDC WIF on EKS/AKS, Managed Identity, Azure
CLI) without any crewAI-specific config."""
from unittest.mock import MagicMock
from crewai.llms.providers.azure.completion import AzureCompletion
sentinel = MagicMock(name="DefaultAzureCredential()")
with patch.dict(os.environ, {}, clear=True):
with patch(
"azure.identity.DefaultAzureCredential", return_value=sentinel
) as mock_cls:
llm = AzureCompletion(
model="gpt-4",
endpoint="https://test-ai.services.example.com",
)
kwargs = llm._make_client_kwargs()
assert kwargs["credential"] is sentinel
mock_cls.assert_called()
llm = AzureCompletion(
model="gpt-4", endpoint="https://test.openai.azure.com"
)
with pytest.raises(ValueError, match="Azure API key is required"):
llm._get_sync_client()
@pytest.mark.asyncio

View File

@@ -4,8 +4,6 @@ from pathlib import Path
import pytest
from crewai import Agent
from crewai.agent.utils import append_skill_context
from crewai.skills.loader import activate_skill, discover_skills, format_skill_context
from crewai.skills.models import INSTRUCTIONS, METADATA
@@ -78,23 +76,3 @@ class TestSkillDiscoveryAndActivation:
all_skills.extend(discover_skills(search_path))
names = {s.name for s in all_skills}
assert names == {"skill-a", "skill-b"}
def test_agent_preserves_metadata_for_discovered_skills(self, tmp_path: Path) -> None:
_create_skill_dir(tmp_path, "travel", body="Use this skill for travel planning.")
discovered = discover_skills(tmp_path)
agent = Agent(
role="Travel Advisor",
goal="Provide personalized travel suggestions.",
backstory="An experienced travel consultant.",
skills=discovered,
)
assert agent.skills is not None
assert agent.skills[0].disclosure_level == METADATA
assert agent.skills[0].instructions is None
prompt = append_skill_context(agent, "Plan a 10-day Japan itinerary.")
assert "## Skill: travel" in prompt
assert "Skill travel" in prompt
assert "Use this skill for travel planning." not in prompt

View File

@@ -11,12 +11,11 @@ from typing import Any
from unittest.mock import MagicMock, patch
import pytest
from pydantic import BaseModel
from crewai.agent.core import Agent
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.crew import Crew
from crewai.flow.flow import _INITIAL_STATE_CLASS_MARKER, Flow, start
from crewai.flow.flow import Flow, start
from crewai.state.checkpoint_config import CheckpointConfig
from crewai.state.checkpoint_listener import (
_find_checkpoint,
@@ -311,65 +310,6 @@ class TestRuntimeStateLineage:
assert state._branch != first
class TestFlowInitialStateSerialization:
"""Regression tests for checkpoint serialization of ``Flow.initial_state``."""
def test_class_ref_serializes_as_schema(self) -> None:
class MyState(BaseModel):
id: str = "x"
foo: str = "bar"
flow = Flow(initial_state=MyState)
state = RuntimeState(root=[flow])
dumped = json.loads(state.model_dump_json())
entity = dumped["entities"][0]
wrapped = entity["initial_state"]
assert isinstance(wrapped, dict)
assert _INITIAL_STATE_CLASS_MARKER in wrapped
assert wrapped[_INITIAL_STATE_CLASS_MARKER].get("title") == "MyState"
def test_class_ref_round_trips_to_basemodel_subclass(self) -> None:
class MyState(BaseModel):
id: str = "x"
foo: str = "bar"
flow = Flow(initial_state=MyState)
raw = RuntimeState(root=[flow]).model_dump_json()
restored = RuntimeState.model_validate_json(
raw, context={"from_checkpoint": True}
)
rehydrated = restored.root[0].initial_state
assert isinstance(rehydrated, type)
assert issubclass(rehydrated, BaseModel)
assert set(rehydrated.model_fields.keys()) == {"id", "foo"}
def test_instance_serializes_as_values(self) -> None:
class MyState(BaseModel):
id: str = "x"
foo: str = "bar"
flow = Flow(initial_state=MyState(foo="baz"))
state = RuntimeState(root=[flow])
dumped = json.loads(state.model_dump_json())
entity = dumped["entities"][0]
assert entity["initial_state"] == {"id": "x", "foo": "baz"}
def test_dict_passthrough(self) -> None:
flow = Flow(initial_state={"id": "x", "foo": "bar"})
state = RuntimeState(root=[flow])
dumped = json.loads(state.model_dump_json())
entity = dumped["entities"][0]
assert entity["initial_state"] == {"id": "x", "foo": "bar"}
def test_dict_round_trips_as_dict(self) -> None:
flow = Flow(initial_state={"id": "x", "foo": "bar"})
raw = RuntimeState(root=[flow]).model_dump_json()
restored = RuntimeState.model_validate_json(
raw, context={"from_checkpoint": True}
)
assert restored.root[0].initial_state == {"id": "x", "foo": "bar"}
# ---------- JsonProvider forking ----------

View File

@@ -4519,8 +4519,8 @@ def test_sets_flow_context_when_using_crewbase_pattern_inside_flow():
flow.kickoff()
assert captured_crew is not None
assert captured_crew._flow_id == flow.execution_id # type: ignore[attr-defined]
assert captured_crew._request_id == flow.execution_id # type: ignore[attr-defined]
assert captured_crew._flow_id == flow.flow_id # type: ignore[attr-defined]
assert captured_crew._request_id == flow.flow_id # type: ignore[attr-defined]
def test_sets_flow_context_when_outside_flow(researcher, writer):
@@ -4554,8 +4554,8 @@ def test_sets_flow_context_when_inside_flow(researcher, writer):
flow = MyFlow()
result = flow.kickoff()
assert result._flow_id == flow.execution_id # type: ignore[attr-defined]
assert result._request_id == flow.execution_id # type: ignore[attr-defined]
assert result._flow_id == flow.flow_id # type: ignore[attr-defined]
assert result._request_id == flow.flow_id # type: ignore[attr-defined]
def test_reset_knowledge_with_no_crew_knowledge(researcher, writer):

View File

@@ -1,127 +0,0 @@
"""Regression tests for ``Flow.execution_id``.
``execution_id`` is the stable tracking identifier for a single flow run.
It must stay independent of ``state.id`` so that consumers passing an
``id`` in ``inputs`` (used for persistence restore) cannot destabilize
the identity used by telemetry, tracing, and external correlation.
"""
from __future__ import annotations
from typing import Any
import pytest
from crewai.flow.flow import Flow, FlowState, start
from crewai.flow.flow_context import current_flow_id, current_flow_request_id
class _CaptureState(FlowState):
captured_flow_id: str = ""
captured_state_id: str = ""
captured_current_flow_id: str = ""
captured_execution_id: str = ""
class _IdentityCaptureFlow(Flow[_CaptureState]):
initial_state = _CaptureState
@start()
def capture(self) -> None:
self.state.captured_flow_id = self.flow_id
self.state.captured_state_id = self.state.id
self.state.captured_current_flow_id = current_flow_id.get() or ""
self.state.captured_execution_id = self.execution_id
def test_execution_id_defaults_to_fresh_uuid_per_instance() -> None:
a = _IdentityCaptureFlow()
b = _IdentityCaptureFlow()
assert a.execution_id
assert b.execution_id
assert a.execution_id != b.execution_id
def test_execution_id_survives_consumer_id_in_inputs() -> None:
flow = _IdentityCaptureFlow()
original_execution_id = flow.execution_id
flow.kickoff(inputs={"id": "consumer-supplied-id"})
assert flow.state.id == "consumer-supplied-id"
assert flow.flow_id == "consumer-supplied-id"
assert flow.execution_id == original_execution_id
assert flow.execution_id != "consumer-supplied-id"
def test_two_runs_with_same_consumer_id_have_distinct_execution_ids() -> None:
flow_a = _IdentityCaptureFlow()
flow_b = _IdentityCaptureFlow()
colliding_id = "shared-consumer-id"
flow_a.kickoff(inputs={"id": colliding_id})
flow_b.kickoff(inputs={"id": colliding_id})
assert flow_a.state.id == colliding_id
assert flow_b.state.id == colliding_id
assert flow_a.execution_id != flow_b.execution_id
def test_execution_id_is_writable() -> None:
flow = _IdentityCaptureFlow()
flow.execution_id = "external-task-id"
assert flow.execution_id == "external-task-id"
flow.kickoff(inputs={"id": "consumer-supplied-id"})
assert flow.execution_id == "external-task-id"
assert flow.state.id == "consumer-supplied-id"
def test_current_flow_id_context_var_matches_execution_id() -> None:
flow = _IdentityCaptureFlow()
flow.execution_id = "external-task-id"
flow.kickoff(inputs={"id": "consumer-supplied-id"})
assert flow.state.captured_current_flow_id == "external-task-id"
assert flow.state.captured_flow_id == "consumer-supplied-id"
assert flow.state.captured_execution_id == "external-task-id"
def test_execution_id_not_included_in_serialized_state() -> None:
flow = _IdentityCaptureFlow()
flow.execution_id = "external-task-id"
flow.kickoff()
dumped = flow.state.model_dump()
assert "execution_id" not in dumped
assert "_execution_id" not in dumped
assert dumped["id"] == flow.state.id
def test_dict_state_flow_also_exposes_stable_execution_id() -> None:
class DictFlow(Flow[dict[str, Any]]):
initial_state = dict # type: ignore[assignment]
@start()
def noop(self) -> None:
pass
flow = DictFlow()
original = flow.execution_id
flow.kickoff(inputs={"id": "consumer-supplied-id"})
assert flow.state["id"] == "consumer-supplied-id"
assert flow.execution_id == original
@pytest.fixture(autouse=True)
def _reset_flow_context_vars():
yield
for var in (current_flow_id, current_flow_request_id):
try:
var.set(None)
except LookupError:
# ContextVar was never set in this context; nothing to reset.
pass

