chore: bump pypdf to 6.10.0 for GHSA-3crg-w4f6-42mx

Resolves CVE-2026-40260 where manipulated XMP metadata entity
declarations can exhaust RAM in pypdf <6.10.0.

.pre-commit-config.yaml

@@ -24,6 +24,14 @@ repos:
     rev: 0.11.3
     hooks:
       - id: uv-lock
+  - repo: local
+    hooks:
+      - id: pip-audit
+        name: pip-audit
+        entry: bash -c 'source .venv/bin/activate && uv run pip-audit --skip-editable --ignore-vuln CVE-2025-69872 --ignore-vuln CVE-2026-25645 --ignore-vuln CVE-2026-27448 --ignore-vuln CVE-2026-27459 --ignore-vuln PYSEC-2023-235' --
+        language: system
+        pass_filenames: false
+        stages: [pre-push, manual]
   - repo: https://github.com/commitizen-tools/commitizen
     rev: v4.10.1
     hooks:

docs/ar/changelog.mdx

@@ -4,6 +4,33 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
 icon: "clock"
 mode: "wide"
 ---
+<Update label="10 أبريل 2026">
+  ## v1.14.2a2
+
+  [عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
+
+  ## ما الذي تغير
+
+  ### الميزات
+  - إضافة واجهة مستخدم نصية لنقطة التحقق مع عرض شجري، ودعم التفرع، ومدخلات/مخرجات قابلة للتعديل
+  - إثراء تتبع رموز LLM مع رموز الاستدلال ورموز إنشاء التخزين المؤقت
+  - إضافة معلمة `from_checkpoint` إلى طرق الانطلاق
+  - تضمين `crewai_version` في نقاط التحقق مع إطار عمل الهجرة
+  - إضافة تفرع نقاط التحقق مع تتبع السلالة
+
+  ### إصلاحات الأخطاء
+  - إصلاح توجيه الوضع الصارم إلى مزودي Anthropic وBedrock
+  - تعزيز NL2SQLTool مع وضع القراءة فقط الافتراضي، والتحقق من الاستعلامات، والاستعلامات المعلمة
+
+  ### الوثائق
+  - تحديث سجل التغييرات والإصدار لـ v1.14.2a1
+
+  ## المساهمون
+
+  @alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
+
+</Update>
+
 <Update label="9 أبريل 2026">
   ## v1.14.2a1
 

docs/en/changelog.mdx

@@ -4,6 +4,33 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="Apr 10, 2026">
+  ## v1.14.2a2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
+
+  ## What's Changed
+
+  ### Features
+  - Add checkpoint TUI with tree view, fork support, and editable inputs/outputs
+  - Enrich LLM token tracking with reasoning tokens and cache creation tokens
+  - Add `from_checkpoint` parameter to kickoff methods
+  - Embed `crewai_version` in checkpoints with migration framework
+  - Add checkpoint forking with lineage tracking
+
+  ### Bug Fixes
+  - Fix strict mode forwarding to Anthropic and Bedrock providers
+  - Harden NL2SQLTool with read-only default, query validation, and parameterized queries
+
+  ### Documentation
+  - Update changelog and version for v1.14.2a1
+
+  ## Contributors
+
+  @alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
+
+</Update>
+
 <Update label="Apr 09, 2026">
   ## v1.14.2a1
 

docs/ko/changelog.mdx

@@ -4,6 +4,33 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="2026년 4월 10일">
+  ## v1.14.2a2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
+
+  ## 변경 사항
+
+  ### 기능
+  - 트리 뷰, 포크 지원 및 편집 가능한 입력/출력을 갖춘 체크포인트 TUI 추가
+  - 추론 토큰 및 캐시 생성 토큰으로 LLM 토큰 추적 강화
+  - 킥오프 메서드에 `from_checkpoint` 매개변수 추가
+  - 마이그레이션 프레임워크와 함께 체크포인트에 `crewai_version` 포함
+  - 계보 추적이 가능한 체크포인트 포킹 추가
+
+  ### 버그 수정
+  - Anthropic 및 Bedrock 공급자로의 엄격 모드 포워딩 수정
+  - 읽기 전용 기본값, 쿼리 검증 및 매개변수화된 쿼리로 NL2SQLTool 강화
+
+  ### 문서
+  - v1.14.2a1에 대한 변경 로그 및 버전 업데이트
+
+  ## 기여자
+
+  @alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
+
+</Update>
+
 <Update label="2026년 4월 9일">
   ## v1.14.2a1
 

docs/pt-BR/changelog.mdx

@@ -4,6 +4,33 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
 icon: "clock"
 mode: "wide"
 ---
+<Update label="10 abr 2026">
+  ## v1.14.2a2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.2a2)
+
+  ## O que Mudou
+
+  ### Funcionalidades
+  - Adicionar TUI de ponto de verificação com visualização em árvore, suporte a bifurcações e entradas/saídas editáveis
+  - Enriquecer o rastreamento de tokens LLM com tokens de raciocínio e tokens de criação de cache
+  - Adicionar parâmetro `from_checkpoint` aos métodos de inicialização
+  - Incorporar `crewai_version` em pontos de verificação com o framework de migração
+  - Adicionar bifurcação de ponto de verificação com rastreamento de linhagem
+
+  ### Correções de Bugs
+  - Corrigir o encaminhamento em modo estrito para os provedores Anthropic e Bedrock
+  - Fortalecer NL2SQLTool com padrão somente leitura, validação de consultas e consultas parametrizadas
+
+  ### Documentação
+  - Atualizar changelog e versão para v1.14.2a1
+
+  ## Contributors
+
+  @alex-clawd, @github-actions[bot], @greysonlalonde, @lucasgomide
+
+</Update>
+
 <Update label="09 abr 2026">
   ## v1.14.2a1
 

lib/crewai-files/pyproject.toml

@@ -9,7 +9,7 @@ authors = [
 requires-python = ">=3.10, <3.14"
 dependencies = [
     "Pillow~=12.1.1",
-    "pypdf~=6.9.1",
+    "pypdf~=6.10.0",
     "python-magic>=0.4.27",
     "aiocache~=0.12.3",
     "aiofiles~=24.1.0",

lib/crewai-files/src/crewai_files/__init__.py

@@ -152,4 +152,4 @@ __all__ = [
     "wrap_file_source",
 ]
 
-__version__ = "1.14.2a1"
+__version__ = "1.14.2a2"

lib/crewai-tools/pyproject.toml

@@ -10,7 +10,7 @@ requires-python = ">=3.10, <3.14"
 dependencies = [
     "pytube~=15.0.0",
     "requests~=2.32.5",
-    "crewai==1.14.2a1",
+    "crewai==1.14.2a2",
     "tiktoken~=0.8.0",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",

lib/crewai-tools/src/crewai_tools/__init__.py

@@ -305,4 +305,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.14.2a1"
+__version__ = "1.14.2a2"

lib/crewai/pyproject.toml

@@ -40,7 +40,7 @@ dependencies = [
     "pydantic-settings~=2.10.1",
     "httpx~=0.28.1",
     "mcp~=1.26.0",
-    "uv~=0.9.13",
+    "uv~=0.11.6",
     "aiosqlite~=0.21.0",
     "pyyaml~=6.0",
     "aiofiles~=24.1.0",
@@ -55,7 +55,7 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.14.2a1",
+    "crewai-tools==1.14.2a2",
 ]
 embeddings = [
     "tiktoken~=0.8.0"

lib/crewai/src/crewai/__init__.py

@@ -46,7 +46,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.14.2a1"
+__version__ = "1.14.2a2"
 _telemetry_submitted = False
 
 

lib/crewai/src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.2a1"
+    "crewai[tools]==1.14.2a2"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.2a1"
+    "crewai[tools]==1.14.2a2"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.14.2a1"
+    "crewai[tools]==1.14.2a2"
 ]
 
 [tool.crewai]

lib/crewai/src/crewai/llms/providers/anthropic/completion.py

@@ -11,10 +11,14 @@ from crewai.events.types.llm_events import LLMCallType
 from crewai.llms.base_llm import BaseLLM, JsonResponseFormat, llm_call_context
 from crewai.llms.hooks.base import BaseInterceptor
 from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
+from crewai.llms.providers.utils.common import safe_tool_conversion
 from crewai.utilities.agent_utils import is_context_length_exceeded
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
+from crewai.utilities.pydantic_schema_utils import (
+    sanitize_tool_params_for_anthropic_strict,
+)
 from crewai.utilities.types import LLMMessage
 
 
@@ -473,10 +477,8 @@ class AnthropicCompletion(BaseLLM):
                 continue
 
             try:
-                from crewai.llms.providers.utils.common import safe_tool_conversion
-
                 name, description, parameters = safe_tool_conversion(tool, "Anthropic")
-            except (ImportError, KeyError, ValueError) as e:
+            except (KeyError, ValueError) as e:
                 logging.error(f"Error converting tool to Anthropic format: {e}")
                 raise e
 
@@ -485,8 +487,15 @@ class AnthropicCompletion(BaseLLM):
                 "description": description,
             }
 
+            func_info = tool.get("function", {})
+            strict_enabled = bool(func_info.get("strict"))
+
             if parameters and isinstance(parameters, dict):
-                anthropic_tool["input_schema"] = parameters
+                anthropic_tool["input_schema"] = (
+                    sanitize_tool_params_for_anthropic_strict(parameters)
+                    if strict_enabled
+                    else parameters
+                )
             else:
                 anthropic_tool["input_schema"] = {
                     "type": "object",
@@ -494,8 +503,7 @@ class AnthropicCompletion(BaseLLM):
                     "required": [],
                 }
 
-            func_info = tool.get("function", {})
-            if func_info.get("strict"):
+            if strict_enabled:
                 anthropic_tool["strict"] = True
 
             anthropic_tools.append(anthropic_tool)

lib/crewai/src/crewai/llms/providers/bedrock/completion.py

@@ -12,11 +12,15 @@ from typing_extensions import Required
 
 from crewai.events.types.llm_events import LLMCallType
 from crewai.llms.base_llm import BaseLLM, llm_call_context
+from crewai.llms.providers.utils.common import safe_tool_conversion
 from crewai.utilities.agent_utils import is_context_length_exceeded
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
-from crewai.utilities.pydantic_schema_utils import generate_model_description
+from crewai.utilities.pydantic_schema_utils import (
+    generate_model_description,
+    sanitize_tool_params_for_bedrock_strict,
+)
 from crewai.utilities.types import LLMMessage
 
 
@@ -1949,8 +1953,6 @@ class BedrockCompletion(BaseLLM):
         tools: list[dict[str, Any]],
     ) -> list[ConverseToolTypeDef]:
         """Convert CrewAI tools to Converse API format following AWS specification."""
-        from crewai.llms.providers.utils.common import safe_tool_conversion
-
         converse_tools: list[ConverseToolTypeDef] = []
 
         for tool in tools:
@@ -1962,12 +1964,19 @@ class BedrockCompletion(BaseLLM):
                     "description": description,
                 }
 
+                func_info = tool.get("function", {})
+                strict_enabled = bool(func_info.get("strict"))
+
                 if parameters and isinstance(parameters, dict):
-                    input_schema: ToolInputSchema = {"json": parameters}
+                    schema_params = (
+                        sanitize_tool_params_for_bedrock_strict(parameters)
+                        if strict_enabled
+                        else parameters
+                    )
+                    input_schema: ToolInputSchema = {"json": schema_params}
                     tool_spec["inputSchema"] = input_schema
 
-                func_info = tool.get("function", {})
-                if func_info.get("strict"):
+                if strict_enabled:
                     tool_spec["strict"] = True
 
                 converse_tool: ConverseToolTypeDef = {"toolSpec": tool_spec}

lib/crewai/src/crewai/llms/providers/openai/completion.py

@@ -32,11 +32,15 @@ from crewai.events.types.llm_events import LLMCallType
 from crewai.llms.base_llm import BaseLLM, JsonResponseFormat, llm_call_context
 from crewai.llms.hooks.base import BaseInterceptor
 from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
+from crewai.llms.providers.utils.common import safe_tool_conversion
 from crewai.utilities.agent_utils import is_context_length_exceeded
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
-from crewai.utilities.pydantic_schema_utils import generate_model_description
+from crewai.utilities.pydantic_schema_utils import (
+    generate_model_description,
+    sanitize_tool_params_for_openai_strict,
+)
 from crewai.utilities.types import LLMMessage
 
