Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
test: adding missing test to ensure multimodal content structures
lucasgomide3deeba4cab96
diff --git a/tests/cassettes/test_multimodal_agent_describing_image_successfully.yaml b/tests/cassettes/test_multimodal_agent_describing_image_successfully.yamlnew file mode 100644index 000000000..c9371c243--- /dev/null+++ b/tests/cassettes/test_multimodal_agent_describing_image_successfully.yaml@@ -0,0 +1,378 @@+interactions:+- request:+ body: !!binary |+ CpIKCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS6QkKEgoQY3Jld2FpLnRl+ bGVtZXRyeRLBBwoQ08SlQ6w2FsCauTgZCqberRIITfOsgNi1qJkqDENyZXcgQ3JlYXRlZDABOdjG+ 6D/PcDAYQahPEkDPcDAYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl+ cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDkwNzMxMTU4MzVlMWNhZjJhNmUxNTIyZDA1+ YTBiNTFkSjEKB2NyZXdfaWQSJgokMzdjOGM4NzgtN2NmZC00YjEyLWE4YzctYzIyZDZlOTIxODBk+ ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3+ X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrgAgoLY3Jl+ d19hZ2VudHMS0AIKzQJbeyJrZXkiOiAiNzYyM2ZjNGY3ZDk0Y2YzZmRiZmNjMjlmYjBiMDIyYmIi+ LCAiaWQiOiAiYmVjMjljMTAtOTljYi00MzQwLWIwYTItMWU1NTVkNGRmZGM0IiwgInJvbGUiOiAi+ VmlzdWFsIFF1YWxpdHkgSW5zcGVjdG9yIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjog+ MjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAi+ b3BlbmFpL2dwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2Rl+ X2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6+ IFtdfV1KjQIKCmNyZXdfdGFza3MS/gEK+wFbeyJrZXkiOiAiMDExM2E5ZTg0N2M2NjI2ZDY0ZDZk+ Yzk4M2IwNDA5MTgiLCAiaWQiOiAiZWQzYmY1YWUtZTBjMS00MjIxLWFhYTgtMThlNjVkYTMyZjc1+ IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdl+ bnRfcm9sZSI6ICJWaXN1YWwgUXVhbGl0eSBJbnNwZWN0b3IiLCAiYWdlbnRfa2V5IjogIjc2MjNm+ YzRmN2Q5NGNmM2ZkYmZjYzI5ZmIwYjAyMmJiIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQAB+ AAASjgIKECo77ESam8oLrZMmgLLaoksSCLE6x14/Kb1vKgxUYXNrIENyZWF0ZWQwATlI/chAz3Aw+ GEEAgMpAz3AwGEouCghjcmV3X2tleRIiCiA5MDczMTE1ODM1ZTFjYWYyYTZlMTUyMmQwNWEwYjUx+ ZEoxCgdjcmV3X2lkEiYKJDM3YzhjODc4LTdjZmQtNGIxMi1hOGM3LWMyMmQ2ZTkyMTgwZEouCgh0+ YXNrX2tleRIiCiAwMTEzYTllODQ3YzY2MjZkNjRkNmRjOTgzYjA0MDkxOEoxCgd0YXNrX2lkEiYK+ JGVkM2JmNWFlLWUwYzEtNDIyMS1hYWE4LTE4ZTY1ZGEzMmY3NXoCGAGFAQABAAA=+ headers:+ Accept:+ - '*/*'+ Accept-Encoding:+ - gzip, deflate, zstd+ Connection:+ - keep-alive+ Content-Length:+ - '1301'+ Content-Type:+ - application/x-protobuf+ User-Agent:+ - OTel-OTLP-Exporter-Python/1.31.1+ method: POST+ uri: https://telemetry.crewai.com:4319/v1/traces+ response:+ body:+ string: "\n\0"+ headers:+ Content-Length:+ - '2'+ Content-Type:+ - application/x-protobuf+ Date:+ - Wed, 26 Mar 2025 19:24:52 GMT+ status:+ code: 200+ message: OK+- request:+ body: '{"messages": [{"role": "system", "content": "You are Visual Quality Inspector.+ Senior quality control expert with expertise in visual inspection\nYour personal+ goal is: Perform detailed quality analysis of product images\nYou ONLY have+ access to the following tools, and should NEVER make up tools that are not listed+ here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':+ ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':+ ''Optional context or question about the image'', ''type'': ''Union[str, NoneType]''}}\nTool+ Description: See image to understand its content, you can optionally ask a question+ about the image\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 [Add image to content], 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": "\nCurrent Task: \n Analyze+ the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244+ with focus on:\n 1. Quality of materials\n 2. Manufacturing defects\n 3.+ Compliance with standards\n Provide a detailed report highlighting any+ issues found.\n \n\nThis is the expected criteria for your final answer:+ A detailed report highlighting any issues found\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nBegin! This is VERY+ important to you, use the tools available and give your best Final Answer, your+ job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],+ "temperature": 0.7}'+ headers:+ accept:+ - application/json+ accept-encoding:+ - gzip, deflate, zstd+ connection:+ - keep-alive+ content-length:+ - '2033'+ content-type:+ - application/json+ host:+ - api.openai.com+ user-agent:+ - OpenAI/Python 1.68.2+ x-stainless-arch:+ - x64+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - MacOS+ x-stainless-package-version:+ - 1.68.2+ x-stainless-raw-response:+ - 'true'+ x-stainless-read-timeout:+ - '600.0'+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.12.9+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ content: "{\n \"id\": \"chatcmpl-BFQepLwSYYzdKLylSFsgcJeg6GTqS\",\n \"object\":+ \"chat.completion\",\n \"created\": 1743017091,\n \"model\": \"gpt-4o-2024-08-06\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"Thought: I need to examine the product+ image to assess the quality of materials, look for any manufacturing defects,+ and check compliance with standards.\\n\\nAction: Add image to content\\nAction+ Input: {\\\"image_url\\\": \\\"https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244\\\",+ \\\"action\\\": \\\"Analyze the quality of materials, manufacturing defects,+ and compliance with standards.\\\"}\",\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 413,\n \"completion_tokens\":+ 101,\n \"total_tokens\": 514,\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_7e8d90e604\"\n}\n"+ headers:+ CF-RAY:+ - 926907d79dcff1e7-GRU+ Connection:+ - keep-alive+ Content-Encoding:+ - gzip+ Content-Type:+ - application/json+ Date:+ - Wed, 26 Mar 2025 19:24:53 GMT+ Server:+ - cloudflare+ Set-Cookie:+ - __cf_bm=WK433.4kW8cr9rwvOlk4EZ2SfRYK9lAPwXCBYEvLcmU-1743017093-1.0.1.1-kVZyUew5rUbMk.2koGJF_rmX.fTseqN241n2M40n8KvBGoKgy6KM6xBmvFbIVWxUs2Y5ZAz8mWy9CrGjaNKSfCzxmv4.pq78z_DGHr37PgI;+ path=/; expires=Wed, 26-Mar-25 19:54:53 GMT; domain=.api.openai.com; HttpOnly;+ Secure; SameSite=None+ - _cfuvid=T77PMcuNYeyzK0tQyDOe7EScjVBVzW_7DpD3YQBqmUc-1743017093675-0.0.1.1-604800000;+ path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - nosniff+ access-control-expose-headers:+ - X-Request-ID+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - crewai-iuxna1+ openai-processing-ms:+ - '1729'+ openai-version:+ - '2020-10-01'+ strict-transport-security:+ - max-age=31536000; includeSubDomains; preload+ x-ratelimit-limit-requests:+ - '50000'+ x-ratelimit-limit-tokens:+ - '150000000'+ x-ratelimit-remaining-requests:+ - '49999'+ x-ratelimit-remaining-tokens:+ - '149999534'+ x-ratelimit-reset-requests:+ - 1ms+ x-ratelimit-reset-tokens:+ - 0s+ x-request-id:+ - req_2399c3355adf16734907c73611a7d330+ http_version: HTTP/1.1+ status_code: 200+- request:+ body: !!binary |+ CtgBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSrwEKEgoQY3Jld2FpLnRl+ bGVtZXRyeRKYAQoQp2ACB2xRGve4HGtU2RdWCBIIlQcsbhK22ykqClRvb2wgVXNhZ2UwATlACEXG+ z3AwGEHAjGPGz3AwGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSiMKCXRvb2xfbmFtZRIW+ ChRBZGQgaW1hZ2UgdG8gY29udGVudEoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA+ headers:+ Accept:+ - '*/*'+ Accept-Encoding:+ - gzip, deflate, zstd+ Connection:+ - keep-alive+ Content-Length:+ - '219'+ Content-Type:+ - application/x-protobuf+ User-Agent:+ - OTel-OTLP-Exporter-Python/1.31.1+ method: POST+ uri: https://telemetry.crewai.com:4319/v1/traces+ response:+ body:+ string: "\n\0"+ headers:+ Content-Length:+ - '2'+ Content-Type:+ - application/x-protobuf+ Date:+ - Wed, 26 Mar 2025 19:24:57 GMT+ status:+ code: 200+ message: OK+- request:+ body: '{"messages": [{"role": "system", "content": "You are Visual Quality Inspector.