View File

@@ -1,411 +0,0 @@
"""Tests for LLM.call() tool loop and LLMResult.
All LLM calls are mocked — no real API traffic.
"""
from __future__ import annotations
import json
from types import SimpleNamespace
from typing import Any
from unittest.mock import MagicMock, patch
import pytest
from crewai.llm_result import (
LLMResult,
ToolCallRecord,
_lookup_pricing,
estimate_cost_usd,
)
def _make_litellm_llm(model: str = "gpt-4o") -> Any:
"""Create an LLM instance that uses the litellm fallback path."""
from crewai.llm import LLM
return LLM(model=model, is_litellm=True)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _make_tool_call(name: str, arguments: dict, call_id: str = "call_1"):
"""Build a tool-call object using litellm's actual types."""
try:
from litellm.types.utils import (
ChatCompletionMessageToolCall,
Function,
)
return ChatCompletionMessageToolCall(
id=call_id,
function=Function(name=name, arguments=json.dumps(arguments)),
type="function",
)
except ImportError:
func = SimpleNamespace(name=name, arguments=json.dumps(arguments))
return SimpleNamespace(id=call_id, function=func, type="function")
def _make_model_response(content: str | None = None, tool_calls: list | None = None):
"""Build a minimal mock ModelResponse that passes isinstance checks.
We need it to be an instance of litellm's ModelResponse/ModelResponseBase
so the internal isinstance() checks work. We import those types when
litellm is available.
"""
try:
from litellm.types.utils import (
Choices,
Message,
ModelResponse,
Usage,
)
message = Message(content=content, tool_calls=tool_calls or None)
choice = Choices(message=message, finish_reason="stop", index=0)
resp = ModelResponse(
choices=[choice],
usage=Usage(
prompt_tokens=100,
completion_tokens=50,
total_tokens=150,
),
)
return resp
except ImportError:
# Fallback to SimpleNamespace if litellm not installed
message = SimpleNamespace(content=content, tool_calls=tool_calls or [])
choice = SimpleNamespace(message=message, finish_reason="stop")
usage = SimpleNamespace(
prompt_tokens=100,
completion_tokens=50,
total_tokens=150,
)
resp = SimpleNamespace(
choices=[choice],
model_extra={"usage": usage},
)
return resp
DUMMY_TOOL_SCHEMA = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get weather for a city",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string"},
},
"required": ["city"],
},
},
}
]
# ---------------------------------------------------------------------------
# Unit tests for LLMResult / ToolCallRecord
# ---------------------------------------------------------------------------
class TestLLMResultModels:
def test_tool_call_record_defaults(self):
r = ToolCallRecord(name="foo")
assert r.input == {}
assert r.output == ""
assert r.duration_ms == 0.0
assert r.is_error is False
def test_llm_result_defaults(self):
r = LLMResult()
assert r.text == ""
assert r.tool_calls == []
assert r.cost_usd == 0.0
assert r.iterations == 0
assert r.usage.total_tokens == 0
def test_llm_result_with_data(self):
r = LLMResult(
text="hello",
tool_calls=[ToolCallRecord(name="foo", input={"a": 1}, output="bar")],
iterations=2,
cost_usd=0.005,
)
assert r.text == "hello"
assert len(r.tool_calls) == 1
assert r.tool_calls[0].name == "foo"
# ---------------------------------------------------------------------------
# Cost estimation
# ---------------------------------------------------------------------------
class TestCostEstimation:
def test_known_model(self):
cost = estimate_cost_usd("gpt-4o", prompt_tokens=1_000_000, completion_tokens=0)
assert cost == pytest.approx(2.50)
def test_known_model_output(self):
cost = estimate_cost_usd("gpt-4o", prompt_tokens=0, completion_tokens=1_000_000)
assert cost == pytest.approx(10.00)
def test_unknown_model_returns_zero(self):
cost = estimate_cost_usd("some-random-model-xyz", 1000, 1000)
assert cost == 0.0
def test_provider_prefix_stripped(self):
cost = estimate_cost_usd("anthropic/claude-sonnet-4-6", 1_000_000, 0)
assert cost == pytest.approx(3.00)
def test_partial_match(self):
# "claude-sonnet-4-6-20250514" should match "claude-sonnet-4-6"
cost = estimate_cost_usd("claude-sonnet-4-6-20250514", 1_000_000, 0)
assert cost == pytest.approx(3.00)
def test_lookup_none(self):
assert _lookup_pricing("") is None
assert _lookup_pricing("nonexistent") is None
# ---------------------------------------------------------------------------
# LLM.call() backwards compatibility (no tools → returns str)
# ---------------------------------------------------------------------------
class TestCallBackwardsCompat:
"""LLM.call() without tools must return str exactly as before."""
@patch("crewai.llm.litellm")
def test_call_without_tools_returns_str(self, mock_litellm):
"""Plain call without tools should return a string."""
mock_litellm.completion.return_value = _make_model_response(content="Hello world")
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
llm = _make_litellm_llm()
result = llm.call("Say hello")
assert isinstance(result, str)
assert result == "Hello world"
# ---------------------------------------------------------------------------
# LLM.call() with tools → returns LLMResult
# ---------------------------------------------------------------------------
class TestCallWithToolLoop:
"""When tools + available_functions are passed, call() returns LLMResult."""
@patch("crewai.llm.litellm")
def test_single_tool_call_then_text(self, mock_litellm):
"""Model calls one tool, then responds with text."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
# First call: model wants to call get_weather
tool_call = _make_tool_call("get_weather", {"city": "SF"})
resp1 = _make_model_response(content=None, tool_calls=[tool_call])
# Second call: model responds with text
resp2 = _make_model_response(content="It's sunny in SF!")
mock_litellm.completion.side_effect = [resp1, resp2]
llm = _make_litellm_llm()
def get_weather(city: str) -> str:
return f"Sunny, 72°F in {city}"
result = llm.call(
messages="What's the weather in SF?",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": get_weather},
)
assert isinstance(result, LLMResult)
assert result.text == "It's sunny in SF!"
assert len(result.tool_calls) == 1
assert result.tool_calls[0].name == "get_weather"
assert result.tool_calls[0].input == {"city": "SF"}
assert "Sunny" in result.tool_calls[0].output
assert result.tool_calls[0].is_error is False
assert result.iterations == 2
@patch("crewai.llm.litellm")
def test_multiple_tool_calls_in_sequence(self, mock_litellm):
"""Model calls two tools across two iterations."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
tc1 = _make_tool_call("get_weather", {"city": "SF"}, "call_1")
resp1 = _make_model_response(content=None, tool_calls=[tc1])
tc2 = _make_tool_call("get_weather", {"city": "NYC"}, "call_2")
resp2 = _make_model_response(content=None, tool_calls=[tc2])
resp3 = _make_model_response(content="SF is sunny, NYC is rainy.")
mock_litellm.completion.side_effect = [resp1, resp2, resp3]
llm = _make_litellm_llm()
def get_weather(city: str) -> str:
return f"Weather for {city}: fine"
result = llm.call(
messages="Compare SF and NYC weather",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": get_weather},
)
assert isinstance(result, LLMResult)
assert len(result.tool_calls) == 2
assert result.tool_calls[0].input["city"] == "SF"
assert result.tool_calls[1].input["city"] == "NYC"
assert result.iterations == 3
@patch("crewai.llm.litellm")
def test_max_iterations_stops_loop(self, mock_litellm):
"""Loop stops when max_iterations is reached."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
# Model always wants to call a tool — never stops
def make_tool_resp():
tc = _make_tool_call("get_weather", {"city": "SF"})
return _make_model_response(content=None, tool_calls=[tc])
mock_litellm.completion.side_effect = [make_tool_resp() for _ in range(5)]
llm = _make_litellm_llm()
result = llm.call(
messages="Loop forever",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": lambda city: "sunny"},
max_iterations=3,
)
assert isinstance(result, LLMResult)
assert result.iterations == 3
assert len(result.tool_calls) == 3
# Should have a text noting max iterations
assert "Max iterations" in result.text
@patch("crewai.llm.litellm")
def test_tool_error_handling(self, mock_litellm):
"""Tool that raises an exception is captured in the record."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
tc = _make_tool_call("get_weather", {"city": "SF"})
resp1 = _make_model_response(content=None, tool_calls=[tc])
resp2 = _make_model_response(content="Sorry, couldn't get weather.")
mock_litellm.completion.side_effect = [resp1, resp2]
llm = _make_litellm_llm()
def broken_weather(city: str) -> str:
raise RuntimeError("API down")
result = llm.call(
messages="Weather?",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": broken_weather},
)
assert isinstance(result, LLMResult)
assert len(result.tool_calls) == 1
assert result.tool_calls[0].is_error is True
assert "API down" in result.tool_calls[0].output
assert result.text == "Sorry, couldn't get weather."
@patch("crewai.llm.litellm")
def test_unknown_function_error(self, mock_litellm):
"""Tool call for a function not in available_functions."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
tc = _make_tool_call("nonexistent_tool", {})
resp1 = _make_model_response(content=None, tool_calls=[tc])
resp2 = _make_model_response(content="I couldn't find that tool.")
mock_litellm.completion.side_effect = [resp1, resp2]
llm = _make_litellm_llm()
result = llm.call(
messages="Do something",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": lambda city: "sunny"},
)
assert isinstance(result, LLMResult)
assert result.tool_calls[0].is_error is True
assert "unknown function" in result.tool_calls[0].output
@patch("crewai.llm.litellm")
def test_cost_estimation_populated(self, mock_litellm):
"""cost_usd is populated from token usage and model pricing."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
resp = _make_model_response(content="Done!")
mock_litellm.completion.return_value = resp
llm = _make_litellm_llm()
result = llm.call(
messages="Hello",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": lambda city: "sunny"},
)
assert isinstance(result, LLMResult)
# cost_usd should be >= 0 (may be 0 if usage tracking didn't fire,
# but the field should exist and be a float)
assert isinstance(result.cost_usd, float)
@patch("crewai.llm.litellm")
def test_immediate_text_response_with_tools(self, mock_litellm):
"""Model responds with text on first call (no tool use)."""
mock_litellm.drop_params = True
mock_litellm.suppress_debug_info = True
mock_litellm.success_callback = []
mock_litellm._async_success_callback = []
mock_litellm.callbacks = []
resp = _make_model_response(content="I know the answer already.")
mock_litellm.completion.return_value = resp
llm = _make_litellm_llm()
result = llm.call(
messages="What's 2+2?",
tools=DUMMY_TOOL_SCHEMA,
available_functions={"get_weather": lambda city: "sunny"},
)
assert isinstance(result, LLMResult)
assert result.text == "I know the answer already."
assert len(result.tool_calls) == 0
assert result.iterations == 1

View File

@@ -1,3 +1,3 @@
"""CrewAI development tools."""
__version__ = "1.14.3"
__version__ = "1.14.3a2"

View File

@@ -164,7 +164,7 @@ info = "Commits must follow Conventional Commits 1.0.0."
[tool.uv]
# Pinned to include the security patch releases (authlib 1.6.11,
# langchain-text-splitters 1.1.2) uploaded on 2026-04-16.
exclude-newer = "2026-04-26"
exclude-newer = "2026-04-22"
# composio-core pins rich<14 but textual requires rich>=14.
# onnxruntime 1.24+ dropped Python 3.10 wheels; cap it so qdrant[fastembed] resolves on 3.10.

View File

@@ -0,0 +1,76 @@
#!/usr/bin/env python3
"""Benchmark `import crewai` cold start time.
Usage:
python scripts/benchmark_import_time.py [--runs N] [--json]
Spawns a fresh Python subprocess for each run to ensure cold imports.
Prints median, mean, min, max across all runs.
With --json, outputs machine-readable results for CI.
"""
import argparse
import json
import statistics
import subprocess
import sys
IMPORT_SCRIPT = "import time; t0 = time.perf_counter(); import crewai; print(time.perf_counter() - t0)"
def measure_import(python: str = sys.executable) -> float:
"""Run a single cold-import measurement in a subprocess."""
result = subprocess.run(
[python, "-c", IMPORT_SCRIPT],
capture_output=True,
text=True,
env={"PATH": "", "VIRTUAL_ENV": "", "PYTHONPATH": ""},
timeout=30,
)
if result.returncode != 0:
raise RuntimeError(f"Import failed: {result.stderr.strip()}")
return float(result.stdout.strip())
def main():
parser = argparse.ArgumentParser(description="Benchmark crewai import time")
parser.add_argument("--runs", type=int, default=5, help="Number of runs (default: 5)")
parser.add_argument("--json", action="store_true", help="Output JSON for CI")
parser.add_argument("--threshold", type=float, default=None,
help="Fail if median exceeds this value (seconds)")
args = parser.parse_args()
times = []
for i in range(args.runs):
t = measure_import()
times.append(t)
if not args.json:
print(f" Run {i + 1}: {t:.3f}s")
median = statistics.median(times)
mean = statistics.mean(times)
stdev = statistics.stdev(times) if len(times) > 1 else 0.0
result = {
"runs": args.runs,
"median_s": round(median, 3),
"mean_s": round(mean, 3),
"stdev_s": round(stdev, 3),
"min_s": round(min(times), 3),
"max_s": round(max(times), 3),
}
if args.json:
print(json.dumps(result))
else:
print(f"\n Median: {median:.3f}s")
print(f" Mean: {mean:.3f}s ± {stdev:.3f}s")
print(f" Range: {min(times):.3f}s {max(times):.3f}s")
if args.threshold and median > args.threshold:
print(f"\n ❌ FAILED: median {median:.3f}s exceeds threshold {args.threshold:.3f}s")
sys.exit(1)
if __name__ == "__main__":
main()

