Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
feat: implement before and after tool call hooks in CrewAgentExecutor… (#4287)
Lorenze Jayf53bdb28ac50
diff --git a/lib/crewai/src/crewai/agents/crew_agent_executor.py b/lib/crewai/src/crewai/agents/crew_agent_executor.pyindex a5fb12d58..150ae4126 100644--- a/lib/crewai/src/crewai/agents/crew_agent_executor.py+++ b/lib/crewai/src/crewai/agents/crew_agent_executor.py@@ -28,6 +28,11 @@ from crewai.hooks.llm_hooks import (get_after_llm_call_hooks,get_before_llm_call_hooks,)+from crewai.hooks.tool_hooks import (+ ToolCallHookContext,+ get_after_tool_call_hooks,+ get_before_tool_call_hooks,+)from crewai.utilities.agent_utils import (aget_llm_response,convert_tools_to_openai_schema,@@ -749,8 +754,41 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):track_delegation_if_needed(func_name, args_dict, self.task)- # Execute the tool (only if not cached and not at max usage)- if not from_cache and not max_usage_reached:+ # Find the structured tool for hook context+ structured_tool = None+ for tool in self.tools or []:+ if sanitize_tool_name(tool.name) == func_name:+ structured_tool = tool+ break++ # Execute before_tool_call hooks+ hook_blocked = False+ before_hook_context = ToolCallHookContext(+ tool_name=func_name,+ tool_input=args_dict,+ tool=structured_tool, # type: ignore[arg-type]+ agent=self.agent,+ task=self.task,+ crew=self.crew,+ )+ before_hooks = get_before_tool_call_hooks()+ try:+ for hook in before_hooks:+ hook_result = hook(before_hook_context)+ if hook_result is False:+ hook_blocked = True+ break+ except Exception as hook_error:+ self._printer.print(+ content=f"Error in before_tool_call hook: {hook_error}",+ color="red",+ )++ # If hook blocked execution, set result and skip tool execution+ if hook_blocked:+ result = f"Tool execution blocked by hook. Tool: {func_name}"+ # Execute the tool (only if not cached, not at max usage, and not blocked by hook)+ elif not from_cache and not max_usage_reached:result = "Tool not found"if func_name in available_functions:try:@@ -798,6 +836,28 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):# Return error message when max usage limit is reachedresult = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."+ after_hook_context = ToolCallHookContext(+ tool_name=func_name,+ tool_input=args_dict,+ tool=structured_tool, # type: ignore[arg-type]+ agent=self.agent,+ task=self.task,+ crew=self.crew,+ tool_result=result,+ )+ after_hooks = get_after_tool_call_hooks()+ try:+ for after_hook in after_hooks:+ hook_result = after_hook(after_hook_context)+ if hook_result is not None:+ result = hook_result+ after_hook_context.tool_result = result+ except Exception as hook_error:+ self._printer.print(+ content=f"Error in after_tool_call hook: {hook_error}",+ color="red",+ )+# Emit tool usage finished eventcrewai_event_bus.emit(self,diff --git a/lib/crewai/src/crewai/experimental/agent_executor.py b/lib/crewai/src/crewai/experimental/agent_executor.pyindex e8bcdf460..8b521f880 100644--- a/lib/crewai/src/crewai/experimental/agent_executor.py+++ b/lib/crewai/src/crewai/experimental/agent_executor.py@@ -36,6 +36,11 @@ from crewai.hooks.llm_hooks import (get_after_llm_call_hooks,get_before_llm_call_hooks,)+from crewai.hooks.tool_hooks import (+ ToolCallHookContext,+ get_after_tool_call_hooks,+ get_before_tool_call_hooks,+)from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookTypefrom crewai.utilities.agent_utils import (convert_tools_to_openai_schema,@@ -665,8 +670,37 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):track_delegation_if_needed(func_name, args_dict, self.task)- # Execute the tool (only if not cached and not at max usage)- if not from_cache and not max_usage_reached:+ structured_tool = None+ for tool in self.tools or []:+ if sanitize_tool_name(tool.name) == func_name:+ structured_tool = tool+ break++ hook_blocked = False+ before_hook_context = ToolCallHookContext(+ tool_name=func_name,+ tool_input=args_dict,+ tool=structured_tool, # type: ignore[arg-type]+ agent=self.agent,+ task=self.task,+ crew=self.crew,+ )+ before_hooks = get_before_tool_call_hooks()+ try:+ for hook in before_hooks:+ hook_result = hook(before_hook_context)+ if hook_result is False:+ hook_blocked = True+ break+ except Exception as hook_error:+ self._printer.print(+ content=f"Error in before_tool_call hook: {hook_error}",+ color="red",+ )++ if hook_blocked:+ result = f"Tool execution blocked by hook. Tool: {func_name}"+ elif not from_cache and not max_usage_reached:result = "Tool not found"if func_name in self._available_functions:try:@@ -711,6 +745,29 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):# Return error message when max usage limit is reachedresult = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."