+ Senior quality control expert with expertise in visual inspection\nYour personal+ goal is: Perform detailed quality analysis of product images\nYou ONLY have+ access to the following tools, and should NEVER make up tools that are not listed+ here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':+ ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':+ ''Optional context or question about the image'', ''type'': ''Union[str, NoneType]''}}\nTool+ Description: See image to understand its content, you can optionally ask a question+ about the image\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 [Add image to content], 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": "\nCurrent Task: \n Analyze+ the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244+ with focus on:\n 1. Quality of materials\n 2. Manufacturing defects\n 3.+ Compliance with standards\n Provide a detailed report highlighting any+ issues found.\n \n\nThis is the expected criteria for your final answer:+ A detailed report highlighting any issues found\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nBegin! This is VERY+ important to you, use the tools available and give your best Final Answer, your+ job depends on it!\n\nThought:"}, {"role": "user", "content": [{"type": "text",+ "text": "Analyze the quality of materials, manufacturing defects, and compliance+ with standards."}, {"type": "image_url", "image_url": {"url": "https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244"}}]},+ {"role": "assistant", "content": "Thought: I need to examine the product image+ to assess the quality of materials, look for any manufacturing defects, and+ check compliance with standards.\n\nAction: Add image to content\nAction Input:+ {\"image_url\": \"https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244\",+ \"action\": \"Analyze the quality of materials, manufacturing defects, and compliance+ with standards.\"}"}], "model": "gpt-4o", "stop": ["\nObservation:"], "temperature":+ 0.7}'+ headers:+ accept:+ - application/json+ accept-encoding:+ - gzip, deflate, zstd+ connection:+ - keep-alive+ content-length:+ - '2797'+ content-type:+ - application/json+ cookie:+ - __cf_bm=WK433.4kW8cr9rwvOlk4EZ2SfRYK9lAPwXCBYEvLcmU-1743017093-1.0.1.1-kVZyUew5rUbMk.2koGJF_rmX.fTseqN241n2M40n8KvBGoKgy6KM6xBmvFbIVWxUs2Y5ZAz8mWy9CrGjaNKSfCzxmv4.pq78z_DGHr37PgI;+ _cfuvid=T77PMcuNYeyzK0tQyDOe7EScjVBVzW_7DpD3YQBqmUc-1743017093675-0.0.1.1-604800000+ host:+ - api.openai.com+ user-agent:+ - OpenAI/Python 1.68.2+ x-stainless-arch:+ - x64+ x-stainless-async:+ - 'false'+ x-stainless-lang:+ - python+ x-stainless-os:+ - MacOS+ x-stainless-package-version:+ - 1.68.2+ x-stainless-raw-response:+ - 'true'+ x-stainless-read-timeout:+ - '600.0'+ x-stainless-retry-count:+ - '0'+ x-stainless-runtime:+ - CPython+ x-stainless-runtime-version:+ - 3.12.9+ method: POST+ uri: https://api.openai.com/v1/chat/completions+ response:+ content: "{\n \"id\": \"chatcmpl-BFQetNNvmPgPxhzaKiHYsPqm8aN0i\",\n \"object\":+ \"chat.completion\",\n \"created\": 1743017095,\n \"model\": \"gpt-4o-2024-08-06\",\n+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":+ \"assistant\",\n \"content\": \"Observation: The image displays a black+ leather boot with a pointed toe and a low heel. \\n\\nQuality of Materials:\\n1.+ The leather appears to be of good quality, displaying a consistent texture and+ finish, which suggests durability.\\n2. The material has a slight sheen, indicating+ a possible finishing treatment that enhances the appearance and may offer some+ protection.\\n\\nManufacturing Defects:\\n1. There are no visible stitching+ errors; the seams appear straight and clean.