Merge branch 'main' into docs/checkpointing-restructure

Move scope restoration from Crew-level global push to a per-task push
inside Task via resume_task_scope() in event_context. Fixes orphan
task_started warning, hierarchical resume (manager_agent now eligible
for _resuming), and parallel async resume (each contextvars copy owns
its own scope). Tests added.

.github/workflows/build-uv-cache.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Install uv
         uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
@@ -39,7 +39,7 @@ jobs:
           echo "Cache populated successfully"
 
       - name: Save uv caches
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

.github/workflows/codeql.yml

@@ -59,7 +59,7 @@ jobs:
         # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
     # Add any setup steps before running the `github/codeql-action/init` action.
     # This includes steps like installing compilers or runtimes (`actions/setup-node`
@@ -69,7 +69,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v4
+      uses: github/codeql-action/init@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4.35.5
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -98,6 +98,6 @@ jobs:
         exit 1
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v4
+      uses: github/codeql-action/analyze@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4.35.5
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/docs-broken-links.yml

@@ -18,10 +18,10 @@ jobs:
     name: Check broken links
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Set up Node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: "22"
 

.github/workflows/generate-tool-specs.yml

@@ -28,7 +28,7 @@ jobs:
           private-key: ${{ secrets.CREWAI_TOOL_SPECS_PRIVATE_KEY }}
 
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
         with:
           ref: ${{ github.head_ref }}
           token: ${{ steps.app-token.outputs.token }}

.github/workflows/linter.yml

@@ -12,7 +12,7 @@ jobs:
     outputs:
       code: ${{ steps.filter.outputs.code }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
       - uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
         id: filter
         with:
@@ -26,11 +26,11 @@ jobs:
     if: needs.changes.outputs.code == 'true'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Restore global uv cache
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv
@@ -58,7 +58,7 @@ jobs:
 
       - name: Save uv caches
         if: steps.cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

.github/workflows/nightly.yml

@@ -18,7 +18,7 @@ jobs:
     outputs:
       has_changes: ${{ steps.check.outputs.has_changes }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
         with:
           fetch-depth: 0
 
@@ -41,7 +41,7 @@ jobs:
     permissions:
       contents: read
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Install uv
         uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
@@ -87,7 +87,7 @@ jobs:
           rm dist/.gitignore
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: dist
           path: dist/
@@ -110,7 +110,7 @@ jobs:
           enable-cache: false
 
       - name: Download artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: dist
           path: dist

.github/workflows/publish.yml

@@ -24,12 +24,12 @@ jobs:
             echo "tag=" >> $GITHUB_OUTPUT
           fi
 
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
         with:
           ref: ${{ steps.release.outputs.tag || github.ref }}
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
@@ -42,7 +42,7 @@ jobs:
           rm dist/.gitignore
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: dist
           path: dist/
@@ -58,7 +58,7 @@ jobs:
       id-token: write
       contents: read
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
         with:
           ref: ${{ inputs.release_tag || github.ref }}
 
@@ -70,7 +70,7 @@ jobs:
           enable-cache: false
 
       - name: Download artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: dist
           path: dist

.github/workflows/stale.yml

@@ -14,7 +14,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/stale@v9
+    - uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9.1.0
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-label: 'no-issue-activity'

.github/workflows/tests.yml

@@ -12,7 +12,7 @@ jobs:
     outputs:
       code: ${{ steps.filter.outputs.code }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
       - uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
         id: filter
         with:
@@ -34,13 +34,13 @@ jobs:
         group: [1, 2, 3, 4, 5, 6, 7, 8]
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
         with:
           fetch-depth: 0  # Fetch all history for proper diff
 
       - name: Restore global uv cache
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv
@@ -61,7 +61,7 @@ jobs:
         run: uv sync --all-groups --all-extras
 
       - name: Restore test durations
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: .test_durations_py*
           key: test-durations-py${{ matrix.python-version }}
@@ -108,7 +108,7 @@ jobs:
 
       - name: Save uv caches
         if: steps.cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

.github/workflows/type-checker.yml

@@ -12,7 +12,7 @@ jobs:
     outputs:
       code: ${{ steps.filter.outputs.code }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
       - uses: dorny/paths-filter@d1c1ffe0248fe513906c8e24db8ea791d46f8590 # v3
         id: filter
         with:
@@ -33,11 +33,11 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Restore global uv cache
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv
@@ -62,7 +62,7 @@ jobs:
 
       - name: Save uv caches
         if: steps.cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

.github/workflows/update-test-durations.yml

@@ -23,11 +23,11 @@ jobs:
     
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
 
       - name: Restore global uv cache
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv
@@ -55,14 +55,14 @@ jobs:
 
       - name: Save durations to cache
         if: always()
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: .test_durations_py*
           key: test-durations-py${{ matrix.python-version }}
 
       - name: Save uv caches
         if: steps.cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

.github/workflows/vulnerability-scan.yml

@@ -16,11 +16,13 @@ jobs:
     name: pip-audit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
+        with:
+          persist-credentials: false
 
       - name: Restore global uv cache
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv
@@ -110,14 +112,14 @@ jobs:
 
       - name: Upload pip-audit report
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: pip-audit-report
           path: pip-audit-report.json
 
       - name: Save uv caches
         if: steps.cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
             ~/.cache/uv

docs/ar/concepts/checkpointing.mdx

@@ -5,225 +5,386 @@ icon: floppy-disk
 mode: "wide"
 ---
 
-<Warning>
-الـ Checkpointing في اصدار مبكر. قد تتغير واجهات البرمجة في الاصدارات المستقبلية.
-</Warning>
+الـ Checkpointing يحفظ لقطة من حالة التنفيذ أثناء التشغيل بحيث يمكن لطاقم أو تدفق أو وكيل الاستئناف بعد الفشل أو التفرع إلى فرع بديل.
 
-## نظرة عامة
+<CardGroup cols={2}>
+  <Card title="الشرح" icon="lightbulb" href="#الشرح">
+    كيف يعمل الـ Checkpointing: الأحداث والتخزين والوراثة.
+  </Card>
+  <Card title="درس تطبيقي" icon="graduation-cap" href="#درس-تطبيقي-استئناف-طاقم-فاشل">
+    دليل 5 دقائق: تشغيل، إيقاف، استئناف.
+  </Card>
+  <Card title="ادلة عملية" icon="screwdriver-wrench" href="#ادلة-عملية">
+    وصفات مركزة على المهام لسير العمل الشائع.
+  </Card>
+  <Card title="المرجع" icon="book" href="#المرجع">
+    `CheckpointConfig` والأحداث والمزودات وسطر الأوامر.
+  </Card>
+</CardGroup>
 
-يقوم الـ Checkpointing بحفظ حالة التنفيذ تلقائيا اثناء التشغيل. اذا فشل طاقم او تدفق او وكيل اثناء التنفيذ، يمكنك الاستعادة من اخر نقطة حفظ والاستئناف دون اعادة تنفيذ العمل المكتمل.
+## الشرح
 
-## البداية السريعة
+### ما هي نقطة الحفظ
 
-```python
-from crewai import Crew, CheckpointConfig
+تلتقط نقطة الحفظ كل ما يحتاجه CrewAI لإعادة إنشاء تشغيل أثناء سيره: الحالة الكاملة للطاقم أو التدفق أو الوكيل — التكوين، وذاكرة الوكلاء ومصادر المعرفة، وتقدم المهام، والمخرجات الوسيطة — إلى جانب مدخلات الـ kickoff، وسجل الأحداث حتى تلك النقطة، ومعرف نسب يربط نقطة الحفظ بالتشغيل الذي جاءت منه.
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=True,  # يستخدم الافتراضيات: ./.checkpoints, عند task_completed
-)
-result = crew.kickoff()
-```
+الاستعادة تعيد بناء تلك الحالة وتستمر. تتخطى المهام المكتملة، وتعاد ترطيب الذاكرة والمعرفة، ويعمل العمل التابع على نفس المخرجات التي أنتجها التشغيل الأصلي. التفرع يجري نفس الاستعادة تحت نسب جديد، بحيث يكتب الفرع الجديد والتشغيل الأصلي نقاط الحفظ جنبا إلى جنب دون أن يطمس أحدهما الآخر.
 
-تتم كتابة ملفات نقاط الحفظ في `./.checkpoints/` بعد اكتمال كل مهمة.
+### متى تكتب نقاط الحفظ
 
-## التكوين
+الـ Checkpointing مدفوع بالأحداث. يشترك وقت التشغيل في الأحداث التي تحددها عبر `on_events` ويكتب نقطة حفظ عند إطلاق أحدها. الافتراضي `task_completed` ينتج نقطة حفظ لكل مهمة منتهية — توازن معقول بين الدقة واستخدام القرص. الأحداث عالية التردد مثل `llm_call_completed` متاحة للاستعادة الدقيقة لكنها تكتب ملفات أكثر بكثير.
 
-استخدم `CheckpointConfig` للتحكم الكامل:
+### التخزين
 
-```python
-from crewai import Crew, CheckpointConfig
+يتضمن CrewAI مزودين:
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        on_events=["task_completed", "crew_kickoff_completed"],
-        max_checkpoints=5,
-    ),
-)
-```
+- `JsonProvider` يكتب ملفا لكل نقطة حفظ. قابل للقراءة وسهل التفقد.
+- `SqliteProvider` يكتب إلى قاعدة بيانات SQLite واحدة. أفضل لنقاط الحفظ عالية التردد.
 
-### حقول CheckpointConfig
+كلاهما يحذف أقدم نقاط الحفظ عند تحديد `max_checkpoints`.
 
-| الحقل | النوع | الافتراضي | الوصف |
-|:------|:------|:----------|:------|
-| `location` | `str` | `"./.checkpoints"` | مسار ملفات نقاط الحفظ |
-| `on_events` | `list[str]` | `["task_completed"]` | انواع الاحداث التي تطلق نقطة حفظ |
-| `provider` | `BaseProvider` | `JsonProvider()` | واجهة التخزين |
-| `max_checkpoints` | `int \| None` | `None` | الحد الاقصى للملفات؛ يتم حذف الاقدم اولا |
+<Note>
+كتابة نقاط الحفظ بأفضل جهد. فشل نقطة حفظ يسجل لكنه لا يقاطع التشغيل.
+</Note>
 
-### الوراثة والانسحاب
+### نموذج الوراثة
 
-يقبل حقل `checkpoint` في Crew و Flow و Agent قيم `CheckpointConfig` او `True` او `False` او `None`:
+`Crew` و`Flow` و`Agent` كلها تقبل وسيط `checkpoint`. يرث الأبناء من الأب ما لم يحددوا قيمتهم الخاصة أو يمرروا `False` للانسحاب. فعل الـ Checkpointing مرة واحدة على الطاقم وتشارك كل الوكلاء، أو استبعد وكيلا واحدا بشكل انتقائي.
 
-| القيمة | السلوك |
-|:-------|:-------|
-| `None` (افتراضي) | يرث من الاصل. الوكيل يرث اعدادات الطاقم. |
-| `True` | تفعيل بالاعدادات الافتراضية. |
-| `False` | انسحاب صريح. يوقف الوراثة من الاصل. |
-| `CheckpointConfig(...)` | اعدادات مخصصة. |
+## درس تطبيقي: استئناف طاقم فاشل
 
-```python
-crew = Crew(
-    agents=[
-        Agent(role="Researcher", ...),                  # يرث checkpoint من الطاقم
-        Agent(role="Writer", ..., checkpoint=False),     # منسحب، بدون نقاط حفظ
-    ],
-    tasks=[...],
-    checkpoint=True,
-)
-```
+هذا الدليل يستغرق حوالي 5 دقائق. ستشغل طاقما بمهمتين، توقفه في المنتصف، ثم تستأنف من نقطة الحفظ المحفوظة.
 
-## الاستئناف من نقطة حفظ
+<Steps>
+  <Step title="أنشئ الطاقم مع تفعيل الـ Checkpointing">
+    ```python
+    from crewai import Agent, Crew, Task
 
-```python
-# استعادة واستئناف
-crew = Crew.from_checkpoint("./my_checkpoints/20260407T120000_abc123.json")
-result = crew.kickoff()  # يستأنف من اخر مهمة مكتملة
-```
+    researcher = Agent(role="Researcher", goal="Research", backstory="Expert")
+    writer = Agent(role="Writer", goal="Write", backstory="Expert")
 
-يتخطى الطاقم المستعاد المهام المكتملة ويستأنف من اول مهمة غير مكتملة.
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[
+            Task(description="Research AI trends", agent=researcher, expected_output="bullets"),
+            Task(description="Write a summary", agent=writer, expected_output="paragraph"),
+        ],
+        checkpoint=True,
+    )
+    ```
+  </Step>
+  <Step title="شغله وأوقفه بعد المهمة الأولى">
+    ```python
+    result = crew.kickoff()
+    ```
 
-## يعمل على Crew و Flow و Agent
+    اضغط `Ctrl+C` بعد انتهاء المهمة الأولى. في `./.checkpoints/`، الملف بصيغة `<timestamp>_<uuid>.json` هو نقطة الحفظ.
+  </Step>
+  <Step title="استأنف من نقطة الحفظ">
+    ```python
+    from crewai import CheckpointConfig
 
-### Crew
+    result = crew.kickoff(
+        from_checkpoint=CheckpointConfig(
+            restore_from="./.checkpoints/<timestamp>_<uuid>.json",
+        ),
+    )
+    ```
 
-```python
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[research_task, write_task, review_task],
-    checkpoint=CheckpointConfig(location="./crew_cp"),
-)
-```
+    يتم تخطي مهمة البحث، ويعمل الكاتب على مخرجات البحث المحفوظة، وينتهي الطاقم.
+  </Step>
+</Steps>
 
-المشغل الافتراضي: `task_completed` (نقطة حفظ واحدة لكل مهمة مكتملة).
+## ادلة عملية
 
-### Flow
+<AccordionGroup>
+  <Accordion title="تفعيل الـ Checkpointing بالإعدادات الافتراضية" icon="play">
+    ```python
+    crew = Crew(agents=[...], tasks=[...], checkpoint=True)
+    ```
 
-```python
-from crewai.flow.flow import Flow, start, listen
-from crewai import CheckpointConfig
+    يكتب إلى `./.checkpoints/` عند كل `task_completed`.
+  </Accordion>
 
-class MyFlow(Flow):
-    @start()
-    def step_one(self):
-        return "data"
+  <Accordion title="تخصيص التخزين والتردد" icon="sliders">
+    ```python
+    from crewai import Crew, CheckpointConfig
 
-    @listen(step_one)
-    def step_two(self, data):
-        return process(data)
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            on_events=["task_completed", "crew_kickoff_completed"],
+            max_checkpoints=5,
+        ),
+    )
+    ```
+  </Accordion>
 
-flow = MyFlow(
-    checkpoint=CheckpointConfig(
-        location="./flow_cp",
-        on_events=["method_execution_finished"],
-    ),
-)
-result = flow.kickoff()
+  <Accordion title="اختيار مزود التخزين" icon="database">
+    <CodeGroup>
+    ```python JsonProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import JsonProvider
 
-# استئناف
-flow = MyFlow.from_checkpoint("./flow_cp/20260407T120000_abc123.json")
-result = flow.kickoff()
-```
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            provider=JsonProvider(),
+            max_checkpoints=5,
+        ),
+    )
+    ```
+    ```python SqliteProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import SqliteProvider
 
-### Agent
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./.checkpoints.db",
+            provider=SqliteProvider(),
+            max_checkpoints=50,
+        ),
+    )
+    ```
+    </CodeGroup>
 
-```python
-agent = Agent(
-    role="Researcher",
-    goal="Research topics",
-    backstory="Expert researcher",
-    checkpoint=CheckpointConfig(
-        location="./agent_cp",
-        on_events=["lite_agent_execution_completed"],
-    ),
-)
-result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
-```
+    <Tip>
+    SQLite يفعل وضع journal WAL للقراءات المتزامنة. يفضل لنقاط الحفظ عالية التردد.
+    </Tip>
+  </Accordion>
 
-## مزودات التخزين
+  <Accordion title="استبعاد وكيل واحد" icon="user-slash">
+    ```python
+    crew = Crew(
+        agents=[
+            Agent(role="Researcher", ...),
+            Agent(role="Writer", ..., checkpoint=False),
+        ],
+        tasks=[...],
+        checkpoint=True,
+    )
+    ```
+  </Accordion>
 
-يتضمن CrewAI مزودي تخزين لنقاط الحفظ.
+  <Accordion title="التفرع إلى فرع جديد" icon="code-branch">
+    `fork()` يستعيد نقطة حفظ تحت نسب جديد بحيث لا يتصادم التشغيل الجديد مع الأصلي.
 
-### JsonProvider (افتراضي)
+    ```python
+    config = CheckpointConfig(restore_from="./my_checkpoints/<file>.json")
+    crew = Crew.fork(config, branch="experiment-a")
+    result = crew.kickoff(inputs={"strategy": "aggressive"})
+    ```
 
-يكتب كل نقطة حفظ كملف JSON منفصل.
+    تسمية `branch` اختيارية؛ يتم إنشاء واحدة إذا أغفلت.
+  </Accordion>
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import JsonProvider
+  <Accordion title="Checkpointing لـ Crew أو Flow أو Agent" icon="cubes">
+    <Tabs>
+      <Tab title="Crew">
+        ```python
+        crew = Crew(
+            agents=[researcher, writer],
+            tasks=[research_task, write_task, review_task],
+            checkpoint=CheckpointConfig(location="./crew_cp"),
+        )
+        ```
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        provider=JsonProvider(),
-        max_checkpoints=5,
-    ),
-)
-```
+        المشغل الافتراضي: `task_completed`.
+      </Tab>
+      <Tab title="Flow">
+        ```python
+        from crewai.flow.flow import Flow, start, listen
+        from crewai import CheckpointConfig
 
-### SqliteProvider
+        class MyFlow(Flow):
+            @start()
+            def step_one(self):
+                return "data"
 
-يخزن جميع نقاط الحفظ في ملف قاعدة بيانات SQLite واحد.
+            @listen(step_one)
+            def step_two(self, data):
+                return process(data)
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import SqliteProvider
+        flow = MyFlow(
+            checkpoint=CheckpointConfig(
+                location="./flow_cp",
+                on_events=["method_execution_finished"],
+            ),
+        )
+        result = flow.kickoff()
+        ```
+      </Tab>
+      <Tab title="Agent">
+        ```python
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            checkpoint=CheckpointConfig(
+                location="./agent_cp",
+                on_events=["lite_agent_execution_completed"],
+            ),
+        )
+        result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
+        ```
+      </Tab>
+    </Tabs>
+  </Accordion>
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./.checkpoints.db",
-        provider=SqliteProvider(),
-    ),
-)
-```
+  <Accordion title="كتابة نقطة حفظ يدويا" icon="code">
+    سجل معالجا على أي حدث واستدع `state.checkpoint()`.
 
+    <CodeGroup>
+    ```python Sync
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-## انواع الاحداث
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    def on_llm_done(source, event, state):
+        path = state.checkpoint("./my_checkpoints")
+        print(f"تم حفظ نقطة الحفظ: {path}")
+    ```
+    ```python Async
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-يقبل حقل `on_events` اي مجموعة من سلاسل انواع الاحداث. الخيارات الشائعة:
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    async def on_llm_done_async(source, event, state):
+        path = await state.acheckpoint("./my_checkpoints")
+        print(f"تم حفظ نقطة الحفظ: {path}")
+    ```
+    </CodeGroup>
 
-| حالة الاستخدام | الاحداث |
-|:---------------|:--------|
-| بعد كل مهمة (Crew) | `["task_completed"]` |
-| بعد كل طريقة في التدفق | `["method_execution_finished"]` |
-| بعد تنفيذ الوكيل | `["agent_execution_completed"]`, `["lite_agent_execution_completed"]` |
-| عند اكتمال الطاقم فقط | `["crew_kickoff_completed"]` |
-| بعد كل استدعاء LLM | `["llm_call_completed"]` |
-| على كل شيء | `["*"]` |
+    يتم تمرير وسيط `state` تلقائيا عندما يقبل المعالج ثلاثة معاملات. راجع [Event Listeners](/ar/concepts/event-listener) لقائمة الأحداث الكاملة.
+  </Accordion>
+
+  <Accordion title="التصفح والاستئناف والتفرع من سطر الأوامر" icon="terminal">
+    ```bash
+    crewai checkpoint                              # كشف تلقائي لـ .checkpoints/ أو .checkpoints.db
+    crewai checkpoint --location ./my_checkpoints
+    crewai checkpoint --location ./.checkpoints.db
+    ```
+
+    <Frame>
+      <img src="/images/checkpointing.png" alt="Checkpoint TUI" />
+    </Frame>
+
+    اللوحة اليسرى تجمع نقاط الحفظ حسب الفرع؛ التفرعات تتداخل تحت أبيها. اختيار نقطة حفظ يعرض بياناتها الوصفية وحالة الكيان وتقدم المهام. **Resume** يكمل التشغيل؛ **Fork** يبدأ فرعا جديدا.
+
+    لوحة التفاصيل تعرض منطقتين قابلتين للتحرير:
+
+    - **Inputs** — مدخلات الـ kickoff الأصلية، معبأة مسبقا وقابلة للتحرير.
+    - **مخرجات المهام** — مخرجات المهام المكتملة. تحرير مخرج والضغط على **Fork** يبطل المهام التابعة لتعاد بالسياق المعدل.
+
+    <Tip>
+    مفيد لاستكشاف "ماذا لو": تفرع، عدل، راقب.
+    </Tip>
+  </Accordion>
+
+  <Accordion title="تفقد نقاط الحفظ بدون TUI" icon="magnifying-glass">
+    ```bash
+    crewai checkpoint list ./my_checkpoints
+    crewai checkpoint info ./my_checkpoints/<file>.json
+    crewai checkpoint info ./.checkpoints.db
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## المرجع
+
+### `CheckpointConfig`
+
+<ParamField path="location" type="str" default='"./.checkpoints"'>
+  وجهة التخزين. مجلد لـ `JsonProvider`، مسار ملف قاعدة بيانات لـ `SqliteProvider`.
+</ParamField>
+
+<ParamField path="on_events" type="list[CheckpointEventType]" default='["task_completed"]'>
+  أنواع الأحداث التي تطلق نقطة حفظ. `CheckpointEventType` هو `Literal` — مدقق الأنواع يكمل تلقائيا ويرفض القيم غير المدعومة. راجع [أنواع الأحداث](#أنواع-الأحداث) للقائمة الكاملة.
+</ParamField>
+
+<ParamField path="provider" type="BaseProvider" default="JsonProvider()">
+  واجهة التخزين. `JsonProvider` أو `SqliteProvider`.
+</ParamField>
+
+<ParamField path="max_checkpoints" type="int | None" default="None">
+  الحد الاقصى لنقاط الحفظ المحتفظ بها. الأقدم تحذف بعد كل كتابة.
+</ParamField>
+
+<ParamField path="restore_from" type="Path | str | None" default="None">
+  نقطة الحفظ المراد استعادتها عند تمريرها عبر `from_checkpoint`.
+</ParamField>
+
+### قيم حقل `checkpoint`
+
+مقبولة في `Crew` و`Flow` و`Agent`.
+
+<ParamField path="None" type="افتراضي">
+  يرث من الأب.
+</ParamField>
+
+<ParamField path="True" type="bool">
+  تفعيل بالإعدادات الافتراضية.
+</ParamField>
+
+<ParamField path="False" type="bool">
+  انسحاب صريح. يوقف الوراثة.
+</ParamField>
+
+<ParamField path="CheckpointConfig(...)" type="CheckpointConfig">
+  إعدادات مخصصة.
+</ParamField>
+
+### أنواع الأحداث
+
+يقبل `on_events` أي مجموعة من قيم `CheckpointEventType`. الافتراضي `["task_completed"]` يكتب نقطة حفظ لكل مهمة منتهية، و`["*"]` يطابق جميع الأحداث.
 
 <Warning>
-استخدام `["*"]` او احداث عالية التردد مثل `llm_call_completed` سيكتب العديد من ملفات نقاط الحفظ وقد يؤثر على الاداء. استخدم `max_checkpoints` للحد من استخدام المساحة.
+`["*"]` والأحداث عالية التردد مثل `llm_call_completed` تكتب نقاط حفظ كثيرة وقد تضر بالاداء. استخدمها مع `max_checkpoints`.
 </Warning>
 
-## نقاط الحفظ اليدوية
+<Expandable title="جميع الأحداث المدعومة">
 
-للتحكم الكامل، سجل معالج الاحداث الخاص بك واستدع `state.checkpoint()` مباشرة:
+- **Task** — `task_started`, `task_completed`, `task_failed`, `task_evaluation`
+- **Crew** — `crew_kickoff_started`, `crew_kickoff_completed`, `crew_kickoff_failed`, `crew_train_started`, `crew_train_completed`, `crew_train_failed`, `crew_test_started`, `crew_test_completed`, `crew_test_failed`, `crew_test_result`
+- **Agent** — `agent_execution_started`, `agent_execution_completed`, `agent_execution_error`, `lite_agent_execution_started`, `lite_agent_execution_completed`, `lite_agent_execution_error`, `agent_evaluation_started`, `agent_evaluation_completed`, `agent_evaluation_failed`
+- **Flow** — `flow_created`, `flow_started`, `flow_finished`, `flow_paused`, `method_execution_started`, `method_execution_finished`, `method_execution_failed`, `method_execution_paused`, `human_feedback_requested`, `human_feedback_received`, `flow_input_requested`, `flow_input_received`
+- **LLM** — `llm_call_started`, `llm_call_completed`, `llm_call_failed`, `llm_stream_chunk`, `llm_thinking_chunk`
+- **LLM Guardrail** — `llm_guardrail_started`, `llm_guardrail_completed`, `llm_guardrail_failed`
+- **Tool** — `tool_usage_started`, `tool_usage_finished`, `tool_usage_error`, `tool_validate_input_error`, `tool_selection_error`, `tool_execution_error`
+- **Memory** — `memory_save_started`, `memory_save_completed`, `memory_save_failed`, `memory_query_started`, `memory_query_completed`, `memory_query_failed`, `memory_retrieval_started`, `memory_retrieval_completed`, `memory_retrieval_failed`
+- **Knowledge** — `knowledge_search_query_started`, `knowledge_search_query_completed`, `knowledge_query_started`, `knowledge_query_completed`, `knowledge_query_failed`, `knowledge_search_query_failed`
+- **Reasoning** — `agent_reasoning_started`, `agent_reasoning_completed`, `agent_reasoning_failed`
+- **MCP** — `mcp_connection_started`, `mcp_connection_completed`, `mcp_connection_failed`, `mcp_tool_execution_started`, `mcp_tool_execution_completed`, `mcp_tool_execution_failed`, `mcp_config_fetch_failed`
+- **Observation** — `step_observation_started`, `step_observation_completed`, `step_observation_failed`, `plan_refinement`, `plan_replan_triggered`, `goal_achieved_early`
+- **Skill** — `skill_discovery_started`, `skill_discovery_completed`, `skill_loaded`, `skill_activated`, `skill_load_failed`
+- **Logging** — `agent_logs_started`, `agent_logs_execution`
+- **A2A** — `a2a_delegation_started`, `a2a_delegation_completed`, `a2a_conversation_started`, `a2a_conversation_completed`, `a2a_message_sent`, `a2a_response_received`, `a2a_polling_started`, `a2a_polling_status`, `a2a_push_notification_registered`, `a2a_push_notification_received`, `a2a_push_notification_sent`, `a2a_push_notification_timeout`, `a2a_streaming_started`, `a2a_streaming_chunk`, `a2a_agent_card_fetched`, `a2a_authentication_failed`, `a2a_artifact_received`, `a2a_connection_error`, `a2a_server_task_started`, `a2a_server_task_completed`, `a2a_server_task_canceled`, `a2a_server_task_failed`, `a2a_parallel_delegation_started`, `a2a_parallel_delegation_completed`, `a2a_transport_negotiated`, `a2a_content_type_negotiated`, `a2a_context_created`, `a2a_context_expired`, `a2a_context_idle`, `a2a_context_completed`, `a2a_context_pruned`
+- **إشارات النظام** — `SIGTERM`, `SIGINT`, `SIGHUP`, `SIGTSTP`, `SIGCONT`
+- **حرف بدل** — `"*"` يطابق جميع الأحداث.
 
-```python
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.types.llm_events import LLMCallCompletedEvent
+</Expandable>
 
-# معالج متزامن
-@crewai_event_bus.on(LLMCallCompletedEvent)
-def on_llm_done(source, event, state):
-    path = state.checkpoint("./my_checkpoints")
-    print(f"تم حفظ نقطة الحفظ: {path}")
+### مزودات التخزين
 
-# معالج غير متزامن
-@crewai_event_bus.on(LLMCallCompletedEvent)
-async def on_llm_done_async(source, event, state):
-    path = await state.acheckpoint("./my_checkpoints")
-    print(f"تم حفظ نقطة الحفظ: {path}")
-```
+<ParamField path="JsonProvider" type="provider">
+  ملف واحد لكل نقطة حفظ بصيغة `<timestamp>_<uuid>.json` داخل `location`.
+</ParamField>
 
-وسيط `state` هو `RuntimeState` الذي يتم تمريره تلقائيا بواسطة ناقل الاحداث عندما يقبل المعالج 3 معاملات. يمكنك تسجيل معالجات على اي نوع حدث مدرج في وثائق [Event Listeners](/ar/concepts/event-listener).
+<ParamField path="SqliteProvider" type="provider">
+  ملف قاعدة بيانات واحد في `location` مع journaling WAL.
+</ParamField>
 
-الـ Checkpointing يعمل بافضل جهد: اذا فشلت كتابة نقطة حفظ، يتم تسجيل الخطأ ولكن التنفيذ يستمر دون انقطاع.
+### سطر الأوامر
+
+| الامر | الغرض |
+|:------|:------|
+| `crewai checkpoint` | تشغيل TUI؛ كشف التخزين تلقائيا. |
+| `crewai checkpoint --location <path>` | تشغيل TUI على موقع محدد. |
+| `crewai checkpoint list <path>` | سرد نقاط الحفظ. |
+| `crewai checkpoint info <path>` | تفقد ملف نقطة حفظ أو آخر مدخل في قاعدة بيانات SQLite. |

docs/en/concepts/checkpointing.mdx

@@ -5,301 +5,386 @@ icon: floppy-disk
 mode: "wide"
 ---
 
-<Warning>
-Checkpointing is in early release. APIs may change in future versions.
-</Warning>
+Checkpointing saves a snapshot of execution state during a run so a crew, flow, or agent can resume after a failure or be forked into an alternate branch.
 
-## Overview
+<CardGroup cols={2}>
+  <Card title="Explanation" icon="lightbulb" href="#explanation">
+    How checkpointing works: events, storage, and inheritance.
+  </Card>
+  <Card title="Tutorial" icon="graduation-cap" href="#tutorial-resume-a-failing-crew">
+    A 5-minute walkthrough: run, interrupt, resume.
+  </Card>
+  <Card title="How-to guides" icon="screwdriver-wrench" href="#how-to-guides">
+    Task-focused recipes for common workflows.
+  </Card>
+  <Card title="Reference" icon="book" href="#reference">
+    `CheckpointConfig`, events, providers, and CLI.
+  </Card>
+</CardGroup>
 
-Checkpointing automatically saves execution state during a run. If a crew, flow, or agent fails mid-execution, you can restore from the last checkpoint and resume without re-running completed work.
+## Explanation
 
-## Quick Start
+### What a checkpoint is
 
-```python
-from crewai import Crew, CheckpointConfig
+A checkpoint captures everything CrewAI needs to recreate a run mid-flight: the full state of the crew, flow, or agent — configuration, agent memory and knowledge sources, task progress, intermediate outputs — alongside the kickoff inputs, the event history up to that point, and a lineage ID that ties the checkpoint to the run it came from.
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=True,  # uses defaults: ./.checkpoints, on task_completed
-)
-result = crew.kickoff()
-```
+Restoring rebuilds that state and continues. Completed tasks are skipped, memory and knowledge are rehydrated, and downstream work runs against the same outputs the original run produced. Forking does the same restore under a new lineage, so the new branch and the original run can write checkpoints side by side without overwriting each other.
 
-Checkpoint files are written to `./.checkpoints/` after each completed task.
+### When checkpoints are written
 
-## Configuration
+Checkpointing is event-driven. The runtime subscribes to events you select via `on_events` and writes a checkpoint each time one fires. The default `task_completed` produces one checkpoint per finished task — a sensible tradeoff between granularity and disk use. Higher-frequency events like `llm_call_completed` are available for fine-grained recovery but write far more files.
 
-Use `CheckpointConfig` for full control:
+### Storage
 
-```python
-from crewai import Crew, CheckpointConfig
+Two providers ship with CrewAI:
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        on_events=["task_completed", "crew_kickoff_completed"],
-        max_checkpoints=5,
-    ),
-)
-```
+- `JsonProvider` writes one file per checkpoint. Human-readable and easy to inspect.
+- `SqliteProvider` writes to a single SQLite database. Better for high-frequency checkpointing.
 
-### CheckpointConfig Fields
+Both prune oldest checkpoints when `max_checkpoints` is set.
 
-| Field | Type | Default | Description |
-|:------|:-----|:--------|:------------|
-| `location` | `str` | `"./.checkpoints"` | Storage destination — a directory for `JsonProvider`, a database file path for `SqliteProvider` |
-| `on_events` | `list[str]` | `["task_completed"]` | Event types that trigger a checkpoint |
-| `provider` | `BaseProvider` | `JsonProvider()` | Storage backend |
-| `max_checkpoints` | `int \| None` | `None` | Max checkpoints to keep. Oldest are pruned after each write. Pruning is handled by the provider. |
-| `restore_from` | `Path \| str \| None` | `None` | Path to a checkpoint to restore from. Used when passing config via a kickoff method's `from_checkpoint` parameter. |
+<Note>
+Checkpoint writes are best-effort. A failed checkpoint is logged but does not interrupt the run.
+</Note>
 
-### Inheritance and Opt-Out
+### Inheritance model
 
-The `checkpoint` field on Crew, Flow, and Agent accepts `CheckpointConfig`, `True`, `False`, or `None`:
+`Crew`, `Flow`, and `Agent` all accept a `checkpoint` argument. Children inherit from their parent unless they set their own value or pass `False` to opt out. Enable checkpointing once on the crew and every agent participates, or selectively exclude one agent.
 
-| Value | Behavior |
-|:------|:---------|
-| `None` (default) | Inherit from parent. An agent inherits its crew's config. |
-| `True` | Enable with defaults. |
-| `False` | Explicit opt-out. Stops inheritance from parent. |
-| `CheckpointConfig(...)` | Custom configuration. |
+## Tutorial: Resume a failing crew
 
-```python
-crew = Crew(
-    agents=[
-        Agent(role="Researcher", ...),                  # inherits crew's checkpoint
-        Agent(role="Writer", ..., checkpoint=False),     # opted out, no checkpoints
-    ],
-    tasks=[...],
-    checkpoint=True,
-)
-```
+This walkthrough takes ~5 minutes. You will run a two-task crew, kill it midway, and resume from the saved checkpoint.
 
-## Resuming from a Checkpoint
+<Steps>
+  <Step title="Create the crew with checkpointing enabled">
+    ```python
+    from crewai import Agent, Crew, Task
 
-Pass a `CheckpointConfig` with `restore_from` to any kickoff method. The crew restores from that checkpoint, skips completed tasks, and resumes.
+    researcher = Agent(role="Researcher", goal="Research", backstory="Expert")
+    writer = Agent(role="Writer", goal="Write", backstory="Expert")
 
-```python
-from crewai import Crew, CheckpointConfig
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[
+            Task(description="Research AI trends", agent=researcher, expected_output="bullets"),
+            Task(description="Write a summary", agent=writer, expected_output="paragraph"),
+        ],
+        checkpoint=True,
+    )
+    ```
+  </Step>
+  <Step title="Run it and interrupt after the first task">
+    ```python
+    result = crew.kickoff()
+    ```
 
-crew = Crew(agents=[...], tasks=[...])
-result = crew.kickoff(
-    from_checkpoint=CheckpointConfig(
-        restore_from="./my_checkpoints/20260407T120000_abc123.json",
-    ),
-)
-```
+    Press `Ctrl+C` after the first task finishes. Look in `./.checkpoints/` — a file named `<timestamp>_<uuid>.json` is the checkpoint.
+  </Step>
+  <Step title="Resume from the checkpoint">
+    ```python
+    from crewai import CheckpointConfig
 
-Remaining `CheckpointConfig` fields apply to the new run, so checkpointing continues after the restore.
+    result = crew.kickoff(
+        from_checkpoint=CheckpointConfig(
+            restore_from="./.checkpoints/<timestamp>_<uuid>.json",
+        ),
+    )
+    ```
 
-You can also use the classmethod directly:
+    The research task is skipped, the writer runs against the saved research output, and the crew finishes.
+  </Step>
+</Steps>
 
-```python
-config = CheckpointConfig(restore_from="./my_checkpoints/20260407T120000_abc123.json")
-crew = Crew.from_checkpoint(config)
-result = crew.kickoff()
-```
+## How-to guides
 
-## Forking from a Checkpoint
+<AccordionGroup>
+  <Accordion title="Enable checkpointing with defaults" icon="play">
+    ```python
+    crew = Crew(agents=[...], tasks=[...], checkpoint=True)
+    ```
 
-`fork()` restores a checkpoint and starts a new execution branch. Useful for exploring alternative paths from the same point.
+    Writes to `./.checkpoints/` on every `task_completed`.
+  </Accordion>
 
-```python
-from crewai import Crew, CheckpointConfig
+  <Accordion title="Customize storage and frequency" icon="sliders">
+    ```python
+    from crewai import Crew, CheckpointConfig
 
-config = CheckpointConfig(restore_from="./my_checkpoints/20260407T120000_abc123.json")
-crew = Crew.fork(config, branch="experiment-a")
-result = crew.kickoff(inputs={"strategy": "aggressive"})
-```
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            on_events=["task_completed", "crew_kickoff_completed"],
+            max_checkpoints=5,
+        ),
+    )
+    ```
+  </Accordion>
 
-Each fork gets a unique lineage ID so checkpoints from different branches don't collide. The `branch` label is optional and auto-generated if omitted.
+  <Accordion title="Choose a storage provider" icon="database">
+    <CodeGroup>
+    ```python JsonProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import JsonProvider
 
-## Works on Crew, Flow, and Agent
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            provider=JsonProvider(),
+            max_checkpoints=5,
+        ),
+    )
+    ```
+    ```python SqliteProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import SqliteProvider
 
-### Crew
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./.checkpoints.db",
+            provider=SqliteProvider(),
+            max_checkpoints=50,
+        ),
+    )
+    ```
+    </CodeGroup>
 
-```python
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[research_task, write_task, review_task],
-    checkpoint=CheckpointConfig(location="./crew_cp"),
-)
-```
+    <Tip>
+    SQLite enables WAL journal mode for concurrent reads. Prefer it for high-frequency checkpointing.
+    </Tip>
+  </Accordion>
 
-Default trigger: `task_completed` (one checkpoint per finished task).
+  <Accordion title="Opt one agent out" icon="user-slash">
+    ```python
+    crew = Crew(
+        agents=[
+            Agent(role="Researcher", ...),
+            Agent(role="Writer", ..., checkpoint=False),
+        ],
+        tasks=[...],
+        checkpoint=True,
+    )
+    ```
+  </Accordion>
 
-### Flow
+  <Accordion title="Fork into a new branch" icon="code-branch">
+    `fork()` restores a checkpoint under a fresh lineage so the new run does not collide with the original.
 
-```python
-from crewai.flow.flow import Flow, start, listen
-from crewai import CheckpointConfig
+    ```python
+    config = CheckpointConfig(restore_from="./my_checkpoints/<file>.json")
+    crew = Crew.fork(config, branch="experiment-a")
+    result = crew.kickoff(inputs={"strategy": "aggressive"})
+    ```
 
-class MyFlow(Flow):
-    @start()
-    def step_one(self):
-        return "data"
+    The `branch` label is optional; one is generated if omitted.
+  </Accordion>
 
-    @listen(step_one)
-    def step_two(self, data):
-        return process(data)
+  <Accordion title="Checkpoint a Crew, Flow, or Agent" icon="cubes">
+    <Tabs>
+      <Tab title="Crew">
+        ```python
+        crew = Crew(
+            agents=[researcher, writer],
+            tasks=[research_task, write_task, review_task],
+            checkpoint=CheckpointConfig(location="./crew_cp"),
+        )
+        ```
 
-flow = MyFlow(
-    checkpoint=CheckpointConfig(
-        location="./flow_cp",
-        on_events=["method_execution_finished"],
-    ),
-)
-result = flow.kickoff()
+        Default trigger: `task_completed`.
+      </Tab>
+      <Tab title="Flow">
+        ```python
+        from crewai.flow.flow import Flow, start, listen
+        from crewai import CheckpointConfig
 
-# Resume
-config = CheckpointConfig(restore_from="./flow_cp/20260407T120000_abc123.json")
-flow = MyFlow.from_checkpoint(config)
-result = flow.kickoff()
-```
+        class MyFlow(Flow):
+            @start()
+            def step_one(self):
+                return "data"
 
-### Agent
+            @listen(step_one)
+            def step_two(self, data):
+                return process(data)
 
-```python
-agent = Agent(
-    role="Researcher",
-    goal="Research topics",
-    backstory="Expert researcher",
-    checkpoint=CheckpointConfig(
-        location="./agent_cp",
-        on_events=["lite_agent_execution_completed"],
-    ),
-)
-result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
-```
+        flow = MyFlow(
+            checkpoint=CheckpointConfig(
+                location="./flow_cp",
+                on_events=["method_execution_finished"],
+            ),
+        )
+        result = flow.kickoff()
+        ```
+      </Tab>
+      <Tab title="Agent">
+        ```python
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            checkpoint=CheckpointConfig(
+                location="./agent_cp",
+                on_events=["lite_agent_execution_completed"],
+            ),
+        )
+        result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
+        ```
+      </Tab>
+    </Tabs>
+  </Accordion>
 
-## Storage Providers
+  <Accordion title="Write a checkpoint manually" icon="code">
+    Register a handler on any event and call `state.checkpoint()`.
 
-CrewAI ships with two checkpoint storage providers.
+    <CodeGroup>
+    ```python Sync
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-### JsonProvider (default)
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    def on_llm_done(source, event, state):
+        path = state.checkpoint("./my_checkpoints")
+        print(f"Saved checkpoint: {path}")
+    ```
+    ```python Async
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-Writes each checkpoint as a separate JSON file. Simple, human-readable, easy to inspect.
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    async def on_llm_done_async(source, event, state):
+        path = await state.acheckpoint("./my_checkpoints")
+        print(f"Saved checkpoint: {path}")
+    ```
+    </CodeGroup>
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import JsonProvider
+    A `state` argument is supplied automatically when the handler takes three parameters. See [Event Listeners](/en/concepts/event-listener) for the full event catalog.
+  </Accordion>
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        provider=JsonProvider(),       # this is the default
-        max_checkpoints=5,             # prunes oldest files
-    ),
-)
-```
+  <Accordion title="Browse, resume, and fork from the CLI" icon="terminal">
+    ```bash
+    crewai checkpoint                              # auto-detects .checkpoints/ or .checkpoints.db
+    crewai checkpoint --location ./my_checkpoints
+    crewai checkpoint --location ./.checkpoints.db
+    ```
 
-Files are named `<timestamp>_<uuid>.json` inside the location directory.
+    <Frame>
+      <img src="/images/checkpointing.png" alt="Checkpoint TUI" />
+    </Frame>
 
-### SqliteProvider
+    The left panel groups checkpoints by branch; forks nest under their parent. Selecting a checkpoint shows its metadata, entity state, and task progress. **Resume** continues the run; **Fork** starts a new branch.
 
-Stores all checkpoints in a single SQLite database file. Better for high-frequency checkpointing and avoids many small files.
+    The detail panel exposes two editable areas:
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import SqliteProvider
+    - **Inputs** — original kickoff inputs, pre-filled and editable.
+    - **Task outputs** — outputs of completed tasks. Editing an output and hitting **Fork** invalidates downstream tasks so they re-run against the modified context.
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./.checkpoints.db",
-        provider=SqliteProvider(),
-        max_checkpoints=50,
-    ),
-)
-```
+    <Tip>
+    Useful for "what if" exploration: fork, tweak, observe.
+    </Tip>
+  </Accordion>
 
-WAL journal mode is enabled for concurrent read access.
+  <Accordion title="Inspect checkpoints without the TUI" icon="magnifying-glass">
+    ```bash
+    crewai checkpoint list ./my_checkpoints
+    crewai checkpoint info ./my_checkpoints/<file>.json
+    crewai checkpoint info ./.checkpoints.db
+    ```
+  </Accordion>
+</AccordionGroup>
 
-## Event Types
+## Reference
 
-The `on_events` field accepts any combination of event type strings. Common choices:
+### `CheckpointConfig`
 
-| Use Case | Events |
-|:---------|:-------|
-| After each task (Crew) | `["task_completed"]` |
-| After each flow method | `["method_execution_finished"]` |
-| After agent execution | `["agent_execution_completed"]`, `["lite_agent_execution_completed"]` |
-| On crew completion only | `["crew_kickoff_completed"]` |
-| After every LLM call | `["llm_call_completed"]` |
-| On everything | `["*"]` |
+<ParamField path="location" type="str" default='"./.checkpoints"'>
+  Storage destination. A directory for `JsonProvider`, a database file path for `SqliteProvider`.
+</ParamField>
+
+<ParamField path="on_events" type="list[CheckpointEventType]" default='["task_completed"]'>
+  Event types that trigger a checkpoint. `CheckpointEventType` is a `Literal` — your type checker will autocomplete and reject unsupported values. See [event types](#event-types) for the full list.
+</ParamField>
+
+<ParamField path="provider" type="BaseProvider" default="JsonProvider()">
+  Storage backend. Either `JsonProvider` or `SqliteProvider`.
+</ParamField>
+
+<ParamField path="max_checkpoints" type="int | None" default="None">
+  Maximum checkpoints to retain. Oldest are pruned after each write.
+</ParamField>
+
+<ParamField path="restore_from" type="Path | str | None" default="None">
+  Checkpoint to restore from when passed via `from_checkpoint`.
+</ParamField>
+
+### `checkpoint` field values
+
+Accepted by `Crew`, `Flow`, and `Agent`.
+
+<ParamField path="None" type="default">
+  Inherit from parent.
+</ParamField>
+
+<ParamField path="True" type="bool">
+  Enable with defaults.
+</ParamField>
+
+<ParamField path="False" type="bool">
+  Explicit opt-out. Stops inheritance.
+</ParamField>
+
+<ParamField path="CheckpointConfig(...)" type="CheckpointConfig">
+  Custom configuration.
+</ParamField>
+
+### Event types
+
+`on_events` accepts any combination of `CheckpointEventType` values. The default `["task_completed"]` writes one checkpoint per finished task; `["*"]` matches every event.
 
 <Warning>
-Using `["*"]` or high-frequency events like `llm_call_completed` will write many checkpoint files and may impact performance. Use `max_checkpoints` to limit disk usage.
+`["*"]` and high-frequency events like `llm_call_completed` write many checkpoints and can degrade performance. Pair them with `max_checkpoints`.
 </Warning>
 
-## Manual Checkpointing
+<Expandable title="All supported events">
 
-For full control, register your own event handler and call `state.checkpoint()` directly:
+- **Task** — `task_started`, `task_completed`, `task_failed`, `task_evaluation`
+- **Crew** — `crew_kickoff_started`, `crew_kickoff_completed`, `crew_kickoff_failed`, `crew_train_started`, `crew_train_completed`, `crew_train_failed`, `crew_test_started`, `crew_test_completed`, `crew_test_failed`, `crew_test_result`
+- **Agent** — `agent_execution_started`, `agent_execution_completed`, `agent_execution_error`, `lite_agent_execution_started`, `lite_agent_execution_completed`, `lite_agent_execution_error`, `agent_evaluation_started`, `agent_evaluation_completed`, `agent_evaluation_failed`
+- **Flow** — `flow_created`, `flow_started`, `flow_finished`, `flow_paused`, `method_execution_started`, `method_execution_finished`, `method_execution_failed`, `method_execution_paused`, `human_feedback_requested`, `human_feedback_received`, `flow_input_requested`, `flow_input_received`
+- **LLM** — `llm_call_started`, `llm_call_completed`, `llm_call_failed`, `llm_stream_chunk`, `llm_thinking_chunk`
+- **LLM Guardrail** — `llm_guardrail_started`, `llm_guardrail_completed`, `llm_guardrail_failed`
+- **Tool** — `tool_usage_started`, `tool_usage_finished`, `tool_usage_error`, `tool_validate_input_error`, `tool_selection_error`, `tool_execution_error`
+- **Memory** — `memory_save_started`, `memory_save_completed`, `memory_save_failed`, `memory_query_started`, `memory_query_completed`, `memory_query_failed`, `memory_retrieval_started`, `memory_retrieval_completed`, `memory_retrieval_failed`
+- **Knowledge** — `knowledge_search_query_started`, `knowledge_search_query_completed`, `knowledge_query_started`, `knowledge_query_completed`, `knowledge_query_failed`, `knowledge_search_query_failed`
+- **Reasoning** — `agent_reasoning_started`, `agent_reasoning_completed`, `agent_reasoning_failed`
+- **MCP** — `mcp_connection_started`, `mcp_connection_completed`, `mcp_connection_failed`, `mcp_tool_execution_started`, `mcp_tool_execution_completed`, `mcp_tool_execution_failed`, `mcp_config_fetch_failed`
+- **Observation** — `step_observation_started`, `step_observation_completed`, `step_observation_failed`, `plan_refinement`, `plan_replan_triggered`, `goal_achieved_early`
+- **Skill** — `skill_discovery_started`, `skill_discovery_completed`, `skill_loaded`, `skill_activated`, `skill_load_failed`
+- **Logging** — `agent_logs_started`, `agent_logs_execution`
+- **A2A** — `a2a_delegation_started`, `a2a_delegation_completed`, `a2a_conversation_started`, `a2a_conversation_completed`, `a2a_message_sent`, `a2a_response_received`, `a2a_polling_started`, `a2a_polling_status`, `a2a_push_notification_registered`, `a2a_push_notification_received`, `a2a_push_notification_sent`, `a2a_push_notification_timeout`, `a2a_streaming_started`, `a2a_streaming_chunk`, `a2a_agent_card_fetched`, `a2a_authentication_failed`, `a2a_artifact_received`, `a2a_connection_error`, `a2a_server_task_started`, `a2a_server_task_completed`, `a2a_server_task_canceled`, `a2a_server_task_failed`, `a2a_parallel_delegation_started`, `a2a_parallel_delegation_completed`, `a2a_transport_negotiated`, `a2a_content_type_negotiated`, `a2a_context_created`, `a2a_context_expired`, `a2a_context_idle`, `a2a_context_completed`, `a2a_context_pruned`
+- **System signals** — `SIGTERM`, `SIGINT`, `SIGHUP`, `SIGTSTP`, `SIGCONT`
+- **Wildcard** — `"*"` matches every event.
 
-```python
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.types.llm_events import LLMCallCompletedEvent
+</Expandable>
 
-# Sync handler
-@crewai_event_bus.on(LLMCallCompletedEvent)
-def on_llm_done(source, event, state):
-    path = state.checkpoint("./my_checkpoints")
-    print(f"Saved checkpoint: {path}")
+### Storage providers
 
-# Async handler
-@crewai_event_bus.on(LLMCallCompletedEvent)
-async def on_llm_done_async(source, event, state):
-    path = await state.acheckpoint("./my_checkpoints")
-    print(f"Saved checkpoint: {path}")
-```
+<ParamField path="JsonProvider" type="provider">
+  One file per checkpoint, named `<timestamp>_<uuid>.json` inside `location`.
+</ParamField>
 
-The `state` argument is the `RuntimeState` passed automatically by the event bus when your handler accepts 3 parameters. You can register handlers on any event type listed in the [Event Listeners](/en/concepts/event-listener) documentation.
+<ParamField path="SqliteProvider" type="provider">
+  Single database file at `location` with WAL journaling.
+</ParamField>
 
-Checkpointing is best-effort: if a checkpoint write fails, the error is logged but execution continues uninterrupted.
+### CLI
 
-## CLI
-
-The `crewai checkpoint` command gives you a TUI for browsing, inspecting, resuming, and forking checkpoints. It auto-detects whether your checkpoints are JSON files or a SQLite database.
-
-```bash
-# Launch the TUI — auto-detects .checkpoints/ or .checkpoints.db
-crewai checkpoint
-
-# Point at a specific location
-crewai checkpoint --location ./my_checkpoints
-crewai checkpoint --location ./.checkpoints.db
-```
-
-<Frame>
-  <img src="/images/checkpointing.png" alt="Checkpoint TUI" />
-</Frame>
-
-The left panel is a tree view. Checkpoints are grouped by branch, and forks nest under the checkpoint they diverged from. Select a checkpoint to see its metadata, entity state, and task progress in the detail panel. Hit **Resume** to pick up where it left off, or **Fork** to start a new branch from that point.
-
-### Editing inputs and task outputs
-
-When a checkpoint is selected, the detail panel shows:
-
-- **Inputs** — if the original kickoff had inputs (e.g. `{topic}`), they appear as editable fields pre-filled with the original values. Change them before resuming or forking.
-- **Task outputs** — completed tasks show their output in editable text areas. Edit a task's output to change the context that downstream tasks receive. When you modify a task output and hit Fork, all subsequent tasks are invalidated and re-run with the new context.
-
-This is useful for "what if" exploration — fork from a checkpoint, tweak a task's result, and see how it changes downstream behavior.
-
-### Subcommands
-
-```bash
-# List all checkpoints
-crewai checkpoint list ./my_checkpoints
-
-# Inspect a specific checkpoint
-crewai checkpoint info ./my_checkpoints/20260407T120000_abc123.json
-
-# Inspect latest in a SQLite database
-crewai checkpoint info ./.checkpoints.db
-```
+| Command | Purpose |
+|:--------|:--------|
+| `crewai checkpoint` | Launch the TUI; auto-detect storage. |
+| `crewai checkpoint --location <path>` | Launch the TUI against a specific location. |
+| `crewai checkpoint list <path>` | List checkpoints. |
+| `crewai checkpoint info <path>` | Inspect a checkpoint file or the latest entry in a SQLite database. |

docs/ko/concepts/checkpointing.mdx

@@ -5,225 +5,386 @@ icon: floppy-disk
 mode: "wide"
 ---
 
-<Warning>
-체크포인팅은 초기 릴리스 단계입니다. API는 향후 버전에서 변경될 수 있습니다.
-</Warning>
+체크포인팅은 실행 중 실행 상태의 스냅샷을 저장하여 크루, 플로우, 에이전트가 실패 후 재개하거나 대체 브랜치로 분기될 수 있도록 합니다.
 
-## 개요
+<CardGroup cols={2}>
+  <Card title="설명" icon="lightbulb" href="#설명">
+    체크포인팅의 작동 방식: 이벤트, 스토리지, 상속.
+  </Card>
+  <Card title="튜토리얼" icon="graduation-cap" href="#튜토리얼-실패한-크루-재개하기">
+    5분 가이드: 실행, 중단, 재개.
+  </Card>
+  <Card title="사용 방법" icon="screwdriver-wrench" href="#사용-방법">
+    일반적인 워크플로우를 위한 작업 중심 레시피.
+  </Card>
+  <Card title="레퍼런스" icon="book" href="#레퍼런스">
+    `CheckpointConfig`, 이벤트, 프로바이더, CLI.
+  </Card>
+</CardGroup>
 
-체크포인팅은 실행 중 자동으로 실행 상태를 저장합니다. 크루, 플로우 또는 에이전트가 실행 도중 실패하면 마지막 체크포인트에서 복원하여 이미 완료된 작업을 다시 실행하지 않고 재개할 수 있습니다.
+## 설명
 
-## 빠른 시작
+### 체크포인트란
 
-```python
-from crewai import Crew, CheckpointConfig
+체크포인트는 실행 중인 작업을 재현하기 위해 CrewAI가 필요한 모든 것을 캡처합니다: 크루, 플로우 또는 에이전트의 전체 상태 — 구성, 에이전트의 메모리 및 지식 소스, 태스크 진행 상황, 중간 출력값 — 그리고 kickoff 입력, 해당 시점까지의 이벤트 기록, 그리고 체크포인트를 원본 실행에 연결하는 lineage ID를 포함합니다.
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=True,  # 기본값 사용: ./.checkpoints, task_completed 이벤트
-)
-result = crew.kickoff()
-```
+복원하면 해당 상태를 재구성하고 계속 진행합니다. 완료된 태스크는 건너뛰고, 메모리와 지식은 재수화되며, 다운스트림 작업은 원본 실행이 생성한 동일한 출력을 기반으로 실행됩니다. 포크하면 새 lineage 아래에서 동일한 복원을 수행하여 새 브랜치와 원본 실행이 서로 덮어쓰지 않고 나란히 체크포인트를 기록할 수 있습니다.
 
-각 태스크가 완료된 후 `./.checkpoints/`에 체크포인트 파일이 기록됩니다.
+### 체크포인트가 기록되는 시점
 
-## 설정
+체크포인팅은 이벤트 기반입니다. 런타임은 `on_events`로 선택한 이벤트를 구독하고, 이벤트가 발생할 때마다 체크포인트를 기록합니다. 기본값 `task_completed`는 완료된 태스크당 하나의 체크포인트를 생성합니다 — 세분화와 디스크 사용의 합리적인 균형입니다. `llm_call_completed`와 같은 고빈도 이벤트는 더 세밀한 복구를 위해 사용 가능하지만 훨씬 많은 파일을 기록합니다.
 
-`CheckpointConfig`를 사용하여 세부 설정을 제어합니다:
+### 스토리지
 
-```python
-from crewai import Crew, CheckpointConfig
+CrewAI에는 두 가지 프로바이더가 포함되어 있습니다:
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        on_events=["task_completed", "crew_kickoff_completed"],
-        max_checkpoints=5,
-    ),
-)
-```
+- `JsonProvider`는 체크포인트당 하나의 파일을 기록합니다. 사람이 읽기 쉽고 검사하기 편리합니다.
+- `SqliteProvider`는 단일 SQLite 데이터베이스에 기록합니다. 고빈도 체크포인팅에 적합합니다.
 
-### CheckpointConfig 필드
+`max_checkpoints`가 설정되면 두 프로바이더 모두 가장 오래된 체크포인트를 자동으로 제거합니다.
 
-| 필드 | 타입 | 기본값 | 설명 |
-|:-----|:-----|:-------|:-----|
-| `location` | `str` | `"./.checkpoints"` | 체크포인트 파일 경로 |
-| `on_events` | `list[str]` | `["task_completed"]` | 체크포인트를 트리거하는 이벤트 타입 |
-| `provider` | `BaseProvider` | `JsonProvider()` | 스토리지 백엔드 |
-| `max_checkpoints` | `int \| None` | `None` | 보관할 최대 파일 수; 오래된 것부터 삭제 |
+<Note>
+체크포인트 기록은 best-effort 방식입니다. 실패한 체크포인트는 로그에 기록되지만 실행을 중단시키지 않습니다.
+</Note>
 
-### 상속 및 옵트아웃
+### 상속 모델
 
-Crew, Flow, Agent의 `checkpoint` 필드는 `CheckpointConfig`, `True`, `False`, `None`을 받습니다:
+`Crew`, `Flow`, `Agent` 모두 `checkpoint` 인수를 받습니다. 자식은 자체 값을 설정하거나 `False`를 전달하여 옵트아웃하지 않는 한 부모로부터 상속합니다. 크루에서 체크포인팅을 한 번 활성화하면 모든 에이전트가 참여하거나, 특정 에이전트만 선택적으로 제외할 수 있습니다.
 
-| 값 | 동작 |
-|:---|:-----|
-| `None` (기본값) | 부모에서 상속. 에이전트는 크루의 설정을 상속합니다. |
-| `True` | 기본값으로 활성화. |
-| `False` | 명시적 옵트아웃. 부모 상속을 중단합니다. |
-| `CheckpointConfig(...)` | 사용자 정의 설정. |
+## 튜토리얼: 실패한 크루 재개하기
 
-```python
-crew = Crew(
-    agents=[
-        Agent(role="Researcher", ...),                  # 크루의 checkpoint 상속
-        Agent(role="Writer", ..., checkpoint=False),     # 옵트아웃, 체크포인트 없음
-    ],
-    tasks=[...],
-    checkpoint=True,
-)
-```
+이 가이드는 약 5분이 소요됩니다. 두 개의 태스크가 있는 크루를 실행하고 중간에 종료한 다음, 저장된 체크포인트에서 재개합니다.
 
-## 체크포인트에서 재개
+<Steps>
+  <Step title="체크포인팅이 활성화된 크루를 생성합니다">
+    ```python
+    from crewai import Agent, Crew, Task
 