+ # Execute after_tool_call hooks (even if blocked, to allow logging/monitoring)+ after_hook_context = ToolCallHookContext(+ tool_name=func_name,+ tool_input=args_dict,+ tool=structured_tool, # type: ignore[arg-type]+ agent=self.agent,+ task=self.task,+ crew=self.crew,+ tool_result=result,+ )+ after_hooks = get_after_tool_call_hooks()+ try:+ for after_hook in after_hooks:+ hook_result = after_hook(after_hook_context)+ if hook_result is not None:+ result = hook_result+ after_hook_context.tool_result = result+ except Exception as hook_error:+ self._printer.print(+ content=f"Error in after_tool_call hook: {hook_error}",+ color="red",+ )+# Emit tool usage finished eventcrewai_event_bus.emit(self,diff --git a/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_agent_native_tool_hooks_before_and_after.yaml b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_agent_native_tool_hooks_before_and_after.yamlnew file mode 100644index 000000000..23719e5c3--- /dev/null+++ b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_agent_native_tool_hooks_before_and_after.yaml@@ -0,0 +1,224 @@+interactions:+- request:+ body: '{"messages":[{"role":"system","content":"You are Calculator. You are a+ calculator assistant\nYour personal goal is: Perform calculations"},{"role":"user","content":"\nCurrent+ Task: What is 7 times 6? Use the multiply_numbers tool.\n\nThis is VERY important+ to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiply_numbers","description":"Multiply+ two numbers together.","parameters":{"properties":{"a":{"title":"A","type":"integer"},"b":{"title":"B","type":"integer"}},"required":["a","b"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '589'+ content-type:+ - application/json+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2gblVDQeSH6tTrJiUtxgjoVoPuAR\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532813,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n+ \ \"id\": \"call_gO6PtjoOIDVeDWs7Wf680BHh\",\n \"type\":+ \"function\",\n \"function\": {\n \"name\": \"multiply_numbers\",\n+ \ \"arguments\": \"{\\\"a\\\":7,\\\"b\\\":6}\"\n }\n+ \ }\n ],\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 100,\n \"completion_tokens\":+ 18,\n \"total_tokens\": 118,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 16:53:34 GMT+ Server:+ - cloudflare+ Set-Cookie:+ - SET-COOKIE-XXX+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '593'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+- request:+ body: '{"messages":[{"role":"system","content":"You are Calculator. You are a+ calculator assistant\nYour personal goal is: Perform calculations"},{"role":"user","content":"\nCurrent+ Task: What is 7 times 6? Use the multiply_numbers tool.\n\nThis is VERY important+ to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_gO6PtjoOIDVeDWs7Wf680BHh","type":"function","function":{"name":"multiply_numbers","arguments":"{\"a\":7,\"b\":6}"}}]},{"role":"tool","tool_call_id":"call_gO6PtjoOIDVeDWs7Wf680BHh","name":"multiply_numbers","content":"42"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiply_numbers","description":"Multiply+ two numbers together.","parameters":{"properties":{"a":{"title":"A","type":"integer"},"b":{"title":"B","type":"integer"}},"required":["a","b"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '1056'+ content-type:+ - application/json+ cookie:+ - COOKIE-XXX+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2gbm9NaGCXkI3QwW3eOTFSP4L4lh\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532814,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"42\",\n \"refusal\": null,\n+ \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":+ \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 162,\n \"completion_tokens\":+ 2,\n \"total_tokens\": 164,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 16:53:34 GMT+ Server:+ - cloudflare+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '259'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+version: 1diff --git a/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_before_hook_blocks_tool_execution_in_crew.yaml b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_before_hook_blocks_tool_execution_in_crew.yamlnew file mode 100644index 000000000..8f3722e9f--- /dev/null+++ b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_before_hook_blocks_tool_execution_in_crew.yaml@@ -0,0 +1,351 @@+interactions:+- request:+ body: '{"messages":[{"role":"system","content":"You are Test Agent. You are a+ test agent\nYour personal goal is: Try to use the dangerous operation tool"},{"role":"user","content":"\nCurrent+ Task: Use the dangerous_operation tool with action ''delete_all''.\n\nThis is+ the expected criteria for your final answer: The result of the operation\nyou+ MUST return the actual complete content as the final answer, not a summary.