\\n2. No apparent glue marks or+ uneven edges, which indicates good craftsmanship.\\n3. There is a slight distressed+ effect, but it appears intentional as part of the design rather than a defect.\\n\\nCompliance+ with Standards:\\n1. The shoe design seems to comply with typical fashion standards,+ showing a balance of aesthetics and functionality.\\n2. The heel height and+ shape appear to provide stability, aligning with safety standards for footwear.\\n\\nFinal+ Answer: The analysis of the product image reveals that the black leather boot+ is made of high-quality materials with no visible manufacturing defects. The+ craftsmanship is precise, with clean seams and a well-executed design. The distressed+ effect appears intentional and part of the aesthetic. The boot seems to comply+ with fashion and safety standards, offering both style and functionality. No+ significant issues were found.\",\n \"refusal\": null,\n \"annotations\":+ []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1300,\n \"completion_tokens\":+ 250,\n \"total_tokens\": 1550,\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_3a5b33c01a\"\n}\n"+ headers:+ CF-RAY:+ - 926907e45f33f1e7-GRU+ Connection:+ - keep-alive+ Content-Encoding:+ - gzip+ Content-Type:+ - application/json+ Date:+ - Wed, 26 Mar 2025 19:25:01 GMT+ Server:+ - cloudflare+ Transfer-Encoding:+ - chunked+ X-Content-Type-Options:+ - nosniff+ access-control-expose-headers:+ - X-Request-ID+ alt-svc:+ - h3=":443"; ma=86400+ cf-cache-status:+ - DYNAMIC+ openai-organization:+ - crewai-iuxna1+ openai-processing-ms:+ - '7242'+ openai-version:+ - '2020-10-01'+ strict-transport-security:+ - max-age=31536000; includeSubDomains; preload+ x-ratelimit-limit-input-images:+ - '250000'+ x-ratelimit-limit-requests:+ - '50000'+ x-ratelimit-limit-tokens:+ - '150000000'+ x-ratelimit-remaining-input-images:+ - '249999'+ x-ratelimit-remaining-requests:+ - '49999'+ x-ratelimit-remaining-tokens:+ - '149998641'+ x-ratelimit-reset-input-images:+ - 0s+ x-ratelimit-reset-requests:+ - 1ms+ x-ratelimit-reset-tokens:+ - 0s+ x-request-id:+ - req_c5dd144c8ac1bb3bd96ffbba40707b2d+ http_version: HTTP/1.1+ status_code: 200+version: 1diff --git a/tests/crew_test.py b/tests/crew_test.pyindex 39a3e9a08..e5f464131 100644--- a/tests/crew_test.py+++ b/tests/crew_test.py@@ -3731,6 +3731,44 @@ def test_multimodal_agent_image_tool_handling():assert result["content"][1]["type"] == "image_url"[email protected](filter_headers=["authorization"])+def test_multimodal_agent_describing_image_successfully():+ """+ Test that a multimodal agent can process images without validation errors.+ This test reproduces the scenario from issue #2475.+ """+ llm = LLM(model="openai/gpt-4o", temperature=0.7) # model with vision capabilities++ expert_analyst = Agent(+ role="Visual Quality Inspector",+ goal="Perform detailed quality analysis of product images",+ backstory="Senior quality control expert with expertise in visual inspection",+ llm=llm,+ verbose=True,+ allow_delegation=False,+ multimodal=True,+ )++ inspection_task = Task(+ description="""+ Analyze the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244 with focus on:+ 1. Quality of materials+ 2. Manufacturing defects+ 3. Compliance with standards+ Provide a detailed report highlighting any issues found.+ """,+ expected_output="A detailed report highlighting any issues found",+ agent=expert_analyst,+ )++ crew = Crew(agents=[expert_analyst], tasks=[inspection_task])+ result = crew.kickoff()++ task_output = result.tasks_output[0]+ assert isinstance(task_output, TaskOutput)+ assert task_output.raw == result.raw++@pytest.mark.vcr(filter_headers=["authorization"])def test_multimodal_agent_live_image_analysis():"""