andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-03 16:22:49 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

feat: native multimodal file handling; openai responses api

Browse Source 
- add input_files parameter to Crew.kickoff(), Flow.kickoff(), Task, and Agent.kickoff()
- add provider-specific file uploaders for OpenAI, Anthropic, Gemini, and Bedrock
- add file type detection, constraint validation, and automatic format conversion
- add URL file source support for multimodal content
- add streaming uploads for large files
- add prompt caching support for Anthropic
- add OpenAI Responses API support
This commit is contained in:
Greyson LaLonde
2026-01-23 15:13:25 -05:00
committed by GitHub
parent bd4d039f63
commit c4c9208229
303 changed files with 46268 additions and 8097 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
lib/crewai/tests/cassettes/test_before_kickoff_callback.yaml
View File

@@ -645,18 +645,21 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-ApfRLkycSd0vwuTw50dfB5bgIoWiC\",\n \"object\":
\"chat.completion\",\n \"created\": 1736877387,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: The final answer must be the great and the most complete as possible,
it must be outcome described.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
158,\n \"completion_tokens\": 31,\n \"total_tokens\": 189,\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_50cad350e4\"\n}\n"
body:
string: "{\n \"id\": \"chatcmpl-ApfRLkycSd0vwuTw50dfB5bgIoWiC\",\n \"object\"\
: \"chat.completion\",\n \"created\": 1736877387,\n \"model\": \"gpt-4o-2024-08-06\"\
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \
\ \"role\": \"assistant\",\n \"content\": \"I now can give a great\
\ answer \\nFinal Answer: The final answer must be the great and the most\
\ complete as possible, it must be outcome described.\",\n \"refusal\"\
: null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\
\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 158,\n \"completion_tokens\"\
: 31,\n \"total_tokens\": 189,\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_50cad350e4\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
@@ -706,8 +709,9 @@ interactions:
- 0s
x-request-id:
- req_4ceac9bc8ae57f631959b91d2ab63c4d
http_version: HTTP/1.1
status_code: 200
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test agent
backstory\nYour personal goal is: Test agent goal\nTo give my best complete
@@ -756,18 +760,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BExKOliqPgvHyozZaBu5oN50CHtsa\",\n \"object\":
\"chat.completion\",\n \"created\": 1742904348,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Test expected output\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 158,\n \"completion_tokens\":
15,\n \"total_tokens\": 173,\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_90d33c15d4\"\n}\n"
body:
string: "{\n \"id\": \"chatcmpl-BExKOliqPgvHyozZaBu5oN50CHtsa\",\n \"object\"\
: \"chat.completion\",\n \"created\": 1742904348,\n \"model\": \"gpt-4o-2024-08-06\"\
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \
\ \"role\": \"assistant\",\n \"content\": \"I now can give a great\
\ answer \\nFinal Answer: Test expected output\",\n \"refusal\": null,\n\
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"\
finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\"\
: 158,\n \"completion_tokens\": 15,\n \"total_tokens\": 173,\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_90d33c15d4\"\n}\n"
headers:
CF-RAY:
- 925e4749af02f227-GRU
@@ -817,6 +823,7 @@ interactions:
- 0s
x-request-id:
- req_fd6b93e3b1a30868482c72306e7f63c2
http_version: HTTP/1.1
status_code: 200
status:
code: 200
message: OK
version: 1