-```python
-# 복원 및 재개
-crew = Crew.from_checkpoint("./my_checkpoints/20260407T120000_abc123.json")
-result = crew.kickoff()  # 마지막으로 완료된 태스크부터 재개
-```
+    researcher = Agent(role="Researcher", goal="Research", backstory="Expert")
+    writer = Agent(role="Writer", goal="Write", backstory="Expert")
 
-복원된 크루는 이미 완료된 태스크를 건너뛰고 첫 번째 미완료 태스크부터 재개합니다.
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[
+            Task(description="Research AI trends", agent=researcher, expected_output="bullets"),
+            Task(description="Write a summary", agent=writer, expected_output="paragraph"),
+        ],
+        checkpoint=True,
+    )
+    ```
+  </Step>
+  <Step title="실행하고 첫 번째 태스크 후에 중단합니다">
+    ```python
+    result = crew.kickoff()
+    ```
 
-## Crew, Flow, Agent에서 사용 가능
+    첫 번째 태스크가 완료된 후 `Ctrl+C`를 누릅니다. `./.checkpoints/` 디렉토리에서 `<timestamp>_<uuid>.json` 형식의 파일이 체크포인트입니다.
+  </Step>
+  <Step title="체크포인트에서 재개합니다">
+    ```python
+    from crewai import CheckpointConfig
 
-### Crew
+    result = crew.kickoff(
+        from_checkpoint=CheckpointConfig(
+            restore_from="./.checkpoints/<timestamp>_<uuid>.json",
+        ),
+    )
+    ```
 
-```python
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[research_task, write_task, review_task],
-    checkpoint=CheckpointConfig(location="./crew_cp"),
-)
-```
+    연구 태스크는 건너뛰고, 작성자는 저장된 연구 출력에 대해 실행되며, 크루가 완료됩니다.
+  </Step>
+</Steps>
 
-기본 트리거: `task_completed` (완료된 태스크당 하나의 체크포인트).
+## 사용 방법
 
-### Flow
+<AccordionGroup>
+  <Accordion title="기본값으로 체크포인팅 활성화" icon="play">
+    ```python
+    crew = Crew(agents=[...], tasks=[...], checkpoint=True)
+    ```
 
-```python
-from crewai.flow.flow import Flow, start, listen
-from crewai import CheckpointConfig
+    `task_completed` 이벤트마다 `./.checkpoints/`에 기록합니다.
+  </Accordion>
 
-class MyFlow(Flow):
-    @start()
-    def step_one(self):
-        return "data"
+  <Accordion title="스토리지와 빈도 사용자 정의" icon="sliders">
+    ```python
+    from crewai import Crew, CheckpointConfig
 
-    @listen(step_one)
-    def step_two(self, data):
-        return process(data)
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            on_events=["task_completed", "crew_kickoff_completed"],
+            max_checkpoints=5,
+        ),
+    )
+    ```
+  </Accordion>
 
-flow = MyFlow(
-    checkpoint=CheckpointConfig(
-        location="./flow_cp",
-        on_events=["method_execution_finished"],
-    ),
-)
-result = flow.kickoff()
+  <Accordion title="스토리지 프로바이더 선택" icon="database">
+    <CodeGroup>
+    ```python JsonProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import JsonProvider
 
-# 재개
-flow = MyFlow.from_checkpoint("./flow_cp/20260407T120000_abc123.json")
-result = flow.kickoff()
-```
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            provider=JsonProvider(),
+            max_checkpoints=5,
+        ),
+    )
+    ```
+    ```python SqliteProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import SqliteProvider
 
-### Agent
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./.checkpoints.db",
+            provider=SqliteProvider(),
+            max_checkpoints=50,
+        ),
+    )
+    ```
+    </CodeGroup>
 
-```python
-agent = Agent(
-    role="Researcher",
-    goal="Research topics",
-    backstory="Expert researcher",
-    checkpoint=CheckpointConfig(
-        location="./agent_cp",
-        on_events=["lite_agent_execution_completed"],
-    ),
-)
-result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
-```
+    <Tip>
+    SQLite는 동시 읽기를 위해 WAL 저널 모드를 활성화합니다. 고빈도 체크포인팅에는 SQLite를 선호하세요.
+    </Tip>
+  </Accordion>
 
-## 스토리지 프로바이더
+  <Accordion title="특정 에이전트 옵트아웃" icon="user-slash">
+    ```python
+    crew = Crew(
+        agents=[
+            Agent(role="Researcher", ...),
+            Agent(role="Writer", ..., checkpoint=False),
+        ],
+        tasks=[...],
+        checkpoint=True,
+    )
+    ```
+  </Accordion>
 
-CrewAI는 두 가지 체크포인트 스토리지 프로바이더를 제공합니다.
+  <Accordion title="새 브랜치로 포크" icon="code-branch">
+    `fork()`는 새 lineage 아래에 체크포인트를 복원하여 새 실행이 원본과 충돌하지 않도록 합니다.
 
-### JsonProvider (기본값)
+    ```python
+    config = CheckpointConfig(restore_from="./my_checkpoints/<file>.json")
+    crew = Crew.fork(config, branch="experiment-a")
+    result = crew.kickoff(inputs={"strategy": "aggressive"})
+    ```
 
-각 체크포인트를 별도의 JSON 파일로 저장합니다.
+    `branch` 레이블은 선택 사항이며, 생략하면 자동 생성됩니다.
+  </Accordion>
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import JsonProvider
+  <Accordion title="Crew, Flow, Agent 체크포인트" icon="cubes">
+    <Tabs>
+      <Tab title="Crew">
+        ```python
+        crew = Crew(
+            agents=[researcher, writer],
+            tasks=[research_task, write_task, review_task],
+            checkpoint=CheckpointConfig(location="./crew_cp"),
+        )
+        ```
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        provider=JsonProvider(),
-        max_checkpoints=5,
-    ),
-)
-```
+        기본 트리거: `task_completed`.
+      </Tab>
+      <Tab title="Flow">
+        ```python
+        from crewai.flow.flow import Flow, start, listen
+        from crewai import CheckpointConfig
 
-### SqliteProvider
+        class MyFlow(Flow):
+            @start()
+            def step_one(self):
+                return "data"
 
-모든 체크포인트를 단일 SQLite 데이터베이스 파일에 저장합니다.
+            @listen(step_one)
+            def step_two(self, data):
+                return process(data)
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import SqliteProvider
+        flow = MyFlow(
+            checkpoint=CheckpointConfig(
+                location="./flow_cp",
+                on_events=["method_execution_finished"],
+            ),
+        )
+        result = flow.kickoff()
+        ```
+      </Tab>
+      <Tab title="Agent">
+        ```python
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            checkpoint=CheckpointConfig(
+                location="./agent_cp",
+                on_events=["lite_agent_execution_completed"],
+            ),
+        )
+        result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
+        ```
+      </Tab>
+    </Tabs>
+  </Accordion>
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./.checkpoints.db",
-        provider=SqliteProvider(),
-    ),
-)
-```
+  <Accordion title="수동으로 체크포인트 기록" icon="code">
+    모든 이벤트에 핸들러를 등록하고 `state.checkpoint()`를 호출합니다.
 
+    <CodeGroup>
+    ```python Sync
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-## 이벤트 타입
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    def on_llm_done(source, event, state):
+        path = state.checkpoint("./my_checkpoints")
+        print(f"체크포인트 저장: {path}")
+    ```
+    ```python Async
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-`on_events` 필드는 이벤트 타입 문자열의 조합을 받습니다. 일반적인 선택:
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    async def on_llm_done_async(source, event, state):
+        path = await state.acheckpoint("./my_checkpoints")
+        print(f"체크포인트 저장: {path}")
+    ```
+    </CodeGroup>
 
-| 사용 사례 | 이벤트 |
-|:----------|:-------|
-| 각 태스크 완료 후 (Crew) | `["task_completed"]` |
-| 각 플로우 메서드 완료 후 | `["method_execution_finished"]` |
-| 에이전트 실행 완료 후 | `["agent_execution_completed"]`, `["lite_agent_execution_completed"]` |
-| 크루 완료 시에만 | `["crew_kickoff_completed"]` |
-| 모든 LLM 호출 후 | `["llm_call_completed"]` |
-| 모든 이벤트 | `["*"]` |
+    핸들러가 세 개의 매개변수를 받을 때 `state` 인수가 자동으로 제공됩니다. 전체 이벤트 카탈로그는 [Event Listeners](/ko/concepts/event-listener) 문서를 참조하세요.
+  </Accordion>
+
+  <Accordion title="CLI에서 탐색, 재개, 포크" icon="terminal">
+    ```bash
+    crewai checkpoint                              # .checkpoints/ 또는 .checkpoints.db 자동 감지
+    crewai checkpoint --location ./my_checkpoints
+    crewai checkpoint --location ./.checkpoints.db
+    ```
+
+    <Frame>
+      <img src="/images/checkpointing.png" alt="Checkpoint TUI" />
+    </Frame>
+
+    왼쪽 패널은 체크포인트를 브랜치별로 그룹화하며, 포크는 부모 아래에 중첩됩니다. 체크포인트를 선택하면 메타데이터, 엔티티 상태, 태스크 진행 상황이 표시됩니다. **Resume**은 실행을 계속하고, **Fork**는 새 브랜치를 시작합니다.
+
+    세부 정보 패널에는 두 개의 편집 가능한 영역이 있습니다:
+
+    - **Inputs** — 원래 kickoff의 입력으로, 미리 채워져 있으며 편집 가능합니다.
+    - **태스크 출력** — 완료된 태스크의 출력. 출력을 편집하고 **Fork**를 누르면 다운스트림 태스크가 무효화되어 수정된 컨텍스트로 다시 실행됩니다.
+
+    <Tip>
+    "what if" 탐색에 유용합니다: 포크, 조정, 관찰.
+    </Tip>
+  </Accordion>
+
+  <Accordion title="TUI 없이 체크포인트 검사" icon="magnifying-glass">
+    ```bash
+    crewai checkpoint list ./my_checkpoints
+    crewai checkpoint info ./my_checkpoints/<file>.json
+    crewai checkpoint info ./.checkpoints.db
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## 레퍼런스
+
+### `CheckpointConfig`
+
+<ParamField path="location" type="str" default='"./.checkpoints"'>
+  스토리지 대상. `JsonProvider`는 디렉토리, `SqliteProvider`는 데이터베이스 파일 경로.
+</ParamField>
+
+<ParamField path="on_events" type="list[CheckpointEventType]" default='["task_completed"]'>
+  체크포인트를 트리거하는 이벤트 타입. `CheckpointEventType`은 `Literal`이므로 타입 체커가 자동 완성하고 지원되지 않는 값을 거부합니다. 전체 목록은 [이벤트 타입](#이벤트-타입) 참조.
+</ParamField>
+
+<ParamField path="provider" type="BaseProvider" default="JsonProvider()">
+  스토리지 백엔드. `JsonProvider` 또는 `SqliteProvider`.
+</ParamField>
+
+<ParamField path="max_checkpoints" type="int | None" default="None">
+  보관할 최대 체크포인트 수. 각 기록 후 가장 오래된 것이 제거됩니다.
+</ParamField>
+
+<ParamField path="restore_from" type="Path | str | None" default="None">
+  `from_checkpoint`를 통해 전달될 때 복원할 체크포인트.
+</ParamField>
+
+### `checkpoint` 필드 값
+
+`Crew`, `Flow`, `Agent`에서 사용 가능.
+
+<ParamField path="None" type="기본값">
+  부모에서 상속.
+</ParamField>
+
+<ParamField path="True" type="bool">
+  기본값으로 활성화.
+</ParamField>
+
+<ParamField path="False" type="bool">
+  명시적 옵트아웃. 상속을 중단합니다.
+</ParamField>
+
+<ParamField path="CheckpointConfig(...)" type="CheckpointConfig">
+  사용자 정의 설정.
+</ParamField>
+
+### 이벤트 타입
+
+`on_events`는 `CheckpointEventType` 값의 임의 조합을 받습니다. 기본값 `["task_completed"]`는 완료된 태스크당 하나의 체크포인트를 기록하며, `["*"]`는 모든 이벤트와 일치합니다.
 