\n\nThis+ is VERY important to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dangerous_operation","description":"Perform+ a dangerous operation that should be blocked.","parameters":{"properties":{"action":{"title":"Action","type":"string"}},"required":["action"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '773'+ content-type:+ - application/json+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2giKEOxBDVqJVqVECwcFjbzdQKSA\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769533220,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n+ \ \"id\": \"call_3OM1qS0QaWqhiJaHyJbNz1ME\",\n \"type\":+ \"function\",\n \"function\": {\n \"name\": \"dangerous_operation\",\n+ \ \"arguments\": \"{\\\"action\\\":\\\"delete_all\\\"}\"\n }\n+ \ }\n ],\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 133,\n \"completion_tokens\":+ 17,\n \"total_tokens\": 150,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 17:00:20 GMT+ Server:+ - cloudflare+ Set-Cookie:+ - SET-COOKIE-XXX+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '484'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+- request:+ body: '{"messages":[{"role":"system","content":"You are Test Agent. You are a+ test agent\nYour personal goal is: Try to use the dangerous operation tool"},{"role":"user","content":"\nCurrent+ Task: Use the dangerous_operation tool with action ''delete_all''.\n\nThis is+ the expected criteria for your final answer: The result of the operation\nyou+ MUST return the actual complete content as the final answer, not a summary.\n\nThis+ is VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_3OM1qS0QaWqhiJaHyJbNz1ME","type":"function","function":{"name":"dangerous_operation","arguments":"{\"action\":\"delete_all\"}"}}]},{"role":"tool","tool_call_id":"call_3OM1qS0QaWqhiJaHyJbNz1ME","name":"dangerous_operation","content":"Tool+ execution blocked by hook. Tool: dangerous_operation"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dangerous_operation","description":"Perform+ a dangerous operation that should be blocked.","parameters":{"properties":{"action":{"title":"Action","type":"string"}},"required":["action"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '1311'+ content-type:+ - application/json+ cookie:+ - COOKIE-XXX+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2giLnD91JxhK0yXninQ7oHYttNDY\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769533221,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n+ \ \"id\": \"call_qF1c2e31GgjoSNJx0HBxI3zX\",\n \"type\":+ \"function\",\n \"function\": {\n \"name\": \"dangerous_operation\",\n+ \ \"arguments\": \"{\\\"action\\\":\\\"delete_all\\\"}\"\n }\n+ \ }\n ],\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 204,\n \"completion_tokens\":+ 17,\n \"total_tokens\": 221,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 17:00:21 GMT+ Server:+ - cloudflare+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '447'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+- request:+ body: '{"messages":[{"role":"system","content":"You are Test Agent. You are a+ test agent\nYour personal goal is: Try to use the dangerous operation tool"},{"role":"user","content":"\nCurrent+ Task: Use the dangerous_operation tool with action ''delete_all''.\n\nThis is+ the expected criteria for your final answer: The result of the operation\nyou+ MUST return the actual complete content as the final answer, not a summary.\n\nThis+ is VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_3OM1qS0QaWqhiJaHyJbNz1ME","type":"function","function":{"name":"dangerous_operation","arguments":"{\"action\":\"delete_all\"}"}}]},{"role":"tool","tool_call_id":"call_3OM1qS0QaWqhiJaHyJbNz1ME","name":"dangerous_operation","content":"Tool+ execution blocked by hook. Tool: dangerous_operation"},{"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."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_qF1c2e31GgjoSNJx0HBxI3zX","type":"function","function":{"name":"dangerous_operation","arguments":"{\"action\":\"delete_all\"}"}}]},{"role":"tool","tool_call_id":"call_qF1c2e31GgjoSNJx0HBxI3zX","name":"dangerous_operation","content":"Tool+ execution blocked by hook. Tool: dangerous_operation"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dangerous_operation","description":"Perform+ a dangerous operation that should be blocked.","parameters":{"properties":{"action":{"title":"Action","type":"string"}},"required":["action"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '1849'+ content-type:+ - application/json+ cookie:+ - COOKIE-XXX+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2giM1tAvEOCNwDw1qNmNUN5PIg2Y\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769533222,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"The dangerous_operation tool with action+ 'delete_all' was blocked and did not execute. There is no result from the+ operation to provide.\",\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 275,\n \"completion_tokens\":+ 28,\n \"total_tokens\": 303,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 17:00:22 GMT+ Server:+ - cloudflare+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '636'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+version: 1diff --git a/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_crew_native_tool_hooks_before_and_after.yaml b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_crew_native_tool_hooks_before_and_after.yamlnew file mode 100644index 000000000..a60224a60--- /dev/null+++ b/lib/crewai/tests/cassettes/hooks/TestNativeToolCallingHooksIntegration.test_crew_native_tool_hooks_before_and_after.yaml@@ -0,0 +1,230 @@+interactions:+- request:+ body: '{"messages":[{"role":"system","content":"You are Math Assistant. You are+ a math assistant that helps with division\nYour personal goal is: Perform division+ calculations accurately"},{"role":"user","content":"\nCurrent Task: Calculate+ 100 divided by 4 using the divide_numbers tool.\n\nThis is the expected criteria+ for your final answer: The result of the division\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nThis is VERY important+ to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"divide_numbers","description":"Divide+ first number by second number.","parameters":{"properties":{"a":{"title":"A","type":"integer"},"b":{"title":"B","type":"integer"}},"required":["a","b"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '809'+ content-type:+ - application/json+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2gbkWUn8InDLeD1Cf8w0LxiUQOIS\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532812,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n+ \ \"id\": \"call_gwIV3i71RNqfpr7KguEciCuV\",\n \"type\":+ \"function\",\n \"function\": {\n \"name\": \"divide_numbers\",\n+ \ \"arguments\": \"{\\\"a\\\":100,\\\"b\\\":4}\"\n }\n+ \ }\n ],\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 140,\n \"completion_tokens\":+ 18,\n \"total_tokens\": 158,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 16:53:32 GMT+ Server:+ - cloudflare+ Set-Cookie:+ - SET-COOKIE-XXX+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '435'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+- request:+ body: '{"messages":[{"role":"system","content":"You are Math Assistant. You are+ a math assistant that helps with division\nYour personal goal is: Perform division+ calculations accurately"},{"role":"user","content":"\nCurrent Task: Calculate+ 100 divided by 4 using the divide_numbers tool.\n\nThis is the expected criteria+ for your final answer: The result of the division\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nThis is VERY important+ to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_gwIV3i71RNqfpr7KguEciCuV","type":"function","function":{"name":"divide_numbers","arguments":"{\"a\":100,\"b\":4}"}}]},{"role":"tool","tool_call_id":"call_gwIV3i71RNqfpr7KguEciCuV","name":"divide_numbers","content":"25.0"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"divide_numbers","description":"Divide+ first number by second number.","parameters":{"properties":{"a":{"title":"A","type":"integer"},"b":{"title":"B","type":"integer"}},"required":["a","b"],"type":"object"}}}]}'+ headers:+ User-Agent:+ - X-USER-AGENT-XXX+ accept:+ - application/json+ accept-encoding:+ - ACCEPT-ENCODING-XXX+ authorization:+ - AUTHORIZATION-XXX+ connection:+ - keep-alive+ content-length:+ - '1276'+ content-type:+ - application/json+ cookie:+ - COOKIE-XXX+ host:+ - api.openai.com+ x-stainless-arch:+ - X-STAINLESS-ARCH-XXX+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - X-STAINLESS-OS-XXX+ x-stainless-package-version:+ - 1.83.0+ x-stainless-read-timeout:+ - X-STAINLESS-READ-TIMEOUT-XXX+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.13.3+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ body:+ string: "{\n \"id\": \"chatcmpl-D2gbkHw19D5oEBOhpZP5FR5MvRFgb\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532812,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"25.0\",\n \"refusal\": null,\n+ \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":+ \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 204,\n \"completion_tokens\":+ 4,\n \"total_tokens\": 208,\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_376a7ccef1\"\n}\n"+ headers:+ CF-RAY:+ - CF-RAY-XXX+ Connection:+ - keep-alive+ Content-Type:+ - application/json+ Date:+ - Tue, 27 Jan 2026 16:53:33 GMT+ Server:+ - cloudflare+ Strict-Transport-Security:+ - STS-XXX+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - X-CONTENT-TYPE-XXX+ access-control-expose-headers:+ - ACCESS-CONTROL-XXX+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - OPENAI-ORG-XXX+ openai-processing-ms:+ - '523'+ openai-project:+ - OPENAI-PROJECT-XXX+ openai-version:+ - '2020-10-01'+ x-openai-proxy-wasm:+ - v0.1+ x-ratelimit-limit-requests:+ - X-RATELIMIT-LIMIT-REQUESTS-XXX+ x-ratelimit-limit-tokens:+ - X-RATELIMIT-LIMIT-TOKENS-XXX+ x-ratelimit-remaining-requests:+ - X-RATELIMIT-REMAINING-REQUESTS-XXX+ x-ratelimit-remaining-tokens:+ - X-RATELIMIT-REMAINING-TOKENS-XXX+ x-ratelimit-reset-requests:+ - X-RATELIMIT-RESET-REQUESTS-XXX+ x-ratelimit-reset-tokens:+ - X-RATELIMIT-RESET-TOKENS-XXX+ x-request-id:+ - X-REQUEST-ID-XXX+ status:+ code: 200+ message: OK+version: 1diff --git a/lib/crewai/tests/cassettes/hooks/TestToolHooksIntegration.test_lite_agent_hooks_integration_with_real_tool.yaml b/lib/crewai/tests/cassettes/hooks/TestToolHooksIntegration.test_lite_agent_hooks_integration_with_real_tool.yamlindex a379c8397..f69c7df52 100644--- a/lib/crewai/tests/cassettes/hooks/TestToolHooksIntegration.test_lite_agent_hooks_integration_with_real_tool.yaml+++ b/lib/crewai/tests/cassettes/hooks/TestToolHooksIntegration.test_lite_agent_hooks_integration_with_real_tool.yaml@@ -1,7 +1,22 @@interactions:- request:- body: '{"messages":[{"role":"system","content":"You are Calculator Assistant. You are a helpful calculator assistant\nYour personal goal is: Help with math calculations\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments: {''a'': {''description'': None, ''type'': ''int''}, ''b'': {''description'': None, ''type'': ''int''}}\nTool Description: Add two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [calculate_sum], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final- answer to the original input question\n```"},{"role":"user","content":"What is 5 + 3? Use the calculate_sum tool."}],"model":"gpt-4.1-mini"}'+ body: '{"messages":[{"role":"system","content":"You are Calculator Assistant.+ You are a helpful calculator assistant\nYour personal goal is: Help with math+ calculations\n\nYou ONLY have access to the following tools, and should NEVER+ make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments:+ {\n \"properties\": {\n \"a\": {\n \"title\": \"A\",\n \"type\":+ \"integer\"\n },\n \"b\": {\n \"title\": \"B\",\n \"type\":+ \"integer\"\n }\n },\n \"required\": [\n \"a\",\n \"b\"\n ],\n \"title\":+ \"Calculate_Sum\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\nTool+ Description: Add two numbers together.\n\nIMPORTANT: Use the following format+ in your response:\n\n```\nThought: you should always think about what to do\nAction:+ the action to take, only one name of [calculate_sum], just the name, exactly+ as it''s written.\nAction Input: the input to the action, just a simple JSON+ object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:+ the result of the action\n```\n\nOnce all necessary information is gathered,+ return the following format:\n\n```\nThought: I now know the final answer\nFinal+ Answer: the final answer to the original input question\n```"},{"role":"user","content":"What+ is 5 + 3? Use the calculate_sum tool."}],"model":"gpt-4.1-mini"}'headers:User-Agent:- X-USER-AGENT-XXX@@ -14,7 +29,7 @@ interactions:connection:- keep-alivecontent-length:- - '1119'+ - '1356'content-type:- application/jsonhost:@@ -41,8 +56,18 @@ interactions:uri: https://api.openai.com/v1/chat/completionsresponse:body:- string: "{\n \"id\": \"chatcmpl-CiksV15hVLWURKZH4BxQEGjiCFWpz\",\n \"object\": \"chat.completion\",\n \"created\": 1764782667,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I should use the calculate_sum tool to add 5 and 3.\\nAction: calculate_sum\\nAction Input: {\\\"a\\\": 5, \\\"b\\\": 3}\\n```\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 234,\n \"completion_tokens\": 40,\n \"total_tokens\": 274,\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_9766e549b2\"\n}\n"+ string: "{\n \"id\": \"chatcmpl-D2gSz7JfTi4NQ2QRTANg8Z2afJI8b\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532269,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"```\\nThought: I need to use the calculate_sum+ tool to find the sum of 5 and 3\\nAction: calculate_sum\\nAction Input: {\\\"a\\\":5,\\\"b\\\":3}\\n```\",\n+ \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":+ null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":+ 295,\n \"completion_tokens\": 41,\n \"total_tokens\": 336,\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_376a7ccef1\"\n}\n"headers:CF-RAY:- CF-RAY-XXX@@ -51,7 +76,7 @@ interactions:Content-Type:- application/jsonDate:- - Wed, 03 Dec 2025 17:24:28 GMT+ - Tue, 27 Jan 2026 16:44:30 GMTServer:- cloudflareSet-Cookie:@@ -71,13 +96,11 @@ interactions:openai-organization:- OPENAI-ORG-XXXopenai-processing-ms:- - '681'+ - '827'openai-project:- OPENAI-PROJECT-XXXopenai-version:- '2020-10-01'- x-envoy-upstream-service-time:- - '871'x-openai-proxy-wasm:- v0.1x-ratelimit-limit-requests:@@ -98,8 +121,25 @@ interactions:code: 200message: OK- request:- body: '{"messages":[{"role":"system","content":"You are Calculator Assistant. You are a helpful calculator assistant\nYour personal goal is: Help with math calculations\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments: {''a'': {''description'': None, ''type'': ''int''}, ''b'': {''description'': None, ''type'': ''int''}}\nTool Description: Add two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [calculate_sum], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final- answer to the original input question\n```"},{"role":"user","content":"What is 5 + 3? Use the calculate_sum tool."},{"role":"assistant","content":"```\nThought: I should use the calculate_sum tool to add 5 and 3.\nAction: calculate_sum\nAction Input: {\"a\": 5, \"b\": 3}\n```\nObservation: 8"}],"model":"gpt-4.1-mini"}'+ body: '{"messages":[{"role":"system","content":"You are Calculator Assistant.+ You are a helpful calculator assistant\nYour personal goal is: Help with math+ calculations\n\nYou ONLY have access to the following tools, and should NEVER+ make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments:+ {\n \"properties\": {\n \"a\": {\n \"title\": \"A\",\n \"type\":+ \"integer\"\n },\n \"b\": {\n \"title\": \"B\",\n \"type\":+ \"integer\"\n }\n },\n \"required\": [\n \"a\",\n \"b\"\n ],\n \"title\":+ \"Calculate_Sum\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\nTool+ Description: Add two numbers together.