feat(vllm): add vLLM integration #14732

PROFeNoM · 2025-09-30T12:08:48Z

Description

MLOB-4847

This PR adds Datadog tracing integration for vLLM V1 engine exclusively. V0 is deprecated and being removed (vLLM Q3 2025 Roadmap), so we're building for the future.

Request Flow and Instrumentation Points

The integration traces at the engine level rather than wrapping high-level APIs. This gives us a single integration point for all operations (completion, chat, embedding, classification) with complete access to internal metadata.

1. Engine Initialization (once per engine)

User creates vllm.LLM() / AsyncLLM()
    ↓
LLMEngine.__init__() / AsyncLLM.__init__()
    → WRAPPED: traced_engine_init()
        • Forces log_stats=True (needed for tokens/latency metrics)
        • Captures model name from engine.model_config.model
        • Injects into output_processor._dd_model_name

2. Request Submission (per request)

User calls llm.generate() / llm.chat() / llm.embed()
    ↓
Processor.process_inputs(trace_headers=...)
    → WRAPPED: traced_processor_process_inputs()
        • Extracts active Datadog trace context
        • Injects headers into trace_headers dict
        • Propagates through engine automatically

3. Output Processing (when request finishes)

Engine completes → OutputProcessor.process_outputs()
    → WRAPPED: traced_output_processor_process_outputs()
        • BEFORE calling original:
            - Capture req_state data (prompt, params, stats, trace_headers)
        • Call original (removes req_state from memory)
        • AFTER original returns:
            - Create span with parent context from trace_headers
            - Tag with LLMObs metadata (model, tokens, params)
            - Set latency metrics (queue, prefill, decode, TTFT)
            - Finish span

The key insight: OutputProcessor.process_outputs has everything in one place: request metadata, output data, and parent context. We wrap three specific points because each serves a distinct purpose: __init__ for setup, process_inputs for context injection, process_outputs for span creation.

Version Support

Requires vLLM >= 0.10.2 for V1 support. Version 0.10.2 includes vLLM PR #20372 which added trace_headers for context propagation.

No V0 support. It's deprecated and being removed. The integration includes a version check that gracefully skips instrumentation on older versions with a warning.

Metadata Captured

Request: prompt, input tokens, sampling params (temperature, top_p, max_tokens, etc.)
Response: output text, output tokens, finish reason, cached tokens
Latency metrics: TTFT, queue time, prefill, decode, inference (mirrors vLLM's OpenTelemetry do_tracing)
Model: name, provider, LoRA adapter (if used)
Embeddings: dimension, count

For chat requests where vLLM only stores token IDs, we decode back to text using the tokenizer to ensure input_messages are captured correctly.

Chat Template Parsing

For chat completions, vLLM applies Jinja2 templates to format messages. We parse the formatted prompt back into structured input_messages for LLMObs.

Supported formats: Llama 3/4, ChatML/Qwen, Phi, DeepSeek, Gemma, Granite, MiniMax, TeleFLM, Inkbot, Alpaca, Falcon. Chosen because they're visible as examples in vLLM repos. Fallback: raw prompt.

Parser uses quick marker detection before regex patterns, avoiding unnecessary regex execution. Prompts decoded with skip_special_tokens=False to preserve chat template markers (vLLM defaults strip them).

Not perfect, but simple enough that adding new templates isn't painful.

FastAPI Pickle Fix for Ray Serve Compatibility

Problem

vLLM's distributed inference (via Ray Serve) serializes FastAPI app components using pickle. When dd-trace-py instruments FastAPI with wrapt.FunctionWrapper, these wrapped objects become unpicklable because wrapt doesn't implement __reduce_ex__() by default.

Solution

We register custom pickle reducers for wrapt proxy types in fastapi/patch.py:

During pickle: _reduce_wrapt_proxy() unwraps the object
During unpickle: _identity() returns the unwrapped object
Result: Instrumentation is stripped across pickle boundaries

This is acceptable because distributed vLLM workers independently instrument their FastAPI instances when dd-trace-py is imported. The registration is guarded by _WRAPT_REDUCERS_REGISTERED flag (only runs once globally).