 
@@ -764,8 +768,6 @@ class OpenAICompletion(BaseLLM):
             "function": {"name": "...", "description": "...", "parameters": {...}}
         }
         """
-        from crewai.llms.providers.utils.common import safe_tool_conversion
-
         responses_tools = []
 
         for tool in tools:
@@ -1548,11 +1550,6 @@ class OpenAICompletion(BaseLLM):
         self, tools: list[dict[str, BaseTool]]
     ) -> list[dict[str, Any]]:
         """Convert CrewAI tool format to OpenAI function calling format."""
-        from crewai.llms.providers.utils.common import safe_tool_conversion
-        from crewai.utilities.pydantic_schema_utils import (
-            force_additional_properties_false,
-        )
-
         openai_tools = []
 
         for tool in tools:
@@ -1571,8 +1568,9 @@ class OpenAICompletion(BaseLLM):
                 params_dict = (
                     parameters if isinstance(parameters, dict) else dict(parameters)
                 )
-                params_dict = force_additional_properties_false(params_dict)
-                openai_tool["function"]["parameters"] = params_dict
+                openai_tool["function"]["parameters"] = (
+                    sanitize_tool_params_for_openai_strict(params_dict)
+                )
 
             openai_tools.append(openai_tool)
         return openai_tools

lib/crewai/src/crewai/utilities/pydantic_schema_utils.py

@@ -19,7 +19,7 @@ from collections.abc import Callable
 from copy import deepcopy
 import datetime
 import logging
-from typing import TYPE_CHECKING, Annotated, Any, Final, Literal, TypedDict, Union
+from typing import TYPE_CHECKING, Annotated, Any, Final, Literal, TypedDict, Union, cast
 import uuid
 
 import jsonref  # type: ignore[import-untyped]
@@ -417,6 +417,119 @@ def strip_null_from_types(schema: dict[str, Any]) -> dict[str, Any]:
     return schema
 
 
+_STRICT_METADATA_KEYS: Final[tuple[str, ...]] = (
+    "title",
+    "default",
+    "examples",
+    "example",
+    "$comment",
+    "readOnly",
+    "writeOnly",
+    "deprecated",
+)
+
+_CLAUDE_STRICT_UNSUPPORTED: Final[tuple[str, ...]] = (
+    "minimum",
+    "maximum",
+    "exclusiveMinimum",
+    "exclusiveMaximum",
+    "multipleOf",
+    "minLength",
+    "maxLength",
+    "pattern",
+    "minItems",
+    "maxItems",
+    "uniqueItems",
+    "minContains",
+    "maxContains",
+    "minProperties",
+    "maxProperties",
+    "patternProperties",
+    "propertyNames",
+    "dependentRequired",
+    "dependentSchemas",
+)
+
+
+def _strip_keys_recursive(d: Any, keys: tuple[str, ...]) -> Any:
+    """Recursively delete a fixed set of keys from a schema."""
+    if isinstance(d, dict):
+        for key in keys:
+            d.pop(key, None)
+        for v in d.values():
+            _strip_keys_recursive(v, keys)
+    elif isinstance(d, list):
+        for i in d:
+            _strip_keys_recursive(i, keys)
+    return d
+
+
+def lift_top_level_anyof(schema: dict[str, Any]) -> dict[str, Any]:
+    """Unwrap a top-level anyOf/oneOf/allOf wrapping a single object variant.
+
+    Anthropic's strict ``input_schema`` rejects top-level union keywords. When
+    exactly one variant is an object schema, lift it so the root is a plain
+    object; otherwise leave the schema alone.
+    """
+    for key in ("anyOf", "oneOf", "allOf"):
+        variants = schema.get(key)
+        if not isinstance(variants, list):
+            continue
+        object_variants = [
+            v for v in variants if isinstance(v, dict) and v.get("type") == "object"
+        ]
+        if len(object_variants) == 1:
+            lifted = deepcopy(object_variants[0])
+            schema.pop(key)
+            schema.update(lifted)
+            break
+    return schema
+
+
+def _common_strict_pipeline(params: dict[str, Any]) -> dict[str, Any]:
+    """Shared strict sanitization: inline refs, close objects, require all properties."""
+    sanitized = resolve_refs(deepcopy(params))
+    sanitized.pop("$defs", None)
+    sanitized = convert_oneof_to_anyof(sanitized)
+    sanitized = ensure_type_in_schemas(sanitized)
+    sanitized = force_additional_properties_false(sanitized)
+    sanitized = ensure_all_properties_required(sanitized)
+    return cast(dict[str, Any], _strip_keys_recursive(sanitized, _STRICT_METADATA_KEYS))
+
+
+def sanitize_tool_params_for_openai_strict(
+    params: dict[str, Any],
+) -> dict[str, Any]:
+    """Sanitize a JSON schema for OpenAI strict function calling."""
+    if not isinstance(params, dict):
+        return params
+    return cast(
+        dict[str, Any], strip_unsupported_formats(_common_strict_pipeline(params))
+    )
+
+
+def sanitize_tool_params_for_anthropic_strict(
+    params: dict[str, Any],
+) -> dict[str, Any]:
+    """Sanitize a JSON schema for Anthropic strict tool use."""
+    if not isinstance(params, dict):
+        return params
+    sanitized = lift_top_level_anyof(_common_strict_pipeline(params))
+    sanitized = _strip_keys_recursive(sanitized, _CLAUDE_STRICT_UNSUPPORTED)
+    return cast(dict[str, Any], strip_unsupported_formats(sanitized))
+
+
+def sanitize_tool_params_for_bedrock_strict(
+    params: dict[str, Any],
+) -> dict[str, Any]:
+    """Sanitize a JSON schema for Bedrock Converse strict tool use.
+
+    Bedrock Converse uses the same grammar compiler as the underlying Claude
+    model, so the constraints match Anthropic's.
+    """
+    return sanitize_tool_params_for_anthropic_strict(params)
+
+
 def generate_model_description(
     model: type[BaseModel],
     *,