\n\nIMPORTANT: Use the following format+ in your response:\n\n```\nThought: you should always think about what to do\nAction:+ the action to take, only one name of [calculate_sum], just the name, exactly+ as it''s written.\nAction Input: the input to the action, just a simple JSON+ object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:+ the result of the action\n```\n\nOnce all necessary information is gathered,+ return the following format:\n\n```\nThought: I now know the final answer\nFinal+ Answer: the final answer to the original input question\n```"},{"role":"user","content":"What+ is 5 + 3? Use the calculate_sum tool."},{"role":"assistant","content":"```\nThought:+ I need to use the calculate_sum tool to find the sum of 5 and 3\nAction: calculate_sum\nAction+ Input: {\"a\":5,\"b\":3}\n```\nObservation: 8"}],"model":"gpt-4.1-mini"}'headers:User-Agent:- X-USER-AGENT-XXX@@ -112,7 +152,7 @@ interactions:connection:- keep-alivecontent-length:- - '1298'+ - '1544'content-type:- application/jsoncookie:@@ -141,7 +181,18 @@ interactions:uri: https://api.openai.com/v1/chat/completionsresponse:body:- string: "{\n \"id\": \"chatcmpl-CiksWrVbyJFurKCm7XPRU1b1pT7qF\",\n \"object\": \"chat.completion\",\n \"created\": 1764782668,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal Answer: 8\\n```\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 283,\n \"completion_tokens\": 18,\n \"total_tokens\": 301,\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_9766e549b2\"\n}\n"+ string: "{\n \"id\": \"chatcmpl-D2gT0RU66XqjAUOXnGmokD1Q8Fman\",\n \"object\":+ \"chat.completion\",\n \"created\": 1769532270,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"```\\nThought: I now know the final+ answer\\nFinal Answer: 8\\n```\",\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 345,\n \"completion_tokens\":+ 18,\n \"total_tokens\": 363,\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_376a7ccef1\"\n}\n"headers:CF-RAY:- CF-RAY-XXX@@ -150,7 +201,7 @@ interactions:Content-Type:- application/jsonDate:- - Wed, 03 Dec 2025 17:24:29 GMT+ - Tue, 27 Jan 2026 16:44:31 GMTServer:- cloudflareStrict-Transport-Security:@@ -168,208 +219,11 @@ interactions:openai-organization:- OPENAI-ORG-XXXopenai-processing-ms:- - '427'+ - '606'openai-project:- OPENAI-PROJECT-XXXopenai-version:- '2020-10-01'- x-envoy-upstream-service-time:- - '442'- x-openai-proxy-wasm:- - v0.1- x-ratelimit-limit-requests:- - X-RATELIMIT-LIMIT-REQUESTS-XXX- x-ratelimit-limit-tokens:- - X-RATELIMIT-LIMIT-TOKENS-XXX- x-ratelimit-remaining-requests:- - X-RATELIMIT-REMAINING-REQUESTS-XXX- x-ratelimit-remaining-tokens:- - X-RATELIMIT-REMAINING-TOKENS-XXX- x-ratelimit-reset-requests:- - X-RATELIMIT-RESET-REQUESTS-XXX- x-ratelimit-reset-tokens:- - X-RATELIMIT-RESET-TOKENS-XXX- x-request-id:- - X-REQUEST-ID-XXX- status:- code: 200- message: OK-- request:- body: '{"messages":[{"role":"system","content":"You are Calculator Assistant. You are a helpful calculator assistant\nYour personal goal is: Help with math calculations\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments: {''a'': {''description'': None, ''type'': ''int''}, ''b'': {''description'': None, ''type'': ''int''}}\nTool Description: Add two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [calculate_sum], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final- answer to the original input question\n```"},{"role":"user","content":"What is 5 + 3? Use the calculate_sum tool."}],"model":"gpt-4.1-mini"}'- headers:- User-Agent:- - X-USER-AGENT-XXX- accept:- - application/json- accept-encoding:- - ACCEPT-ENCODING-XXX- authorization:- - AUTHORIZATION-XXX- connection:- - keep-alive- content-length:- - '1119'- content-type:- - application/json- host:- - api.openai.com- x-stainless-arch:- - X-STAINLESS-ARCH-XXX- x-stainless-async:- - 'false'- x-stainless-lang:- - python- x-stainless-os:- - X-STAINLESS-OS-XXX- x-stainless-package-version:- - 1.83.0- x-stainless-read-timeout:- - X-STAINLESS-READ-TIMEOUT-XXX- x-stainless-retry-count:- - '0'- x-stainless-runtime:- - CPython- x-stainless-runtime-version:- - 3.13.3- method: POST- uri: https://api.openai.com/v1/chat/completions- response:- body:- string: "{\n \"id\": \"chatcmpl-CimX8hwYiUUZijApUDk1yBMzTpBj9\",\n \"object\": \"chat.completion\",\n \"created\": 1764789030,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I need to add 5 and 3 using the calculate_sum tool.\\nAction: calculate_sum\\nAction Input: {\\\"a\\\":5,\\\"b\\\":3}\\n```\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 234,\n \"completion_tokens\": 37,\n \"total_tokens\": 271,\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_9766e549b2\"\n}\n"- headers:- CF-RAY:- - CF-RAY-XXX- Connection:- - keep-alive- Content-Type:- - application/json- Date:- - Wed, 03 Dec 2025 19:10:33 