fix(ai): introduce message truncation for openai

[shellmayr]

• Splitting out introduction of the message truncation from fix(ai): truncate long message histories #4885
• Introduce for openai

Contributes to TET-1208

[linear]

TET-1208 Python SDK: truncate gen_ai messages

[codecov]

❌ 1 Tests Failed:

Tests completed	Failed	Passed	Skipped
22122	1	22121	1566

View the top 1 failed test(s) by shortest run time

::tests.integrations.openai.test_openai

Stack Traces | 0s run time

ImportError while importing test module '.../integrations/openai/test_openai.py'.
Hint: make sure your test modules/packages have valid Python names.
Traceback:
.tox/py3.11-openai-base-v1.0.1/lib/python3.11.../site-packages/_pytest/python.py:498: in importtestmodule
    mod = import_path(
.tox/py3.11-openai-base-v1.0.1/lib/python3.11.../site-packages/_pytest/pathlib.py:587: in import_path
    importlib.import_module(module_name)
.../hostedtoolcache/Python/3.11.13.../x64/lib/python3.11/importlib/__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
<frozen importlib._bootstrap>:1204: in _gcd_import
    ???
<frozen importlib._bootstrap>:1176: in _find_and_load
    ???
<frozen importlib._bootstrap>:1147: in _find_and_load_unlocked
    ???
<frozen importlib._bootstrap>:690: in _load_unlocked
    ???
.tox/py3.11-openai-base-v1.0.1/lib/python3.11.../_pytest/assertion/rewrite.py:186: in exec_module
    exec(co, module.__dict__)
.../integrations/openai/test_openai.py:15: in <module>
    from openai import AsyncOpenAI, Omit, OpenAI, AsyncStream, Stream, OpenAIError
E   ImportError: cannot import name 'Omit' from 'openai' (.../sentry-python/sentry-python/.tox/py3.11-openai-base-v1.0.1/lib/python3.11.../site-packages/openai/__init__.py)

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}

[seer-by-sentry]

Potential bug: The spans variable is initialized as an empty list, so the subsequent loop that should annotate spans with truncation information never runs.

• Description: In the _prepare_event method, the spans variable is initialized as an empty list. The code then immediately attempts to iterate over this list. Because spans is always empty at this point, the loop body that is intended to annotate spans with AI message truncation information never executes. This causes the new message truncation annotation feature to fail silently, as the expected AnnotatedValue metadata will not be added to the event's spans.

• Suggested fix: Initialize the spans variable by retrieving the spans from the event object. Change the line spans = [] to spans = event.get("spans", []) to ensure the annotation logic can execute on the event's spans.
  _{severity: 0.65, confidence: 0.99}

_{Did we get this right? 👍 / 👎 to inform future reviews.}