273
uv.lock generated
View File

@@ -13,7 +13,7 @@ resolution-markers = [
]
[options]
exclude-newer = "2026-04-23T07:00:00Z"
exclude-newer = "2026-04-17T16:00:00Z"
[manifest]
members = [
@@ -510,22 +510,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/7e/d6/8ebcd05b01a580f086ac9a97fb9fac65c09a4b012161cc97c21a336e880b/azure_core-1.39.0-py3-none-any.whl", hash = "sha256:4ac7b70fab5438c3f68770649a78daf97833caa83827f91df9c14e0e0ea7d34f", size = 218318, upload-time = "2026-03-19T01:31:31.25Z" },
]
[[package]]
name = "azure-identity"
version = "1.25.3"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "azure-core" },
{ name = "cryptography" },
{ name = "msal" },
{ name = "msal-extensions" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/c5/0e/3a63efb48aa4a5ae2cfca61ee152fbcb668092134d3eb8bfda472dd5c617/azure_identity-1.25.3.tar.gz", hash = "sha256:ab23c0d63015f50b630ef6c6cf395e7262f439ce06e5d07a64e874c724f8d9e6", size = 286304, upload-time = "2026-03-13T01:12:20.892Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/49/9a/417b3a533e01953a7c618884df2cb05a71e7b68bdbce4fbdb62349d2a2e8/azure_identity-1.25.3-py3-none-any.whl", hash = "sha256:f4d0b956a8146f30333e071374171f3cfa7bdb8073adb8c3814b65567aa7447c", size = 192138, upload-time = "2026-03-13T01:12:22.951Z" },
]
[[package]]
name = "backoff"
version = "2.2.1"
@@ -716,15 +700,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/32/76/cab7af7f16c0b09347f2ebe7ffda7101132f786acb767666dce43055faab/botocore_stubs-1.42.41-py3-none-any.whl", hash = "sha256:9423110fb0e391834bd2ed44ae5f879d8cb370a444703d966d30842ce2bcb5f0", size = 66759, upload-time = "2026-02-03T20:46:13.02Z" },
]
[[package]]
name = "bracex"
version = "2.6"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/63/9a/fec38644694abfaaeca2798b58e276a8e61de49e2e37494ace423395febc/bracex-2.6.tar.gz", hash = "sha256:98f1347cd77e22ee8d967a30ad4e310b233f7754dbf31ff3fceb76145ba47dc7", size = 26642, upload-time = "2025-06-22T19:12:31.254Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/9d/2a/9186535ce58db529927f6cf5990a849aa9e052eea3e2cfefe20b9e1802da/bracex-2.6-py3-none-any.whl", hash = "sha256:0b0049264e7340b3ec782b5cb99beb325f36c3782a32e36e876452fd49a09952", size = 11508, upload-time = "2025-06-22T19:12:29.781Z" },
]
[[package]]
name = "browserbase"
version = "1.8.0"
@@ -1321,7 +1296,6 @@ aws = [
]
azure-ai-inference = [
{ name = "azure-ai-inference" },
{ name = "azure-identity" },
]
bedrock = [
{ name = "boto3" },
@@ -1376,7 +1350,6 @@ requires-dist = [
{ name = "anthropic", marker = "extra == 'anthropic'", specifier = "~=0.73.0" },
{ name = "appdirs", specifier = "~=1.4.4" },
{ name = "azure-ai-inference", marker = "extra == 'azure-ai-inference'", specifier = "~=1.0.0b9" },
{ name = "azure-identity", marker = "extra == 'azure-ai-inference'", specifier = ">=1.17.0,<2" },
{ name = "boto3", marker = "extra == 'aws'", specifier = "~=1.42.79" },
{ name = "boto3", marker = "extra == 'bedrock'", specifier = "~=1.42.79" },
{ name = "chromadb", specifier = "~=1.1.0" },
@@ -1516,10 +1489,6 @@ databricks-sdk = [
daytona = [
{ name = "daytona" },
]
e2b = [
{ name = "e2b" },
{ name = "e2b-code-interpreter" },
]
exa-py = [
{ name = "exa-py" },
]
@@ -1621,15 +1590,13 @@ requires-dist = [
{ name = "cryptography", marker = "extra == 'snowflake'", specifier = ">=43.0.3" },
{ name = "databricks-sdk", marker = "extra == 'databricks-sdk'", specifier = ">=0.46.0" },
{ name = "daytona", marker = "extra == 'daytona'", specifier = "~=0.140.0" },
{ name = "e2b", marker = "extra == 'e2b'", specifier = "~=2.20.0" },
{ name = "e2b-code-interpreter", marker = "extra == 'e2b'", specifier = "~=2.6.0" },
{ name = "exa-py", marker = "extra == 'exa-py'", specifier = ">=1.8.7" },
{ name = "firecrawl-py", marker = "extra == 'firecrawl-py'", specifier = ">=1.8.0" },
{ name = "gitpython", marker = "extra == 'github'", specifier = ">=3.1.41,<4" },
{ name = "hyperbrowser", marker = "extra == 'hyperbrowser'", specifier = ">=0.18.0" },
{ name = "langchain-apify", marker = "extra == 'apify'", specifier = ">=0.1.2,<1.0.0" },
{ name = "linkup-sdk", marker = "extra == 'linkup-sdk'", specifier = ">=0.2.2" },
{ name = "lxml", marker = "extra == 'rag'", specifier = ">=6.1.0,<7" },
{ name = "lxml", marker = "extra == 'rag'", specifier = ">=5.3.0,<5.4.0" },
{ name = "mcp", marker = "extra == 'mcp'", specifier = ">=1.6.0" },
{ name = "mcpadapt", marker = "extra == 'mcp'", specifier = ">=0.1.9" },
{ name = "multion", marker = "extra == 'multion'", specifier = ">=1.1.0" },
@@ -1665,7 +1632,7 @@ requires-dist = [
{ name = "weaviate-client", marker = "extra == 'weaviate-client'", specifier = ">=4.10.2" },
{ name = "youtube-transcript-api", specifier = "~=1.2.2" },
]
provides-extras = ["apify", "beautifulsoup4", "bedrock", "browserbase", "composio-core", "contextual", "couchbase", "databricks-sdk", "daytona", "e2b", "exa-py", "firecrawl-py", "github", "hyperbrowser", "linkup-sdk", "mcp", "mongodb", "multion", "mysql", "oxylabs", "patronus", "postgresql", "qdrant-client", "rag", "scrapegraph-py", "scrapfly-sdk", "selenium", "serpapi", "singlestore", "snowflake", "spider-client", "sqlalchemy", "stagehand", "tavily-python", "weaviate-client", "xml"]
provides-extras = ["apify", "beautifulsoup4", "bedrock", "browserbase", "composio-core", "contextual", "couchbase", "databricks-sdk", "daytona", "exa-py", "firecrawl-py", "github", "hyperbrowser", "linkup-sdk", "mcp", "mongodb", "multion", "mysql", "oxylabs", "patronus", "postgresql", "qdrant-client", "rag", "scrapegraph-py", "scrapfly-sdk", "selenium", "serpapi", "singlestore", "snowflake", "spider-client", "sqlalchemy", "stagehand", "tavily-python", "weaviate-client", "xml"]
[[package]]
name = "cryptography"
@@ -2008,15 +1975,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/ba/5a/18ad964b0086c6e62e2e7500f7edc89e3faa45033c71c1893d34eed2b2de/dnspython-2.8.0-py3-none-any.whl", hash = "sha256:01d9bbc4a2d76bf0db7c1f729812ded6d912bd318d3b1cf81d30c0f845dbf3af", size = 331094, upload-time = "2025-09-07T18:57:58.071Z" },
]
[[package]]
name = "dockerfile-parse"
version = "2.0.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/92/df/929ee0b5d2c8bd8d713c45e71b94ab57c7e11e322130724d54f469b2cd48/dockerfile-parse-2.0.1.tar.gz", hash = "sha256:3184ccdc513221983e503ac00e1aa504a2aa8f84e5de673c46b0b6eee99ec7bc", size = 24556, upload-time = "2023-07-18T13:36:07.897Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/7a/6c/79cd5bc1b880d8c1a9a5550aa8dacd57353fa3bb2457227e1fb47383eb49/dockerfile_parse-2.0.1-py2.py3-none-any.whl", hash = "sha256:bdffd126d2eb26acf1066acb54cb2e336682e1d72b974a40894fac76a4df17f6", size = 14845, upload-time = "2023-07-18T13:36:06.052Z" },
]
[[package]]
name = "docling"
version = "2.84.0"
@@ -2167,41 +2125,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b0/0d/9feae160378a3553fa9a339b0e9c1a048e147a4127210e286ef18b730f03/durationpy-0.10-py3-none-any.whl", hash = "sha256:3b41e1b601234296b4fb368338fdcd3e13e0b4fb5b67345948f4f2bf9868b286", size = 3922, upload-time = "2025-05-17T13:52:36.463Z" },
]
[[package]]
name = "e2b"
version = "2.20.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "attrs" },
{ name = "dockerfile-parse" },
{ name = "httpcore" },
{ name = "httpx" },
{ name = "packaging" },
{ name = "protobuf" },
{ name = "python-dateutil" },
{ name = "rich" },
{ name = "typing-extensions" },
{ name = "wcmatch" },
]
sdist = { url = "https://files.pythonhosted.org/packages/8c/87/e9b3bd252a4fe2b3fd6967ff985c7a5a15a31b2d5b8c37e50afb18797b17/e2b-2.20.0.tar.gz", hash = "sha256:52b3a00ac7015bbdce84913b2a57664d2def33d5a4069e34fa2354de31759173", size = 156575, upload-time = "2026-04-02T19:20:32.375Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/c2/ce/e402e2ecebe40ed9af20cddb862386f2ce20336e35c0dea257812129020e/e2b-2.20.0-py3-none-any.whl", hash = "sha256:66f6edcf6b742ca180f3aadcff7966fda86d68430fa6b2becdfa0fcc72224988", size = 296483, upload-time = "2026-04-02T19:20:30.573Z" },
]
[[package]]
name = "e2b-code-interpreter"
version = "2.6.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "attrs" },
{ name = "e2b" },
{ name = "httpx" },
]
sdist = { url = "https://files.pythonhosted.org/packages/cf/dd/f90b56d1597abfcdabdc018ac184fa714066be93d24b97edc2bf0671d483/e2b_code_interpreter-2.6.0.tar.gz", hash = "sha256:67e66531e5cf65c9df6e82aa0bdb1e73223a1ab205f10d47c027eb2ea09b73f9", size = 10683, upload-time = "2026-03-23T17:01:07.327Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/6b/79/f70d50604584df66064892f3fca7ab57b10ad40c826fd003be53a4cd5fa5/e2b_code_interpreter-2.6.0-py3-none-any.whl", hash = "sha256:a15f1d155566aef98cf2ccc0f8d9b07d15e07582d6cc8a128bc97de371bd617c", size = 13715, upload-time = "2026-03-23T17:01:06.111Z" },
]
[[package]]
name = "effdet"
version = "0.4.1"
@@ -3990,84 +3913,84 @@ wheels = [
[[package]]
name = "lxml"
version = "6.1.0"
version = "5.3.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/28/30/9abc9e34c657c33834eaf6cd02124c61bdf5944d802aa48e69be8da3585d/lxml-6.1.0.tar.gz", hash = "sha256:bfd57d8008c4965709a919c3e9a98f76c2c7cb319086b3d26858250620023b13", size = 4197006, upload-time = "2026-04-18T04:32:51.613Z" }
sdist = { url = "https://files.pythonhosted.org/packages/80/61/d3dc048cd6c7be6fe45b80cedcbdd4326ba4d550375f266d9f4246d0f4bc/lxml-5.3.2.tar.gz", hash = "sha256:773947d0ed809ddad824b7b14467e1a481b8976e87278ac4a730c2f7c7fcddc1", size = 3679948, upload-time = "2025-04-05T18:31:58.757Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/02/6e/ee8fc0e01202eb3dd2b9e1ea4f0910d72425d35c66187c63931d7a3ea73f/lxml-6.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:41dcc4c7b10484257cbd6c37b83ddb26df2b0e5aff5ac00d095689015af868ec", size = 8540733, upload-time = "2026-04-18T04:27:33.185Z" },