GMT- Server:- - cloudflare- Set-Cookie:- - SET-COOKIE-XXX- Strict-Transport-Security:- - STS-XXX- Transfer-Encoding:- - chunked- X-Content-Type-Options:- - X-CONTENT-TYPE-XXX- access-control-expose-headers:- - ACCESS-CONTROL-XXX- alt-svc:- - h3=":443"; ma=86400- cf-cache-status:- - DYNAMIC- openai-organization:- - OPENAI-ORG-XXX- openai-processing-ms:- - '2329'- openai-project:- - OPENAI-PROJECT-XXX- openai-version:- - '2020-10-01'- x-envoy-upstream-service-time:- - '2349'- x-openai-proxy-wasm:- - v0.1- x-ratelimit-limit-requests:- - X-RATELIMIT-LIMIT-REQUESTS-XXX- x-ratelimit-limit-tokens:- - X-RATELIMIT-LIMIT-TOKENS-XXX- x-ratelimit-remaining-requests:- - X-RATELIMIT-REMAINING-REQUESTS-XXX- x-ratelimit-remaining-tokens:- - X-RATELIMIT-REMAINING-TOKENS-XXX- x-ratelimit-reset-requests:- - X-RATELIMIT-RESET-REQUESTS-XXX- x-ratelimit-reset-tokens:- - X-RATELIMIT-RESET-TOKENS-XXX- x-request-id:- - X-REQUEST-ID-XXX- status:- code: 200- message: OK-- request:- body: '{"messages":[{"role":"system","content":"You are Calculator Assistant. You are a helpful calculator assistant\nYour personal goal is: Help with math calculations\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: calculate_sum\nTool Arguments: {''a'': {''description'': None, ''type'': ''int''}, ''b'': {''description'': None, ''type'': ''int''}}\nTool Description: Add two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [calculate_sum], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final- answer to the original input question\n```"},{"role":"user","content":"What is 5 + 3? Use the calculate_sum tool."},{"role":"assistant","content":"```\nThought: I need to add 5 and 3 using the calculate_sum tool.\nAction: calculate_sum\nAction Input: {\"a\":5,\"b\":3}\n```\nObservation: 8"}],"model":"gpt-4.1-mini"}'- headers:- User-Agent:- - X-USER-AGENT-XXX- accept:- - application/json- accept-encoding:- - ACCEPT-ENCODING-XXX- authorization:- - AUTHORIZATION-XXX- connection:- - keep-alive- content-length:- - '1295'- content-type:- - application/json- cookie:- - COOKIE-XXX- host:- - api.openai.com- x-stainless-arch:- - X-STAINLESS-ARCH-XXX- x-stainless-async:- - 'false'- x-stainless-lang:- - python- x-stainless-os:- - X-STAINLESS-OS-XXX- x-stainless-package-version:- - 1.83.0- x-stainless-read-timeout:- - X-STAINLESS-READ-TIMEOUT-XXX- x-stainless-retry-count:- - '0'- x-stainless-runtime:- - CPython- x-stainless-runtime-version:- - 3.13.3- method: POST- uri: https://api.openai.com/v1/chat/completions- response:- body:- string: "{\n \"id\": \"chatcmpl-CimXBrY5sdbr2pJnqGlazPTra4dor\",\n \"object\": \"chat.completion\",\n \"created\": 1764789033,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal Answer: 8\\n```\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 280,\n \"completion_tokens\": 18,\n \"total_tokens\": 298,\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_9766e549b2\"\n}\n"- headers:- CF-RAY:- - CF-RAY-XXX- Connection:- - keep-alive- Content-Type:- - application/json- Date:- - Wed, 03 Dec 2025 19:10:35 GMT- Server:- - cloudflare- Strict-Transport-Security:- - STS-XXX- Transfer-Encoding:- - chunked- X-Content-Type-Options:- - X-CONTENT-TYPE-XXX- access-control-expose-headers:- - ACCESS-CONTROL-XXX- alt-svc:- - h3=":443"; ma=86400- cf-cache-status:- - DYNAMIC- openai-organization:- - OPENAI-ORG-XXX- openai-processing-ms:- - '1647'- openai-project:- - OPENAI-PROJECT-XXX- openai-version:- - '2020-10-01'- x-envoy-upstream-service-time:- - '1694'x-openai-proxy-wasm:- v0.1x-ratelimit-limit-requests:diff --git a/lib/crewai/tests/hooks/test_tool_hooks.py b/lib/crewai/tests/hooks/test_tool_hooks.pyindex e8c6bd7d0..b9245fab0 100644--- a/lib/crewai/tests/hooks/test_tool_hooks.py+++ b/lib/crewai/tests/hooks/test_tool_hooks.py@@ -590,3 +590,233 @@ class TestToolHooksIntegration:# Clean up hooksunregister_before_tool_call_hook(before_tool_call_hook)unregister_after_tool_call_hook(after_tool_call_hook)+++class TestNativeToolCallingHooksIntegration:+ """Integration tests for hooks with native function calling (Agent and Crew)."""++ @pytest.mark.vcr()+ def test_agent_native_tool_hooks_before_and_after(self):+ """Test that Agent with native tool calling executes before/after hooks."""+ import os+ from crewai import Agent+ from crewai.tools import tool++ hook_calls = {"before": [], "after": []}++ @tool("multiply_numbers")+ def multiply_numbers(a: int, b: int) -> int:+ """Multiply two numbers together."""+ return a * b++ def before_hook(context: ToolCallHookContext) -> bool | None:+ hook_calls["before"].append({+ "tool_name": context.tool_name,+ "tool_input": dict(context.tool_input),+ "has_agent": context.agent is not None,+ })+ return None++ def after_hook(context: ToolCallHookContext) -> str | None:+ hook_calls["after"].append({+ "tool_name": context.tool_name,+ "tool_result": context.tool_result,+ "has_agent": context.agent is not None,+ })+ return None++ register_before_tool_call_hook(before_hook)+ register_after_tool_call_hook(after_hook)++ try:+ agent = Agent(+ role="Calculator",+ goal="Perform calculations",+ backstory="You are a calculator assistant",+ tools=[multiply_numbers],+ verbose=True,+ )++ agent.kickoff(+ messages="What is 7 times 6? Use the multiply_numbers tool."