chore(llmobs): dac strip io from anthropic #13767
Open
+104
−508
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
|
jsimpher
changed the title
Bootstrap import analysisComparison of import times between this PR and base. SummaryThe average import time from this PR is: 277 ± 2 ms. The average import time from base is: 278 ± 2 ms. The import time difference between this PR and base is: -1.53 ± 0.1 ms. Import time breakdownThe following import paths have shrunk:
|
BenchmarksBenchmark execution time: 2025-06-27 17:35:48 Comparing candidate commit a6f1f47 in PR branch Found 0 performance improvements and 1 performance regressions! Performance is the same for 568 metrics, 3 unstable metrics. scenario:iastaspects-lstrip_aspect
|
ncybul
reviewed
Jun 27, 2025
| @@ -155,7 +154,7 @@ def _process_finished_stream(integration, span, args, kwargs, streamed_chunks): | |||
| try: | |||
| resp_message = _construct_message(streamed_chunks) | |||
| if integration.is_pc_sampled_span(span): | |||
| _tag_streamed_chat_completion_response(integration, span, resp_message) | |||
| _tag_streamed_chat_completion_usage(integration, span, resp_message) | |||
There was a problem hiding this comment.
Should this depend on integration.is_pc_sampled_span?
| @@ -10,30 +10,19 @@ | |||
| "error": 0, | |||
| "meta": { | |||
| "_dd.p.dm": "-0", | |||
| "_dd.p.tid": "665f5f5200000000", | |||
| "_dd.p.tid": "685c01fa00000000", | |||
| "anthropic.request.api_key": "sk-...key>", | |||
There was a problem hiding this comment.
Do we still need API key on the APM span?
Comment on lines
+197
to
+201
| metrics[OUTPUT_TOKENS_METRIC_KEY] = output_tokens | ||
| total_tokens = total_tokens + output_tokens if total_tokens else output_tokens | ||
| if total_tokens is not None: | ||
| metrics[TOTAL_TOKENS_METRIC_KEY] = total_tokens | ||
| span._set_ctx_item(METRICS, metrics) |
There was a problem hiding this comment.
I think we probably should be consistent with the old way of calculating the total tokens (e.g. we only set total tokens if both input and output tokens are set). I think in your new implementation, we could end up with total_tokens being just input_tokens or output_tokens.
emmettbutler
approved these changes
Jun 27, 2025
emmettbutler
approved these changes
Jun 27, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Remove potentially sensitive i/o data from apm spans. This way, prompt and completion data will only appear on the llm obs spans, which are/will be subject to data access controls.
Mostly, this just removes io tag sets. A few things (mostly metrics) have llmobs tags dependent on span tags, so there is a bit more refactoring there.
Let me know if I removed anything that should really stay, or if I missed something that should be restricted.
Checklist
Reviewer Checklist