lib/crewai/tests/cassettes/test_hierarchical_verbose_false_manager_agent.yaml

@@ -55,7 +55,7 @@ interactions:
       x-stainless-os:
       - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.83.0
+      - 2.31.0
       x-stainless-read-timeout:
       - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
@@ -63,50 +63,51 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-DIqxWpJbbFJoV8WlXhb9UYFbCmdPk\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1773385850,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DTApYQx2LepfeRL1XcDKPgrhMFnQr\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1775845516,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
         \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-        \           \"id\": \"call_G2i9RJGNXKVfnd8ZTaBG8Fwi\",\n            \"type\":
-        \"function\",\n            \"function\": {\n              \"name\": \"ask_question_to_coworker\",\n
-        \             \"arguments\": \"{\\\"question\\\": \\\"What are some trending
-        topics or ideas in various fields that could be explored for an article?\\\",
-        \\\"context\\\": \\\"We need to generate a list of 5 interesting ideas to
-        explore for an article. These ideas should be engaging and relevant to current
-        trends or captivating subjects.\\\", \\\"coworker\\\": \\\"Researcher\\\"}\"\n
-        \           }\n          },\n          {\n            \"id\": \"call_j4KH2SGZvNeioql0HcRQ9NTp\",\n
+        \           \"id\": \"call_BCh6lXsBTdixRuRh6OTBPoIJ\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"delegate_work_to_coworker\",\n
+        \             \"arguments\": \"{\\\"task\\\": \\\"Come up with a list of 5
+        interesting ideas to explore for an article.\\\", \\\"context\\\": \\\"We
+        need five intriguing ideas worth exploring for an article. Each idea should
+        have potential for in-depth exploration and appeal to a broad audience, possibly
+        touching on current trends, historical insights, future possibilities, or
+        human interest stories.\\\", \\\"coworker\\\": \\\"Researcher\\\"}\"\n            }\n
+        \         },\n          {\n            \"id\": \"call_rAQFeCrS4ogsqvIWRGAYFHGI\",\n
         \           \"type\": \"function\",\n            \"function\": {\n              \"name\":
-        \"ask_question_to_coworker\",\n              \"arguments\": \"{\\\"question\\\":
-        \\\"What unique angles or perspectives could we explore to make articles more
-        compelling and engaging?\\\", \\\"context\\\": \\\"Our task involves coming
-        up with 5 ideas for articles, each with an exciting paragraph highlight that
-        illustrates the promise and intrigue of the topic. We want them to be more
-        than generic concepts, shining for readers with fresh insights or engaging
-        twists.\\\", \\\"coworker\\\": \\\"Senior Writer\\\"}\"\n            }\n          }\n
-        \       ],\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
-        \     \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n    }\n
-        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 476,\n    \"completion_tokens\":
-        183,\n    \"total_tokens\": 659,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        \"delegate_work_to_coworker\",\n              \"arguments\": \"{\\\"task\\\":
+        \\\"Write one amazing paragraph highlight for each of 5 ideas that showcases
+        how good an article about this topic could be.\\\", \\\"context\\\": \\\"Upon
+        receiving five intriguing ideas from the Researcher, create a compelling paragraph
+        for each idea that highlights its potential as a fascinating article. These
+        paragraphs must capture the essence of the topic and explain why it would
+        captivate readers, incorporating possible themes and insights.\\\", \\\"coworker\\\":
+        \\\"Senior Writer\\\"}\"\n            }\n          }\n        ],\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        476,\n    \"completion_tokens\": 201,\n    \"total_tokens\": 677,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_b7c8e3f100\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_2ca5b70601\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-Ray:
-      - 9db9389a3f9e424c-EWR
+      - 9ea3cb06ba66b301-TPE
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 13 Mar 2026 07:10:53 GMT
+      - Fri, 10 Apr 2026 18:25:18 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -122,7 +123,7 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '2402'
+      - '1981'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
@@ -154,13 +155,14 @@ interactions:
       You work as a freelancer and is now working on doing research and analysis for
       a new customer.\nYour personal goal is: Make the best research and analysis
       on content about AI and AI agents"},{"role":"user","content":"\nCurrent Task:
-      What are some trending topics or ideas in various fields that could be explored
-      for an article?\n\nThis is the expected criteria for your final answer: Your
-      best answer to your coworker asking you this, accounting for the context shared.\nyou
-      MUST return the actual complete content as the final answer, not a summary.\n\nThis
-      is the context you''re working with:\nWe need to generate a list of 5 interesting
-      ideas to explore for an article. These ideas should be engaging and relevant
-      to current trends or captivating subjects.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+      Come up with a list of 5 interesting ideas to explore for an article.\n\nThis
+      is the expected criteria for your final answer: Your best answer to your coworker
+      asking you this, accounting for the context shared.\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\nWe need five intriguing ideas worth exploring for an
+      article. Each idea should have potential for in-depth exploration and appeal
+      to a broad audience, possibly touching on current trends, historical insights,
+      future possibilities, or human interest stories.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -173,7 +175,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '978'
+      - '1046'
       content-type:
       - application/json
       host:
@@ -187,7 +189,7 @@ interactions:
       x-stainless-os:
       - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.83.0
+      - 2.31.0
       x-stainless-read-timeout:
       - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
@@ -195,63 +197,69 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-DIqxak88AexErt9PGFGHnWPIJLwNV\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1773385854,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+      string: "{\n  \"id\": \"chatcmpl-DTApalbfnYkqIc8slLS3DKwo9KXbc\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1775845518,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Here are five trending and engaging
-        topics across various fields that could be explored for an article:\\n\\n1.
-        **The Rise of Autonomous AI Agents and Their Impact on the Future of Work**
-        \ \\nExplore how autonomous AI agents\u2014systems capable of performing complex
-        tasks independently\u2014are transforming industries such as customer service,
-        software development, and logistics. Discuss implications for job automation,
-        human-AI collaboration, and ethical considerations surrounding decision-making
-        autonomy.\\n\\n2. **Generative AI Beyond Text: Innovations in Audio, Video,
-        and 3D Content Creation**  \\nDelve into advancements in generative AI models
-        that create not only text but also realistic audio, video content, virtual
-        environments, and 3D models. Highlight applications in gaming, entertainment,
-        education, and digital marketing, as well as challenges like misinformation
-        and deepfake detection.\\n\\n3. **AI-Driven Climate Modeling: Enhancing Predictive
-        Accuracy to Combat Climate Change**  \\nExamine how AI and machine learning
-        are improving climate models by analyzing vast datasets, uncovering patterns,
-        and simulating environmental scenarios. Discuss how these advances are aiding
-        policymakers in making informed decisions to address climate risks and sustainability
-        goals.\\n\\n4. **The Ethical Frontiers of AI in Healthcare: Balancing Innovation
-        with Patient Privacy**  \\nInvestigate ethical challenges posed by AI applications
-        in healthcare, including diagnosis, personalized treatment, and patient data
-        management. Focus on balancing rapid technological innovation with privacy,
-        bias mitigation, and regulatory frameworks to ensure equitable access and
-        trust.\\n\\n5. **Quantum Computing Meets AI: Exploring the Next Leap in Computational
-        Power**  \\nCover the intersection of quantum computing and artificial intelligence,
-        exploring how quantum algorithms could accelerate AI training processes and
-        solve problems beyond the reach of classical computers. Outline current research,
-        potential breakthroughs, and the timeline for real-world applications.\\n\\nEach
-        of these topics is timely, relevant, and has the potential to engage readers
-        interested in cutting-edge technology, societal impact, and future trends.
-        Let me know if you want me to help develop an outline or deeper research into
-        any of these areas!\",\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 178,\n    \"completion_tokens\":
-        402,\n    \"total_tokens\": 580,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \"assistant\",\n        \"content\": \"Certainly! Here are five intriguing
+        article ideas that offer rich potential for deep exploration and broad audience
+        appeal, especially aligned with current trends and human interest in AI and
+        technology:\\n\\n1. **The Evolution of AI Agents: From Rule-Based Bots to
+        Autonomous Decision Makers**  \\n   Explore the historical development of
+        AI agents, tracing the journey from simple scripted chatbots to advanced autonomous
+        systems capable of complex decision-making and learning. Dive into key technological
+        milestones, breakthroughs in machine learning, and current state-of-the-art
+        AI agents. Discuss implications for industries such as customer service, healthcare,
+        and autonomous vehicles, highlighting both opportunities and ethical concerns.\\n\\n2.
+        **AI in Daily Life: How Intelligent Agents Are Reshaping Human Routines**
+        \ \\n   Investigate the integration of AI agents in everyday life\u2014from
+        virtual assistants like Siri and Alexa to personalized recommendation systems
+        and smart home devices. Analyze how these AI tools influence productivity,
+        privacy, and social behavior. Include human interest elements through stories
+        of individuals or communities who have embraced or resisted these technologies.\\n\\n3.
+        **The Future of Work: AI Agents as Collaborative Colleagues**  \\n   Examine
+        how AI agents are transforming workplaces by acting as collaborators rather
+        than just tools. Cover applications in creative fields, data analysis, and
+        decision support, while addressing potential challenges such as job displacement,
+        new skill requirements, and the evolving definition of teamwork. Use expert
+        opinions and case studies to paint a nuanced future outlook.\\n\\n4. **Ethics
+        and Accountability in AI Agent Development**  \\n   Delve into the ethical
+        dilemmas posed by increasingly autonomous AI agents\u2014topics like bias
+        in algorithms, data privacy, and accountability for AI-driven decisions. Explore
+        measures being taken globally to regulate AI, frameworks for responsible AI
+        development, and the role of public awareness. Include historical context
+        about technology ethics to provide depth.\\n\\n5. **Human-AI Symbiosis: Stories
+        of Innovative Partnerships Shaping Our World**  \\n   Tell compelling human
+        interest stories about individuals or organizations pioneering collaborative
+        projects with AI agents that lead to breakthroughs in science, art, or social
+        good. Highlight how these partnerships transcend traditional human-machine
+        interaction and open new creative and problem-solving possibilities, inspiring
+        readers about the potential of human-AI synergy.\\n\\nThese ideas are designed
+        to be both engaging and informative, offering multiple angles\u2014technical,
+        historical, ethical, and personal\u2014to keep readers captivated while providing
+        substantial content for in-depth analysis.\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 189,\n    \"completion_tokens\":
+        472,\n    \"total_tokens\": 661,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
         0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_e76a310957\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_fbf43a1ff3\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-Ray:
-      - 9db938b0493c4b9f-EWR
+      - 9ea3cb1b5c943323-TPE
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 13 Mar 2026 07:10:59 GMT
+      - Fri, 10 Apr 2026 18:25:25 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -267,7 +275,7 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '5699'
+      - '6990'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
@@ -298,15 +306,16 @@ interactions:
       a senior writer, specialized in technology, software engineering, AI and startups.
       You work as a freelancer and are now working on writing content for a new customer.\nYour
       personal goal is: Write the best content about AI and AI agents."},{"role":"user","content":"\nCurrent
-      Task: What unique angles or perspectives could we explore to make articles more
-      compelling and engaging?\n\nThis is the expected criteria for your final answer:
-      Your best answer to your coworker asking you this, accounting for the context
-      shared.\nyou MUST return the actual complete content as the final answer, not
-      a summary.\n\nThis is the context you''re working with:\nOur task involves coming
-      up with 5 ideas for articles, each with an exciting paragraph highlight that
-      illustrates the promise and intrigue of the topic. We want them to be more than
-      generic concepts, shining for readers with fresh insights or engaging twists.\n\nProvide
-      your complete response:"}],"model":"gpt-4.1-mini"}'
+      Task: Write one amazing paragraph highlight for each of 5 ideas that showcases
+      how good an article about this topic could be.\n\nThis is the expected criteria
+      for your final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\nyou MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nUpon
+      receiving five intriguing ideas from the Researcher, create a compelling paragraph
+      for each idea that highlights its potential as a fascinating article. These
+      paragraphs must capture the essence of the topic and explain why it would captivate
+      readers, incorporating possible themes and insights.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -319,7 +328,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1041'
+      - '1103'
       content-type:
       - application/json
       host:
@@ -333,7 +342,7 @@ interactions:
       x-stainless-os:
       - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.83.0
+      - 2.31.0
       x-stainless-read-timeout:
       - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
@@ -341,78 +350,83 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-DIqxZCl1kFIE7WXznIKow9QFNZ2QT\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1773385853,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+      string: "{\n  \"id\": \"chatcmpl-DTApbrh9Z4yFAKPHIR48ubdB1R5xK\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1775845519,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"Absolutely! To create compelling and
-        engaging AI articles that stand out, we need to go beyond surface-level discussions
-        and deliver fresh perspectives that challenge assumptions and spark curiosity.
-        Here are five unique angles with their highlight paragraphs that could really
-        captivate our readers:\\n\\n1. **The Hidden Psychology of AI Agents: How They
-        Learn Human Biases and What That Means for Our Future**  \\n*Highlight:* AI
-        agents don\u2019t just process data\u2014they absorb the subtle nuances and
-        biases embedded in human language, behavior, and culture. This article dives
-        deep into the psychological parallels between AI learning mechanisms and human
-        cognitive biases, revealing surprising ways AI can both mirror and amplify
-        our prejudices. Understanding these dynamics is crucial for building trustworthy
-        AI systems and reshaping the future relationship between humans and machines.\\n\\n2.
-        **From Assistants to Autonomous Creators: The Rise of AI Agents as Artists,
-        Writers, and Innovators**  \\n*Highlight:* What do we lose and gain when AI
-        agents start producing original art, literature, and innovations? This piece
-        explores groundbreaking examples where AI isn\u2019t just a tool but a creative
-        partner that challenges our definition of authorship and genius. We\u2019ll
-        examine ethical dilemmas, collaborative workflows, and the exciting frontier
-        where human intuition meets algorithmic originality.\\n\\n3. **AI Agents in
-        the Wild: How Decentralized Autonomous Organizations Could Redefine Economy
-        and Governance**  \\n*Highlight:* Imagine AI agents operating autonomously
-        in decentralized networks, making real-time decisions that affect finances,
-        resource management, and governance without human intervention. This article
-        uncovers how DAOs powered by AI agents might spontaneously evolve new forms
-        of organization\u2014transparent, efficient, and resistant to traditional
-        corruption. We\u2019ll investigate early case studies and speculate on how
-        this might disrupt centuries-old societal structures.\\n\\n4. **Beyond Chatbots:
-        The Next Generation of AI Agents as Empathetic Digital Companions**  \\n*Highlight:*
-        Moving past scripted conversations, emerging AI agents simulate empathy and
-        emotional intelligence in ways that can transform mental health care, education,
-        and companionship. This article provides an insider look at the complex algorithms
-        and biofeedback mechanisms enabling AI to recognize, respond to, and foster
-        human emotions\u2014potentially filling gaps in underserved populations while
-        raising profound questions about authenticity and connection.\\n\\n5. **The
-        Environmental Toll of AI Agents: Unmasking the Ecological Cost of Intelligent
-        Automation**  \\n*Highlight:* While AI promises efficiency and innovation,
-        the environmental footprint of training and deploying millions of AI agents
-        is rarely discussed. This eye-opening article quantifies the energy demands
-        of current models, challenges the narrative of AI as an unequivocal green
-        solution, and explores emerging approaches pathing toward sustainable intelligent
-        automation\u2014an urgent conversation for an increasingly eco-conscious tech
-        landscape.\\n\\nEach of these angles opens a door to rich storytelling that
-        blends technical depth, ethical inquiry, and visionary implications\u2014perfect
-        for readers hungry for insight that\u2019s both sophisticated and accessible.
-        Let me know which ones resonate most, or if you want me to refine any into
-        full article outlines!\",\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 188,\n    \"completion_tokens\":
-        595,\n    \"total_tokens\": 783,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        \"assistant\",\n        \"content\": \"1. **The Rise of Autonomous AI Agents:
+        Revolutionizing Everyday Tasks**  \\nImagine a world where AI agents autonomously
+        manage your daily schedule, optimize your work routines, and even handle complex
+        decision-making with minimal human intervention. An article exploring the
+        rise of autonomous AI agents would captivate readers by diving into how advancements
+        in machine learning and natural language processing have matured these agents
+        from simple chatbots to intelligent collaborators. Themes could include practical
+        applications in industries like healthcare, finance, and personal productivity,
+        the challenges of trust and transparency, and a glimpse into the ethical questions
+        surrounding AI autonomy. This topic not only showcases cutting-edge technology
+        but also invites readers to envision the near future of human-AI synergy.\\n\\n2.
+        **Building Ethical AI Agents: Balancing Innovation with Responsibility**  \\nAs
+        AI agents become more powerful and independent, the imperative to embed ethical
+        frameworks within their design comes sharply into focus. An insightful article
+        on this theme would engage readers by unpacking the complexities of programming
+        morality, fairness, and accountability into AI systems that influence critical
+        decisions\u2014whether in hiring processes, law enforcement, or digital content
+        moderation. Exploring real-world case studies alongside philosophical and
+        regulatory perspectives, the piece could illuminate the delicate balance between
+        technological innovation and societal values, offering a nuanced discussion
+        that appeals to technologists, ethicists, and everyday users alike.\\n\\n3.
+        **AI Agents in Startups: Accelerating Growth and Disrupting Markets**  \\nStartups
+        are uniquely positioned to leverage AI agents as game-changers that turbocharge
+        growth, optimize workflows, and unlock new business models. This article could
+        enthrall readers by detailing how nimble companies integrate AI-driven agents
+        for customer engagement, market analysis, and personalized product recommendations\u2014outpacing
+        larger incumbents. It would also examine hurdles such as data privacy, scaling
+        complexities, and the human-AI collaboration dynamic, providing actionable
+        insights for entrepreneurs and investors. The story of AI agents fueling startup
+        innovation not only inspires but also outlines the practical pathways and
+        pitfalls on the frontier of modern entrepreneurship.\\n\\n4. **The Future
+        of Work with AI Agents: Redefining Roles and Skills**  \\nAI agents are redefining
+        professional landscapes by automating routine tasks and augmenting human creativity
+        and decision-making. An article on this topic could engage readers by painting
+        a vivid picture of the evolving workplace, where collaboration between humans
+        and AI agents becomes the norm. Delving into emerging roles, necessary skill
+        sets, and how education and training must adapt, the piece would offer a forward-thinking
+        analysis that resonates deeply with employees, managers, and policymakers.
+        Exploring themes of workforce transformation, productivity gains, and potential
+        socioeconomic impacts, it provides a comprehensive outlook on an AI-integrated
+        work environment.\\n\\n5. **From Reactive to Proactive: How Next-Gen AI Agents
+        Anticipate Needs**  \\nThe leap from reactive AI assistants to truly proactive
+        AI agents signifies one of the most thrilling advances in artificial intelligence.
+        An article centered on this evolution would captivate readers by illustrating
+        how these agents utilize predictive analytics, contextual understanding, and
+        continuous learning to anticipate user needs before they are expressed. By
+        showcasing pioneering applications in personalized healthcare management,
+        smart homes, and adaptive learning platforms, the article would highlight
+        the profound shift toward intuitive, anticipatory technology. This theme not
+        only excites with futuristic promise but also probes the technical and privacy
+        challenges that come with increased agency and foresight.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        197,\n    \"completion_tokens\": 666,\n    \"total_tokens\": 863,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_ae0f8c9a7b\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_d45f83c5fd\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-Ray:
-      - 9db938b0489680d4-EWR
+      - 9ea3cb1cbfe2b312-TPE
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 13 Mar 2026 07:11:02 GMT
+      - Fri, 10 Apr 2026 18:25:28 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -428,7 +442,7 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '8310'
+      - '9479'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:
@@ -467,91 +481,105 @@ interactions:
       good an article about this topic could be. Return the list of ideas with their
       paragraph and your notes.\\n\\nThis is the expected criteria for your final
       answer: 5 bullet points with a paragraph for each idea.\\nyou MUST return the
-      actual complete content as the final answer, not a summary.\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_G2i9RJGNXKVfnd8ZTaBG8Fwi\",\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"arguments\":\"{\\\"question\\\":
-      \\\"What are some trending topics or ideas in various fields that could be explored
-      for an article?\\\", \\\"context\\\": \\\"We need to generate a list of 5 interesting
-      ideas to explore for an article. These ideas should be engaging and relevant
-      to current trends or captivating subjects.\\\", \\\"coworker\\\": \\\"Researcher\\\"}\"}},{\"id\":\"call_j4KH2SGZvNeioql0HcRQ9NTp\",\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"arguments\":\"{\\\"question\\\":
-      \\\"What unique angles or perspectives could we explore to make articles more
-      compelling and engaging?\\\", \\\"context\\\": \\\"Our task involves coming
-      up with 5 ideas for articles, each with an exciting paragraph highlight that
-      illustrates the promise and intrigue of the topic. We want them to be more than
-      generic concepts, shining for readers with fresh insights or engaging twists.\\\",
-      \\\"coworker\\\": \\\"Senior Writer\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_G2i9RJGNXKVfnd8ZTaBG8Fwi\",\"name\":\"ask_question_to_coworker\",\"content\":\"Here
-      are five trending and engaging topics across various fields that could be explored
-      for an article:\\n\\n1. **The Rise of Autonomous AI Agents and Their Impact
-      on the Future of Work**  \\nExplore how autonomous AI agents\u2014systems capable
-      of performing complex tasks independently\u2014are transforming industries such
-      as customer service, software development, and logistics. Discuss implications
-      for job automation, human-AI collaboration, and ethical considerations surrounding
-      decision-making autonomy.\\n\\n2. **Generative AI Beyond Text: Innovations in
-      Audio, Video, and 3D Content Creation**  \\nDelve into advancements in generative
-      AI models that create not only text but also realistic audio, video content,
-      virtual environments, and 3D models. Highlight applications in gaming, entertainment,
-      education, and digital marketing, as well as challenges like misinformation
-      and deepfake detection.\\n\\n3. **AI-Driven Climate Modeling: Enhancing Predictive
-      Accuracy to Combat Climate Change**  \\nExamine how AI and machine learning
-      are improving climate models by analyzing vast datasets, uncovering patterns,
-      and simulating environmental scenarios. Discuss how these advances are aiding
-      policymakers in making informed decisions to address climate risks and sustainability
-      goals.\\n\\n4. **The Ethical Frontiers of AI in Healthcare: Balancing Innovation
-      with Patient Privacy**  \\nInvestigate ethical challenges posed by AI applications
-      in healthcare, including diagnosis, personalized treatment, and patient data
-      management. Focus on balancing rapid technological innovation with privacy,
-      bias mitigation, and regulatory frameworks to ensure equitable access and trust.\\n\\n5.
-      **Quantum Computing Meets AI: Exploring the Next Leap in Computational Power**
-      \ \\nCover the intersection of quantum computing and artificial intelligence,
-      exploring how quantum algorithms could accelerate AI training processes and
-      solve problems beyond the reach of classical computers. Outline current research,
-      potential breakthroughs, and the timeline for real-world applications.\\n\\nEach
-      of these topics is timely, relevant, and has the potential to engage readers
-      interested in cutting-edge technology, societal impact, and future trends. Let
-      me know if you want me to help develop an outline or deeper research into any
-      of these areas!\"},{\"role\":\"tool\",\"tool_call_id\":\"call_j4KH2SGZvNeioql0HcRQ9NTp\",\"name\":\"ask_question_to_coworker\",\"content\":\"Absolutely!
-      To create compelling and engaging AI articles that stand out, we need to go
-      beyond surface-level discussions and deliver fresh perspectives that challenge
-      assumptions and spark curiosity. Here are five unique angles with their highlight
-      paragraphs that could really captivate our readers:\\n\\n1. **The Hidden Psychology
-      of AI Agents: How They Learn Human Biases and What That Means for Our Future**
-      \ \\n*Highlight:* AI agents don\u2019t just process data\u2014they absorb the
-      subtle nuances and biases embedded in human language, behavior, and culture.
-      This article dives deep into the psychological parallels between AI learning
-      mechanisms and human cognitive biases, revealing surprising ways AI can both
-      mirror and amplify our prejudices. Understanding these dynamics is crucial for
-      building trustworthy AI systems and reshaping the future relationship between
-      humans and machines.\\n\\n2. **From Assistants to Autonomous Creators: The Rise
-      of AI Agents as Artists, Writers, and Innovators**  \\n*Highlight:* What do
-      we lose and gain when AI agents start producing original art, literature, and
-      innovations? This piece explores groundbreaking examples where AI isn\u2019t
-      just a tool but a creative partner that challenges our definition of authorship
-      and genius. We\u2019ll examine ethical dilemmas, collaborative workflows, and
-      the exciting frontier where human intuition meets algorithmic originality.\\n\\n3.
-      **AI Agents in the Wild: How Decentralized Autonomous Organizations Could Redefine
-      Economy and Governance**  \\n*Highlight:* Imagine AI agents operating autonomously
-      in decentralized networks, making real-time decisions that affect finances,
-      resource management, and governance without human intervention. This article
-      uncovers how DAOs powered by AI agents might spontaneously evolve new forms
-      of organization\u2014transparent, efficient, and resistant to traditional corruption.
-      We\u2019ll investigate early case studies and speculate on how this might disrupt
-      centuries-old societal structures.\\n\\n4. **Beyond Chatbots: The Next Generation
-      of AI Agents as Empathetic Digital Companions**  \\n*Highlight:* Moving past
-      scripted conversations, emerging AI agents simulate empathy and emotional intelligence
-      in ways that can transform mental health care, education, and companionship.
-      This article provides an insider look at the complex algorithms and biofeedback
-      mechanisms enabling AI to recognize, respond to, and foster human emotions\u2014potentially
-      filling gaps in underserved populations while raising profound questions about
-      authenticity and connection.\\n\\n5. **The Environmental Toll of AI Agents:
-      Unmasking the Ecological Cost of Intelligent Automation**  \\n*Highlight:* While
-      AI promises efficiency and innovation, the environmental footprint of training
-      and deploying millions of AI agents is rarely discussed. This eye-opening article
-      quantifies the energy demands of current models, challenges the narrative of
-      AI as an unequivocal green solution, and explores emerging approaches pathing
-      toward sustainable intelligent automation\u2014an urgent conversation for an
-      increasingly eco-conscious tech landscape.\\n\\nEach of these angles opens a
-      door to rich storytelling that blends technical depth, ethical inquiry, and
-      visionary implications\u2014perfect for readers hungry for insight that\u2019s
-      both sophisticated and accessible. Let me know which ones resonate most, or
-      if you want me to refine any into full article outlines!\"},{\"role\":\"user\",\"content\":\"Analyze
+      actual complete content as the final answer, not a summary.\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_BCh6lXsBTdixRuRh6OTBPoIJ\",\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"arguments\":\"{\\\"task\\\":
+      \\\"Come up with a list of 5 interesting ideas to explore for an article.\\\",
+      \\\"context\\\": \\\"We need five intriguing ideas worth exploring for an article.
+      Each idea should have potential for in-depth exploration and appeal to a broad
+      audience, possibly touching on current trends, historical insights, future possibilities,
+      or human interest stories.\\\", \\\"coworker\\\": \\\"Researcher\\\"}\"}},{\"id\":\"call_rAQFeCrS4ogsqvIWRGAYFHGI\",\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"arguments\":\"{\\\"task\\\":
+      \\\"Write one amazing paragraph highlight for each of 5 ideas that showcases
+      how good an article about this topic could be.\\\", \\\"context\\\": \\\"Upon
+      receiving five intriguing ideas from the Researcher, create a compelling paragraph
+      for each idea that highlights its potential as a fascinating article. These
+      paragraphs must capture the essence of the topic and explain why it would captivate
+      readers, incorporating possible themes and insights.\\\", \\\"coworker\\\":
+      \\\"Senior Writer\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_BCh6lXsBTdixRuRh6OTBPoIJ\",\"name\":\"delegate_work_to_coworker\",\"content\":\"Certainly!
+      Here are five intriguing article ideas that offer rich potential for deep exploration
+      and broad audience appeal, especially aligned with current trends and human
+      interest in AI and technology:\\n\\n1. **The Evolution of AI Agents: From Rule-Based
+      Bots to Autonomous Decision Makers**  \\n   Explore the historical development
+      of AI agents, tracing the journey from simple scripted chatbots to advanced
+      autonomous systems capable of complex decision-making and learning. Dive into
+      key technological milestones, breakthroughs in machine learning, and current
+      state-of-the-art AI agents. Discuss implications for industries such as customer
+      service, healthcare, and autonomous vehicles, highlighting both opportunities
+      and ethical concerns.\\n\\n2. **AI in Daily Life: How Intelligent Agents Are
+      Reshaping Human Routines**  \\n   Investigate the integration of AI agents in
+      everyday life\u2014from virtual assistants like Siri and Alexa to personalized
+      recommendation systems and smart home devices. Analyze how these AI tools influence
+      productivity, privacy, and social behavior. Include human interest elements
+      through stories of individuals or communities who have embraced or resisted
+      these technologies.\\n\\n3. **The Future of Work: AI Agents as Collaborative
+      Colleagues**  \\n   Examine how AI agents are transforming workplaces by acting
+      as collaborators rather than just tools. Cover applications in creative fields,
+      data analysis, and decision support, while addressing potential challenges such
+      as job displacement, new skill requirements, and the evolving definition of
+      teamwork. Use expert opinions and case studies to paint a nuanced future outlook.\\n\\n4.
+      **Ethics and Accountability in AI Agent Development**  \\n   Delve into the
+      ethical dilemmas posed by increasingly autonomous AI agents\u2014topics like
+      bias in algorithms, data privacy, and accountability for AI-driven decisions.
+      Explore measures being taken globally to regulate AI, frameworks for responsible
+      AI development, and the role of public awareness. Include historical context
+      about technology ethics to provide depth.\\n\\n5. **Human-AI Symbiosis: Stories
+      of Innovative Partnerships Shaping Our World**  \\n   Tell compelling human
+      interest stories about individuals or organizations pioneering collaborative
+      projects with AI agents that lead to breakthroughs in science, art, or social
+      good. Highlight how these partnerships transcend traditional human-machine interaction
+      and open new creative and problem-solving possibilities, inspiring readers about
+      the potential of human-AI synergy.\\n\\nThese ideas are designed to be both
+      engaging and informative, offering multiple angles\u2014technical, historical,
+      ethical, and personal\u2014to keep readers captivated while providing substantial
+      content for in-depth analysis.\"},{\"role\":\"tool\",\"tool_call_id\":\"call_rAQFeCrS4ogsqvIWRGAYFHGI\",\"name\":\"delegate_work_to_coworker\",\"content\":\"1.
+      **The Rise of Autonomous AI Agents: Revolutionizing Everyday Tasks**  \\nImagine
+      a world where AI agents autonomously manage your daily schedule, optimize your
+      work routines, and even handle complex decision-making with minimal human intervention.
+      An article exploring the rise of autonomous AI agents would captivate readers
+      by diving into how advancements in machine learning and natural language processing
+      have matured these agents from simple chatbots to intelligent collaborators.
+      Themes could include practical applications in industries like healthcare, finance,
+      and personal productivity, the challenges of trust and transparency, and a glimpse
+      into the ethical questions surrounding AI autonomy. This topic not only showcases
+      cutting-edge technology but also invites readers to envision the near future
+      of human-AI synergy.\\n\\n2. **Building Ethical AI Agents: Balancing Innovation
+      with Responsibility**  \\nAs AI agents become more powerful and independent,
+      the imperative to embed ethical frameworks within their design comes sharply
+      into focus. An insightful article on this theme would engage readers by unpacking
+      the complexities of programming morality, fairness, and accountability into
+      AI systems that influence critical decisions\u2014whether in hiring processes,
+      law enforcement, or digital content moderation. Exploring real-world case studies
+      alongside philosophical and regulatory perspectives, the piece could illuminate
+      the delicate balance between technological innovation and societal values, offering
+      a nuanced discussion that appeals to technologists, ethicists, and everyday
+      users alike.\\n\\n3. **AI Agents in Startups: Accelerating Growth and Disrupting
+      Markets**  \\nStartups are uniquely positioned to leverage AI agents as game-changers
+      that turbocharge growth, optimize workflows, and unlock new business models.
+      This article could enthrall readers by detailing how nimble companies integrate
+      AI-driven agents for customer engagement, market analysis, and personalized
+      product recommendations\u2014outpacing larger incumbents. It would also examine
+      hurdles such as data privacy, scaling complexities, and the human-AI collaboration
+      dynamic, providing actionable insights for entrepreneurs and investors. The
+      story of AI agents fueling startup innovation not only inspires but also outlines
+      the practical pathways and pitfalls on the frontier of modern entrepreneurship.\\n\\n4.
+      **The Future of Work with AI Agents: Redefining Roles and Skills**  \\nAI agents
+      are redefining professional landscapes by automating routine tasks and augmenting
+      human creativity and decision-making. An article on this topic could engage
+      readers by painting a vivid picture of the evolving workplace, where collaboration
+      between humans and AI agents becomes the norm. Delving into emerging roles,
+      necessary skill sets, and how education and training must adapt, the piece would
+      offer a forward-thinking analysis that resonates deeply with employees, managers,
+      and policymakers. Exploring themes of workforce transformation, productivity
+      gains, and potential socioeconomic impacts, it provides a comprehensive outlook
+      on an AI-integrated work environment.\\n\\n5. **From Reactive to Proactive:
+      How Next-Gen AI Agents Anticipate Needs**  \\nThe leap from reactive AI assistants
+      to truly proactive AI agents signifies one of the most thrilling advances in
+      artificial intelligence. An article centered on this evolution would captivate
+      readers by illustrating how these agents utilize predictive analytics, contextual
+      understanding, and continuous learning to anticipate user needs before they
+      are expressed. By showcasing pioneering applications in personalized healthcare
+      management, smart homes, and adaptive learning platforms, the article would
+      highlight the profound shift toward intuitive, anticipatory technology. This
+      theme not only excites with futuristic promise but also probes the technical
+      and privacy challenges that come with increased agency and foresight.\"},{\"role\":\"user\",\"content\":\"Analyze
       the tool result. If requirements are met, provide the Final Answer. Otherwise,
       call the next tool. Deliver only the answer without meta-commentary.\"}],\"model\":\"gpt-4o\",\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"description\":\"Delegate
       a specific task to one of the following coworkers: Researcher, Senior Writer\\nThe
@@ -582,7 +610,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '9923'
+      - '11056'
       content-type:
       - application/json
       cookie:
@@ -598,7 +626,7 @@ interactions:
       x-stainless-os:
       - X-STAINLESS-OS-XXX
       x-stainless-package-version:
-      - 1.83.0
+      - 2.31.0
       x-stainless-read-timeout:
       - X-STAINLESS-READ-TIMEOUT-XXX
       x-stainless-retry-count:
@@ -606,58 +634,64 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.3
+      - 3.13.12
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: "{\n  \"id\": \"chatcmpl-DIqxidsfoqQl7qXSIVHfSCyETUwlU\",\n  \"object\":
-        \"chat.completion\",\n  \"created\": 1773385862,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      string: "{\n  \"id\": \"chatcmpl-DTApljTaq8nDgNMS21B319i56seCn\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1775845529,\n  \"model\": \"gpt-4o-2024-08-06\",\n
         \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-        \"assistant\",\n        \"content\": \"1. **The Rise of Autonomous AI Agents
-        and Their Impact on the Future of Work**  \\nExplore how autonomous AI agents\u2014systems
-        capable of performing complex tasks independently\u2014are transforming industries
-        such as customer service, software development, and logistics. Discuss implications
-        for job automation, human-AI collaboration, and ethical considerations surrounding
-        decision-making autonomy.\\n\\n2. **Generative AI Beyond Text: Innovations
-        in Audio, Video, and 3D Content Creation**  \\nDelve into advancements in
-        generative AI models that create not only text but also realistic audio, video
-        content, virtual environments, and 3D models. Highlight applications in gaming,
-        entertainment, education, and digital marketing, as well as challenges like
-        misinformation and deepfake detection.\\n\\n3. **AI-Driven Climate Modeling:
-        Enhancing Predictive Accuracy to Combat Climate Change**  \\nExamine how AI
-        and machine learning are improving climate models by analyzing vast datasets,
-        uncovering patterns, and simulating environmental scenarios. Discuss how these
-        advances are aiding policymakers in making informed decisions to address climate
-        risks and sustainability goals.\\n\\n4. **The Ethical Frontiers of AI in Healthcare:
-        Balancing Innovation with Patient Privacy**  \\nInvestigate ethical challenges
-        posed by AI applications in healthcare, including diagnosis, personalized
-        treatment, and patient data management. Focus on balancing rapid technological
-        innovation with privacy, bias mitigation, and regulatory frameworks to ensure
-        equitable access and trust.\\n\\n5. **Quantum Computing Meets AI: Exploring
-        the Next Leap in Computational Power**  \\nCover the intersection of quantum
-        computing and artificial intelligence, exploring how quantum algorithms could
-        accelerate AI training processes and solve problems beyond the reach of classical
-        computers. Outline current research, potential breakthroughs, and the timeline
-        for real-world applications.\",\n        \"refusal\": null,\n        \"annotations\":
-        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1748,\n    \"completion_tokens\":
-        335,\n    \"total_tokens\": 2083,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        \"assistant\",\n        \"content\": \"- **The Evolution of AI Agents: From
+        Rule-Based Bots to Autonomous Decision Makers**  \\n   Explore the historical
+        development of AI agents, tracing the journey from simple scripted chatbots
+        to advanced autonomous systems capable of complex decision-making and learning.
+        Dive into key technological milestones, breakthroughs in machine learning,
+        and current state-of-the-art AI agents. Discuss implications for industries
+        such as customer service, healthcare, and autonomous vehicles, highlighting
+        both opportunities and ethical concerns.\\n\\n- **AI in Daily Life: How Intelligent
+        Agents Are Reshaping Human Routines**  \\n   Investigate the integration of
+        AI agents in everyday life\u2014from virtual assistants like Siri and Alexa
+        to personalized recommendation systems and smart home devices. Analyze how
+        these AI tools influence productivity, privacy, and social behavior. Include
+        human interest elements through stories of individuals or communities who
+        have embraced or resisted these technologies.\\n\\n- **The Future of Work:
+        AI Agents as Collaborative Colleagues**  \\n   Examine how AI agents are transforming
+        workplaces by acting as collaborators rather than just tools. Cover applications
+        in creative fields, data analysis, and decision support, while addressing
+        potential challenges such as job displacement, new skill requirements, and
+        the evolving definition of teamwork. Use expert opinions and case studies
+        to paint a nuanced future outlook.\\n\\n- **Ethics and Accountability in AI
+        Agent Development**  \\n   Delve into the ethical dilemmas posed by increasingly
+        autonomous AI agents\u2014topics like bias in algorithms, data privacy, and
+        accountability for AI-driven decisions. Explore measures being taken globally
+        to regulate AI, frameworks for responsible AI development, and the role of
+        public awareness. Include historical context about technology ethics to provide
+        depth.\\n\\n- **Human-AI Symbiosis: Stories of Innovative Partnerships Shaping
+        Our World**  \\n   Tell compelling human interest stories about individuals
+        or organizations pioneering collaborative projects with AI agents that lead
+        to breakthroughs in science, art, or social good. Highlight how these partnerships
+        transcend traditional human-machine interaction and open new creative and
+        problem-solving possibilities, inspiring readers about the potential of human-AI
+        synergy.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 1903,\n    \"completion_tokens\": 399,\n
+        \   \"total_tokens\": 2302,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
         0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
         {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
         0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-        \"default\",\n  \"system_fingerprint\": \"fp_b7c8e3f100\"\n}\n"
+        \"default\",\n  \"system_fingerprint\": \"fp_df40ab6c25\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-Ray:
-      - 9db938e60d5bc5e7-EWR
+      - 9ea3cb5a6957b301-TPE
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Fri, 13 Mar 2026 07:11:04 GMT
+      - Fri, 10 Apr 2026 18:25:31 GMT
       Server:
       - cloudflare
       Strict-Transport-Security:
@@ -673,7 +707,7 @@ interactions:
       openai-organization:
       - OPENAI-ORG-XXX
       openai-processing-ms:
-      - '2009'
+      - '2183'
       openai-project:
       - OPENAI-PROJECT-XXX
       openai-version:

lib/crewai/tests/llms/anthropic/test_anthropic_async.py

@@ -3,13 +3,9 @@ import json
 import logging
 
 import pytest
-import tiktoken
 from pydantic import BaseModel
 
 from crewai.llm import LLM
-
-# Pre-cache tiktoken encoding so VCR doesn't intercept the download request
-tiktoken.get_encoding("cl100k_base")
 from crewai.llms.providers.anthropic.completion import AnthropicCompletion
 
 
@@ -48,9 +44,7 @@ async def test_anthropic_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 10
+    assert len(result.split()) <= 10
 
 
 @pytest.mark.vcr()

lib/crewai/tests/llms/azure/test_azure_async.py

@@ -1,7 +1,6 @@
 """Tests for Azure async completion functionality."""
 
 import pytest
-import tiktoken
 
 from crewai import Agent, Task, Crew
 from crewai.llm import LLM
@@ -57,9 +56,7 @@ async def test_azure_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 10
+    assert len(result.split()) <= 10
 
 
 @pytest.mark.vcr()

lib/crewai/tests/llms/bedrock/test_bedrock_async.py

@@ -6,7 +6,6 @@ cannot be played back properly in CI.
 """
 
 import pytest
-import tiktoken
 
 from crewai.llm import LLM
 
@@ -51,9 +50,7 @@ async def test_bedrock_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 10
+    assert len(result.split()) <= 10
 
 
 @pytest.mark.vcr()

lib/crewai/tests/llms/google/test_google_async.py

@@ -1,7 +1,6 @@
 """Tests for Google (Gemini) async completion functionality."""
 
 import pytest
-import tiktoken
 
 from crewai import Agent, Task, Crew
 from crewai.llm import LLM
@@ -43,9 +42,7 @@ async def test_gemini_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 1000
+    assert len(result.split()) <= 1000
 
 
 @pytest.mark.vcr()

lib/crewai/tests/llms/litellm/test_litellm_async.py

@@ -1,7 +1,6 @@
 """Tests for LiteLLM fallback async completion functionality."""
 
 import pytest
-import tiktoken
 
 from crewai.llm import LLM
 
@@ -44,9 +43,7 @@ async def test_litellm_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 10
+    assert len(result.split()) <= 10
 
 
 @pytest.mark.asyncio

lib/crewai/tests/llms/openai/test_openai_async.py

@@ -1,7 +1,6 @@
 """Tests for OpenAI async completion functionality."""
 
 import pytest
-import tiktoken
 
 from crewai import Agent, Task, Crew
 from crewai.llm import LLM
@@ -42,9 +41,7 @@ async def test_openai_async_with_max_tokens():
 
     assert result is not None
     assert isinstance(result, str)
-    encoder = tiktoken.get_encoding("cl100k_base")
-    token_count = len(encoder.encode(result))
-    assert token_count <= 10
+    assert len(result.split()) <= 10
 
 
 @pytest.mark.vcr()

lib/crewai/tests/memory/test_unified_memory.py

@@ -51,14 +51,13 @@ def test_memory_record_embedding_excluded_from_serialization() -> None:
     dumped = r.model_dump()
     assert "embedding" not in dumped
     assert dumped["content"] == "hello"
-
-    # model_dump_json excludes embedding
     json_str = r.model_dump_json()
-    assert "0.1" not in json_str
     assert "embedding" not in json_str
+    rehydrated = MemoryRecord.model_validate_json(json_str)
+    assert rehydrated.embedding is None
 
     # repr excludes embedding
-    assert "0.1" not in repr(r)
+    assert "embedding=" not in repr(r)
 
     # Direct attribute access still works for storage layer
     assert r.embedding is not None

lib/devtools/src/crewai_devtools/__init__.py

@@ -1,3 +1,3 @@
 """CrewAI development tools."""
 
-__version__ = "1.14.2a1"
+__version__ = "1.14.2a2"

pyproject.toml

@@ -30,6 +30,7 @@ dev = [
     "types-pymysql==1.1.0.20250916",
     "types-aiofiles~=25.1.0",
     "commitizen>=4.13.9",
+    "pip-audit==2.9.0",
 ]
 
 

uv.lock

@@ -38,6 +38,7 @@ dev = [
     { name = "boto3-stubs", extras = ["bedrock-runtime"], specifier = "==1.42.40" },
     { name = "commitizen", specifier = ">=4.13.9" },
     { name = "mypy", specifier = "==1.19.1" },
+    { name = "pip-audit", specifier = "==2.9.0" },
     { name = "pre-commit", specifier = "==4.5.1" },
     { name = "pytest", specifier = "==8.4.2" },
     { name = "pytest-asyncio", specifier = "==1.3.0" },
@@ -613,6 +614,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/36/b7/a5cc566901af27314408b95701f8e1d9c286b0aecfa50fc76c53d73efa6f/bedrock_agentcore-1.3.2-py3-none-any.whl", hash = "sha256:3a4e7122f777916f8bd74b42f29eb881415e37fda784a5ff8fab3c813b921706", size = 121703, upload-time = "2026-02-23T20:52:55.038Z" },
 ]
 
+[[package]]
+name = "boolean-py"
+version = "5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c4/cf/85379f13b76f3a69bca86b60237978af17d6aa0bc5998978c3b8cf05abb2/boolean_py-5.0.tar.gz", hash = "sha256:60cbc4bad079753721d32649545505362c754e121570ada4658b852a3a318d95", size = 37047, upload-time = "2025-04-03T10:39:49.734Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e5/ca/78d423b324b8d77900030fa59c4aa9054261ef0925631cd2501dd015b7b7/boolean_py-5.0-py3-none-any.whl", hash = "sha256:ef28a70bd43115208441b53a045d1549e2f0ec6e3d08a9d142cbc41c1938e8d9", size = 26577, upload-time = "2025-04-03T10:39:48.449Z" },
+]
+
 [[package]]
 name = "boto3"
 version = "1.42.84"
@@ -705,6 +715,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4a/57/3b7d4dd193ade4641c865bc2b93aeeb71162e81fc348b8dad020215601ed/build-1.4.2-py3-none-any.whl", hash = "sha256:7a4d8651ea877cb2a89458b1b198f2e69f536c95e89129dbf5d448045d60db88", size = 24643, upload-time = "2026-03-25T14:20:26.568Z" },
 ]
 
+[[package]]
+name = "cachecontrol"
+version = "0.14.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "msgpack" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/2d/f6/c972b32d80760fb79d6b9eeb0b3010a46b89c0b23cf6329417ff7886cd22/cachecontrol-0.14.4.tar.gz", hash = "sha256:e6220afafa4c22a47dd0badb319f84475d79108100d04e26e8542ef7d3ab05a1", size = 16150, upload-time = "2025-11-14T04:32:13.138Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ef/79/c45f2d53efe6ada1110cf6f9fca095e4ff47a0454444aefdde6ac4789179/cachecontrol-0.14.4-py3-none-any.whl", hash = "sha256:b7ac014ff72ee199b5f8af1de29d60239954f223e948196fa3d84adaffc71d2b", size = 22247, upload-time = "2025-11-14T04:32:11.733Z" },
+]
+
+[package.optional-dependencies]
+filecache = [
+    { name = "filelock" },
+]
+
 [[package]]
 name = "cachetools"
 version = "7.0.5"
@@ -1346,7 +1374,7 @@ requires-dist = [
     { name = "tokenizers", specifier = ">=0.21,<1" },
     { name = "tomli", specifier = "~=2.0.2" },
     { name = "tomli-w", specifier = "~=1.1.0" },
-    { name = "uv", specifier = "~=0.9.13" },
+    { name = "uv", specifier = "~=0.11.6" },
     { name = "voyageai", marker = "extra == 'voyageai'", specifier = "~=0.3.5" },
 ]
 provides-extras = ["a2a", "anthropic", "aws", "azure-ai-inference", "bedrock", "docling", "embeddings", "file-processing", "google-genai", "litellm", "mem0", "openpyxl", "pandas", "qdrant", "qdrant-edge", "tools", "voyageai", "watson"]
@@ -1392,7 +1420,7 @@ requires-dist = [
     { name = "aiofiles", specifier = "~=24.1.0" },
     { name = "av", specifier = "~=13.0.0" },
     { name = "pillow", specifier = "~=12.1.1" },
-    { name = "pypdf", specifier = "~=6.9.1" },
+    { name = "pypdf", specifier = "~=6.10.0" },
     { name = "python-magic", specifier = ">=0.4.27" },
     { name = "tinytag", specifier = "~=2.2.1" },
 ]
@@ -1708,6 +1736,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e7/05/c19819d5e3d95294a6f5947fb9b9629efb316b96de511b418c53d245aae6/cycler-0.12.1-py3-none-any.whl", hash = "sha256:85cef7cff222d8644161529808465972e51340599459b8ac3ccbac5a854e0d30", size = 8321, upload-time = "2023-10-07T05:32:16.783Z" },
 ]
 
+[[package]]
+name = "cyclonedx-python-lib"
+version = "9.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "license-expression" },
+    { name = "packageurl-python" },
+    { name = "py-serializable" },
+    { name = "sortedcontainers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/66/fc/abaad5482f7b59c9a0a9d8f354ce4ce23346d582a0d85730b559562bbeb4/cyclonedx_python_lib-9.1.0.tar.gz", hash = "sha256:86935f2c88a7b47a529b93c724dbd3e903bc573f6f8bd977628a7ca1b5dadea1", size = 1048735, upload-time = "2025-02-27T17:23:40.367Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/53/f1/f3be2e9820a2c26fa77622223e91f9c504e1581830930d477e06146073f4/cyclonedx_python_lib-9.1.0-py3-none-any.whl", hash = "sha256:55693fca8edaecc3363b24af14e82cc6e659eb1e8353e58b587c42652ce0fb52", size = 374968, upload-time = "2025-02-27T17:23:37.766Z" },
+]
+
 [[package]]
 name = "databricks-sdk"
 version = "0.102.0"
@@ -3635,6 +3678,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a4/0a/92c244309b774e290ddb15e93363846ae7aa753d9586b8aad511c5e6145b/librt-0.9.0-cp313-cp313-win_arm64.whl", hash = "sha256:4c4d0440a3a8e31d962340c3e1cc3fc9ee7febd34c8d8f770d06adb947779ea5", size = 53728, upload-time = "2026-04-09T16:05:33.31Z" },
 ]
 
+[[package]]
+name = "license-expression"
+version = "30.4.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "boolean-py" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/40/71/d89bb0e71b1415453980fd32315f2a037aad9f7f70f695c7cec7035feb13/license_expression-30.4.4.tar.gz", hash = "sha256:73448f0aacd8d0808895bdc4b2c8e01a8d67646e4188f887375398c761f340fd", size = 186402, upload-time = "2025-07-22T11:13:32.17Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/af/40/791891d4c0c4dab4c5e187c17261cedc26285fd41541577f900470a45a4d/license_expression-30.4.4-py3-none-any.whl", hash = "sha256:421788fdcadb41f049d2dc934ce666626265aeccefddd25e162a26f23bcbf8a4", size = 120615, upload-time = "2025-07-22T11:13:31.217Z" },
+]
+
 [[package]]
 name = "linkify-it-py"
 version = "2.1.0"
@@ -4246,6 +4301,49 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c", size = 536198, upload-time = "2023-03-07T16:47:09.197Z" },
 ]
 
+[[package]]
+name = "msgpack"
+version = "1.1.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/4d/f2/bfb55a6236ed8725a96b0aa3acbd0ec17588e6a2c3b62a93eb513ed8783f/msgpack-1.1.2.tar.gz", hash = "sha256:3b60763c1373dd60f398488069bcdc703cd08a711477b5d480eecc9f9626f47e", size = 173581, upload-time = "2025-10-08T09:15:56.596Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f5/a2/3b68a9e769db68668b25c6108444a35f9bd163bb848c0650d516761a59c0/msgpack-1.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0051fffef5a37ca2cd16978ae4f0aef92f164df86823871b5162812bebecd8e2", size = 81318, upload-time = "2025-10-08T09:14:38.722Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/e1/2b720cc341325c00be44e1ed59e7cfeae2678329fbf5aa68f5bda57fe728/msgpack-1.1.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a605409040f2da88676e9c9e5853b3449ba8011973616189ea5ee55ddbc5bc87", size = 83786, upload-time = "2025-10-08T09:14:40.082Z" },
+    { url = "https://files.pythonhosted.org/packages/71/e5/c2241de64bfceac456b140737812a2ab310b10538a7b34a1d393b748e095/msgpack-1.1.2-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8b696e83c9f1532b4af884045ba7f3aa741a63b2bc22617293a2c6a7c645f251", size = 398240, upload-time = "2025-10-08T09:14:41.151Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/09/2a06956383c0fdebaef5aa9246e2356776f12ea6f2a44bd1368abf0e46c4/msgpack-1.1.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:365c0bbe981a27d8932da71af63ef86acc59ed5c01ad929e09a0b88c6294e28a", size = 406070, upload-time = "2025-10-08T09:14:42.821Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/74/2957703f0e1ef20637d6aead4fbb314330c26f39aa046b348c7edcf6ca6b/msgpack-1.1.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:41d1a5d875680166d3ac5c38573896453bbbea7092936d2e107214daf43b1d4f", size = 393403, upload-time = "2025-10-08T09:14:44.38Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/09/3bfc12aa90f77b37322fc33e7a8a7c29ba7c8edeadfa27664451801b9860/msgpack-1.1.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:354e81bcdebaab427c3df4281187edc765d5d76bfb3a7c125af9da7a27e8458f", size = 398947, upload-time = "2025-10-08T09:14:45.56Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/4f/05fcebd3b4977cb3d840f7ef6b77c51f8582086de5e642f3fefee35c86fc/msgpack-1.1.2-cp310-cp310-win32.whl", hash = "sha256:e64c8d2f5e5d5fda7b842f55dec6133260ea8f53c4257d64494c534f306bf7a9", size = 64769, upload-time = "2025-10-08T09:14:47.334Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/3e/b4547e3a34210956382eed1c85935fff7e0f9b98be3106b3745d7dec9c5e/msgpack-1.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:db6192777d943bdaaafb6ba66d44bf65aa0e9c5616fa1d2da9bb08828c6b39aa", size = 71293, upload-time = "2025-10-08T09:14:48.665Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/97/560d11202bcd537abca693fd85d81cebe2107ba17301de42b01ac1677b69/msgpack-1.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2e86a607e558d22985d856948c12a3fa7b42efad264dca8a3ebbcfa2735d786c", size = 82271, upload-time = "2025-10-08T09:14:49.967Z" },
+    { url = "https://files.pythonhosted.org/packages/83/04/28a41024ccbd67467380b6fb440ae916c1e4f25e2cd4c63abe6835ac566e/msgpack-1.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:283ae72fc89da59aa004ba147e8fc2f766647b1251500182fac0350d8af299c0", size = 84914, upload-time = "2025-10-08T09:14:50.958Z" },
+    { url = "https://files.pythonhosted.org/packages/71/46/b817349db6886d79e57a966346cf0902a426375aadc1e8e7a86a75e22f19/msgpack-1.1.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:61c8aa3bd513d87c72ed0b37b53dd5c5a0f58f2ff9f26e1555d3bd7948fb7296", size = 416962, upload-time = "2025-10-08T09:14:51.997Z" },
+    { url = "https://files.pythonhosted.org/packages/da/e0/6cc2e852837cd6086fe7d8406af4294e66827a60a4cf60b86575a4a65ca8/msgpack-1.1.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:454e29e186285d2ebe65be34629fa0e8605202c60fbc7c4c650ccd41870896ef", size = 426183, upload-time = "2025-10-08T09:14:53.477Z" },
+    { url = "https://files.pythonhosted.org/packages/25/98/6a19f030b3d2ea906696cedd1eb251708e50a5891d0978b012cb6107234c/msgpack-1.1.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:7bc8813f88417599564fafa59fd6f95be417179f76b40325b500b3c98409757c", size = 411454, upload-time = "2025-10-08T09:14:54.648Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/cd/9098fcb6adb32187a70b7ecaabf6339da50553351558f37600e53a4a2a23/msgpack-1.1.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:bafca952dc13907bdfdedfc6a5f579bf4f292bdd506fadb38389afa3ac5b208e", size = 422341, upload-time = "2025-10-08T09:14:56.328Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/ae/270cecbcf36c1dc85ec086b33a51a4d7d08fc4f404bdbc15b582255d05ff/msgpack-1.1.2-cp311-cp311-win32.whl", hash = "sha256:602b6740e95ffc55bfb078172d279de3773d7b7db1f703b2f1323566b878b90e", size = 64747, upload-time = "2025-10-08T09:14:57.882Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/79/309d0e637f6f37e83c711f547308b91af02b72d2326ddd860b966080ef29/msgpack-1.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:d198d275222dc54244bf3327eb8cbe00307d220241d9cec4d306d49a44e85f68", size = 71633, upload-time = "2025-10-08T09:14:59.177Z" },
+    { url = "https://files.pythonhosted.org/packages/73/4d/7c4e2b3d9b1106cd0aa6cb56cc57c6267f59fa8bfab7d91df5adc802c847/msgpack-1.1.2-cp311-cp311-win_arm64.whl", hash = "sha256:86f8136dfa5c116365a8a651a7d7484b65b13339731dd6faebb9a0242151c406", size = 64755, upload-time = "2025-10-08T09:15:00.48Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/bd/8b0d01c756203fbab65d265859749860682ccd2a59594609aeec3a144efa/msgpack-1.1.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:70a0dff9d1f8da25179ffcf880e10cf1aad55fdb63cd59c9a49a1b82290062aa", size = 81939, upload-time = "2025-10-08T09:15:01.472Z" },
+    { url = "https://files.pythonhosted.org/packages/34/68/ba4f155f793a74c1483d4bdef136e1023f7bcba557f0db4ef3db3c665cf1/msgpack-1.1.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:446abdd8b94b55c800ac34b102dffd2f6aa0ce643c55dfc017ad89347db3dbdb", size = 85064, upload-time = "2025-10-08T09:15:03.764Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/60/a064b0345fc36c4c3d2c743c82d9100c40388d77f0b48b2f04d6041dbec1/msgpack-1.1.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c63eea553c69ab05b6747901b97d620bb2a690633c77f23feb0c6a947a8a7b8f", size = 417131, upload-time = "2025-10-08T09:15:05.136Z" },
+    { url = "https://files.pythonhosted.org/packages/65/92/a5100f7185a800a5d29f8d14041f61475b9de465ffcc0f3b9fba606e4505/msgpack-1.1.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:372839311ccf6bdaf39b00b61288e0557916c3729529b301c52c2d88842add42", size = 427556, upload-time = "2025-10-08T09:15:06.837Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/87/ffe21d1bf7d9991354ad93949286f643b2bb6ddbeab66373922b44c3b8cc/msgpack-1.1.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2929af52106ca73fcb28576218476ffbb531a036c2adbcf54a3664de124303e9", size = 404920, upload-time = "2025-10-08T09:15:08.179Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/41/8543ed2b8604f7c0d89ce066f42007faac1eaa7d79a81555f206a5cdb889/msgpack-1.1.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:be52a8fc79e45b0364210eef5234a7cf8d330836d0a64dfbb878efa903d84620", size = 415013, upload-time = "2025-10-08T09:15:09.83Z" },
+    { url = "https://files.pythonhosted.org/packages/41/0d/2ddfaa8b7e1cee6c490d46cb0a39742b19e2481600a7a0e96537e9c22f43/msgpack-1.1.2-cp312-cp312-win32.whl", hash = "sha256:1fff3d825d7859ac888b0fbda39a42d59193543920eda9d9bea44d958a878029", size = 65096, upload-time = "2025-10-08T09:15:11.11Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/ec/d431eb7941fb55a31dd6ca3404d41fbb52d99172df2e7707754488390910/msgpack-1.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:1de460f0403172cff81169a30b9a92b260cb809c4cb7e2fc79ae8d0510c78b6b", size = 72708, upload-time = "2025-10-08T09:15:12.554Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/31/5b1a1f70eb0e87d1678e9624908f86317787b536060641d6798e3cf70ace/msgpack-1.1.2-cp312-cp312-win_arm64.whl", hash = "sha256:be5980f3ee0e6bd44f3a9e9dea01054f175b50c3e6cdb692bc9424c0bbb8bf69", size = 64119, upload-time = "2025-10-08T09:15:13.589Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/31/b46518ecc604d7edf3a4f94cb3bf021fc62aa301f0cb849936968164ef23/msgpack-1.1.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4efd7b5979ccb539c221a4c4e16aac1a533efc97f3b759bb5a5ac9f6d10383bf", size = 81212, upload-time = "2025-10-08T09:15:14.552Z" },
+    { url = "https://files.pythonhosted.org/packages/92/dc/c385f38f2c2433333345a82926c6bfa5ecfff3ef787201614317b58dd8be/msgpack-1.1.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:42eefe2c3e2af97ed470eec850facbe1b5ad1d6eacdbadc42ec98e7dcf68b4b7", size = 84315, upload-time = "2025-10-08T09:15:15.543Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/68/93180dce57f684a61a88a45ed13047558ded2be46f03acb8dec6d7c513af/msgpack-1.1.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1fdf7d83102bf09e7ce3357de96c59b627395352a4024f6e2458501f158bf999", size = 412721, upload-time = "2025-10-08T09:15:16.567Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/ba/459f18c16f2b3fc1a1ca871f72f07d70c07bf768ad0a507a698b8052ac58/msgpack-1.1.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fac4be746328f90caa3cd4bc67e6fe36ca2bf61d5c6eb6d895b6527e3f05071e", size = 424657, upload-time = "2025-10-08T09:15:17.825Z" },
+    { url = "https://files.pythonhosted.org/packages/38/f8/4398c46863b093252fe67368b44edc6c13b17f4e6b0e4929dbf0bdb13f23/msgpack-1.1.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:fffee09044073e69f2bad787071aeec727183e7580443dfeb8556cbf1978d162", size = 402668, upload-time = "2025-10-08T09:15:19.003Z" },
+    { url = "https://files.pythonhosted.org/packages/28/ce/698c1eff75626e4124b4d78e21cca0b4cc90043afb80a507626ea354ab52/msgpack-1.1.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5928604de9b032bc17f5099496417f113c45bc6bc21b5c6920caf34b3c428794", size = 419040, upload-time = "2025-10-08T09:15:20.183Z" },
+    { url = "https://files.pythonhosted.org/packages/67/32/f3cd1667028424fa7001d82e10ee35386eea1408b93d399b09fb0aa7875f/msgpack-1.1.2-cp313-cp313-win32.whl", hash = "sha256:a7787d353595c7c7e145e2331abf8b7ff1e6673a6b974ded96e6d4ec09f00c8c", size = 65037, upload-time = "2025-10-08T09:15:21.416Z" },
+    { url = "https://files.pythonhosted.org/packages/74/07/1ed8277f8653c40ebc65985180b007879f6a836c525b3885dcc6448ae6cb/msgpack-1.1.2-cp313-cp313-win_amd64.whl", hash = "sha256:a465f0dceb8e13a487e54c07d04ae3ba131c7c5b95e2612596eafde1dccf64a9", size = 72631, upload-time = "2025-10-08T09:15:22.431Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/db/0314e4e2db56ebcf450f277904ffd84a7988b9e5da8d0d61ab2d057df2b6/msgpack-1.1.2-cp313-cp313-win_arm64.whl", hash = "sha256:e69b39f8c0aa5ec24b57737ebee40be647035158f14ed4b40e6f150077e21a84", size = 64118, upload-time = "2025-10-08T09:15:23.402Z" },
+]
+
 [[package]]
 name = "msoffcrypto-tool"
 version = "6.0.0"
@@ -5215,6 +5313,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b7/c1/88bf70a327c86f8529ad3a4ae35e92fcebf05295668fca7973279e189afe/oxylabs-2.0.0-py3-none-any.whl", hash = "sha256:3848d53bc47acdcea16ea829dc52416cdf96edae130e17bb3ac7146b012387d7", size = 34274, upload-time = "2025-03-28T13:54:15.188Z" },
 ]
 