 <Warning>
-`["*"]` 또는 `llm_call_completed`와 같은 고빈도 이벤트를 사용하면 많은 체크포인트 파일이 생성되어 성능에 영향을 줄 수 있습니다. `max_checkpoints`를 사용하여 디스크 사용량을 제한하세요.
+`["*"]` 및 `llm_call_completed`와 같은 고빈도 이벤트는 많은 체크포인트를 기록하고 성능을 저하시킬 수 있습니다. `max_checkpoints`와 함께 사용하세요.
 </Warning>
 
-## 수동 체크포인팅
+<Expandable title="지원되는 모든 이벤트">
 
-완전한 제어를 위해 자체 이벤트 핸들러를 등록하고 `state.checkpoint()`를 직접 호출할 수 있습니다:
+- **Task** — `task_started`, `task_completed`, `task_failed`, `task_evaluation`
+- **Crew** — `crew_kickoff_started`, `crew_kickoff_completed`, `crew_kickoff_failed`, `crew_train_started`, `crew_train_completed`, `crew_train_failed`, `crew_test_started`, `crew_test_completed`, `crew_test_failed`, `crew_test_result`
+- **Agent** — `agent_execution_started`, `agent_execution_completed`, `agent_execution_error`, `lite_agent_execution_started`, `lite_agent_execution_completed`, `lite_agent_execution_error`, `agent_evaluation_started`, `agent_evaluation_completed`, `agent_evaluation_failed`
+- **Flow** — `flow_created`, `flow_started`, `flow_finished`, `flow_paused`, `method_execution_started`, `method_execution_finished`, `method_execution_failed`, `method_execution_paused`, `human_feedback_requested`, `human_feedback_received`, `flow_input_requested`, `flow_input_received`
+- **LLM** — `llm_call_started`, `llm_call_completed`, `llm_call_failed`, `llm_stream_chunk`, `llm_thinking_chunk`
+- **LLM Guardrail** — `llm_guardrail_started`, `llm_guardrail_completed`, `llm_guardrail_failed`
+- **Tool** — `tool_usage_started`, `tool_usage_finished`, `tool_usage_error`, `tool_validate_input_error`, `tool_selection_error`, `tool_execution_error`
+- **Memory** — `memory_save_started`, `memory_save_completed`, `memory_save_failed`, `memory_query_started`, `memory_query_completed`, `memory_query_failed`, `memory_retrieval_started`, `memory_retrieval_completed`, `memory_retrieval_failed`
+- **Knowledge** — `knowledge_search_query_started`, `knowledge_search_query_completed`, `knowledge_query_started`, `knowledge_query_completed`, `knowledge_query_failed`, `knowledge_search_query_failed`
+- **Reasoning** — `agent_reasoning_started`, `agent_reasoning_completed`, `agent_reasoning_failed`
+- **MCP** — `mcp_connection_started`, `mcp_connection_completed`, `mcp_connection_failed`, `mcp_tool_execution_started`, `mcp_tool_execution_completed`, `mcp_tool_execution_failed`, `mcp_config_fetch_failed`
+- **Observation** — `step_observation_started`, `step_observation_completed`, `step_observation_failed`, `plan_refinement`, `plan_replan_triggered`, `goal_achieved_early`
+- **Skill** — `skill_discovery_started`, `skill_discovery_completed`, `skill_loaded`, `skill_activated`, `skill_load_failed`
+- **Logging** — `agent_logs_started`, `agent_logs_execution`
+- **A2A** — `a2a_delegation_started`, `a2a_delegation_completed`, `a2a_conversation_started`, `a2a_conversation_completed`, `a2a_message_sent`, `a2a_response_received`, `a2a_polling_started`, `a2a_polling_status`, `a2a_push_notification_registered`, `a2a_push_notification_received`, `a2a_push_notification_sent`, `a2a_push_notification_timeout`, `a2a_streaming_started`, `a2a_streaming_chunk`, `a2a_agent_card_fetched`, `a2a_authentication_failed`, `a2a_artifact_received`, `a2a_connection_error`, `a2a_server_task_started`, `a2a_server_task_completed`, `a2a_server_task_canceled`, `a2a_server_task_failed`, `a2a_parallel_delegation_started`, `a2a_parallel_delegation_completed`, `a2a_transport_negotiated`, `a2a_content_type_negotiated`, `a2a_context_created`, `a2a_context_expired`, `a2a_context_idle`, `a2a_context_completed`, `a2a_context_pruned`
+- **시스템 시그널** — `SIGTERM`, `SIGINT`, `SIGHUP`, `SIGTSTP`, `SIGCONT`
+- **와일드카드** — `"*"`는 모든 이벤트와 일치합니다.
 
-```python
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.types.llm_events import LLMCallCompletedEvent
+</Expandable>
 
-# 동기 핸들러
-@crewai_event_bus.on(LLMCallCompletedEvent)
-def on_llm_done(source, event, state):
-    path = state.checkpoint("./my_checkpoints")
-    print(f"체크포인트 저장: {path}")
+### 스토리지 프로바이더
 
-# 비동기 핸들러
-@crewai_event_bus.on(LLMCallCompletedEvent)
-async def on_llm_done_async(source, event, state):
-    path = await state.acheckpoint("./my_checkpoints")
-    print(f"체크포인트 저장: {path}")
-```
+<ParamField path="JsonProvider" type="provider">
+  체크포인트당 하나의 파일, `location` 내부에 `<timestamp>_<uuid>.json` 형식으로 명명.
+</ParamField>
 
-`state` 인수는 핸들러가 3개의 매개변수를 받을 때 이벤트 버스가 자동으로 전달하는 `RuntimeState`입니다. [Event Listeners](/ko/concepts/event-listener) 문서에 나열된 모든 이벤트 타입에 핸들러를 등록할 수 있습니다.
+<ParamField path="SqliteProvider" type="provider">
+  WAL 저널링이 있는 `location`의 단일 데이터베이스 파일.
+</ParamField>
 
-체크포인팅은 best-effort입니다: 체크포인트 기록이 실패하면 오류가 로그에 기록되지만 실행은 중단 없이 계속됩니다.
+### CLI
+
+| 명령 | 목적 |
+|:-----|:-----|
+| `crewai checkpoint` | TUI 실행; 스토리지 자동 감지. |
+| `crewai checkpoint --location <path>` | 특정 위치에 대해 TUI 실행. |
+| `crewai checkpoint list <path>` | 체크포인트 나열. |
+| `crewai checkpoint info <path>` | 체크포인트 파일 또는 SQLite 데이터베이스의 최신 항목 검사. |

docs/pt-BR/concepts/checkpointing.mdx

@@ -5,225 +5,386 @@ icon: floppy-disk
 mode: "wide"
 ---
 
-<Warning>
-O checkpointing esta em versao inicial. As APIs podem mudar em versoes futuras.
-</Warning>
+O checkpointing salva um snapshot do estado de execucao durante uma execucao para que uma crew, flow ou agente possa retomar apos uma falha ou ser bifurcado em uma branch alternativa.
 
-## Visao Geral
+<CardGroup cols={2}>
+  <Card title="Explicacao" icon="lightbulb" href="#explicacao">
+    Como o checkpointing funciona: eventos, armazenamento e heranca.
+  </Card>
+  <Card title="Tutorial" icon="graduation-cap" href="#tutorial-retomar-uma-crew-com-falha">
+    Um passo a passo de 5 minutos: executar, interromper, retomar.
+  </Card>
+  <Card title="Guias de uso" icon="screwdriver-wrench" href="#guias-de-uso">
+    Receitas focadas em tarefas para fluxos comuns.
+  </Card>
+  <Card title="Referencia" icon="book" href="#referencia">
+    `CheckpointConfig`, eventos, provedores e CLI.
+  </Card>
+</CardGroup>
 
-O checkpointing salva automaticamente o estado de execucao durante uma execucao. Se uma crew, flow ou agente falhar no meio da execucao, voce pode restaurar a partir do ultimo checkpoint e retomar sem reexecutar o trabalho ja concluido.
+## Explicacao
 
-## Inicio Rapido
+### O que e um checkpoint
 
-```python
-from crewai import Crew, CheckpointConfig
+Um checkpoint captura tudo o que o CrewAI precisa para recriar uma execucao em andamento: o estado completo da crew, flow ou agente — configuracao, memoria e fontes de conhecimento dos agentes, progresso das tarefas, saidas intermediarias — junto com os inputs do kickoff, o historico de eventos ate aquele ponto e um ID de linhagem que liga o checkpoint a execucao de origem.
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=True,  # usa padroes: ./.checkpoints, em task_completed
-)
-result = crew.kickoff()
-```
+Restaurar reconstroi esse estado e continua. Tarefas concluidas sao puladas, memoria e conhecimento sao reidratados, e o trabalho downstream roda contra as mesmas saidas que a execucao original produziu. Fazer fork executa a mesma restauracao sob uma nova linhagem, para que a nova branch e a execucao original gravem checkpoints lado a lado sem sobrescrever uma a outra.
 
-Os arquivos de checkpoint sao gravados em `./.checkpoints/` apos cada tarefa concluida.
+### Quando os checkpoints sao gravados
 
-## Configuracao
+O checkpointing e orientado a eventos. O runtime se inscreve nos eventos selecionados em `on_events` e grava um checkpoint sempre que um e disparado. O padrao `task_completed` produz um checkpoint por tarefa finalizada — um equilibrio razoavel entre granularidade e uso de disco. Eventos de alta frequencia como `llm_call_completed` estao disponiveis para recuperacao mais granular, mas gravam muito mais arquivos.
 
-Use `CheckpointConfig` para controle total:
+### Armazenamento
 
-```python
-from crewai import Crew, CheckpointConfig
+Dois provedores acompanham o CrewAI:
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        on_events=["task_completed", "crew_kickoff_completed"],
-        max_checkpoints=5,
-    ),
-)
-```
+- `JsonProvider` grava um arquivo por checkpoint. Legivel e facil de inspecionar.
+- `SqliteProvider` grava em um unico banco SQLite. Melhor para checkpointing de alta frequencia.
 
-### Campos do CheckpointConfig
+Ambos removem os checkpoints mais antigos quando `max_checkpoints` esta definido.
 
-| Campo | Tipo | Padrao | Descricao |
-|:------|:-----|:-------|:----------|
-| `location` | `str` | `"./.checkpoints"` | Caminho para os arquivos de checkpoint |
-| `on_events` | `list[str]` | `["task_completed"]` | Tipos de evento que acionam um checkpoint |
-| `provider` | `BaseProvider` | `JsonProvider()` | Backend de armazenamento |
-| `max_checkpoints` | `int \| None` | `None` | Maximo de arquivos a manter; os mais antigos sao removidos primeiro |
+<Note>
+As gravacoes de checkpoint sao best-effort. Um checkpoint que falha e registrado em log, mas nao interrompe a execucao.
+</Note>
 
-### Heranca e Desativacao
+### Modelo de heranca
 
-O campo `checkpoint` em Crew, Flow e Agent aceita `CheckpointConfig`, `True`, `False` ou `None`:
+`Crew`, `Flow` e `Agent` aceitam um argumento `checkpoint`. Filhos herdam do pai a menos que definam seu proprio valor ou passem `False` para desativar. Ative o checkpointing uma vez na crew e todos os agentes participam, ou exclua um agente seletivamente.
 
-| Valor | Comportamento |
-|:------|:--------------|
-| `None` (padrao) | Herda do pai. Um agente herda a configuracao da crew. |
-| `True` | Ativa com padroes. |
-| `False` | Desativacao explicita. Interrompe a heranca do pai. |
-| `CheckpointConfig(...)` | Configuracao personalizada. |
+## Tutorial: Retomar uma crew com falha
 
-```python
-crew = Crew(
-    agents=[
-        Agent(role="Researcher", ...),                  # herda checkpoint da crew
-        Agent(role="Writer", ..., checkpoint=False),     # desativado, sem checkpoints
-    ],
-    tasks=[...],
-    checkpoint=True,
-)
-```
+Este passo a passo leva cerca de 5 minutos. Voce executara uma crew de duas tarefas, a interrompera no meio e a retomara a partir do checkpoint salvo.
 
-## Retomando a partir de um Checkpoint
+<Steps>
+  <Step title="Crie a crew com checkpointing ativado">
+    ```python
+    from crewai import Agent, Crew, Task
 
-```python
-# Restaurar e retomar
-crew = Crew.from_checkpoint("./my_checkpoints/20260407T120000_abc123.json")
-result = crew.kickoff()  # retoma a partir da ultima tarefa concluida
-```
+    researcher = Agent(role="Researcher", goal="Research", backstory="Expert")
+    writer = Agent(role="Writer", goal="Write", backstory="Expert")
 
-A crew restaurada pula tarefas ja concluidas e retoma a partir da primeira incompleta.
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[
+            Task(description="Research AI trends", agent=researcher, expected_output="bullets"),
+            Task(description="Write a summary", agent=writer, expected_output="paragraph"),
+        ],
+        checkpoint=True,
+    )
+    ```
+  </Step>
+  <Step title="Execute e interrompa apos a primeira tarefa">
+    ```python
+    result = crew.kickoff()
+    ```
 
-## Funciona em Crew, Flow e Agent
+    Pressione `Ctrl+C` apos a primeira tarefa concluir. Em `./.checkpoints/`, um arquivo `<timestamp>_<uuid>.json` e o checkpoint.
+  </Step>
+  <Step title="Retome a partir do checkpoint">
+    ```python
+    from crewai import CheckpointConfig
 
-### Crew
+    result = crew.kickoff(
+        from_checkpoint=CheckpointConfig(
+            restore_from="./.checkpoints/<timestamp>_<uuid>.json",
+        ),
+    )
+    ```
 
-```python
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[research_task, write_task, review_task],
-    checkpoint=CheckpointConfig(location="./crew_cp"),
-)
-```
+    A tarefa de pesquisa e pulada, o escritor executa contra a saida de pesquisa salva e a crew finaliza.
+  </Step>
+</Steps>
 
-Gatilho padrao: `task_completed` (um checkpoint por tarefa finalizada).
+## Guias de uso
 
-### Flow
+<AccordionGroup>
+  <Accordion title="Ativar checkpointing com padroes" icon="play">
+    ```python
+    crew = Crew(agents=[...], tasks=[...], checkpoint=True)
+    ```
 
-```python
-from crewai.flow.flow import Flow, start, listen
-from crewai import CheckpointConfig
+    Grava em `./.checkpoints/` em cada `task_completed`.
+  </Accordion>
 
-class MyFlow(Flow):
-    @start()
-    def step_one(self):
-        return "data"
+  <Accordion title="Personalizar armazenamento e frequencia" icon="sliders">
+    ```python
+    from crewai import Crew, CheckpointConfig
 
-    @listen(step_one)
-    def step_two(self, data):
-        return process(data)
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            on_events=["task_completed", "crew_kickoff_completed"],
+            max_checkpoints=5,
+        ),
+    )
+    ```
+  </Accordion>
 
-flow = MyFlow(
-    checkpoint=CheckpointConfig(
-        location="./flow_cp",
-        on_events=["method_execution_finished"],
-    ),
-)
-result = flow.kickoff()
+  <Accordion title="Escolher um provedor de armazenamento" icon="database">
+    <CodeGroup>
+    ```python JsonProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import JsonProvider
 
-# Retomar
-flow = MyFlow.from_checkpoint("./flow_cp/20260407T120000_abc123.json")
-result = flow.kickoff()
-```
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./my_checkpoints",
+            provider=JsonProvider(),
+            max_checkpoints=5,
+        ),
+    )
+    ```
+    ```python SqliteProvider
+    from crewai import Crew, CheckpointConfig
+    from crewai.state import SqliteProvider
 
-### Agent
+    crew = Crew(
+        agents=[...],
+        tasks=[...],
+        checkpoint=CheckpointConfig(
+            location="./.checkpoints.db",
+            provider=SqliteProvider(),
+            max_checkpoints=50,
+        ),
+    )
+    ```
+    </CodeGroup>
 
-```python
-agent = Agent(
-    role="Researcher",
-    goal="Research topics",
-    backstory="Expert researcher",
-    checkpoint=CheckpointConfig(
-        location="./agent_cp",
-        on_events=["lite_agent_execution_completed"],
-    ),
-)
-result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
-```
+    <Tip>
+    O SQLite ativa o modo journal WAL para leituras concorrentes. Prefira-o para checkpointing de alta frequencia.
+    </Tip>
+  </Accordion>
 
-## Provedores de Armazenamento
+  <Accordion title="Desativar um agente especifico" icon="user-slash">
+    ```python
+    crew = Crew(
+        agents=[
+            Agent(role="Researcher", ...),
+            Agent(role="Writer", ..., checkpoint=False),
+        ],
+        tasks=[...],
+        checkpoint=True,
+    )
+    ```
+  </Accordion>
 
-O CrewAI inclui dois provedores de armazenamento para checkpoints.
+  <Accordion title="Fazer fork em uma nova branch" icon="code-branch">
+    `fork()` restaura um checkpoint sob uma nova linhagem para que a nova execucao nao colida com a original.
 