+ )++ # Verify before hook was called+ assert len(hook_calls["before"]) > 0, "Before hook was never called"+ before_call = hook_calls["before"][0]+ assert before_call["tool_name"] == "multiply_numbers"+ assert "a" in before_call["tool_input"]+ assert "b" in before_call["tool_input"]+ assert before_call["has_agent"] is True++ # Verify after hook was called+ assert len(hook_calls["after"]) > 0, "After hook was never called"+ after_call = hook_calls["after"][0]+ assert after_call["tool_name"] == "multiply_numbers"+ assert "42" in str(after_call["tool_result"])+ assert after_call["has_agent"] is True++ finally:+ unregister_before_tool_call_hook(before_hook)+ unregister_after_tool_call_hook(after_hook)++ @pytest.mark.vcr()+ def test_crew_native_tool_hooks_before_and_after(self):+ """Test that Crew with Agent executes before/after hooks with full context."""+ import os+ from crewai import Agent, Crew, Task+ from crewai.tools import tool+++ hook_calls = {"before": [], "after": []}++ @tool("divide_numbers")+ def divide_numbers(a: int, b: int) -> float:+ """Divide first number by second number."""+ return a / b++ def before_hook(context: ToolCallHookContext) -> bool | None:+ hook_calls["before"].append({+ "tool_name": context.tool_name,+ "tool_input": dict(context.tool_input),+ "has_agent": context.agent is not None,+ "has_task": context.task is not None,+ "has_crew": context.crew is not None,+ "agent_role": context.agent.role if context.agent else None,+ })+ return None++ def after_hook(context: ToolCallHookContext) -> str | None:+ hook_calls["after"].append({+ "tool_name": context.tool_name,+ "tool_result": context.tool_result,+ "has_agent": context.agent is not None,+ "has_task": context.task is not None,+ "has_crew": context.crew is not None,+ })+ return None++ register_before_tool_call_hook(before_hook)+ register_after_tool_call_hook(after_hook)++ try:+ agent = Agent(+ role="Math Assistant",+ goal="Perform division calculations accurately",+ backstory="You are a math assistant that helps with division",+ tools=[divide_numbers],+ verbose=True,+ )++ task = Task(+ description="Calculate 100 divided by 4 using the divide_numbers tool.",+ expected_output="The result of the division",+ agent=agent,+ )++ crew = Crew(+ agents=[agent],+ tasks=[task],+ verbose=True,+ )++ crew.kickoff()++ # Verify before hook was called with full context+ assert len(hook_calls["before"]) > 0, "Before hook was never called"+ before_call = hook_calls["before"][0]+ assert before_call["tool_name"] == "divide_numbers"+ assert "a" in before_call["tool_input"]+ assert "b" in before_call["tool_input"]+ assert before_call["has_agent"] is True+ assert before_call["has_task"] is True+ assert before_call["has_crew"] is True+ assert before_call["agent_role"] == "Math Assistant"++ # Verify after hook was called with full context+ assert len(hook_calls["after"]) > 0, "After hook was never called"+ after_call = hook_calls["after"][0]+ assert after_call["tool_name"] == "divide_numbers"+ assert "25" in str(after_call["tool_result"])+ assert after_call["has_agent"] is True+ assert after_call["has_task"] is True+ assert after_call["has_crew"] is True++ finally:+ unregister_before_tool_call_hook(before_hook)+ unregister_after_tool_call_hook(after_hook)++ @pytest.mark.vcr()+ def test_before_hook_blocks_tool_execution_in_crew(self):+ """Test that returning False from before hook blocks tool execution."""+ import os+ from crewai import Agent, Crew, Task+ from crewai.tools import tool++ hook_calls = {"before": [], "after": [], "tool_executed": False}++ @tool("dangerous_operation")+ def dangerous_operation(action: str) -> str:+ """Perform a dangerous operation that should be blocked."""+ hook_calls["tool_executed"] = True+ return f"Executed: {action}"++ def blocking_before_hook(context: ToolCallHookContext) -> bool | None:+ hook_calls["before"].append({+ "tool_name": context.tool_name,+ "tool_input": dict(context.tool_input),+ })+ # Block all calls to dangerous_operation+ if context.tool_name == "dangerous_operation":+ return False+ return None++ def after_hook(context: ToolCallHookContext) -> str | None:+ hook_calls["after"].append({+ "tool_name": context.tool_name,+ "tool_result": context.tool_result,+ })+ return None++ register_before_tool_call_hook(blocking_before_hook)+ register_after_tool_call_hook(after_hook)++ try:+ agent = Agent(+ role="Test Agent",+ goal="Try to use the dangerous operation tool",+ backstory="You are a test agent",+ tools=[dangerous_operation],+ verbose=True,+ )++ task = Task(+ description="Use the dangerous_operation tool with action 'delete_all'.",+ expected_output="The result of the operation",+ agent=agent,+ )++ crew = Crew(+ agents=[agent],+ tasks=[task],+ verbose=True,+ )++ crew.kickoff()++ # Verify before hook was called+ assert len(hook_calls["before"]) > 0, "Before hook was never called"+ before_call = hook_calls["before"][0]+ assert before_call["tool_name"] == "dangerous_operation"++ # Verify the actual tool function was NOT executed+ assert hook_calls["tool_executed"] is False, "Tool should have been blocked"++ # Verify after hook was still called (with blocked message)+ assert len(hook_calls["after"]) > 0, "After hook was never called"+ after_call = hook_calls["after"][0]+ assert "blocked" in after_call["tool_result"].lower()++ finally:+ unregister_before_tool_call_hook(blocking_before_hook)+ unregister_after_tool_call_hook(after_hook)