+[[package]]
+name = "packageurl-python"
+version = "0.17.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f5/d6/3b5a4e3cfaef7a53869a26ceb034d1ff5e5c27c814ce77260a96d50ab7bb/packageurl_python-0.17.6.tar.gz", hash = "sha256:1252ce3a102372ca6f86eb968e16f9014c4ba511c5c37d95a7f023e2ca6e5c25", size = 50618, upload-time = "2025-11-24T15:20:17.998Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b1/2f/c7277b7615a93f51b5fbc1eacfc1b75e8103370e786fd8ce2abf6e5c04ab/packageurl_python-0.17.6-py3-none-any.whl", hash = "sha256:31a85c2717bc41dd818f3c62908685ff9eebcb68588213745b14a6ee9e7df7c9", size = 36776, upload-time = "2025-11-24T15:20:16.962Z" },
+]
+
 [[package]]
 name = "packaging"
 version = "26.0"
@@ -5545,6 +5652,60 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/60/5382c03e1970de634027cee8e1b7d39776b778b81812aaf45b694dfe9e28/pillow-12.2.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:bfa9c230d2fe991bed5318a5f119bd6780cda2915cca595393649fc118ab895e", size = 7080946, upload-time = "2026-04-01T14:46:11.734Z" },
 ]
 
+[[package]]
+name = "pip"
+version = "26.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/48/83/0d7d4e9efe3344b8e2fe25d93be44f64b65364d3c8d7bc6dc90198d5422e/pip-26.0.1.tar.gz", hash = "sha256:c4037d8a277c89b320abe636d59f91e6d0922d08a05b60e85e53b296613346d8", size = 1812747, upload-time = "2026-02-05T02:20:18.702Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/de/f0/c81e05b613866b76d2d1066490adf1a3dbc4ee9d9c839961c3fc8a6997af/pip-26.0.1-py3-none-any.whl", hash = "sha256:bdb1b08f4274833d62c1aa29e20907365a2ceb950410df15fc9521bad440122b", size = 1787723, upload-time = "2026-02-05T02:20:16.416Z" },
+]
+
+[[package]]
+name = "pip-api"
+version = "0.0.34"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pip" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b9/f1/ee85f8c7e82bccf90a3c7aad22863cc6e20057860a1361083cd2adacb92e/pip_api-0.0.34.tar.gz", hash = "sha256:9b75e958f14c5a2614bae415f2adf7eeb54d50a2cfbe7e24fd4826471bac3625", size = 123017, upload-time = "2024-07-09T20:32:30.641Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/91/f7/ebf5003e1065fd00b4cbef53bf0a65c3d3e1b599b676d5383ccb7a8b88ba/pip_api-0.0.34-py3-none-any.whl", hash = "sha256:8b2d7d7c37f2447373aa2cf8b1f60a2f2b27a84e1e9e0294a3f6ef10eb3ba6bb", size = 120369, upload-time = "2024-07-09T20:32:29.099Z" },
+]
+
+[[package]]
+name = "pip-audit"
+version = "2.9.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cachecontrol", extra = ["filecache"] },
+    { name = "cyclonedx-python-lib" },
+    { name = "packaging" },
+    { name = "pip-api" },
+    { name = "pip-requirements-parser" },
+    { name = "platformdirs" },
+    { name = "requests" },
+    { name = "rich" },
+    { name = "toml" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/cc/7f/28fad19a9806f796f13192ab6974c07c4a04d9cbb8e30dd895c3c11ce7ee/pip_audit-2.9.0.tar.gz", hash = "sha256:0b998410b58339d7a231e5aa004326a294e4c7c6295289cdc9d5e1ef07b1f44d", size = 52089, upload-time = "2025-04-07T16:45:23.679Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/43/9e/f4dfd9d3dadb6d6dc9406f1111062f871e2e248ed7b584cca6020baf2ac1/pip_audit-2.9.0-py3-none-any.whl", hash = "sha256:348b16e60895749a0839875d7cc27ebd692e1584ebe5d5cb145941c8e25a80bd", size = 58634, upload-time = "2025-04-07T16:45:22.056Z" },
+]
+
+[[package]]
+name = "pip-requirements-parser"
+version = "32.0.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+    { name = "pyparsing" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5e/2a/63b574101850e7f7b306ddbdb02cb294380d37948140eecd468fae392b54/pip-requirements-parser-32.0.1.tar.gz", hash = "sha256:b4fa3a7a0be38243123cf9d1f3518da10c51bdb165a2b2985566247f9155a7d3", size = 209359, upload-time = "2022-12-21T15:25:22.732Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/d0/d04f1d1e064ac901439699ee097f58688caadea42498ec9c4b4ad2ef84ab/pip_requirements_parser-32.0.1-py3-none-any.whl", hash = "sha256:4659bc2a667783e7a15d190f6fccf8b2486685b6dba4c19c3876314769c57526", size = 35648, upload-time = "2022-12-21T15:25:21.046Z" },
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.9.6"
@@ -5887,6 +6048,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3a/15/b1894b9741f7a48f0b4cbea458f7d4141a6df6a1b26bec05fcde96703ce1/py_rust_stemmers-0.1.5-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:57b061c3b4af9e409d009d729b21bc53dabe47116c955ccf0b642a5a2d438f93", size = 324879, upload-time = "2025-02-19T13:56:27.462Z" },
 ]
 
+[[package]]
+name = "py-serializable"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "defusedxml" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/73/21/d250cfca8ff30c2e5a7447bc13861541126ce9bd4426cd5d0c9f08b5547d/py_serializable-2.1.0.tar.gz", hash = "sha256:9d5db56154a867a9b897c0163b33a793c804c80cee984116d02d49e4578fc103", size = 52368, upload-time = "2025-07-21T09:56:48.07Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9b/bf/7595e817906a29453ba4d99394e781b6fabe55d21f3c15d240f85dd06bb1/py_serializable-2.1.0-py3-none-any.whl", hash = "sha256:b56d5d686b5a03ba4f4db5e769dc32336e142fc3bd4d68a8c25579ebb0a67304", size = 23045, upload-time = "2025-07-21T09:56:46.848Z" },
+]
+
 [[package]]
 name = "pyarrow"
 version = "23.0.1"
@@ -6551,14 +6724,14 @@ wheels = [
 
 [[package]]
 name = "pypdf"
-version = "6.9.2"
+version = "6.10.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/31/83/691bdb309306232362503083cb15777491045dd54f45393a317dc7d8082f/pypdf-6.9.2.tar.gz", hash = "sha256:7f850faf2b0d4ab936582c05da32c52214c2b089d61a316627b5bfb5b0dab46c", size = 5311837, upload-time = "2026-03-23T14:53:27.983Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/b8/9f/ca96abf18683ca12602065e4ed2bec9050b672c87d317f1079abc7b6d993/pypdf-6.10.0.tar.gz", hash = "sha256:4c5a48ba258c37024ec2505f7e8fd858525f5502784a2e1c8d415604af29f6ef", size = 5314833, upload-time = "2026-04-10T09:34:57.102Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a5/7e/c85f41243086a8fe5d1baeba527cb26a1918158a565932b41e0f7c0b32e9/pypdf-6.9.2-py3-none-any.whl", hash = "sha256:662cf29bcb419a36a1365232449624ab40b7c2d0cfc28e54f42eeecd1fd7e844", size = 333744, upload-time = "2026-03-23T14:53:26.573Z" },
+    { url = "https://files.pythonhosted.org/packages/55/f2/7ebe366f633f30a6ad105f650f44f24f98cb1335c4157d21ae47138b3482/pypdf-6.10.0-py3-none-any.whl", hash = "sha256:90005e959e1596c6e6c84c8b0ad383285b3e17011751cedd17f2ce8fcdfc86de", size = 334459, upload-time = "2026-04-10T09:34:54.966Z" },
 ]
 
 [[package]]
@@ -8125,6 +8298,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/59/8c/b1c87148aa15e099243ec9f0cf9d0e970cc2234c3257d558c25a2c5304e6/tokenizers-0.22.2-pp310-pypy310_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f01a9c019878532f98927d2bacb79bbb404b43d3437455522a00a30718cdedb5", size = 3373542, upload-time = "2026-01-05T10:40:52.803Z" },
 ]
 
+[[package]]
+name = "toml"
+version = "0.10.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/be/ba/1f744cdc819428fc6b5084ec34d9b30660f6f9daaf70eead706e3203ec3c/toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f", size = 22253, upload-time = "2020-11-01T01:40:22.204Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/44/6f/7120676b6d73228c96e17f1f794d8ab046fc910d781c8d151120c3f1569e/toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b", size = 16588, upload-time = "2020-11-01T01:40:20.672Z" },
+]
+
 [[package]]
 name = "tomli"
 version = "2.0.2"
@@ -8794,28 +8976,28 @@ wheels = [
 
 [[package]]
 name = "uv"
-version = "0.9.30"
+version = "0.11.6"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/4e/a0/63cea38fe839fb89592728b91928ee6d15705f1376a7940fee5bbc77fea0/uv-0.9.30.tar.gz", hash = "sha256:03ebd4b22769e0a8d825fa09d038e31cbab5d3d48edf755971cb0cec7920ab95", size = 3846526, upload-time = "2026-02-04T21:45:37.58Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/dd/f3/8aceeab67ea69805293ab290e7ca8cc1b61a064d28b8a35c76d8eba063dd/uv-0.11.6.tar.gz", hash = "sha256:e3b21b7e80024c95ff339fcd147ac6fc3dd98d3613c9d45d3a1f4fd1057f127b", size = 4073298, upload-time = "2026-04-09T12:09:01.738Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a3/3c/71be72f125f0035348b415468559cc3b335ec219376d17a3d242d2bd9b23/uv-0.9.30-py3-none-linux_armv6l.whl", hash = "sha256:a5467dddae1cd5f4e093f433c0f0d9a0df679b92696273485ec91bbb5a8620e6", size = 21927585, upload-time = "2026-02-04T21:46:14.935Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/fd/8070b5423a77d4058d14e48a970aa075762bbff4c812dda3bb3171543e44/uv-0.9.30-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6ec38ae29aa83a37c6e50331707eac8ecc90cf2b356d60ea6382a94de14973be", size = 21050392, upload-time = "2026-02-04T21:45:55.649Z" },
-    { url = "https://files.pythonhosted.org/packages/42/5f/3ccc9415ef62969ed01829572338ea7bdf4c5cf1ffb9edc1f8cb91b571f3/uv-0.9.30-py3-none-macosx_11_0_arm64.whl", hash = "sha256:777ecd117cf1d8d6bb07de8c9b7f6c5f3e802415b926cf059d3423699732eb8c", size = 19817085, upload-time = "2026-02-04T21:45:40.881Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/3f/76b44e2a224f4c4a8816fc92686ef6d4c2656bc5fc9d4f673816162c994d/uv-0.9.30-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.musllinux_1_1_aarch64.whl", hash = "sha256:93049ba3c41fa2cc38b467cb78ef61b2ddedca34b6be924a5481d7750c8111c6", size = 21620537, upload-time = "2026-02-04T21:45:47.846Z" },
-    { url = "https://files.pythonhosted.org/packages/60/2a/50f7e8c6d532af8dd327f77bdc75ce4652322ac34f5e29f79a8e04ea3cc8/uv-0.9.30-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.musllinux_1_1_armv7l.whl", hash = "sha256:f295604fee71224ebe2685a0f1f4ff7a45c77211a60bd57133a4a02056d7c775", size = 21550855, upload-time = "2026-02-04T21:46:26.269Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/10/f823d4af1125fae559194b356757dc7d4a8ac79d10d11db32c2d4c9e2f63/uv-0.9.30-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2faf84e1f3b6fc347a34c07f1291d11acf000b0dd537a61d541020f22b17ccd9", size = 21516576, upload-time = "2026-02-04T21:46:03.494Z" },
-    { url = "https://files.pythonhosted.org/packages/91/f3/64b02db11f38226ed34458c7fbdb6f16b6d4fd951de24c3e51acf02b30f8/uv-0.9.30-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0b3b3700ecf64a09a07fd04d10ec35f0973ec15595d38bbafaa0318252f7e31f", size = 22718097, upload-time = "2026-02-04T21:45:51.875Z" },
-    { url = "https://files.pythonhosted.org/packages/28/21/a48d1872260f04a68bb5177b0f62ddef62ab892d544ed1922f2d19fd2b00/uv-0.9.30-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:b176fc2937937dd81820445cb7e7e2e3cd1009a003c512f55fa0ae10064c8a38", size = 24107844, upload-time = "2026-02-04T21:46:19.032Z" },
-    { url = "https://files.pythonhosted.org/packages/1c/c6/d7e5559bfe1ab7a215a7ad49c58c8a5701728f2473f7f436ef00b4664e88/uv-0.9.30-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:180e8070b8c438b9a3fb3fde8a37b365f85c3c06e17090f555dc68fdebd73333", size = 23685378, upload-time = "2026-02-04T21:46:07.166Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/bf/b937bbd50d14c6286e353fd4c7bdc09b75f6b3a26bd4e2f3357e99891f28/uv-0.9.30-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4125a9aa2a751e1589728f6365cfe204d1be41499148ead44b6180b7df576f27", size = 22848471, upload-time = "2026-02-04T21:45:18.728Z" },
-    { url = "https://files.pythonhosted.org/packages/6a/57/12a67c569e69b71508ad669adad266221f0b1d374be88eaf60109f551354/uv-0.9.30-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4366dd740ac9ad3ec50a58868a955b032493bb7d7e6ed368289e6ced8bbc70f3", size = 22774258, upload-time = "2026-02-04T21:46:10.798Z" },
-    { url = "https://files.pythonhosted.org/packages/3d/b8/a26cc64685dddb9fb13f14c3dc1b12009f800083405f854f84eb8c86b494/uv-0.9.30-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:33e50f208e01a0c20b3c5f87d453356a5cbcfd68f19e47a28b274cd45618881c", size = 21699573, upload-time = "2026-02-04T21:45:44.365Z" },
-    { url = "https://files.pythonhosted.org/packages/c8/59/995af0c5f0740f8acb30468e720269e720352df1d204e82c2d52d9a8c586/uv-0.9.30-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:5e7a6fa7a3549ce893cf91fe4b06629e3e594fc1dca0a6050aba2ea08722e964", size = 22460799, upload-time = "2026-02-04T21:45:26.658Z" },
-    { url = "https://files.pythonhosted.org/packages/bb/0b/6affe815ecbaebf38b35d6230fbed2f44708c67d5dd5720f81f2ec8f96ff/uv-0.9.30-py3-none-musllinux_1_1_i686.whl", hash = "sha256:62d7e408d41e392b55ffa4cf9b07f7bbd8b04e0929258a42e19716c221ac0590", size = 22001777, upload-time = "2026-02-04T21:45:34.656Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/b6/47a515171c891b0d29f8e90c8a1c0e233e4813c95a011799605cfe04c74c/uv-0.9.30-py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:6dc65c24f5b9cdc78300fa6631368d3106e260bbffa66fb1e831a318374da2df", size = 22968416, upload-time = "2026-02-04T21:45:22.863Z" },
-    { url = "https://files.pythonhosted.org/packages/3d/3a/c1df8615385138bb7c43342586431ca32b77466c5fb086ac0ed14ab6ca28/uv-0.9.30-py3-none-win32.whl", hash = "sha256:74e94c65d578657db94a753d41763d0364e5468ec0d368fb9ac8ddab0fb6e21f", size = 20889232, upload-time = "2026-02-04T21:46:22.617Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/a8/e8761c8414a880d70223723946576069e042765475f73b4436d78b865dba/uv-0.9.30-py3-none-win_amd64.whl", hash = "sha256:88a2190810684830a1ba4bb1cf8fb06b0308988a1589559404259d295260891c", size = 23432208, upload-time = "2026-02-04T21:45:30.85Z" },
-    { url = "https://files.pythonhosted.org/packages/49/e8/6f2ebab941ec559f97110bbbae1279cd0333d6bc352b55f6fa3fefb020d9/uv-0.9.30-py3-none-win_arm64.whl", hash = "sha256:7fde83a5b5ea027315223c33c30a1ab2f2186910b933d091a1b7652da879e230", size = 21887273, upload-time = "2026-02-04T21:45:59.787Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/fe/4b61a3d5ad9d02e8a4405026ccd43593d7044598e0fa47d892d4dafe44c9/uv-0.11.6-py3-none-linux_armv6l.whl", hash = "sha256:ada04dcf89ddea5b69d27ac9cdc5ef575a82f90a209a1392e930de504b2321d6", size = 23780079, upload-time = "2026-04-09T12:08:56.609Z" },
+    { url = "https://files.pythonhosted.org/packages/52/db/d27519a9e1a5ffee9d71af1a811ad0e19ce7ab9ae815453bef39dd479389/uv-0.11.6-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:5be013888420f96879c6e0d3081e7bcf51b539b034a01777041934457dfbedf3", size = 23214721, upload-time = "2026-04-09T12:09:32.228Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/8f/4399fa8b882bd7e0efffc829f73ab24d117d490a93e6bc7104a50282b854/uv-0.11.6-py3-none-macosx_11_0_arm64.whl", hash = "sha256:ffa5dc1cbb52bdce3b8447e83d1601a57ad4da6b523d77d4b47366db8b1ceb18", size = 21750109, upload-time = "2026-04-09T12:09:24.357Z" },
+    { url = "https://files.pythonhosted.org/packages/32/07/5a12944c31c3dda253632da7a363edddb869ed47839d4d92a2dc5f546c93/uv-0.11.6-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.musllinux_1_1_aarch64.whl", hash = "sha256:bfb107b4dade1d2c9e572992b06992d51dd5f2136eb8ceee9e62dd124289e825", size = 23551146, upload-time = "2026-04-09T12:09:10.439Z" },
+    { url = "https://files.pythonhosted.org/packages/79/5b/2ec8b0af80acd1016ed596baf205ddc77b19ece288473b01926c4a9cf6db/uv-0.11.6-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.musllinux_1_1_armv7l.whl", hash = "sha256:9e2fe7ce12161d8016b7deb1eaad7905a76ff7afec13383333ca75e0c4b5425d", size = 23331192, upload-time = "2026-04-09T12:09:34.792Z" },
+    { url = "https://files.pythonhosted.org/packages/62/7d/eea35935f2112b21c296a3e42645f3e4b1aa8bcd34dcf13345fbd55134b7/uv-0.11.6-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7ed9c6f70c25e8dfeedddf4eddaf14d353f5e6b0eb43da9a14d3a1033d51d915", size = 23337686, upload-time = "2026-04-09T12:09:18.522Z" },
+    { url = "https://files.pythonhosted.org/packages/21/47/2584f5ab618f6ebe9bdefb2f765f2ca8540e9d739667606a916b35449eec/uv-0.11.6-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d68a013e609cebf82077cbeeb0809ed5e205257814273bfd31e02fc0353bbfc2", size = 25008139, upload-time = "2026-04-09T12:09:03.983Z" },
+    { url = "https://files.pythonhosted.org/packages/95/81/497ae5c1d36355b56b97dc59f550c7e89d0291c163a3f203c6f341dff195/uv-0.11.6-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:93f736dddca03dae732c6fdea177328d3bc4bf137c75248f3d433c57416a4311", size = 25712458, upload-time = "2026-04-09T12:09:07.598Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/1c/74083238e4fab2672b63575b9008f1ea418b02a714bcfcf017f4f6a309b6/uv-0.11.6-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e96a66abe53fced0e3389008b8d2eff8278cfa8bb545d75631ae8ceb9c929aba", size = 24915507, upload-time = "2026-04-09T12:08:50.892Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/ee/e14fe10ba455a823ed18233f12de6699a601890905420b5c504abf115116/uv-0.11.6-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b096311b2743b228df911a19532b3f18fa420bf9530547aecd6a8e04bbfaccd", size = 24971011, upload-time = "2026-04-09T12:08:54.016Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/a1/7b9c83eaadf98e343317ff6384a7227a4855afd02cdaf9696bcc71ee6155/uv-0.11.6-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:904d537b4a6e798015b4a64ff5622023bd4601b43b6cd1e5f423d63471f5e948", size = 23640234, upload-time = "2026-04-09T12:09:15.735Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/51/75ccdd23e76ff1703b70eb82881cd5b4d2a954c9679f8ef7e0136ef2cfab/uv-0.11.6-py3-none-manylinux_2_31_riscv64.musllinux_1_1_riscv64.whl", hash = "sha256:4ed8150c26b5e319381d75ae2ce6aba1e9c65888f4850f4e3b3fa839953c90a5", size = 24452664, upload-time = "2026-04-09T12:09:26.875Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/86/ace80fe47d8d48b5e3b5aee0b6eb1a49deaacc2313782870250b3faa36f5/uv-0.11.6-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:1c9218c8d4ac35ca6e617fb0951cc0ab2d907c91a6aea2617de0a5494cf162c0", size = 24494599, upload-time = "2026-04-09T12:09:37.368Z" },
+    { url = "https://files.pythonhosted.org/packages/05/2d/4b642669b56648194f026de79bc992cbfc3ac2318b0a8d435f3c284934e8/uv-0.11.6-py3-none-musllinux_1_1_i686.whl", hash = "sha256:9e211c83cc890c569b86a4183fcf5f8b6f0c7adc33a839b699a98d30f1310d3a", size = 24159150, upload-time = "2026-04-09T12:09:13.17Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/24/7eecd76fe983a74fed1fc700a14882e70c4e857f1d562a9f2303d4286c12/uv-0.11.6-py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:d2a1d2089afdf117ad19a4c1dd36b8189c00ae1ad4135d3bfbfced82342595cf", size = 25164324, upload-time = "2026-04-09T12:08:59.56Z" },
+    { url = "https://files.pythonhosted.org/packages/27/e0/bbd4ba7c2e5067bbba617d87d306ec146889edaeeaa2081d3e122178ca08/uv-0.11.6-py3-none-win32.whl", hash = "sha256:6e8344f38fa29f85dcfd3e62dc35a700d2448f8e90381077ef393438dcd5012e", size = 22865693, upload-time = "2026-04-09T12:09:21.415Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/33/1983ce113c538a856f2d620d16e39691962ecceef091a84086c5785e32e5/uv-0.11.6-py3-none-win_amd64.whl", hash = "sha256:a28bea69c1186303d1200f155c7a28c449f8a4431e458fcf89360cc7ef546e40", size = 25371258, upload-time = "2026-04-09T12:09:40.52Z" },
+    { url = "https://files.pythonhosted.org/packages/35/01/be0873f44b9c9bc250fcbf263367fcfc1f59feab996355bcb6b52fff080d/uv-0.11.6-py3-none-win_arm64.whl", hash = "sha256:a78f6d64b9950e24061bc7ec7f15ff8089ad7f5a976e7b65fcadce58fe02f613", size = 23869585, upload-time = "2026-04-09T12:09:29.425Z" },
 ]
 
 [[package]]