{ url = "https://files.pythonhosted.org/packages/54/e8/325fe9b942824c773dffe1baf0c35b046a763851fdff4393af4450bceeb7/lxml-6.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a31286dbb5e74c8e9a5344465b77ab4c5bd511a253b355b5ca2fae7e579fafec", size = 4602805, upload-time = "2026-04-18T04:27:36.097Z" },
{ url = "https://files.pythonhosted.org/packages/2d/81/221aa3ea4a40370bb0358fa454cbe7e5a837e522f7630c24dfef3f9a73b0/lxml-6.1.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1bc4cc83fb7f66ffb16f74d6dd0162e144333fc36ebcce32246f80c8735b2551", size = 5002652, upload-time = "2026-04-18T04:27:30.603Z" },
{ url = "https://files.pythonhosted.org/packages/c6/e1/fdbfb9019542f1875c093576df7f37adc2983c8ba7ecf17e5f14490bc107/lxml-6.1.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:20cf4d0651987c906a2f5cba4e3a8d6ba4bfdf973cfe2a96c0d6053888ea2ecd", size = 5155332, upload-time = "2026-04-18T04:27:33.507Z" },
{ url = "https://files.pythonhosted.org/packages/56/b1/4087c782fff397cd03abf9c551069be59bb04a7e548c50fb7b9c4cdaca28/lxml-6.1.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ffb34ea45a82dd637c2c97ae1bbb920850c1e59bcae79ce1c15af531d83e7215", size = 5057226, upload-time = "2026-04-18T04:27:37.567Z" },
{ url = "https://files.pythonhosted.org/packages/5d/66/516c79dec8417f3a972327330254c0b5fac93d5c3ecfd8a5b43650a5a4d9/lxml-6.1.0-cp310-cp310-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a1d9b99e5b2597e4f5aed2484fef835256fa1b68a19e4265c97628ef4bf8bcf4", size = 5287588, upload-time = "2026-04-18T04:27:41.4Z" },
{ url = "https://files.pythonhosted.org/packages/94/1d/e578f4cbeb42b9df9f29b0d44a45a7cdfa3a5ae300dd59ec68e3602d29bb/lxml-6.1.0-cp310-cp310-manylinux_2_28_i686.whl", hash = "sha256:d43aa26dcda363f21e79afa0668f5029ed7394b3bb8c92a6927a3d34e8b610ea", size = 5412438, upload-time = "2026-04-18T04:27:45.589Z" },
{ url = "https://files.pythonhosted.org/packages/47/5b/2aa68307d6d15959e84d4882f9c04f2da63127eac463e1594166f681ef77/lxml-6.1.0-cp310-cp310-manylinux_2_31_armv7l.whl", hash = "sha256:6262b87f9e5c1e5fe501d6c153247289af42eb44ad7660b9b3de17baaf92d6f6", size = 4770997, upload-time = "2026-04-18T04:27:49.853Z" },
{ url = "https://files.pythonhosted.org/packages/ae/c9/3e51fc1228310a836b4eb32595ae00154ab12197fca944676a3ab3b163ea/lxml-6.1.0-cp310-cp310-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d1392c569c032f78a11a25d1de1c43fff13294c793b39e19d84fade3045cbbc3", size = 5359678, upload-time = "2026-04-18T04:31:56.184Z" },
{ url = "https://files.pythonhosted.org/packages/b5/91/ab8bc834f977fbbd310e697b120787c153db026f9151e02a88d2645d4e5b/lxml-6.1.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:045e387d1f4f42a418380930fa3f45c73c9b392faf67e495e58902e68e8f44a7", size = 5107890, upload-time = "2026-04-18T04:32:00.387Z" },
{ url = "https://files.pythonhosted.org/packages/bb/10/8a143cfa3ac99cb5b0523ff6d0429a9c9dddf25ffeae09caa3866c7964d9/lxml-6.1.0-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:9f93d5b8b07f73e8c77e3c6556a3db269918390c804b5e5fcdd4858232cc8f16", size = 4803977, upload-time = "2026-04-18T04:32:05.099Z" },
{ url = "https://files.pythonhosted.org/packages/45/fd/ee02faf52fa39c2fe32f824628958b9aa86dff21343dc3161f0e3c6ccd15/lxml-6.1.0-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:de550d129f18d8ab819651ffe4f38b1b713c7e116707de3c0c6400d0ef34fbc1", size = 5350277, upload-time = "2026-04-18T04:32:09.176Z" },
{ url = "https://files.pythonhosted.org/packages/85/8c/b3481364b8554b5d36d540189a87fc71e94b0b01c24f8f152bd662dd2e45/lxml-6.1.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:c08da09dc003c9e8c70e06b53a11db6fb3b250c21c4236b03c7d7b443c318e7a", size = 5309717, upload-time = "2026-04-18T04:32:13.303Z" },
{ url = "https://files.pythonhosted.org/packages/74/e8/a6b21927077a9127afa17473b6576b322616f34ac50ee4f577e763b75ec0/lxml-6.1.0-cp310-cp310-win32.whl", hash = "sha256:37448bf9c7d7adfc5254763901e2bbd6bb876228dfc1fc7f66e58c06368a7544", size = 3598491, upload-time = "2026-04-18T04:27:24.288Z" },
{ url = "https://files.pythonhosted.org/packages/ea/82/14dea800d041274d96c07d49ff9191f011d1427450850de19bf541e2cc12/lxml-6.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:2593a0a6621545b9095b71ad74ed4226eba438a7d9fc3712a99bdb15508cf93a", size = 4020906, upload-time = "2026-04-18T04:27:27.53Z" },
{ url = "https://files.pythonhosted.org/packages/f2/ba/d3539aaf4d9d21456b9a7b902816623227d05d63e7c5aafd8834c4b9bed6/lxml-6.1.0-cp310-cp310-win_arm64.whl", hash = "sha256:e80807d72f96b96ad5588cb85c75616e4f2795a7737d4630784c51497beb7776", size = 3667787, upload-time = "2026-04-18T04:27:29.407Z" },
{ url = "https://files.pythonhosted.org/packages/5e/5d/3bccad330292946f97962df9d5f2d3ae129cce6e212732a781e856b91e07/lxml-6.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:cec05be8c876f92a5aa07b01d60bbb4d11cfbdd654cad0561c0d7b5c043a61b9", size = 8526232, upload-time = "2026-04-18T04:27:40.389Z" },
{ url = "https://files.pythonhosted.org/packages/a7/51/adc8826570a112f83bb4ddb3a2ab510bbc2ccd62c1b9fe1f34fae2d90b57/lxml-6.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9c03e048b6ce8e77b09c734e931584894ecd58d08296804ca2d0b184c933ce50", size = 4595448, upload-time = "2026-04-18T04:27:44.208Z" },
{ url = "https://files.pythonhosted.org/packages/54/84/5a9ec07cbe1d2334a6465f863b949a520d2699a755738986dcd3b6b89e3f/lxml-6.1.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:942454ff253da14218f972b23dc72fa4edf6c943f37edd19cd697618b626fac5", size = 4923771, upload-time = "2026-04-18T04:32:17.402Z" },
{ url = "https://files.pythonhosted.org/packages/a7/23/851cfa33b6b38adb628e45ad51fb27105fa34b2b3ba9d1d4aa7a9428dfe0/lxml-6.1.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d036ee7b99d5148072ac7c9b847193decdfeac633db350363f7bce4fff108f0e", size = 5068101, upload-time = "2026-04-18T04:32:21.437Z" },
{ url = "https://files.pythonhosted.org/packages/b0/38/41bf99c2023c6b79916ba057d83e9db21d642f473cac210201222882d38b/lxml-6.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3ae5d8d5427f3cc317e7950f2da7ad276df0cfa37b8de2f5658959e618ea8512", size = 5002573, upload-time = "2026-04-18T04:32:25.373Z" },
{ url = "https://files.pythonhosted.org/packages/c2/20/053aa10bdc39747e1e923ce2d45413075e84f70a136045bb09e5eaca41d3/lxml-6.1.0-cp311-cp311-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:363e47283bde87051b821826e71dde47f107e08614e1aa312ba0c5711e77738c", size = 5202816, upload-time = "2026-04-18T04:32:29.393Z" },
{ url = "https://files.pythonhosted.org/packages/9a/da/bc710fad8bf04b93baee752c192eaa2210cd3a84f969d0be7830fea55802/lxml-6.1.0-cp311-cp311-manylinux_2_28_i686.whl", hash = "sha256:f504d861d9f2a8f94020130adac88d66de93841707a23a86244263d1e54682f5", size = 5329999, upload-time = "2026-04-18T04:32:34.019Z" },
{ url = "https://files.pythonhosted.org/packages/b3/cb/bf035dedbdf7fab49411aa52e4236f3445e98d38647d85419e6c0d2806b9/lxml-6.1.0-cp311-cp311-manylinux_2_31_armv7l.whl", hash = "sha256:23a5dc68e08ed13331d61815c08f260f46b4a60fdd1640bbeb82cf89a9d90289", size = 4659643, upload-time = "2026-04-18T04:32:37.932Z" },
{ url = "https://files.pythonhosted.org/packages/5c/4f/22be31f33727a5e4c7b01b0a874503026e50329b259d3587e0b923cf964b/lxml-6.1.0-cp311-cp311-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f15401d8d3dbf239e23c818afc10c7207f7b95f9a307e092122b6f86dd43209a", size = 5265963, upload-time = "2026-04-18T04:32:41.881Z" },
{ url = "https://files.pythonhosted.org/packages/c8/2b/d44d0e5c79226017f4ab8c87a802ebe4f89f97e6585a8e4166dffcdd7b6e/lxml-6.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:fcf3da95e93349e0647d48d4b36a12783105bcc74cb0c416952f9988410846a3", size = 5045444, upload-time = "2026-04-18T04:32:44.512Z" },
{ url = "https://files.pythonhosted.org/packages/d3/c3/3f034fec1594c331a6dbf9491238fdcc9d66f68cc529e109ec75b97197e1/lxml-6.1.0-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:0d082495c5fcf426e425a6e28daaba1fcb6d8f854a4ff01effb1f1f381203eb9", size = 4712703, upload-time = "2026-04-18T04:32:47.16Z" },
{ url = "https://files.pythonhosted.org/packages/12/16/0b83fccc158218aca75a7aa33e97441df737950734246b9fffa39301603d/lxml-6.1.0-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:e3c4f84b24a1fcba435157d111c4b755099c6ff00a3daee1ad281817de75ed11", size = 5252745, upload-time = "2026-04-18T04:32:50.427Z" },
{ url = "https://files.pythonhosted.org/packages/dd/ee/12e6c1b39a77666c02eaa77f94a870aaf63c4ac3a497b2d52319448b01c6/lxml-6.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:976a6b39b1b13e8c354ad8d3f261f3a4ac6609518af91bdb5094760a08f132c4", size = 5226822, upload-time = "2026-04-18T04:32:53.437Z" },
{ url = "https://files.pythonhosted.org/packages/34/20/c7852904858b4723af01d2fc14b5d38ff57cb92f01934a127ebd9a9e51aa/lxml-6.1.0-cp311-cp311-win32.whl", hash = "sha256:857efde87d365706590847b916baff69c0bc9252dc5af030e378c9800c0b10e3", size = 3594026, upload-time = "2026-04-18T04:27:31.903Z" },
{ url = "https://files.pythonhosted.org/packages/02/05/d60c732b56da5085175c07c74b2df4e6d181b0c9a61e1691474f06ef4b39/lxml-6.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:183bfb45a493081943be7ea2b5adfc2b611e1cf377cefa8b8a8be404f45ef9a7", size = 4025114, upload-time = "2026-04-18T04:27:34.077Z" },
{ url = "https://files.pythonhosted.org/packages/c2/df/c84dcc175fd690823436d15b41cb920cd5ba5e14cd8bfb00949d5903b320/lxml-6.1.0-cp311-cp311-win_arm64.whl", hash = "sha256:19f4164243fc206d12ed3d866e80e74f5bc3627966520da1a5f97e42c32a3f39", size = 3667742, upload-time = "2026-04-18T04:27:38.45Z" },
{ url = "https://files.pythonhosted.org/packages/d2/d4/9326838b59dc36dfae42eec9656b97520f9997eee1de47b8316aaeed169c/lxml-6.1.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:d2f17a16cd8751e8eb233a7e41aecdf8e511712e00088bf9be455f604cd0d28d", size = 8570663, upload-time = "2026-04-18T04:27:48.253Z" },
{ url = "https://files.pythonhosted.org/packages/d8/a4/053745ce1f8303ccbb788b86c0db3a91b973675cefc42566a188637b7c40/lxml-6.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f0cea5b1d3e6e77d71bd2b9972eb2446221a69dc52bb0b9c3c6f6e5700592d93", size = 4624024, upload-time = "2026-04-18T04:27:52.594Z" },
{ url = "https://files.pythonhosted.org/packages/90/97/a517944b20f8fd0932ad2109482bee4e29fe721416387a363306667941f6/lxml-6.1.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fc46da94826188ed45cb53bd8e3fc076ae22675aea2087843d4735627f867c6d", size = 4930895, upload-time = "2026-04-18T04:32:56.29Z" },
{ url = "https://files.pythonhosted.org/packages/94/7c/e08a970727d556caa040a44773c7b7e3ad0f0d73dedc863543e9a8b931f2/lxml-6.1.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9147d8e386ec3b82c3b15d88927f734f565b0aaadef7def562b853adca45784a", size = 5093820, upload-time = "2026-04-18T04:32:58.94Z" },
{ url = "https://files.pythonhosted.org/packages/88/ee/2a5c2aa2c32016a226ca25d3e1056a8102ea6e1fe308bf50213586635400/lxml-6.1.0-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5715e0e28736a070f3f34a7ccc09e2fdcba0e3060abbcf61a1a5718ff6d6b105", size = 5005790, upload-time = "2026-04-18T04:33:01.272Z" },
{ url = "https://files.pythonhosted.org/packages/e3/38/a0db9be8f38ad6043ab9429487c128dd1d30f07956ef43040402f8da49e8/lxml-6.1.0-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4937460dc5df0cdd2f06a86c285c28afda06aefa3af949f9477d3e8df430c485", size = 5630827, upload-time = "2026-04-18T04:33:04.036Z" },
{ url = "https://files.pythonhosted.org/packages/31/ba/3c13d3fc24b7cacf675f808a3a1baabf43a30d0cd24c98f94548e9aa58eb/lxml-6.1.0-cp312-cp312-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bc783ee3147e60a25aa0445ea82b3e8aabb83b240f2b95d32cb75587ff781814", size = 5240445, upload-time = "2026-04-18T04:33:06.87Z" },
{ url = "https://files.pythonhosted.org/packages/55/ba/eeef4ccba09b2212fe239f46c1692a98db1878e0872ae320756488878a94/lxml-6.1.0-cp312-cp312-manylinux_2_28_i686.whl", hash = "sha256:40d9189f80075f2e1f88db21ef815a2b17b28adf8e50aaf5c789bfe737027f32", size = 5350121, upload-time = "2026-04-18T04:33:09.365Z" },
{ url = "https://files.pythonhosted.org/packages/7e/01/1da87c7b587c38d0cbe77a01aae3b9c1c49ed47d76918ef3db8fc151b1ca/lxml-6.1.0-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:05b9b8787e35bec69e68daf4952b2e6dfcfb0db7ecf1a06f8cdfbbac4eb71aad", size = 4694949, upload-time = "2026-04-18T04:33:11.628Z" },
{ url = "https://files.pythonhosted.org/packages/a1/88/7db0fe66d5aaf128443ee1623dec3db1576f3e4c17751ec0ef5866468590/lxml-6.1.0-cp312-cp312-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0f0f08beb0182e3e9a86fae124b3c47a7b41b7b69b225e1377db983802404e54", size = 5243901, upload-time = "2026-04-18T04:33:13.95Z" },
{ url = "https://files.pythonhosted.org/packages/00/a8/1346726af7d1f6fca1f11223ba34001462b0a3660416986d37641708d57c/lxml-6.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:73becf6d8c81d4c76b1014dbd3584cb26d904492dcf73ca85dc8bff08dcd6d2d", size = 5048054, upload-time = "2026-04-18T04:33:16.965Z" },
{ url = "https://files.pythonhosted.org/packages/2e/b7/85057012f035d1a0c87e02f8c723ca3c3e6e0728bcf4cb62080b21b1c1e3/lxml-6.1.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:1ae225f66e5938f4fa29d37e009a3bb3b13032ac57eb4eb42afa44f6e4054e69", size = 4777324, upload-time = "2026-04-18T04:33:19.832Z" },
{ url = "https://files.pythonhosted.org/packages/75/6c/ad2f94a91073ef570f33718040e8e160d5fb93331cf1ab3ca1323f939e2d/lxml-6.1.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:690022c7fae793b0489aa68a658822cea83e0d5933781811cabbf5ea3bcfe73d", size = 5645702, upload-time = "2026-04-18T04:33:22.436Z" },
{ url = "https://files.pythonhosted.org/packages/3b/89/0bb6c0bd549c19004c60eea9dc554dd78fd647b72314ef25d460e0d208c6/lxml-6.1.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:63aeafc26aac0be8aff14af7871249e87ea1319be92090bfd632ec68e03b16a5", size = 5232901, upload-time = "2026-04-18T04:33:26.21Z" },
{ url = "https://files.pythonhosted.org/packages/a1/d9/d609a11fb567da9399f525193e2b49847b5a409cdebe737f06a8b7126bdc/lxml-6.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:264c605ab9c0e4aa1a679636f4582c4d3313700009fac3ec9c3412ed0d8f3e1d", size = 5261333, upload-time = "2026-04-18T04:33:28.984Z" },
{ url = "https://files.pythonhosted.org/packages/a6/3a/ac3f99ec8ac93089e7dd556f279e0d14c24de0a74a507e143a2e4b496e7c/lxml-6.1.0-cp312-cp312-win32.whl", hash = "sha256:56971379bc5ee8037c5a0f09fa88f66cdb7d37c3e38af3e45cf539f41131ac1f", size = 3596289, upload-time = "2026-04-18T04:27:42.819Z" },
{ url = "https://files.pythonhosted.org/packages/f2/a7/0a915557538593cb1bbeedcd40e13c7a261822c26fecbbdb71dad0c2f540/lxml-6.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:bba078de0031c219e5dd06cf3e6bf8fb8e6e64a77819b358f53bb132e3e03366", size = 3997059, upload-time = "2026-04-18T04:27:46.764Z" },
{ url = "https://files.pythonhosted.org/packages/92/96/a5dc078cf0126fbfbc35611d77ecd5da80054b5893e28fb213a5613b9e1d/lxml-6.1.0-cp312-cp312-win_arm64.whl", hash = "sha256:c3592631e652afa34999a088f98ba7dfc7d6aff0d535c410bea77a71743f3819", size = 3659552, upload-time = "2026-04-18T04:27:51.133Z" },
{ url = "https://files.pythonhosted.org/packages/08/03/69347590f1cf4a6d5a4944bb6099e6d37f334784f16062234e1f892fdb1d/lxml-6.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:a0092f2b107b69601adf562a57c956fbb596e05e3e6651cabd3054113b007e45", size = 8559689, upload-time = "2026-04-18T04:31:57.785Z" },
{ url = "https://files.pythonhosted.org/packages/3f/58/25e00bb40b185c974cfe156c110474d9a8a8390d5f7c92a4e328189bb60e/lxml-6.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:fc7140d7a7386e6b545d41b7358f4d02b656d4053f5fa6859f92f4b9c2572c4d", size = 4617892, upload-time = "2026-04-18T04:32:01.78Z" },
{ url = "https://files.pythonhosted.org/packages/f5/54/92ad98a94ac318dc4f97aaac22ff8d1b94212b2ae8af5b6e9b354bf825f7/lxml-6.1.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:419c58fc92cc3a2c3fa5f78c63dbf5da70c1fa9c1b25f25727ecee89a96c7de2", size = 4923489, upload-time = "2026-04-18T04:33:31.401Z" },
{ url = "https://files.pythonhosted.org/packages/15/3b/a20aecfab42bdf4f9b390590d345857ad3ffd7c51988d1c89c53a0c73faf/lxml-6.1.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:37fabd1452852636cf38ecdcc9dd5ca4bba7a35d6c53fa09725deeb894a87491", size = 5082162, upload-time = "2026-04-18T04:33:34.262Z" },
{ url = "https://files.pythonhosted.org/packages/45/26/2cdb3d281ac1bd175603e290cbe4bad6eff127c0f8de90bafd6f8548f0fd/lxml-6.1.0-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a2853c8b2170cc6cd54a6b4d50d2c1a8a7aeca201f23804b4898525c7a152cfc", size = 4993247, upload-time = "2026-04-18T04:33:36.674Z" },
{ url = "https://files.pythonhosted.org/packages/f6/05/d735aef963740022a08185c84821f689fc903acb3d50326e6b1e9886cc22/lxml-6.1.0-cp313-cp313-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8e369cbd690e788c8d15e56222d91a09c6a417f49cbc543040cba0fe2e25a79e", size = 5613042, upload-time = "2026-04-18T04:33:39.205Z" },
{ url = "https://files.pythonhosted.org/packages/ee/b8/ead7c10efff731738c72e59ed6eb5791854879fbed7ae98781a12006263a/lxml-6.1.0-cp313-cp313-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e69aa6805905807186eb00e66c6d97a935c928275182eb02ee40ba00da9623b2", size = 5228304, upload-time = "2026-04-18T04:33:41.647Z" },
{ url = "https://files.pythonhosted.org/packages/6b/10/e9842d2ec322ea65f0a7270aa0315a53abed06058b88ef1b027f620e7a5f/lxml-6.1.0-cp313-cp313-manylinux_2_28_i686.whl", hash = "sha256:4bd1bdb8a9e0e2dd229de19b5f8aebac80e916921b4b2c6ef8a52bc131d0c1f9", size = 5341578, upload-time = "2026-04-18T04:33:44.596Z" },
{ url = "https://files.pythonhosted.org/packages/89/54/40d9403d7c2775fa7301d3ddd3464689bfe9ba71acc17dfff777071b4fdc/lxml-6.1.0-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:cbd7b79cdcb4986ad78a2662625882747f09db5e4cd7b2ae178a88c9c51b3dfe", size = 4700209, upload-time = "2026-04-18T04:33:47.552Z" },
{ url = "https://files.pythonhosted.org/packages/85/b2/bbdcc2cf45dfc7dfffef4fd97e5c47b15919b6a365247d95d6f684ef5e82/lxml-6.1.0-cp313-cp313-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:43e4d297f11080ec9d64a4b1ad7ac02b4484c9f0e2179d9c4ef78e886e747b88", size = 5232365, upload-time = "2026-04-18T04:33:50.249Z" },
{ url = "https://files.pythonhosted.org/packages/48/5a/b06875665e53aaba7127611a7bed3b7b9658e20b22bc2dd217a0b7ab0091/lxml-6.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:cc16682cc987a3da00aa56a3aa3075b08edb10d9b1e476938cfdbee8f3b67181", size = 5043654, upload-time = "2026-04-18T04:33:52.71Z" },
{ url = "https://files.pythonhosted.org/packages/e9/9c/e71a069d09641c1a7abeb30e693f828c7c90a41cbe3d650b2d734d876f85/lxml-6.1.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:d6d8efe71429635f0559579092bb5e60560d7b9115ee38c4adbea35632e7fa24", size = 4769326, upload-time = "2026-04-18T04:33:55.244Z" },
{ url = "https://files.pythonhosted.org/packages/cc/06/7a9cd84b3d4ed79adf35f874750abb697dec0b4a81a836037b36e47c091a/lxml-6.1.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7e39ab3a28af7784e206d8606ec0e4bcad0190f63a492bca95e94e5a4aef7f6e", size = 5635879, upload-time = "2026-04-18T04:33:58.509Z" },
{ url = "https://files.pythonhosted.org/packages/cc/f0/9d57916befc1e54c451712c7ee48e9e74e80ae4d03bdce49914e0aee42cd/lxml-6.1.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:9eb667bf50856c4a58145f8ca2d5e5be160191e79eb9e30855a476191b3c3495", size = 5224048, upload-time = "2026-04-18T04:34:00.943Z" },
{ url = "https://files.pythonhosted.org/packages/99/75/90c4eefda0c08c92221fe0753db2d6699a4c628f76ff4465ec20dea84cc1/lxml-6.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7f4a77d6f7edf9230cee3e1f7f6764722a41604ee5681844f18db9a81ea0ec33", size = 5250241, upload-time = "2026-04-18T04:34:03.365Z" },
{ url = "https://files.pythonhosted.org/packages/5e/73/16596f7e4e38fa33084b9ccbccc22a15f82a290a055126f2c1541236d2ff/lxml-6.1.0-cp313-cp313-win32.whl", hash = "sha256:28902146ffbe5222df411c5d19e5352490122e14447e98cd118907ee3fd6ee62", size = 3596938, upload-time = "2026-04-18T04:31:56.206Z" },
{ url = "https://files.pythonhosted.org/packages/8e/63/981401c5680c1eb30893f00a19641ac80db5d1e7086c62cb4b13ed813038/lxml-6.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:4a1503c56e4e2b38dc76f2f2da7bae69670c0f1933e27cfa34b2fa5876410b16", size = 3995728, upload-time = "2026-04-18T04:31:58.763Z" },
{ url = "https://files.pythonhosted.org/packages/e7/e8/c358a38ac3e541d16a1b527e4e9cb78c0419b0506a070ace11777e5e8404/lxml-6.1.0-cp313-cp313-win_arm64.whl", hash = "sha256:e0af85773850417d994d019741239b901b22c6680206f46a34766926e466141d", size = 3658372, upload-time = "2026-04-18T04:32:03.629Z" },
{ url = "https://files.pythonhosted.org/packages/f2/88/55143966481409b1740a3ac669e611055f49efd68087a5ce41582325db3e/lxml-6.1.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:546b66c0dd1bb8d9fa89d7123e5fa19a8aff3a1f2141eb22df96112afb17b842", size = 3930134, upload-time = "2026-04-18T04:32:35.008Z" },
{ url = "https://files.pythonhosted.org/packages/b5/97/28b985c2983938d3cb696dd5501423afb90a8c3e869ef5d3c62569282c0f/lxml-6.1.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5cfa1a34df366d9dc0d5eaf420f4cf2bb1e1bebe1066d1c2fc28c179f8a4004c", size = 4210749, upload-time = "2026-04-18T04:36:03.626Z" },
{ url = "https://files.pythonhosted.org/packages/29/67/dfab2b7d58214921935ccea7ce9b3df9b7d46f305d12f0f532ac7cf6b804/lxml-6.1.0-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:db88156fcf544cdbf0d95588051515cfdfd4c876fc66444eb98bceb5d6db76de", size = 4318463, upload-time = "2026-04-18T04:36:06.309Z" },
{ url = "https://files.pythonhosted.org/packages/32/a2/4ac7eb32a4d997dd352c32c32399aae27b3f268d440e6f9cfa405b575d2f/lxml-6.1.0-pp311-pypy311_pp73-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:07f98f5496f96bf724b1e3c933c107f0cbf2745db18c03d2e13a291c3afd2635", size = 4251124, upload-time = "2026-04-18T04:36:09.056Z" },
{ url = "https://files.pythonhosted.org/packages/33/ef/d6abd850bb4822f9b720cfe36b547a558e694881010ff7d012191e8769c6/lxml-6.1.0-pp311-pypy311_pp73-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4642e04449a1e164b5ff71ffd901ddb772dfabf5c9adf1b7be5dffe1212bc037", size = 4401758, upload-time = "2026-04-18T04:36:11.803Z" },
{ url = "https://files.pythonhosted.org/packages/40/44/3ee09a5b60cb44c4f2fbc1c9015cfd6ff5afc08f991cab295d3024dcbf2d/lxml-6.1.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:7da13bb6fbadfafb474e0226a30570a3445cfd47c86296f2446dafbd77079ace", size = 3508860, upload-time = "2026-04-18T04:32:48.619Z" },
{ url = "https://files.pythonhosted.org/packages/f7/9c/b015de0277a13d1d51924810b248b8a685a4e3dcd02d2ffb9b4e65cc37f4/lxml-5.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:c4b84d6b580a9625dfa47269bf1fd7fbba7ad69e08b16366a46acb005959c395", size = 8144077, upload-time = "2025-04-05T18:25:05.832Z" },
{ url = "https://files.pythonhosted.org/packages/a7/6a/30467f6b66ae666d20b52dffa98c00f0f15e0567d1333d70db7c44a6939e/lxml-5.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b4c08ecb26e4270a62f81f81899dfff91623d349e433b126931c9c4577169666", size = 4423433, upload-time = "2025-04-05T18:25:10.126Z" },
{ url = "https://files.pythonhosted.org/packages/12/85/5a50121c0b57c8aba1beec30d324dc9272a193ecd6c24ad1efb5e223a035/lxml-5.3.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ef926e9f11e307b5a7c97b17c5c609a93fb59ffa8337afac8f89e6fe54eb0b37", size = 5230753, upload-time = "2025-04-05T18:25:12.638Z" },
{ url = "https://files.pythonhosted.org/packages/81/07/a62896efbb74ff23e9d19a14713fb9c808dfd89d79eecb8a583d1ca722b1/lxml-5.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:017ceeabe739100379fe6ed38b033cd244ce2da4e7f6f07903421f57da3a19a2", size = 4945993, upload-time = "2025-04-05T18:25:15.63Z" },
{ url = "https://files.pythonhosted.org/packages/74/ca/c47bffbafcd98c53c2ccd26dcb29b2de8fa0585d5afae76e5c5a9dce5f96/lxml-5.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dae97d9435dc90590f119d056d233c33006b2fd235dd990d5564992261ee7ae8", size = 5562292, upload-time = "2025-04-05T18:25:18.744Z" },
{ url = "https://files.pythonhosted.org/packages/8f/79/f4ad46c00b72eb465be2032dad7922a14c929ae983e40cd9a179f1e727db/lxml-5.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:910f39425c6798ce63c93976ae5af5fff6949e2cb446acbd44d6d892103eaea8", size = 5000296, upload-time = "2025-04-05T18:25:21.268Z" },
{ url = "https://files.pythonhosted.org/packages/44/cb/c974078e015990f83d13ef00dac347d74b1d62c2e6ec6e8eeb40ec9a1f1a/lxml-5.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9780de781a0d62a7c3680d07963db3048b919fc9e3726d9cfd97296a65ffce1", size = 5114822, upload-time = "2025-04-05T18:25:24.401Z" },
{ url = "https://files.pythonhosted.org/packages/1b/c4/dde5d197d176f232c018e7dfd1acadf3aeb8e9f3effa73d13b62f9540061/lxml-5.3.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:1a06b0c6ba2e3ca45a009a78a4eb4d6b63831830c0a83dcdc495c13b9ca97d3e", size = 4941338, upload-time = "2025-04-05T18:25:27.402Z" },
{ url = "https://files.pythonhosted.org/packages/eb/8b/72f8df23f6955bb0f6aca635f72ec52799104907d6b11317099e79e1c752/lxml-5.3.2-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:4c62d0a34d1110769a1bbaf77871a4b711a6f59c4846064ccb78bc9735978644", size = 5586914, upload-time = "2025-04-05T18:25:30.604Z" },
{ url = "https://files.pythonhosted.org/packages/0f/93/7b5ff2971cc5cf017de8ef0e9fdfca6afd249b1e187cb8195e27ed40bb9a/lxml-5.3.2-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:8f961a4e82f411b14538fe5efc3e6b953e17f5e809c463f0756a0d0e8039b700", size = 5082388, upload-time = "2025-04-05T18:25:33.147Z" },
{ url = "https://files.pythonhosted.org/packages/a3/3e/f81d28bceb4e978a3d450098bdc5364d9c58473ad2f4ded04f679dc76e7e/lxml-5.3.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:3dfc78f5f9251b6b8ad37c47d4d0bfe63ceb073a916e5b50a3bf5fd67a703335", size = 5161925, upload-time = "2025-04-05T18:25:36.128Z" },
{ url = "https://files.pythonhosted.org/packages/4d/4b/1218fcfa0dfc8917ce29c66150cc8f6962d35579f412080aec480cc1a990/lxml-5.3.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:10e690bc03214d3537270c88e492b8612d5e41b884f232df2b069b25b09e6711", size = 5022096, upload-time = "2025-04-05T18:25:38.949Z" },
{ url = "https://files.pythonhosted.org/packages/8c/de/8eb6fffecd9c5f129461edcdd7e1ac944f9de15783e3d89c84ed6e0374bc/lxml-5.3.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:aa837e6ee9534de8d63bc4c1249e83882a7ac22bd24523f83fad68e6ffdf41ae", size = 5652903, upload-time = "2025-04-05T18:25:41.991Z" },
{ url = "https://files.pythonhosted.org/packages/95/79/80f4102a08495c100014593680f3f0f7bd7c1333b13520aed855fc993326/lxml-5.3.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:da4c9223319400b97a2acdfb10926b807e51b69eb7eb80aad4942c0516934858", size = 5491813, upload-time = "2025-04-05T18:25:44.983Z" },
{ url = "https://files.pythonhosted.org/packages/15/f5/9b1f7edf6565ee31e4300edb1bcc61eaebe50a3cff4053c0206d8dc772f2/lxml-5.3.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:dc0e9bdb3aa4d1de703a437576007d366b54f52c9897cae1a3716bb44fc1fc85", size = 5227837, upload-time = "2025-04-05T18:25:47.433Z" },
{ url = "https://files.pythonhosted.org/packages/dd/53/a187c4ccfcd5fbfca01e6c96da39499d8b801ab5dcf57717db95d7a968a8/lxml-5.3.2-cp310-cp310-win32.win32.whl", hash = "sha256:dd755a0a78dd0b2c43f972e7b51a43be518ebc130c9f1a7c4480cf08b4385486", size = 3477533, upload-time = "2025-04-18T06:15:35.546Z" },
{ url = "https://files.pythonhosted.org/packages/f2/2c/397c5a9d76a7a0faf9e5b13143ae1a7e223e71d2197a45da71c21aacb3d4/lxml-5.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:d64ea1686474074b38da13ae218d9fde0d1dc6525266976808f41ac98d9d7980", size = 3805160, upload-time = "2025-04-05T18:25:52.007Z" },
{ url = "https://files.pythonhosted.org/packages/84/b8/2b727f5a90902f7cc5548349f563b60911ca05f3b92e35dfa751349f265f/lxml-5.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9d61a7d0d208ace43986a92b111e035881c4ed45b1f5b7a270070acae8b0bfb4", size = 8163457, upload-time = "2025-04-05T18:25:55.176Z" },
{ url = "https://files.pythonhosted.org/packages/91/84/23135b2dc72b3440d68c8f39ace2bb00fe78e3a2255f7c74f7e76f22498e/lxml-5.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:856dfd7eda0b75c29ac80a31a6411ca12209183e866c33faf46e77ace3ce8a79", size = 4433445, upload-time = "2025-04-05T18:25:57.631Z" },
{ url = "https://files.pythonhosted.org/packages/c9/1c/6900ade2294488f80598af7b3229669562166384bb10bf4c915342a2f288/lxml-5.3.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7a01679e4aad0727bedd4c9407d4d65978e920f0200107ceeffd4b019bd48529", size = 5029603, upload-time = "2025-04-05T18:26:00.145Z" },
