Skip to content

feat: add tests for cohere#63

Open
shellmayr wants to merge 6 commits intomainfrom
shellmayr/feat/add-tests-for-cohere
Open

feat: add tests for cohere#63
shellmayr wants to merge 6 commits intomainfrom
shellmayr/feat/add-tests-for-cohere

Conversation

@shellmayr
Copy link
Member

@shellmayr shellmayr commented Feb 27, 2026

  • Add tests for cohere
  • We need two templates, because there are two versions of the API that both need to be supported

Closes TET-2025

@github-actions
Copy link

github-actions bot commented Feb 27, 2026

🟡 AI SDK Integration Test Results

Status: 1 test fixed, 236 still failing

Summary

Metric main PR Change
Total Tests 448 464 +16
Passed 227 228 +1 ✅
Failed 221 236 +15 ⚠️

✅ Fixed

These tests were failing on main but are now passing:

  • cloudflare/google-genai :: Vision LLM Test (blocking)

🆕 New Tests

Failing (16):

python/cohere :: Basic LLM Test (sync, streaming)

Error: 3 check(s) failed:

3 check(s) failed:
Should have exactly 1 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one chat or agent span
python/cohere :: Basic LLM Test (sync, blocking)

Error: 3 check(s) failed:

3 check(s) failed:
Should have exactly 1 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one chat or agent span
python/cohere :: Multi-Turn LLM Test (sync, streaming)

Error: 3 check(s) failed:

3 check(s) failed:
Should have exactly 3 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one chat or agent span
python/cohere :: Multi-Turn LLM Test (sync, blocking)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 88, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 83, in main
    response = client.chat(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 159, in new_chat
    reraise(*exc_info)
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/utils.py", line 1785, in reraise
    raise value
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 153, in new_chat
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/base_client.py", line 1111, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='ccf222f8-4b53-4f95-8d19-288df85a1ab2' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 88, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 83, in main
    response = client.chat(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 159, in new_chat
    reraise(*exc_info)
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/utils.py", line 1785, in reraise
    raise value
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 153, in new_chat
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/base_client.py", line 1111, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='ccf222f8-4b53-4f95-8d19-288df85a1ab2' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

python/cohere :: Basic Error LLM Test (sync, streaming)

Error: 1 check(s) failed:

1 check(s) failed:
Should have at least 1 AI span(s) but found 0
python/cohere :: Basic Error LLM Test (sync, blocking)

Error: 1 check(s) failed:

1 check(s) failed:
Should have at least 1 AI span(s) but found 0
python/cohere :: Conversation ID LLM Test (sync, streaming)

Error: 4 check(s) failed:

4 check(s) failed:
Should have exactly 4 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one AI span
Should have at least one chat or agent span
python/cohere :: Conversation ID LLM Test (sync, blocking)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 105, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 100, in main
    response = client.chat(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 159, in new_chat
    reraise(*exc_info)
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/utils.py", line 1785, in reraise
    raise value
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 153, in new_chat
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/base_client.py", line 1111, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='fc42724d-46f8-460a-b83b-338ea7cc2575' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 105, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 100, in main
    response = client.chat(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 159, in new_chat
    reraise(*exc_info)
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/utils.py", line 1785, in reraise
    raise value
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/sentry_sdk/integrations/cohere.py", line 153, in new_chat
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/base_client.py", line 1111, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='fc42724d-46f8-460a-b83b-338ea7cc2575' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

python/cohere-v2 :: Basic LLM Test (sync, streaming)

Error: 3 check(s) failed:

3 check(s) failed:
Should have exactly 1 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one chat or agent span
python/cohere-v2 :: Basic LLM Test (sync, blocking)

Error: 3 check(s) failed:

3 check(s) failed:
Should have exactly 1 AI span(s) but found 0
Should have at least one chat/completion span
Should have at least one chat or agent span
python/cohere-v2 :: Multi-Turn LLM Test (sync, streaming)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py", line 82, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py", line 74, in main
    for event in stream:
                 ^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 333, in chat_stream
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='bebb7136-2b27-4ed7-b5d8-070a1d6d097d' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py", line 82, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-streaming.py", line 74, in main
    for event in stream:
                 ^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 333, in chat_stream
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='bebb7136-2b27-4ed7-b5d8-070a1d6d097d' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

python/cohere-v2 :: Multi-Turn LLM Test (sync, blocking)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 70, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 61, in main
    response = client.chat(
               ^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 636, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='0799700e-e1a6-4992-a3dd-5ee59153c085' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 70, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-multi-turn-llm-test-sync-blocking.py", line 61, in main
    response = client.chat(
               ^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 636, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='0799700e-e1a6-4992-a3dd-5ee59153c085' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

python/cohere-v2 :: Basic Error LLM Test (sync, streaming)

Error: 1 check(s) failed:

1 check(s) failed:
Should have at least 1 AI span(s) but found 0
python/cohere-v2 :: Basic Error LLM Test (sync, blocking)

Error: 1 check(s) failed:

1 check(s) failed:
Should have at least 1 AI span(s) but found 0
python/cohere-v2 :: Conversation ID LLM Test (sync, streaming)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py", line 97, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py", line 51, in main
    for event in stream:
                 ^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 333, in chat_stream
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='663fe78e-3c86-4d42-853e-6a151ab29052' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py", line 97, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-streaming.py", line 51, in main
    for event in stream:
                 ^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 333, in chat_stream
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='663fe78e-3c86-4d42-853e-6a151ab29052' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

python/cohere-v2 :: Conversation ID LLM Test (sync, blocking)

Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py

Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py
Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 81, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 42, in main
    response = client.chat(
               ^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 636, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='7c0e4b22-17dd-48dd-8443-955fdd933271' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Traceback (most recent call last):
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 81, in <module>
    main()
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/test-conversation-id-llm-test-sync-blocking.py", line 42, in main
    response = client.chat(
               ^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 103, in _wrapped
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/client.py", line 35, in _wrapped
    return method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/cohere-v2-5.13.0-sentry-latest/.venv/lib/python3.12/site-packages/cohere/v2/client.py", line 636, in chat
    raise TooManyRequestsError(
cohere.errors.too_many_requests_error.TooManyRequestsError: status_code: 429, body: data=None id='7c0e4b22-17dd-48dd-8443-955fdd933271' message="You are using a Trial key, which is limited to 20 API calls / minute. You can continue to use the Trial key for free or upgrade to a Production key with higher rate limits at 'https://dashboard.cohere.com/api-keys'. Contact us on 'https://discord.gg/XW44jPfYJu' or email us at support@cohere.com with any questions"

Test Matrix

Agent Tests

SDK Basic Agent Test Conversation ID Agent Test Long Input Agent Test Tool Call Agent Test Tool Error Agent Test Vision Agent Test
cloudflare/langgraph
cloudflare/vercel
nextjs/mastra
nextjs/vercel blkstr blkstr blkstr blkstr blkstr blkstr
node/manual
node/mastra
node/vercel
php/laravel blkstr blkstr blkstr blkstr blkstr blkstr
python/langgraph as as as as as as
python/manual as as as as as as
python/openai-agents
python/pydantic-ai

Embedding Tests

SDK Basic Embeddings Test
browser/google-genai
browser/langchain
browser/openai
cloudflare/google-genai
cloudflare/langchain
cloudflare/openai
cloudflare/vercel
nextjs/google-genai
nextjs/langchain
nextjs/openai
nextjs/vercel
node/google-genai
node/langchain
node/openai
node/vercel
php/laravel
python/google-genai a, blks, blk
python/langchain a, blks, blk
python/litellm a, blks, blk
python/manual a, blks, blk
python/openai a, blks, blk

LLM Tests

SDK Basic Error LLM Test Basic LLM Test Conversation ID LLM Test Long Input LLM Test Multi-Turn LLM Test Vision LLM Test
browser/anthropic blkstr blkstr blkstr blkstr blkstr blkstr
browser/google-genai blkstr blkstr blkstr blkstr blkstr blkstr
browser/langchain blkstr blkstr blkstr blkstr blkstr blkstr
browser/openai blkstr blkstr blkstr blkstr blkstr blkstr
cloudflare/anthropic blkstr blkstr blkstr blkstr blkstr blkstr
cloudflare/google-genai blkstr blkstr blkstr blkstr blkstr ✅🔧blkstr
cloudflare/langchain blkstr blkstr blkstr blkstr blkstr blkstr
cloudflare/openai blkstr blkstr blkstr blkstr blkstr blkstr
nextjs/anthropic blkstr blkstr blkstr blkstr blkstr blkstr
nextjs/google-genai blkstr blkstr blkstr blkstr blkstr blkstr
nextjs/langchain blkstr blkstr blkstr blkstr blkstr blkstr
nextjs/openai blkstr blkstr blkstr blkstr blkstr blkstr
node/anthropic blkstr blkstr blkstr blkstr blkstr blkstr
node/google-genai blkstr blkstr blkstr blkstr blkstr blkstr
node/langchain blkstr blkstr blkstr blkstr blkstr blkstr
node/manual
node/openai blkstr blkstr blkstr blkstr blkstr blkstr
python/anthropic a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str
python/cohere ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str
python/cohere-v2 ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str ❌🆕s, blk ❌🆕s, str
python/google-genai a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str
python/langchain a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str
python/litellm a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str
python/manual a, blks, blk a, blks, blk a, blks, blk a, blks, blk a, blks, blk
python/openai a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str a, blka, strs, blks, str

Legend: ✅ Pass | ❌ Fail | ✅🔧 Fixed | ❌📉 Regressed | ✅🆕 New (pass) | ❌🆕 New (fail) | 🗑️ Removed | str=streaming blk=blocking a=async s=sync


Generated by AI SDK Integration Tests

@shellmayr shellmayr requested a review from constantinius March 6, 2026 07:11
@linear-code
Copy link

linear-code bot commented Mar 6, 2026

@shellmayr shellmayr marked this pull request as ready for review March 6, 2026 07:12
Copy link

@cursor cursor bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes and found 1 potential issue.

Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants