fix(llmobs): don't drop IO annotations equal to zero (#11044)

Fixes an issue where we are dropping I/O annotations that were equal to
zero for workflow, task, agent and tool spans.

- [x] PR author has checked that all the criteria below are met
- The PR description includes an overview of the change
- The PR description articulates the motivation for the change
- The change includes tests OR the PR description describes a testing
strategy
- The PR description notes risks associated with the change, if any
- Newly-added code is easy to change
- The change follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
- The change includes or references documentation updates if necessary
- Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

- [x] Reviewer has checked that all the criteria below are met
- Title is accurate
- All changes are related to the pull request's stated goal
- Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- Testing strategy adequately addresses listed risks
- Newly-added code is easy to change
- Release note makes sense to a user of the library
- If necessary, author has acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment
- Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

---------

Co-authored-by: lievan <[email protected]>

ddtrace/llmobs/_llmobs.py

@@ -491,7 +491,7 @@ def annotate(
         if parameters is not None:
             log.warning("Setting parameters is deprecated, please set parameters and other metadata as tags instead.")
             cls._tag_params(span, parameters)
-        if input_data or output_data:
+        if input_data is not None or output_data is not None:
             if span_kind == "llm":
                 cls._tag_llm_io(span, input_messages=input_data, output_messages=output_data)
             elif span_kind == "embedding":

releasenotes/notes/fix-numeric-annotations-7cf06b5ceb615282.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    LLM Observability: This fix resolves an issue where input and output values equal to zero were not being annotated
+    on workflow, task, agent and tool spans when using `LLMObs.annotate`.

tests/llmobs/test_llmobs_service.py

@@ -388,6 +388,17 @@ def test_annotate_input_string(LLMObs):
         assert retrieval_span.get_tag(INPUT_VALUE) == "test_input"
 
 
+def test_annotate_numeric_io(LLMObs):
+    with LLMObs.task() as task_span:
+        LLMObs.annotate(span=task_span, input_data=0, output_data=0)
+        assert task_span.get_tag(INPUT_VALUE) == "0"
+        assert task_span.get_tag(OUTPUT_VALUE) == "0"
+    with LLMObs.task() as task_span:
+        LLMObs.annotate(span=task_span, input_data=1.23, output_data=1.23)
+        assert task_span.get_tag(INPUT_VALUE) == "1.23"
+        assert task_span.get_tag(OUTPUT_VALUE) == "1.23"
+
+
 def test_annotate_input_serializable_value(LLMObs):
     with LLMObs.task() as task_span:
         LLMObs.annotate(span=task_span, input_data=["test_input"])