Why This Works

Ray Serve's @serve.ingress(app) decorator pickles the FastAPI app
cloudpickle encounters wrapt.FunctionWrapper objects (ddtrace wrappers)
wrapt raises NotImplementedError for __reduce_ex__()
copyreg intercepts via dispatch table and uses our reducer
Reducer returns unwrapped function → pickle succeeds
On Ray worker, ddtrace re-patches when imported → tracing works

Reproducer

Without the fix, this crashes with ddtrace-run:

#!/usr/bin/env python3
"""Minimal reproducer for Ray Serve + ddtrace serialization failure."""

from fastapi import FastAPI
from ray import serve


def main():
    app = FastAPI()

    @app.get("/v1/models")
    def list_models():
        return {"data": [{"id": "dummy"}]}

    print("Applying @serve.ingress(app), which triggers pickle internally…")

    @serve.ingress(app)
    class Ingress:
        pass

    print("Pickle succeeded!")
    return Ingress


if __name__ == "__main__":
    main()

Run with ddtrace-run python repro.py → crashes without fix, works with fix.

Testing

Tests run on GPU hardware using gpu:a10-amd64 runner tag in GitLab CI (GPU Runners docs). Cannot be run locally on Macs. Requires actual GPU hardware. During dev, I used a g6.8xlarge EC2 instance.

Coverage:

Unit tests validate LLMObs events for all operations: completion, chat, embedding, classification, scoring, rewards
Integration test validates RAG scenario with parent-child spans and context propagation across async engines

Tests converge on same instrumentation points (as shown in request flow), so current coverage should be solid for first release.

Infrastructure notes:

Runners take ~5-10 minutes to start on CI (slow iterations)
Module-scoped fixtures cache LLM instances to reduce test time
Kubernetes memory increased to 12 Gi to handle caching pressure
Tests run in ~1 min on EC2 instance

Risks

V1 maturity: V1 is production-ready but still evolving toward vLLM 1.0. Our instrumentation points (process_inputs, process_outputs) are core to V1's design and unlikely to change significantly.

No V0 support: Customers on V0 won't get tracing. However, V0 is deprecated and most production deployments have migrated (V0 doesn't support pooling models anymore).

Version requirement: Requiring 0.10.2+ may exclude some users, but trace header propagation is essential to a maintainable design.

High span burst in RAG scenarios: RAG apps indexing large document collections generate significant span volumes (e.g., 1000 docs = 1000 embedding spans). This is expected behavior but may impact trace readability and ingestion costs. Could add DD_VLLM_TRACE_EMBEDDINGS=false config later if needed, but let's monitor customer feedback first rather than over-engineer.

Additional Notes

Main Files

patch.py: Wraps vLLM engine methods
extractors.py: Extracts request/response data from vLLM structures
utils.py: Span creation, context injection, metrics utilities
llmobs/_integrations/vllm.py: LLMObs-specific tagging and event building

github-actions · 2025-09-30T12:09:25Z

CODEOWNERS have been resolved as:

.riot/requirements/2043c14.txt                                          @DataDog/apm-python
.riot/requirements/460aab7.txt                                          @DataDog/apm-python
.riot/requirements/494e77a.txt                                          @DataDog/apm-python
ddtrace/contrib/internal/vllm/__init__.py                               @DataDog/ml-observability
ddtrace/contrib/internal/vllm/_constants.py                             @DataDog/ml-observability
ddtrace/contrib/internal/vllm/extractors.py                             @DataDog/ml-observability
ddtrace/contrib/internal/vllm/patch.py                                  @DataDog/ml-observability
ddtrace/contrib/internal/vllm/utils.py                                  @DataDog/ml-observability
ddtrace/llmobs/_integrations/vllm.py                                    @DataDog/ml-observability
docker-compose.gpu.yml                                                  @DataDog/apm-core-python
releasenotes/notes/add-vllm-integration-b93a517daeb45f61.yaml           @DataDog/apm-python
tests/contrib/vllm/__init__.py                                          @DataDog/ml-observability
tests/contrib/vllm/_utils.py                                            @DataDog/ml-observability
tests/contrib/vllm/api_app.py                                           @DataDog/ml-observability
tests/contrib/vllm/conftest.py                                          @DataDog/ml-observability
tests/contrib/vllm/test_api_app.py                                      @DataDog/ml-observability
tests/contrib/vllm/test_extractors.py                                   @DataDog/ml-observability
tests/contrib/vllm/test_vllm_llmobs.py                                  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_api_app.test_rag_parent_child.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_basic.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_chat.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_classify.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_embed.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_reward.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.vllm.test_vllm_llmobs.test_llmobs_score.json  @DataDog/ml-observability
.github/CODEOWNERS                                                      @DataDog/python-guild @DataDog/apm-core-python
.gitlab/testrunner.yml                                                  @DataDog/python-guild @DataDog/apm-core-python
.gitlab/tests.yml                                                       @DataDog/python-guild @DataDog/apm-core-python
ddtrace/_monkey.py                                                      @DataDog/apm-core-python
ddtrace/contrib/integration_registry/registry.yaml                      @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/contrib/internal/fastapi/patch.py                               @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/internal/settings/_config.py                                    @DataDog/python-guild @DataDog/apm-sdk-capabilities-python
ddtrace/llmobs/_constants.py                                            @DataDog/ml-observability
ddtrace/llmobs/_integrations/base.py                                    @DataDog/ml-observability
docs/integrations.rst                                                   @DataDog/python-guild
docs/spelling_wordlist.txt                                              @DataDog/python-guild
riotfile.py                                                             @DataDog/apm-python
scripts/ddtest                                                          @DataDog/apm-core-python
scripts/gen_gitlab_config.py                                            @DataDog/apm-core-python
supported_versions_output.json                                          @DataDog/apm-core-python
supported_versions_table.csv                                            @DataDog/apm-core-python
tests/llmobs/suitespec.yml                                              @DataDog/ml-observability

github-actions · 2025-09-30T12:34:35Z

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 248 ± 3 ms.

The average import time from base is: 250 ± 2 ms.

The import time difference between this PR and base is: -2.2 ± 0.1 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.616 ms (1.05%)

ddtrace 1.351 ms (0.54%)

ddtrace._logger 0.674 ms (0.27%)

ddtrace.internal.telemetry 0.674 ms (0.27%)

ddtrace.internal.telemetry.writer 0.674 ms (0.27%)

ddtrace.internal.utils.version 0.674 ms (0.27%)

ddtrace.version 0.674 ms (0.27%)

ddtrace.internal._unpatched 0.028 ms (0.01%)

json 0.028 ms (0.01%)

json.decoder 0.028 ms (0.01%)

re 0.028 ms (0.01%)

enum 0.028 ms (0.01%)

types 0.028 ms (0.01%)

ddtrace.bootstrap.sitecustomize 1.264 ms (0.51%)

ddtrace.bootstrap.preload 1.264 ms (0.51%)

ddtrace.internal.remoteconfig.client 0.630 ms (0.25%)

pr-commenter · 2025-09-30T13:02:31Z

Performance SLOs

Comparing candidate alex/feat/vllm (58b6893) with baseline main (68a6181)

📈 Performance Regressions (3 suites)