{ url = "https://files.pythonhosted.org/packages/2f/e9/31dbe5deaccf0d33ec279cf400306ad4b32dfd1a0fee1fca40c5e90678fe/lxml-5.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b6b37b4c3acb8472d191816d4582379f64d81cecbdce1a668601745c963ca5cc", size = 4771236, upload-time = "2025-04-05T18:26:02.656Z" },
{ url = "https://files.pythonhosted.org/packages/68/41/c3412392884130af3415af2e89a2007e00b2a782be6fb848a95b598a114c/lxml-5.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3df5a54e7b7c31755383f126d3a84e12a4e0333db4679462ef1165d702517477", size = 5369815, upload-time = "2025-04-05T18:26:05.842Z" },
{ url = "https://files.pythonhosted.org/packages/34/0a/ba0309fd5f990ea0cc05aba2bea225ef1bcb07ecbf6c323c6b119fc46e7f/lxml-5.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c09a40f28dcded933dc16217d6a092be0cc49ae25811d3b8e937c8060647c353", size = 4843663, upload-time = "2025-04-05T18:26:09.143Z" },
{ url = "https://files.pythonhosted.org/packages/b6/c6/663b5d87d51d00d4386a2d52742a62daa486c5dc6872a443409d9aeafece/lxml-5.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a1ef20f1851ccfbe6c5a04c67ec1ce49da16ba993fdbabdce87a92926e505412", size = 4918028, upload-time = "2025-04-05T18:26:12.243Z" },
{ url = "https://files.pythonhosted.org/packages/75/5f/f6a72ccbe05cf83341d4b6ad162ed9e1f1ffbd12f1c4b8bc8ae413392282/lxml-5.3.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:f79a63289dbaba964eb29ed3c103b7911f2dce28c36fe87c36a114e6bd21d7ad", size = 4792005, upload-time = "2025-04-05T18:26:15.081Z" },
{ url = "https://files.pythonhosted.org/packages/37/7b/8abd5b332252239ffd28df5842ee4e5bf56e1c613c323586c21ccf5af634/lxml-5.3.2-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:75a72697d95f27ae00e75086aed629f117e816387b74a2f2da6ef382b460b710", size = 5405363, upload-time = "2025-04-05T18:26:17.618Z" },
{ url = "https://files.pythonhosted.org/packages/5a/79/549b7ec92b8d9feb13869c1b385a0749d7ccfe5590d1e60f11add9cdd580/lxml-5.3.2-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:b9b00c9ee1cc3a76f1f16e94a23c344e0b6e5c10bec7f94cf2d820ce303b8c01", size = 4932915, upload-time = "2025-04-05T18:26:20.269Z" },
{ url = "https://files.pythonhosted.org/packages/57/eb/4fa626d0bac8b4f2aa1d0e6a86232db030fd0f462386daf339e4a0ee352b/lxml-5.3.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:77cbcab50cbe8c857c6ba5f37f9a3976499c60eada1bf6d38f88311373d7b4bc", size = 4983473, upload-time = "2025-04-05T18:26:23.828Z" },
{ url = "https://files.pythonhosted.org/packages/1b/c8/79d61d13cbb361c2c45fbe7c8bd00ea6a23b3e64bc506264d2856c60d702/lxml-5.3.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:29424058f072a24622a0a15357bca63d796954758248a72da6d512f9bd9a4493", size = 4855284, upload-time = "2025-04-05T18:26:26.504Z" },
{ url = "https://files.pythonhosted.org/packages/80/16/9f84e1ef03a13136ab4f9482c9adaaad425c68b47556b9d3192a782e5d37/lxml-5.3.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:7d82737a8afe69a7c80ef31d7626075cc7d6e2267f16bf68af2c764b45ed68ab", size = 5458355, upload-time = "2025-04-05T18:26:29.086Z" },
{ url = "https://files.pythonhosted.org/packages/aa/6d/f62860451bb4683e87636e49effb76d499773337928e53356c1712ccec24/lxml-5.3.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:95473d1d50a5d9fcdb9321fdc0ca6e1edc164dce4c7da13616247d27f3d21e31", size = 5300051, upload-time = "2025-04-05T18:26:31.723Z" },
{ url = "https://files.pythonhosted.org/packages/3f/5f/3b6c4acec17f9a57ea8bb89a658a70621db3fb86ea588e7703b6819d9b03/lxml-5.3.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:2162068f6da83613f8b2a32ca105e37a564afd0d7009b0b25834d47693ce3538", size = 5033481, upload-time = "2025-04-05T18:26:34.312Z" },
{ url = "https://files.pythonhosted.org/packages/79/bd/3c4dd7d903bb9981f4876c61ef2ff5d5473e409ef61dc7337ac207b91920/lxml-5.3.2-cp311-cp311-win32.whl", hash = "sha256:f8695752cf5d639b4e981afe6c99e060621362c416058effd5c704bede9cb5d1", size = 3474266, upload-time = "2025-04-05T18:26:36.545Z" },
{ url = "https://files.pythonhosted.org/packages/1f/ea/9311fa1ef75b7d601c89600fc612838ee77ad3d426184941cba9cf62641f/lxml-5.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:d1a94cbb4ee64af3ab386c2d63d6d9e9cf2e256ac0fd30f33ef0a3c88f575174", size = 3815230, upload-time = "2025-04-05T18:26:39.486Z" },
{ url = "https://files.pythonhosted.org/packages/0d/7e/c749257a7fabc712c4df57927b0f703507f316e9f2c7e3219f8f76d36145/lxml-5.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:16b3897691ec0316a1aa3c6585f61c8b7978475587c5b16fc1d2c28d283dc1b0", size = 8193212, upload-time = "2025-04-05T18:26:42.692Z" },
{ url = "https://files.pythonhosted.org/packages/a8/50/17e985ba162c9f1ca119f4445004b58f9e5ef559ded599b16755e9bfa260/lxml-5.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a8d4b34a0eeaf6e73169dcfd653c8d47f25f09d806c010daf074fba2db5e2d3f", size = 4451439, upload-time = "2025-04-05T18:26:46.468Z" },
{ url = "https://files.pythonhosted.org/packages/c2/b5/4960ba0fcca6ce394ed4a2f89ee13083e7fcbe9641a91166e8e9792fedb1/lxml-5.3.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9cd7a959396da425022e1e4214895b5cfe7de7035a043bcc2d11303792b67554", size = 5052146, upload-time = "2025-04-05T18:26:49.737Z" },
{ url = "https://files.pythonhosted.org/packages/5f/d1/184b04481a5d1f5758916de087430752a7b229bddbd6c1d23405078c72bd/lxml-5.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cac5eaeec3549c5df7f8f97a5a6db6963b91639389cdd735d5a806370847732b", size = 4789082, upload-time = "2025-04-05T18:26:52.295Z" },
{ url = "https://files.pythonhosted.org/packages/7d/75/1a19749d373e9a3d08861addccdf50c92b628c67074b22b8f3c61997cf5a/lxml-5.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:29b5f7d77334877c2146e7bb8b94e4df980325fab0a8af4d524e5d43cd6f789d", size = 5312300, upload-time = "2025-04-05T18:26:54.923Z" },
{ url = "https://files.pythonhosted.org/packages/fb/00/9d165d4060d3f347e63b219fcea5c6a3f9193e9e2868c6801e18e5379725/lxml-5.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:13f3495cfec24e3d63fffd342cc8141355d1d26ee766ad388775f5c8c5ec3932", size = 4836655, upload-time = "2025-04-05T18:26:57.488Z" },
{ url = "https://files.pythonhosted.org/packages/b8/e9/06720a33cc155966448a19677f079100517b6629a872382d22ebd25e48aa/lxml-5.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e70ad4c9658beeff99856926fd3ee5fde8b519b92c693f856007177c36eb2e30", size = 4961795, upload-time = "2025-04-05T18:27:00.126Z" },
{ url = "https://files.pythonhosted.org/packages/2d/57/4540efab2673de2904746b37ef7f74385329afd4643ed92abcc9ec6e00ca/lxml-5.3.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:507085365783abd7879fa0a6fa55eddf4bdd06591b17a2418403bb3aff8a267d", size = 4779791, upload-time = "2025-04-05T18:27:03.061Z" },
{ url = "https://files.pythonhosted.org/packages/99/ad/6056edf6c9f4fa1d41e6fbdae52c733a4a257fd0d7feccfa26ae051bb46f/lxml-5.3.2-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:5bb304f67cbf5dfa07edad904732782cbf693286b9cd85af27059c5779131050", size = 5346807, upload-time = "2025-04-05T18:27:05.877Z" },
{ url = "https://files.pythonhosted.org/packages/a1/fa/5be91fc91a18f3f705ea5533bc2210b25d738c6b615bf1c91e71a9b2f26b/lxml-5.3.2-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:3d84f5c093645c21c29a4e972b84cb7cf682f707f8706484a5a0c7ff13d7a988", size = 4909213, upload-time = "2025-04-05T18:27:08.588Z" },
{ url = "https://files.pythonhosted.org/packages/f3/74/71bb96a3b5ae36b74e0402f4fa319df5559a8538577f8c57c50f1b57dc15/lxml-5.3.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:bdc13911db524bd63f37b0103af014b7161427ada41f1b0b3c9b5b5a9c1ca927", size = 4987694, upload-time = "2025-04-05T18:27:11.66Z" },
{ url = "https://files.pythonhosted.org/packages/08/c2/3953a68b0861b2f97234b1838769269478ccf872d8ea7a26e911238220ad/lxml-5.3.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1ec944539543f66ebc060ae180d47e86aca0188bda9cbfadff47d86b0dc057dc", size = 4862865, upload-time = "2025-04-05T18:27:14.194Z" },
{ url = "https://files.pythonhosted.org/packages/e0/9a/52e48f7cfd5a5e61f44a77e679880580dfb4f077af52d6ed5dd97e3356fe/lxml-5.3.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:59d437cc8a7f838282df5a199cf26f97ef08f1c0fbec6e84bd6f5cc2b7913f6e", size = 5423383, upload-time = "2025-04-05T18:27:16.988Z" },
{ url = "https://files.pythonhosted.org/packages/17/67/42fe1d489e4dcc0b264bef361aef0b929fbb2b5378702471a3043bc6982c/lxml-5.3.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0e275961adbd32e15672e14e0cc976a982075208224ce06d149c92cb43db5b93", size = 5286864, upload-time = "2025-04-05T18:27:19.703Z" },
{ url = "https://files.pythonhosted.org/packages/29/e4/03b1d040ee3aaf2bd4e1c2061de2eae1178fe9a460d3efc1ea7ef66f6011/lxml-5.3.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:038aeb6937aa404480c2966b7f26f1440a14005cb0702078c173c028eca72c31", size = 5056819, upload-time = "2025-04-05T18:27:22.814Z" },
{ url = "https://files.pythonhosted.org/packages/83/b3/e2ec8a6378e4d87da3af9de7c862bcea7ca624fc1a74b794180c82e30123/lxml-5.3.2-cp312-cp312-win32.whl", hash = "sha256:3c2c8d0fa3277147bff180e3590be67597e17d365ce94beb2efa3138a2131f71", size = 3486177, upload-time = "2025-04-05T18:27:25.078Z" },
{ url = "https://files.pythonhosted.org/packages/d5/8a/6a08254b0bab2da9573735725caab8302a2a1c9b3818533b41568ca489be/lxml-5.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:77809fcd97dfda3f399102db1794f7280737b69830cd5c961ac87b3c5c05662d", size = 3817134, upload-time = "2025-04-05T18:27:27.481Z" },
{ url = "https://files.pythonhosted.org/packages/19/fe/904fd1b0ba4f42ed5a144fcfff7b8913181892a6aa7aeb361ee783d441f8/lxml-5.3.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:77626571fb5270ceb36134765f25b665b896243529eefe840974269b083e090d", size = 8173598, upload-time = "2025-04-05T18:27:31.229Z" },