-### JsonProvider (padrao)
+    ```python
+    config = CheckpointConfig(restore_from="./my_checkpoints/<file>.json")
+    crew = Crew.fork(config, branch="experiment-a")
+    result = crew.kickoff(inputs={"strategy": "aggressive"})
+    ```
 
-Grava cada checkpoint como um arquivo JSON separado.
+    O label `branch` e opcional; um e gerado se omitido.
+  </Accordion>
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import JsonProvider
+  <Accordion title="Checkpoint em Crew, Flow ou Agent" icon="cubes">
+    <Tabs>
+      <Tab title="Crew">
+        ```python
+        crew = Crew(
+            agents=[researcher, writer],
+            tasks=[research_task, write_task, review_task],
+            checkpoint=CheckpointConfig(location="./crew_cp"),
+        )
+        ```
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./my_checkpoints",
-        provider=JsonProvider(),
-        max_checkpoints=5,
-    ),
-)
-```
+        Gatilho padrao: `task_completed`.
+      </Tab>
+      <Tab title="Flow">
+        ```python
+        from crewai.flow.flow import Flow, start, listen
+        from crewai import CheckpointConfig
 
-### SqliteProvider
+        class MyFlow(Flow):
+            @start()
+            def step_one(self):
+                return "data"
 
-Armazena todos os checkpoints em um unico arquivo SQLite.
+            @listen(step_one)
+            def step_two(self, data):
+                return process(data)
 
-```python
-from crewai import Crew, CheckpointConfig
-from crewai.state import SqliteProvider
+        flow = MyFlow(
+            checkpoint=CheckpointConfig(
+                location="./flow_cp",
+                on_events=["method_execution_finished"],
+            ),
+        )
+        result = flow.kickoff()
+        ```
+      </Tab>
+      <Tab title="Agent">
+        ```python
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="Expert researcher",
+            checkpoint=CheckpointConfig(
+                location="./agent_cp",
+                on_events=["lite_agent_execution_completed"],
+            ),
+        )
+        result = agent.kickoff(messages=[{"role": "user", "content": "Research AI trends"}])
+        ```
+      </Tab>
+    </Tabs>
+  </Accordion>
 
-crew = Crew(
-    agents=[...],
-    tasks=[...],
-    checkpoint=CheckpointConfig(
-        location="./.checkpoints.db",
-        provider=SqliteProvider(),
-    ),
-)
-```
+  <Accordion title="Gravar um checkpoint manualmente" icon="code">
+    Registre um handler em qualquer evento e chame `state.checkpoint()`.
 
+    <CodeGroup>
+    ```python Sync
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-## Tipos de Evento
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    def on_llm_done(source, event, state):
+        path = state.checkpoint("./my_checkpoints")
+        print(f"Checkpoint salvo: {path}")
+    ```
+    ```python Async
+    from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.types.llm_events import LLMCallCompletedEvent
 
-O campo `on_events` aceita qualquer combinacao de strings de tipo de evento. Escolhas comuns:
+    @crewai_event_bus.on(LLMCallCompletedEvent)
+    async def on_llm_done_async(source, event, state):
+        path = await state.acheckpoint("./my_checkpoints")
+        print(f"Checkpoint salvo: {path}")
+    ```
+    </CodeGroup>
 
-| Caso de Uso | Eventos |
-|:------------|:--------|
-| Apos cada tarefa (Crew) | `["task_completed"]` |
-| Apos cada metodo do flow | `["method_execution_finished"]` |
-| Apos execucao do agente | `["agent_execution_completed"]`, `["lite_agent_execution_completed"]` |
-| Apenas na conclusao da crew | `["crew_kickoff_completed"]` |
-| Apos cada chamada LLM | `["llm_call_completed"]` |
-| Em tudo | `["*"]` |
+    Um argumento `state` e fornecido automaticamente quando o handler recebe tres parametros. Veja [Event Listeners](/pt-BR/concepts/event-listener) para o catalogo completo de eventos.
+  </Accordion>
+
+  <Accordion title="Navegar, retomar e fazer fork pela CLI" icon="terminal">
+    ```bash
+    crewai checkpoint                              # detecta automaticamente .checkpoints/ ou .checkpoints.db
+    crewai checkpoint --location ./my_checkpoints
+    crewai checkpoint --location ./.checkpoints.db
+    ```
+
+    <Frame>
+      <img src="/images/checkpointing.png" alt="Checkpoint TUI" />
+    </Frame>
+
+    O painel esquerdo agrupa checkpoints por branch; forks aninham sob seu pai. Selecionar um checkpoint mostra seus metadados, estado da entidade e progresso das tarefas. **Resume** continua a execucao; **Fork** inicia uma nova branch.
+
+    O painel de detalhes expoe duas areas editaveis:
+
+    - **Inputs** — os inputs originais do kickoff, preenchidos e editaveis.
+    - **Saidas das tarefas** — saidas das tarefas concluidas. Editar uma saida e pressionar **Fork** invalida tarefas downstream para que sejam reexecutadas com o contexto modificado.
+
+    <Tip>
+    Util para exploracao de cenarios: fork, ajuste, observe.
+    </Tip>
+  </Accordion>
+
+  <Accordion title="Inspecionar checkpoints sem a TUI" icon="magnifying-glass">
+    ```bash
+    crewai checkpoint list ./my_checkpoints
+    crewai checkpoint info ./my_checkpoints/<file>.json
+    crewai checkpoint info ./.checkpoints.db
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## Referencia
+
+### `CheckpointConfig`
+
+<ParamField path="location" type="str" default='"./.checkpoints"'>
+  Destino do armazenamento. Diretorio para `JsonProvider`, caminho de arquivo de banco para `SqliteProvider`.
+</ParamField>
+
+<ParamField path="on_events" type="list[CheckpointEventType]" default='["task_completed"]'>
+  Tipos de evento que disparam um checkpoint. `CheckpointEventType` e um `Literal` — seu type checker autocompleta e rejeita valores nao suportados. Veja [tipos de evento](#tipos-de-evento) para a lista completa.
+</ParamField>
+
+<ParamField path="provider" type="BaseProvider" default="JsonProvider()">
+  Backend de armazenamento. `JsonProvider` ou `SqliteProvider`.
+</ParamField>
+
+<ParamField path="max_checkpoints" type="int | None" default="None">
+  Maximo de checkpoints a reter. Os mais antigos sao removidos apos cada gravacao.
+</ParamField>
+
+<ParamField path="restore_from" type="Path | str | None" default="None">
+  Checkpoint a restaurar quando passado via `from_checkpoint`.
+</ParamField>
+
+### Valores do campo `checkpoint`
+
+Aceito por `Crew`, `Flow` e `Agent`.
+
+<ParamField path="None" type="padrao">
+  Herda do pai.
+</ParamField>
+
+<ParamField path="True" type="bool">
+  Ativa com padroes.
+</ParamField>
+
+<ParamField path="False" type="bool">
+  Desativacao explicita. Interrompe a heranca.
+</ParamField>
+
+<ParamField path="CheckpointConfig(...)" type="CheckpointConfig">
+  Configuracao personalizada.
+</ParamField>
+
+### Tipos de evento
+
+`on_events` aceita qualquer combinacao de valores `CheckpointEventType`. O padrao `["task_completed"]` grava um checkpoint por tarefa finalizada; `["*"]` corresponde a todos os eventos.
 
 <Warning>
-Usar `["*"]` ou eventos de alta frequencia como `llm_call_completed` gravara muitos arquivos de checkpoint e pode impactar o desempenho. Use `max_checkpoints` para limitar o uso de disco.
+`["*"]` e eventos de alta frequencia como `llm_call_completed` gravam muitos checkpoints e podem degradar o desempenho. Combine com `max_checkpoints`.
 </Warning>
 
-## Checkpointing Manual
+<Expandable title="Todos os eventos suportados">
 
-Para controle total, registre seu proprio handler de evento e chame `state.checkpoint()` diretamente:
+- **Task** — `task_started`, `task_completed`, `task_failed`, `task_evaluation`
+- **Crew** — `crew_kickoff_started`, `crew_kickoff_completed`, `crew_kickoff_failed`, `crew_train_started`, `crew_train_completed`, `crew_train_failed`, `crew_test_started`, `crew_test_completed`, `crew_test_failed`, `crew_test_result`
+- **Agent** — `agent_execution_started`, `agent_execution_completed`, `agent_execution_error`, `lite_agent_execution_started`, `lite_agent_execution_completed`, `lite_agent_execution_error`, `agent_evaluation_started`, `agent_evaluation_completed`, `agent_evaluation_failed`
+- **Flow** — `flow_created`, `flow_started`, `flow_finished`, `flow_paused`, `method_execution_started`, `method_execution_finished`, `method_execution_failed`, `method_execution_paused`, `human_feedback_requested`, `human_feedback_received`, `flow_input_requested`, `flow_input_received`
+- **LLM** — `llm_call_started`, `llm_call_completed`, `llm_call_failed`, `llm_stream_chunk`, `llm_thinking_chunk`
+- **LLM Guardrail** — `llm_guardrail_started`, `llm_guardrail_completed`, `llm_guardrail_failed`
+- **Tool** — `tool_usage_started`, `tool_usage_finished`, `tool_usage_error`, `tool_validate_input_error`, `tool_selection_error`, `tool_execution_error`
+- **Memory** — `memory_save_started`, `memory_save_completed`, `memory_save_failed`, `memory_query_started`, `memory_query_completed`, `memory_query_failed`, `memory_retrieval_started`, `memory_retrieval_completed`, `memory_retrieval_failed`
+- **Knowledge** — `knowledge_search_query_started`, `knowledge_search_query_completed`, `knowledge_query_started`, `knowledge_query_completed`, `knowledge_query_failed`, `knowledge_search_query_failed`
+- **Reasoning** — `agent_reasoning_started`, `agent_reasoning_completed`, `agent_reasoning_failed`
+- **MCP** — `mcp_connection_started`, `mcp_connection_completed`, `mcp_connection_failed`, `mcp_tool_execution_started`, `mcp_tool_execution_completed`, `mcp_tool_execution_failed`, `mcp_config_fetch_failed`
+- **Observation** — `step_observation_started`, `step_observation_completed`, `step_observation_failed`, `plan_refinement`, `plan_replan_triggered`, `goal_achieved_early`
+- **Skill** — `skill_discovery_started`, `skill_discovery_completed`, `skill_loaded`, `skill_activated`, `skill_load_failed`
+- **Logging** — `agent_logs_started`, `agent_logs_execution`
+- **A2A** — `a2a_delegation_started`, `a2a_delegation_completed`, `a2a_conversation_started`, `a2a_conversation_completed`, `a2a_message_sent`, `a2a_response_received`, `a2a_polling_started`, `a2a_polling_status`, `a2a_push_notification_registered`, `a2a_push_notification_received`, `a2a_push_notification_sent`, `a2a_push_notification_timeout`, `a2a_streaming_started`, `a2a_streaming_chunk`, `a2a_agent_card_fetched`, `a2a_authentication_failed`, `a2a_artifact_received`, `a2a_connection_error`, `a2a_server_task_started`, `a2a_server_task_completed`, `a2a_server_task_canceled`, `a2a_server_task_failed`, `a2a_parallel_delegation_started`, `a2a_parallel_delegation_completed`, `a2a_transport_negotiated`, `a2a_content_type_negotiated`, `a2a_context_created`, `a2a_context_expired`, `a2a_context_idle`, `a2a_context_completed`, `a2a_context_pruned`
+- **Sinais de sistema** — `SIGTERM`, `SIGINT`, `SIGHUP`, `SIGTSTP`, `SIGCONT`
+- **Wildcard** — `"*"` corresponde a todos os eventos.
 
-```python
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.types.llm_events import LLMCallCompletedEvent
+</Expandable>
 
-# Handler sincrono
-@crewai_event_bus.on(LLMCallCompletedEvent)
-def on_llm_done(source, event, state):
-    path = state.checkpoint("./my_checkpoints")
-    print(f"Checkpoint salvo: {path}")
+### Provedores de armazenamento
 
-# Handler assincrono
-@crewai_event_bus.on(LLMCallCompletedEvent)
-async def on_llm_done_async(source, event, state):
-    path = await state.acheckpoint("./my_checkpoints")
-    print(f"Checkpoint salvo: {path}")
-```
+<ParamField path="JsonProvider" type="provider">
+  Um arquivo por checkpoint, nomeado `<timestamp>_<uuid>.json` dentro de `location`.
+</ParamField>
 
-O argumento `state` e o `RuntimeState` passado automaticamente pelo barramento de eventos quando seu handler aceita 3 parametros. Voce pode registrar handlers em qualquer tipo de evento listado na documentacao de [Event Listeners](/pt-BR/concepts/event-listener).
+<ParamField path="SqliteProvider" type="provider">
+  Arquivo de banco unico em `location` com journaling WAL.
+</ParamField>
 
-O checkpointing e best-effort: se uma gravacao de checkpoint falhar, o erro e registrado no log, mas a execucao continua sem interrupcao.
+### CLI
+
+| Comando | Proposito |
+|:--------|:----------|
+| `crewai checkpoint` | Inicia a TUI; detecta o armazenamento automaticamente. |
+| `crewai checkpoint --location <path>` | Inicia a TUI em uma localizacao especifica. |
+| `crewai checkpoint list <path>` | Lista checkpoints. |
+| `crewai checkpoint info <path>` | Inspeciona um arquivo de checkpoint ou a entrada mais recente em um banco SQLite. |

lib/crewai/src/crewai/agent/core.py

@@ -1109,9 +1109,14 @@ class Agent(BaseAgent):
         """
         if self.agent_executor is None:
             raise RuntimeError("Agent executor is not initialized.")
+        if not isinstance(self.llm, BaseLLM):
+            raise RuntimeError(
+                "LLM must be resolved before updating agent executor parameters."
+            )
 
         if task is not None:
             self.agent_executor.task = task
+        self.agent_executor.llm = self.llm
         self.agent_executor.tools = tools
         self.agent_executor.original_tools = raw_tools
         self.agent_executor.prompt = prompt
@@ -1411,6 +1416,11 @@ class Agent(BaseAgent):
 
         if _is_resuming_agent_executor(self.agent_executor):
             executor = self.agent_executor
+            if not isinstance(self.llm, BaseLLM):
+                raise RuntimeError(
+                    "LLM must be resolved before resuming agent executor."
+                )
+            executor.llm = self.llm
             executor.tools = parsed_tools
             executor.tools_names = get_tool_names(parsed_tools)
             executor.tools_description = render_text_description_and_args(parsed_tools)

lib/crewai/src/crewai/crew.py

@@ -443,16 +443,20 @@ class Crew(FlowTrackable, BaseModel):
                 if node.event.type == "task_started" and node.event.task_id:
                     started_task_ids.add(node.event.task_id)
 
+        is_hierarchical = self.process == Process.hierarchical
         resuming_task_agent_roles: set[str] = set()
         for task in self.tasks:
-            if (
-                task.output is None
-                and task.agent is not None
-                and str(task.id) in started_task_ids
-            ):
-                resuming_task_agent_roles.add(task.agent.role)
+            if task.output is not None or str(task.id) not in started_task_ids:
+                continue
+            executing_agent = self.manager_agent if is_hierarchical else task.agent
+            if executing_agent is not None:
+                resuming_task_agent_roles.add(executing_agent.role)
 
-        for agent in self.agents:
+        candidate_agents: list[BaseAgent] = list(self.agents)
+        if self.manager_agent is not None:
+            candidate_agents.append(self.manager_agent)
+
+        for agent in candidate_agents:
             agent.crew = self
             executor = agent.agent_executor
             if (
@@ -467,7 +471,7 @@ class Crew(FlowTrackable, BaseModel):
                 agent.agent_executor = None
         for task in self.tasks:
             if task.agent is not None:
-                for agent in self.agents:
+                for agent in candidate_agents:
                     if agent.role == task.agent.role:
                         task.agent = agent
                         if agent.agent_executor is not None and task.output is None:
@@ -536,25 +540,9 @@ class Crew(FlowTrackable, BaseModel):
         if state is None:
             return
 
-        # Restore crew scope and the in-progress task scope. Inner scopes
-        # (agent, llm, tool) are re-created by the executor on resume.
         stack: list[tuple[str, str]] = []
         if self._kickoff_event_id:
             stack.append((self._kickoff_event_id, "crew_kickoff_started"))
-
-        # Find the task_started event for the in-progress task (skipped on resume)
-        for task in self.tasks:
-            if task.output is None:
-                task_id_str = str(task.id)
-                for node in state.event_record.nodes.values():
-                    if (
-                        node.event.type == "task_started"
-                        and node.event.task_id == task_id_str
-                    ):
-                        stack.append((node.event.event_id, "task_started"))
-                        break
-                break
-
         restore_event_scope(tuple(stack))
 
         # Restore last_event_id and emission counter from the record

lib/crewai/src/crewai/events/event_context.py

@@ -138,6 +138,36 @@ def restore_event_scope(stack: tuple[tuple[str, str], ...]) -> None:
     _event_id_stack.set(stack)
 
 
+def resume_task_scope(task_id: str) -> bool:
+    """Push the latest recorded ``task_started`` scope for a task.
+
+    Args:
+        task_id: The task identifier to look up in the active event record.
+
+    Returns:
+        ``True`` if a prior scope was pushed; ``False`` otherwise.
+    """
+    from crewai.events.event_bus import crewai_event_bus
+
+    state = crewai_event_bus._runtime_state
+    if state is None:
+        return False
+    latest_event_id: str | None = None
+    latest_seq = -1
+    for node in list(state.event_record.nodes.values()):
+        ev = node.event
+        if ev.type != "task_started" or ev.task_id != task_id:
+            continue
+        seq = ev.emission_sequence or 0
+        if seq > latest_seq:
+            latest_seq = seq
+            latest_event_id = ev.event_id
+    if latest_event_id is None:
+        return False
+    push_event_scope(latest_event_id, "task_started")
+    return True
+
+
 def push_event_scope(event_id: str, event_type: str = "") -> None:
     """Push an event ID and type onto the scope stack."""
     config = _event_context_config.get() or _default_config

lib/crewai/src/crewai/experimental/agent_executor.py

@@ -173,8 +173,10 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
     executor_type: Literal["experimental"] = "experimental"
     suppress_flow_events: bool = True  # always suppress for executor
-    llm: BaseLLM = Field(exclude=True)
-    prompt: SystemPromptResult | StandardPromptResult = Field(exclude=True)
+    llm: BaseLLM | None = Field(default=None, exclude=True)
+    prompt: SystemPromptResult | StandardPromptResult | None = Field(
+        default=None, exclude=True
+    )
     max_iter: int = Field(default=25, exclude=True)
     tools: list[CrewStructuredTool] = Field(default_factory=list, exclude=True)
     tools_names: str = Field(default="", exclude=True)
@@ -2585,6 +2587,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
             self._kickoff_input = inputs.get("input", "")
 
+            if self.llm is None or self.prompt is None:
+                raise RuntimeError(
+                    "AgentExecutor.llm or .prompt is unset; the executor was "
+                    "not fully restored or initialized before execution."
+                )
             if "system" in self.prompt:
                 from crewai.llms.cache import mark_cache_breakpoint
 
@@ -2686,6 +2693,11 @@ class AgentExecutor(Flow[AgentExecutorState], BaseAgentExecutor):
 
             self._kickoff_input = inputs.get("input", "")
 
+            if self.llm is None or self.prompt is None:
+                raise RuntimeError(
+                    "AgentExecutor.llm or .prompt is unset; the executor was "
+                    "not fully restored or initialized before execution."
+                )
             if "system" in self.prompt:
                 from crewai.llms.cache import mark_cache_breakpoint
 

lib/crewai/src/crewai/task.py

@@ -40,6 +40,7 @@ from crewai.agents.agent_builder.base_agent import BaseAgent, _resolve_agent
 from crewai.context import reset_current_task_id, set_current_task_id
 from crewai.core.providers.content_processor import process_content
 from crewai.events.event_bus import crewai_event_bus
+from crewai.events.event_context import resume_task_scope
 from crewai.events.types.task_events import (
     TaskCompletedEvent,
     TaskFailedEvent,
@@ -661,7 +662,10 @@ class Task(BaseModel):
             tools = tools or self.tools or []
 
             self.processed_by_agents.add(agent.role)
-            if not (agent.agent_executor and agent.agent_executor._resuming):
+            executor = agent.agent_executor
+            if not (
+                executor and executor._resuming and resume_task_scope(str(self.id))
+            ):
                 crewai_event_bus.emit(
                     self, TaskStartedEvent(context=context, task=self)
                 )
@@ -783,7 +787,10 @@ class Task(BaseModel):
             tools = tools or self.tools or []
 
             self.processed_by_agents.add(agent.role)
-            if not (agent.agent_executor and agent.agent_executor._resuming):
+            executor = agent.agent_executor
+            if not (
+                executor and executor._resuming and resume_task_scope(str(self.id))
+            ):
                 crewai_event_bus.emit(
                     self, TaskStartedEvent(context=context, task=self)
                 )

lib/crewai/tests/events/test_event_context.py

@@ -11,6 +11,7 @@ from crewai.events.event_context import (
     MismatchBehavior,
     StackDepthExceededError,
     _event_context_config,
+    _event_id_stack,
     EventContextConfig,
     get_current_parent_id,
     get_enclosing_parent_id,
@@ -21,6 +22,7 @@ from crewai.events.event_context import (
     pop_event_scope,
     push_event_scope,
     reset_last_event_id,
+    resume_task_scope,
     set_last_event_id,
     set_triggering_event_id,
     triggered_by_scope,
@@ -180,6 +182,91 @@ class TestTriggeredByScope:
         assert get_triggering_event_id() is None
 
 
+class TestResumeTaskScope:
+    """Tests for the checkpoint-resume scope helper."""
+
+    @pytest.fixture(autouse=True)
+    def _reset_stack(self) -> None:
+        _event_id_stack.set(())
+
+    def _bind_runtime_state(self, *event_dicts: dict[str, object]):
+        from crewai.events import crewai_event_bus
+        from crewai.events.types.task_events import TaskStartedEvent
+        from crewai.state.event_record import EventRecord
+        from crewai.state.runtime import RuntimeState
+
+        record = EventRecord()
+        for spec in event_dicts:
+            ev = TaskStartedEvent(context=None, task=None)
+            ev.task_id = spec["task_id"]  # type: ignore[assignment]
+            ev.event_id = spec["event_id"]  # type: ignore[assignment]
+            ev.emission_sequence = spec["emission_sequence"]  # type: ignore[assignment]
+            record.add(ev)
+        state = RuntimeState(root=[])
+        state._event_record = record
+
+        previous = crewai_event_bus._runtime_state
+        crewai_event_bus._runtime_state = state
+        return crewai_event_bus, previous
+
+    def test_returns_false_when_no_runtime_state(self) -> None:
+        from crewai.events import crewai_event_bus
+
+        previous = crewai_event_bus._runtime_state
+        crewai_event_bus._runtime_state = None
+        try:
+            assert resume_task_scope("any-task") is False
+            assert _event_id_stack.get() == ()
+        finally:
+            crewai_event_bus._runtime_state = previous
+
+    def test_returns_false_when_no_matching_event(self) -> None:
+        bus, previous = self._bind_runtime_state(
+            {"task_id": "other", "event_id": "e1", "emission_sequence": 1},
+        )
+        try:
+            assert resume_task_scope("missing") is False
+            assert _event_id_stack.get() == ()
+        finally:
+            bus._runtime_state = previous
+
+    def test_pushes_latest_event_for_task(self) -> None:
+        bus, previous = self._bind_runtime_state(
+            {"task_id": "t1", "event_id": "e1", "emission_sequence": 1},
+            {"task_id": "t1", "event_id": "e2", "emission_sequence": 5},
+            {"task_id": "t1", "event_id": "e3", "emission_sequence": 3},
+            {"task_id": "t2", "event_id": "x1", "emission_sequence": 9},
+        )
+        try:
+            assert resume_task_scope("t1") is True
+            assert _event_id_stack.get() == (("e2", "task_started"),)
+        finally:
+            bus._runtime_state = previous
+
+    def test_pairs_cleanly_with_task_completed(self) -> None:
+        """The pushed scope must be popped by a matching task_completed."""
+        from crewai.events import crewai_event_bus
+        from crewai.events.types.task_events import TaskCompletedEvent
+        from crewai.tasks.task_output import TaskOutput
+
+        push_event_scope("kickoff-1", "crew_kickoff_started")
+        bus, previous = self._bind_runtime_state(
+            {"task_id": "t1", "event_id": "started-1", "emission_sequence": 1},
+        )
+        try:
+            assert resume_task_scope("t1") is True
+            output = TaskOutput(description="d", raw="r", agent="a")
+            completed = TaskCompletedEvent(output=output, task=None)
+            completed.task_id = "t1"
+            crewai_event_bus.emit(None, completed)
+            crewai_event_bus.flush()
+            assert _event_id_stack.get() == (("kickoff-1", "crew_kickoff_started"),)
+            assert completed.started_event_id == "started-1"
+        finally:
+            bus._runtime_state = previous
+            _event_id_stack.set(())
+
+
 def test_agent_scope_preserved_after_tool_error_event() -> None:
     from crewai.events import crewai_event_bus
     from crewai.events.types.tool_usage_events import (

pyproject.toml

@@ -189,6 +189,7 @@ exclude-newer = "3 days"
 # authlib <1.6.11 has GHSA-jj8c-mmj3-mmgv (CSRF bypass in cache-based state storage).
 # pip <26.1.1 has GHSA-58qw-9mgm-455v (archive handling); OSV considers 26.1.1 unaffected.
 # paramiko <5.0.0 has GHSA-r374-rxx8-8654 (SHA-1 in rsakey.py); OSV considers 5.0.0 unaffected. Transitive via composio-core.
+# starlette <1.0.1 has PYSEC-2026-161 (missing Host header validation poisons request.url.path, bypassing path-based auth). Transitive via fastapi.
 # litellm 1.83.8+ hard-pins openai==2.24.0, missing openai.types.responses used by crewai;
 # override to >=2.30.0 (the version litellm 1.83.7 used) until upstream relaxes the pin.
 override-dependencies = [
@@ -209,6 +210,7 @@ override-dependencies = [
     "authlib>=1.6.11",
     "pip>=26.1.1",
     "paramiko>=5.0.0",
+    "starlette>=1.0.1",
 ]
 
 [tool.uv.workspace]

uv.lock

@@ -13,9 +13,12 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-05-17T14:20:01.778505Z"
+exclude-newer = "2026-05-19T15:27:50.647689Z"
 exclude-newer-span = "P3D"
 
+[options.exclude-newer-package]
+starlette = "2026-05-22T16:00:00Z"
+
 [manifest]
 members = [
     "crewai",
@@ -40,6 +43,7 @@ overrides = [
     { name = "pypdf", specifier = ">=6.10.2,<7" },
     { name = "python-multipart", specifier = ">=0.0.27,<1" },
     { name = "rich", specifier = ">=13.7.1" },
+    { name = "starlette", specifier = ">=1.0.1" },
     { name = "transformers", marker = "python_full_version >= '3.10'", specifier = ">=5.4.0" },
     { name = "urllib3", specifier = ">=2.7.0" },
     { name = "uv", specifier = ">=0.11.6,<1" },
@@ -8528,15 +8532,15 @@ wheels = [
 
 [[package]]
 name = "starlette"
-version = "1.0.0"
+version = "1.0.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
     { name = "typing-extensions", marker = "python_full_version < '3.13'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/81/69/17425771797c36cded50b7fe44e850315d039f28b15901ab44839e70b593/starlette-1.0.0.tar.gz", hash = "sha256:6a4beaf1f81bb472fd19ea9b918b50dc3a77a6f2e190a12954b25e6ed5eea149", size = 2655289, upload-time = "2026-03-22T18:29:46.779Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/08/a3/84e821cc54b4ab50ae6dbc6ac3800a651b65ec35f045cc73785380654057/starlette-1.0.1.tar.gz", hash = "sha256:512399c5f1de7fac99c88572212ded9ddeddef2fb32afa82d724000e88b38f4f", size = 2659596, upload-time = "2026-05-21T21:58:58.433Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0b/c9/584bc9651441b4ba60cc4d557d8a547b5aff901af35bda3a4ee30c819b82/starlette-1.0.0-py3-none-any.whl", hash = "sha256:d3ec55e0bb321692d275455ddfd3df75fff145d009685eb40dc91fc66b03d38b", size = 72651, upload-time = "2026-03-22T18:29:45.111Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/e1/b2df4bc09a1e51ff664c1e17018a4274b42e5e9352e4a478ea540512dc88/starlette-1.0.1-py3-none-any.whl", hash = "sha256:7c0e69b2ee1c848bd54669d908500117a3ee13de603a21427e5c6fc1adf98dcd", size = 72802, upload-time = "2026-05-21T21:58:56.551Z" },
 ]
 
 [[package]]