📈 iastaspects - 118/118

✅ add_aspect

Time: ✅ 0.400µs (SLO: <10.000µs 📉 -96.0%) vs baseline: ~same

Memory: ✅ 40.280MB (SLO: <41.500MB -2.9%) vs baseline: +4.2%

✅ add_inplace_aspect

Time: ✅ 0.408µs (SLO: <10.000µs 📉 -95.9%) vs baseline: -0.5%

Memory: ✅ 40.441MB (SLO: <41.500MB -2.6%) vs baseline: +5.4%

✅ add_inplace_noaspect

Time: ✅ 0.314µs (SLO: <10.000µs 📉 -96.9%) vs baseline: -1.9%

Memory: ✅ 40.285MB (SLO: <41.500MB -2.9%) vs baseline: +4.9%

✅ add_noaspect

Time: ✅ 0.277µs (SLO: <10.000µs 📉 -97.2%) vs baseline: +0.4%

Memory: ✅ 40.383MB (SLO: <41.500MB -2.7%) vs baseline: +5.2%

✅ bytearray_aspect

Time: ✅ 1.341µs (SLO: <10.000µs 📉 -86.6%) vs baseline: -0.3%

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +5.1%

✅ bytearray_extend_aspect

Time: ✅ 1.492µs (SLO: <10.000µs 📉 -85.1%) vs baseline: -0.7%

Memory: ✅ 40.088MB (SLO: <41.500MB -3.4%) vs baseline: +4.1%

✅ bytearray_extend_noaspect

Time: ✅ 0.608µs (SLO: <10.000µs 📉 -93.9%) vs baseline: -0.7%

Memory: ✅ 40.344MB (SLO: <41.500MB -2.8%) vs baseline: +5.0%

✅ bytearray_noaspect

Time: ✅ 0.482µs (SLO: <10.000µs 📉 -95.2%) vs baseline: +0.6%

Memory: ✅ 40.128MB (SLO: <41.500MB -3.3%) vs baseline: +4.6%

✅ bytes_aspect

Time: ✅ 1.285µs (SLO: <10.000µs 📉 -87.2%) vs baseline: -0.2%

Memory: ✅ 40.036MB (SLO: <41.500MB -3.5%) vs baseline: +3.4%

✅ bytes_noaspect

Time: ✅ 0.492µs (SLO: <10.000µs 📉 -95.1%) vs baseline: +0.1%

Memory: ✅ 40.324MB (SLO: <41.500MB -2.8%) vs baseline: +4.8%

✅ bytesio_aspect

Time: ✅ 1.330µs (SLO: <10.000µs 📉 -86.7%) vs baseline: +0.5%

Memory: ✅ 40.265MB (SLO: <41.500MB -3.0%) vs baseline: +4.3%

✅ bytesio_noaspect

Time: ✅ 0.495µs (SLO: <10.000µs 📉 -95.0%) vs baseline: ~same

Memory: ✅ 40.108MB (SLO: <41.500MB -3.4%) vs baseline: +4.3%

✅ capitalize_aspect

Time: ✅ 0.730µs (SLO: <10.000µs 📉 -92.7%) vs baseline: -0.4%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.9%

✅ capitalize_noaspect

Time: ✅ 0.432µs (SLO: <10.000µs 📉 -95.7%) vs baseline: -1.3%

Memory: ✅ 40.128MB (SLO: <41.500MB -3.3%) vs baseline: +4.6%

✅ casefold_aspect

Time: ✅ 0.733µs (SLO: <10.000µs 📉 -92.7%) vs baseline: -0.1%

Memory: ✅ 40.206MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ casefold_noaspect

Time: ✅ 0.370µs (SLO: <10.000µs 📉 -96.3%) vs baseline: -0.2%

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +4.3%

✅ decode_aspect

Time: ✅ 0.726µs (SLO: <10.000µs 📉 -92.7%) vs baseline: +0.3%

Memory: ✅ 40.442MB (SLO: <41.500MB -2.5%) vs baseline: +5.4%

✅ decode_noaspect

Time: ✅ 0.416µs (SLO: <10.000µs 📉 -95.8%) vs baseline: -1.1%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ encode_aspect

Time: ✅ 0.704µs (SLO: <10.000µs 📉 -93.0%) vs baseline: ~same

Memory: ✅ 40.167MB (SLO: <41.500MB -3.2%) vs baseline: +4.1%

✅ encode_noaspect

Time: ✅ 0.402µs (SLO: <10.000µs 📉 -96.0%) vs baseline: +0.8%

Memory: ✅ 40.246MB (SLO: <41.500MB -3.0%) vs baseline: +4.9%

✅ format_aspect

Time: ✅ 3.345µs (SLO: <10.000µs 📉 -66.5%) vs baseline: -1.4%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.6%

✅ format_map_aspect

Time: ✅ 3.501µs (SLO: <10.000µs 📉 -65.0%) vs baseline: -2.2%

Memory: ✅ 40.246MB (SLO: <41.500MB -3.0%) vs baseline: +4.7%

✅ format_map_noaspect

Time: ✅ 0.774µs (SLO: <10.000µs 📉 -92.3%) vs baseline: +0.5%

Memory: ✅ 40.403MB (SLO: <41.500MB -2.6%) vs baseline: +5.1%

✅ format_noaspect

Time: ✅ 0.592µs (SLO: <10.000µs 📉 -94.1%) vs baseline: ~same

Memory: ✅ 40.108MB (SLO: <41.500MB -3.4%) vs baseline: +4.7%

✅ index_aspect

Time: ✅ 0.355µs (SLO: <10.000µs 📉 -96.5%) vs baseline: +0.1%

Memory: ✅ 40.338MB (SLO: <41.500MB -2.8%) vs baseline: +4.2%

✅ index_noaspect

Time: ✅ 0.277µs (SLO: <10.000µs 📉 -97.2%) vs baseline: +0.7%

Memory: ✅ 40.364MB (SLO: <41.500MB -2.7%) vs baseline: +5.2%

✅ join_aspect

Time: ✅ 1.340µs (SLO: <10.000µs 📉 -86.6%) vs baseline: +1.9%

Memory: ✅ 40.080MB (SLO: <41.500MB -3.4%) vs baseline: +3.4%

✅ join_noaspect

Time: ✅ 0.487µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -1.8%

Memory: ✅ 40.324MB (SLO: <41.500MB -2.8%) vs baseline: +5.1%

✅ ljust_aspect

Time: ✅ 2.904µs (SLO: <20.000µs 📉 -85.5%) vs baseline: 📈 +13.8%

Memory: ✅ 40.285MB (SLO: <41.500MB -2.9%) vs baseline: +4.8%

✅ ljust_noaspect

Time: ✅ 0.400µs (SLO: <10.000µs 📉 -96.0%) vs baseline: -0.3%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.4%

✅ lower_aspect

Time: ✅ 2.274µs (SLO: <10.000µs 📉 -77.3%) vs baseline: +4.2%

Memory: ✅ 40.204MB (SLO: <41.500MB -3.1%) vs baseline: +4.5%

✅ lower_noaspect

Time: ✅ 0.369µs (SLO: <10.000µs 📉 -96.3%) vs baseline: +0.3%

Memory: ✅ 40.344MB (SLO: <41.500MB -2.8%) vs baseline: +5.3%

✅ lstrip_aspect

Time: ✅ 2.248µs (SLO: <20.000µs 📉 -88.8%) vs baseline: +0.7%

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +4.6%

✅ lstrip_noaspect

Time: ✅ 0.382µs (SLO: <10.000µs 📉 -96.2%) vs baseline: +0.5%

Memory: ✅ 40.324MB (SLO: <41.500MB -2.8%) vs baseline: +5.2%

✅ modulo_aspect

Time: ✅ 1.037µs (SLO: <10.000µs 📉 -89.6%) vs baseline: +3.6%

Memory: ✅ 40.305MB (SLO: <41.500MB -2.9%) vs baseline: +4.1%

✅ modulo_aspect_for_bytearray_bytearray

Time: ✅ 1.542µs (SLO: <10.000µs 📉 -84.6%) vs baseline: ~same

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.7%

✅ modulo_aspect_for_bytes

Time: ✅ 0.976µs (SLO: <10.000µs 📉 -90.2%) vs baseline: +0.6%

Memory: ✅ 40.128MB (SLO: <41.500MB -3.3%) vs baseline: +4.4%

✅ modulo_aspect_for_bytes_bytearray

Time: ✅ 1.244µs (SLO: <10.000µs 📉 -87.6%) vs baseline: +2.6%

Memory: ✅ 40.265MB (SLO: <41.500MB -3.0%) vs baseline: +5.0%

✅ modulo_noaspect

Time: ✅ 0.626µs (SLO: <10.000µs 📉 -93.7%) vs baseline: -0.1%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.4%