{ url = "https://files.pythonhosted.org/packages/97/e8/5e332877b3ce4e2840507b35d6dbe1cc33b17678ece945ba48d2962f8c06/lxml-5.3.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:78a533375dc7aa16d0da44af3cf6e96035e484c8c6b2b2445541a5d4d3d289ee", size = 4441586, upload-time = "2025-04-05T18:27:33.883Z" },
{ url = "https://files.pythonhosted.org/packages/de/f4/8fe2e6d8721803182fbce2325712e98f22dbc478126070e62731ec6d54a0/lxml-5.3.2-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a6f62b2404b3f3f0744bbcabb0381c5fe186fa2a9a67ecca3603480f4846c585", size = 5038447, upload-time = "2025-04-05T18:27:36.426Z" },
{ url = "https://files.pythonhosted.org/packages/a6/ac/fa63f86a1a4b1ba8b03599ad9e2f5212fa813223ac60bfe1155390d1cc0c/lxml-5.3.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2ea918da00091194526d40c30c4996971f09dacab032607581f8d8872db34fbf", size = 4783583, upload-time = "2025-04-05T18:27:39.492Z" },
{ url = "https://files.pythonhosted.org/packages/1a/7a/08898541296a02c868d4acc11f31a5839d80f5b21d4a96f11d4c0fbed15e/lxml-5.3.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c35326f94702a7264aa0eea826a79547d3396a41ae87a70511b9f6e9667ad31c", size = 5305684, upload-time = "2025-04-05T18:27:42.16Z" },
{ url = "https://files.pythonhosted.org/packages/0b/be/9a6d80b467771b90be762b968985d3de09e0d5886092238da65dac9c1f75/lxml-5.3.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e3bef90af21d31c4544bc917f51e04f94ae11b43156356aff243cdd84802cbf2", size = 4830797, upload-time = "2025-04-05T18:27:45.071Z" },
{ url = "https://files.pythonhosted.org/packages/8d/1c/493632959f83519802637f7db3be0113b6e8a4e501b31411fbf410735a75/lxml-5.3.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52fa7ba11a495b7cbce51573c73f638f1dcff7b3ee23697467dc063f75352a69", size = 4950302, upload-time = "2025-04-05T18:27:47.979Z" },
{ url = "https://files.pythonhosted.org/packages/c7/13/01aa3b92a6b93253b90c061c7527261b792f5ae7724b420cded733bfd5d6/lxml-5.3.2-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:ad131e2c4d2c3803e736bb69063382334e03648de2a6b8f56a878d700d4b557d", size = 4775247, upload-time = "2025-04-05T18:27:51.174Z" },
{ url = "https://files.pythonhosted.org/packages/60/4a/baeb09fbf5c84809e119c9cf8e2e94acec326a9b45563bf5ae45a234973b/lxml-5.3.2-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:00a4463ca409ceacd20490a893a7e08deec7870840eff33dc3093067b559ce3e", size = 5338824, upload-time = "2025-04-05T18:27:54.15Z" },
{ url = "https://files.pythonhosted.org/packages/69/c7/a05850f169ad783ed09740ac895e158b06d25fce4b13887a8ac92a84d61c/lxml-5.3.2-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:87e8d78205331cace2b73ac8249294c24ae3cba98220687b5b8ec5971a2267f1", size = 4899079, upload-time = "2025-04-05T18:27:57.03Z" },
{ url = "https://files.pythonhosted.org/packages/de/48/18ca583aba5235582db0e933ed1af6540226ee9ca16c2ee2d6f504fcc34a/lxml-5.3.2-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:bf6389133bb255e530a4f2f553f41c4dd795b1fbb6f797aea1eff308f1e11606", size = 4978041, upload-time = "2025-04-05T18:27:59.918Z" },
{ url = "https://files.pythonhosted.org/packages/b6/55/6968ddc88554209d1dba0dca196360c629b3dfe083bc32a3370f9523a0c4/lxml-5.3.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:b3709fc752b42fb6b6ffa2ba0a5b9871646d97d011d8f08f4d5b3ee61c7f3b2b", size = 4859761, upload-time = "2025-04-05T18:28:02.83Z" },
{ url = "https://files.pythonhosted.org/packages/2e/52/d2d3baa1e0b7d04a729613160f1562f466fb1a0e45085a33acb0d6981a2b/lxml-5.3.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:abc795703d0de5d83943a4badd770fbe3d1ca16ee4ff3783d7caffc252f309ae", size = 5418209, upload-time = "2025-04-05T18:28:05.851Z" },
{ url = "https://files.pythonhosted.org/packages/d3/50/6005b297ba5f858a113d6e81ccdb3a558b95a615772e7412d1f1cbdf22d7/lxml-5.3.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:98050830bb6510159f65d9ad1b8aca27f07c01bb3884ba95f17319ccedc4bcf9", size = 5274231, upload-time = "2025-04-05T18:28:08.849Z" },
{ url = "https://files.pythonhosted.org/packages/fb/33/6f40c09a5f7d7e7fcb85ef75072e53eba3fbadbf23e4991ca069ab2b1abb/lxml-5.3.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6ba465a91acc419c5682f8b06bcc84a424a7aa5c91c220241c6fd31de2a72bc6", size = 5051899, upload-time = "2025-04-05T18:28:11.729Z" },
{ url = "https://files.pythonhosted.org/packages/8b/3a/673bc5c0d5fb6596ee2963dd016fdaefaed2c57ede82c7634c08cbda86c1/lxml-5.3.2-cp313-cp313-win32.whl", hash = "sha256:56a1d56d60ea1ec940f949d7a309e0bff05243f9bd337f585721605670abb1c1", size = 3485315, upload-time = "2025-04-05T18:28:14.815Z" },
{ url = "https://files.pythonhosted.org/packages/8c/be/cab8dd33b0dbe3af5b5d4d24137218f79ea75d540f74eb7d8581195639e0/lxml-5.3.2-cp313-cp313-win_amd64.whl", hash = "sha256:1a580dc232c33d2ad87d02c8a3069d47abbcdce974b9c9cc82a79ff603065dbe", size = 3814639, upload-time = "2025-04-05T18:28:17.268Z" },
{ url = "https://files.pythonhosted.org/packages/3d/1a/480682ac974e0f8778503300a61d96c3b4d992d2ae024f9db18d5fd895d1/lxml-5.3.2-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:521ab9c80b98c30b2d987001c3ede2e647e92eeb2ca02e8cb66ef5122d792b24", size = 3937182, upload-time = "2025-04-05T18:30:39.214Z" },
{ url = "https://files.pythonhosted.org/packages/74/e6/ac87269713e372b58c4334913601a65d7a6f3b7df9ac15a4a4014afea7ae/lxml-5.3.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f1231b0f9810289d41df1eacc4ebb859c63e4ceee29908a0217403cddce38d0", size = 4235148, upload-time = "2025-04-05T18:30:42.261Z" },
{ url = "https://files.pythonhosted.org/packages/75/ec/7d7af58047862fb59fcdec6e3abcffc7a98f7f7560e580485169ce28b706/lxml-5.3.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:271f1a4d5d2b383c36ad8b9b489da5ea9c04eca795a215bae61ed6a57cf083cd", size = 4349974, upload-time = "2025-04-05T18:30:45.291Z" },
{ url = "https://files.pythonhosted.org/packages/ff/de/021ef34a57a372778f44182d2043fa3cae0b0407ac05fc35834f842586f2/lxml-5.3.2-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:6fca8a5a13906ba2677a5252752832beb0f483a22f6c86c71a2bb320fba04f61", size = 4238656, upload-time = "2025-04-05T18:30:48.383Z" },
{ url = "https://files.pythonhosted.org/packages/0a/96/00874cb83ebb2cf649f2a8cad191d8da64fe1cf15e6580d5a7967755d6a3/lxml-5.3.2-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ea0c3b7922209160faef194a5b6995bfe7fa05ff7dda6c423ba17646b7b9de10", size = 4373836, upload-time = "2025-04-05T18:30:52.189Z" },
{ url = "https://files.pythonhosted.org/packages/6b/40/7d49ff503cc90b03253eba0768feec909b47ce92a90591b025c774a29a95/lxml-5.3.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:0a006390834603e5952a2ff74b9a31a6007c7cc74282a087aa6467afb4eea987", size = 3487898, upload-time = "2025-04-05T18:30:55.122Z" },
]
[[package]]
@@ -4502,32 +4425,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c", size = 536198, upload-time = "2023-03-07T16:47:09.197Z" },
]
[[package]]
name = "msal"
version = "1.36.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "cryptography" },
{ name = "pyjwt", extra = ["crypto"] },
{ name = "requests" },
]
sdist = { url = "https://files.pythonhosted.org/packages/de/cb/b02b0f748ac668922364ccb3c3bff5b71628a05f5adfec2ba2a5c3031483/msal-1.36.0.tar.gz", hash = "sha256:3f6a4af2b036b476a4215111c4297b4e6e236ed186cd804faefba23e4990978b", size = 174217, upload-time = "2026-04-09T10:20:33.525Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/2a/d3/414d1f0a5f6f4fe5313c2b002c54e78a3332970feb3f5fed14237aa17064/msal-1.36.0-py3-none-any.whl", hash = "sha256:36ecac30e2ff4322d956029aabce3c82301c29f0acb1ad89b94edcabb0e58ec4", size = 121547, upload-time = "2026-04-09T10:20:32.336Z" },
]
[[package]]
name = "msal-extensions"
version = "1.3.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "msal" },
]
sdist = { url = "https://files.pythonhosted.org/packages/01/99/5d239b6156eddf761a636bded1118414d161bd6b7b37a9335549ed159396/msal_extensions-1.3.1.tar.gz", hash = "sha256:c5b0fd10f65ef62b5f1d62f4251d51cbcaf003fcedae8c91b040a488614be1a4", size = 23315, upload-time = "2025-03-14T23:51:03.902Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/5e/75/bd9b7bb966668920f06b200e84454c8f3566b102183bc55c5473d96cb2b9/msal_extensions-1.3.1-py3-none-any.whl", hash = "sha256:96d3de4d034504e969ac5e85bae8106c8373b5c6568e4c8fa7af2eca9dbe6bca", size = 20583, upload-time = "2025-03-14T23:51:03.016Z" },
]
[[package]]
name = "msgpack"
version = "1.1.2"
@@ -9510,18 +9407,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/6e/d4/ed38dd3b1767193de971e694aa544356e63353c33a85d948166b5ff58b9e/watchfiles-1.1.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e6f39af2eab0118338902798b5aa6664f46ff66bc0280de76fca67a7f262a49", size = 457546, upload-time = "2025-10-14T15:06:13.372Z" },
]
[[package]]
name = "wcmatch"
version = "10.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "bracex" },
]
sdist = { url = "https://files.pythonhosted.org/packages/79/3e/c0bdc27cf06f4e47680bd5803a07cb3dfd17de84cde92dd217dcb9e05253/wcmatch-10.1.tar.gz", hash = "sha256:f11f94208c8c8484a16f4f48638a85d771d9513f4ab3f37595978801cb9465af", size = 117421, upload-time = "2025-06-22T19:14:02.49Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/eb/d8/0d1d2e9d3fabcf5d6840362adcf05f8cf3cd06a73358140c3a97189238ae/wcmatch-10.1-py3-none-any.whl", hash = "sha256:5848ace7dbb0476e5e55ab63c6bbd529745089343427caa5537f230cc01beb8a", size = 39854, upload-time = "2025-06-22T19:14:00.978Z" },
]
[[package]]
name = "wcwidth"
version = "0.6.0"