✅ replace_aspect

Time: ✅ 4.821µs (SLO: <10.000µs 📉 -51.8%) vs baseline: -0.9%

Memory: ✅ 40.206MB (SLO: <41.500MB -3.1%) vs baseline: +4.3%

✅ replace_noaspect

Time: ✅ 0.459µs (SLO: <10.000µs 📉 -95.4%) vs baseline: -0.5%

Memory: ✅ 40.383MB (SLO: <41.500MB -2.7%) vs baseline: +4.9%

✅ repr_aspect

Time: ✅ 0.908µs (SLO: <10.000µs 📉 -90.9%) vs baseline: +0.6%

Memory: ✅ 40.179MB (SLO: <41.500MB -3.2%) vs baseline: +3.7%

✅ repr_noaspect

Time: ✅ 0.417µs (SLO: <10.000µs 📉 -95.8%) vs baseline: -0.3%

Memory: ✅ 40.482MB (SLO: <41.500MB -2.5%) vs baseline: +5.4%

✅ rstrip_aspect

Time: ✅ 1.931µs (SLO: <20.000µs 📉 -90.3%) vs baseline: +1.1%

Memory: ✅ 40.246MB (SLO: <41.500MB -3.0%) vs baseline: +4.8%

✅ rstrip_noaspect

Time: ✅ 0.380µs (SLO: <10.000µs 📉 -96.2%) vs baseline: -0.7%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.7%

✅ slice_aspect

Time: ✅ 0.489µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -0.2%

Memory: ✅ 40.240MB (SLO: <41.500MB -3.0%) vs baseline: +3.9%

✅ slice_noaspect

Time: ✅ 0.447µs (SLO: <10.000µs 📉 -95.5%) vs baseline: +0.4%

Memory: ✅ 40.265MB (SLO: <41.500MB -3.0%) vs baseline: +5.0%

✅ stringio_aspect

Time: ✅ 1.769µs (SLO: <10.000µs 📉 -82.3%) vs baseline: 📈 +15.4%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +5.3%

✅ stringio_noaspect

Time: ✅ 0.713µs (SLO: <10.000µs 📉 -92.9%) vs baseline: -0.2%

Memory: ✅ 40.128MB (SLO: <41.500MB -3.3%) vs baseline: +4.7%

✅ strip_aspect

Time: ✅ 2.213µs (SLO: <20.000µs 📉 -88.9%) vs baseline: -0.3%

Memory: ✅ 40.266MB (SLO: <41.500MB -3.0%) vs baseline: +4.9%

✅ strip_noaspect

Time: ✅ 0.387µs (SLO: <10.000µs 📉 -96.1%) vs baseline: +1.3%

Memory: ✅ 40.403MB (SLO: <41.500MB -2.6%) vs baseline: +4.9%

✅ swapcase_aspect

Time: ✅ 2.486µs (SLO: <10.000µs 📉 -75.1%) vs baseline: +2.7%

Memory: ✅ 40.147MB (SLO: <41.500MB -3.3%) vs baseline: +4.7%

✅ swapcase_noaspect

Time: ✅ 0.536µs (SLO: <10.000µs 📉 -94.6%) vs baseline: +0.2%

Memory: ✅ 40.324MB (SLO: <41.500MB -2.8%) vs baseline: +5.1%

✅ title_aspect

Time: ✅ 2.406µs (SLO: <10.000µs 📉 -75.9%) vs baseline: +2.5%

Memory: ✅ 40.344MB (SLO: <41.500MB -2.8%) vs baseline: +5.2%

✅ title_noaspect

Time: ✅ 0.502µs (SLO: <10.000µs 📉 -95.0%) vs baseline: +0.7%

Memory: ✅ 40.226MB (SLO: <41.500MB -3.1%) vs baseline: +4.3%

✅ translate_aspect

Time: ✅ 3.221µs (SLO: <10.000µs 📉 -67.8%) vs baseline: +0.2%

Memory: ✅ 40.246MB (SLO: <41.500MB -3.0%) vs baseline: +4.7%

✅ translate_noaspect

Time: ✅ 1.043µs (SLO: <10.000µs 📉 -89.6%) vs baseline: ~same

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +4.9%

✅ upper_aspect

Time: ✅ 2.281µs (SLO: <10.000µs 📉 -77.2%) vs baseline: +3.3%

Memory: ✅ 40.202MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ upper_noaspect

Time: ✅ 0.367µs (SLO: <10.000µs 📉 -96.3%) vs baseline: -0.7%

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +4.2%

📈 iastaspectsospath - 24/24

✅ ospathbasename_aspect

Time: ✅ 5.008µs (SLO: <10.000µs 📉 -49.9%) vs baseline: 📈 +27.8%

Memory: ✅ 40.344MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +5.0%

✅ ospathbasename_noaspect

Time: ✅ 1.074µs (SLO: <10.000µs 📉 -89.3%) vs baseline: -0.5%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.7%

✅ ospathjoin_aspect

Time: ✅ 5.949µs (SLO: <10.000µs 📉 -40.5%) vs baseline: -0.4%

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.9%

✅ ospathjoin_noaspect

Time: ✅ 2.281µs (SLO: <10.000µs 📉 -77.2%) vs baseline: ~same

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.5%

✅ ospathnormcase_aspect

Time: ✅ 3.245µs (SLO: <10.000µs 📉 -67.6%) vs baseline: -0.1%

Memory: ✅ 40.324MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +4.7%

✅ ospathnormcase_noaspect

Time: ✅ 0.564µs (SLO: <10.000µs 📉 -94.4%) vs baseline: -0.1%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +5.0%

✅ ospathsplit_aspect

Time: ✅ 4.473µs (SLO: <10.000µs 📉 -55.3%) vs baseline: -1.1%

Memory: ✅ 40.383MB (SLO: <41.000MB 🟡 -1.5%) vs baseline: +5.2%

✅ ospathsplit_noaspect

Time: ✅ 1.576µs (SLO: <10.000µs 📉 -84.2%) vs baseline: -0.4%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.5%

✅ ospathsplitdrive_aspect

Time: ✅ 3.385µs (SLO: <10.000µs 📉 -66.1%) vs baseline: -0.5%

Memory: ✅ 40.147MB (SLO: <41.000MB -2.1%) vs baseline: +4.7%

✅ ospathsplitdrive_noaspect

Time: ✅ 0.689µs (SLO: <10.000µs 📉 -93.1%) vs baseline: -0.5%

Memory: ✅ 40.383MB (SLO: <41.000MB 🟡 -1.5%) vs baseline: +5.1%

✅ ospathsplitext_aspect

Time: ✅ 4.317µs (SLO: <10.000µs 📉 -56.8%) vs baseline: +1.5%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.5%

✅ ospathsplitext_noaspect

Time: ✅ 1.380µs (SLO: <10.000µs 📉 -86.2%) vs baseline: +0.3%

Memory: ✅ 40.246MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.6%

📈 telemetryaddmetric - 30/30

✅ 1-count-metric-1-times

Time: ✅ 3.407µs (SLO: <20.000µs 📉 -83.0%) vs baseline: 📈 +16.0%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.7%

✅ 1-count-metrics-100-times

Time: ✅ 203.395µs (SLO: <220.000µs -7.5%) vs baseline: -0.1%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ 1-distribution-metric-1-times

Time: ✅ 3.321µs (SLO: <20.000µs 📉 -83.4%) vs baseline: +1.2%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.9%

✅ 1-distribution-metrics-100-times

Time: ✅ 219.755µs (SLO: <230.000µs -4.5%) vs baseline: +0.7%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.9%

✅ 1-gauge-metric-1-times

Time: ✅ 2.179µs (SLO: <20.000µs 📉 -89.1%) vs baseline: +0.2%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ 1-gauge-metrics-100-times

Time: ✅ 137.086µs (SLO: <150.000µs -8.6%) vs baseline: ~same

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.7%

✅ 1-rate-metric-1-times

Time: ✅ 3.109µs (SLO: <20.000µs 📉 -84.5%) vs baseline: ~same

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ 1-rate-metrics-100-times

Time: ✅ 218.372µs (SLO: <250.000µs 📉 -12.7%) vs baseline: +1.7%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.6%

✅ 100-count-metrics-100-times

Time: ✅ 20.481ms (SLO: <22.000ms -6.9%) vs baseline: +0.2%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.8%

✅ 100-distribution-metrics-100-times

Time: ✅ 2.270ms (SLO: <2.550ms 📉 -11.0%) vs baseline: -1.9%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.7%

✅ 100-gauge-metrics-100-times

Time: ✅ 1.419ms (SLO: <1.550ms -8.5%) vs baseline: +1.0%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.0%

✅ 100-rate-metrics-100-times

Time: ✅ 2.212ms (SLO: <2.550ms 📉 -13.3%) vs baseline: -0.2%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +5.4%

✅ flush-1-metric

Time: ✅ 4.595µs (SLO: <20.000µs 📉 -77.0%) vs baseline: -0.6%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.3%

✅ flush-100-metrics

Time: ✅ 173.994µs (SLO: <250.000µs 📉 -30.4%) vs baseline: -0.6%

Memory: ✅ 35.134MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +4.6%

✅ flush-1000-metrics

Time: ✅ 2.178ms (SLO: <2.500ms 📉 -12.9%) vs baseline: -0.8%

Memory: ✅ 36.019MB (SLO: <36.500MB 🟡 -1.3%) vs baseline: +5.0%

🟡 Near SLO Breach (16 suites)

🟡 coreapiscenario - 10/10 (1 unstable)

⚠️ context_with_data_listeners

Time: ⚠️ 13.234µs (SLO: <20.000µs 📉 -33.8%) vs baseline: -0.2%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

✅ context_with_data_no_listeners

Time: ✅ 3.295µs (SLO: <10.000µs 📉 -67.1%) vs baseline: +1.4%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.2%

✅ get_item_exists

Time: ✅ 0.577µs (SLO: <10.000µs 📉 -94.2%) vs baseline: -0.2%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.9%

✅ get_item_missing

Time: ✅ 0.632µs (SLO: <10.000µs 📉 -93.7%) vs baseline: ~same

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.9%

✅ set_item

Time: ✅ 24.029µs (SLO: <30.000µs 📉 -19.9%) vs baseline: -0.2%

Memory: ✅ 34.721MB (SLO: <35.500MB -2.2%) vs baseline: +4.7%

🟡 djangosimple - 30/30

✅ appsec

Time: ✅ 19.561ms (SLO: <22.300ms 📉 -12.3%) vs baseline: -0.3%

Memory: ✅ 68.144MB (SLO: <70.500MB -3.3%) vs baseline: +4.6%

✅ exception-replay-enabled

Time: ✅ 1.363ms (SLO: <1.450ms -6.0%) vs baseline: -0.1%

Memory: ✅ 66.252MB (SLO: <67.500MB 🟡 -1.8%) vs baseline: +4.8%

✅ iast

Time: ✅ 19.476ms (SLO: <22.250ms 📉 -12.5%) vs baseline: -0.6%

Memory: ✅ 68.144MB (SLO: <70.000MB -2.7%) vs baseline: +4.8%

✅ profiler

Time: ✅ 15.417ms (SLO: <16.550ms -6.8%) vs baseline: -0.3%

Memory: ✅ 56.457MB (SLO: <57.500MB 🟡 -1.8%) vs baseline: +5.1%

✅ resource-renaming

Time: ✅ 19.511ms (SLO: <21.750ms 📉 -10.3%) vs baseline: -0.1%

Memory: ✅ 68.164MB (SLO: <70.500MB -3.3%) vs baseline: +4.9%

✅ span-code-origin

Time: ✅ 20.113ms (SLO: <28.200ms 📉 -28.7%) vs baseline: +1.6%

Memory: ✅ 68.176MB (SLO: <71.000MB -4.0%) vs baseline: +4.9%

✅ tracer

Time: ✅ 19.488ms (SLO: <21.750ms 📉 -10.4%) vs baseline: -1.1%

Memory: ✅ 68.164MB (SLO: <70.000MB -2.6%) vs baseline: +4.8%

✅ tracer-and-profiler

Time: ✅ 21.699ms (SLO: <23.500ms -7.7%) vs baseline: +0.4%

Memory: ✅ 69.186MB (SLO: <71.000MB -2.6%) vs baseline: +4.7%

✅ tracer-dont-create-db-spans

Time: ✅ 19.661ms (SLO: <21.500ms -8.6%) vs baseline: +0.3%

Memory: ✅ 68.184MB (SLO: <70.000MB -2.6%) vs baseline: +4.9%

✅ tracer-minimal

Time: ✅ 16.802ms (SLO: <17.500ms -4.0%) vs baseline: -0.3%

Memory: ✅ 67.869MB (SLO: <70.000MB -3.0%) vs baseline: +5.0%

✅ tracer-native

Time: ✅ 19.488ms (SLO: <21.750ms 📉 -10.4%) vs baseline: +0.4%

Memory: ✅ 68.262MB (SLO: <72.500MB -5.8%) vs baseline: +4.8%

✅ tracer-no-caches

Time: ✅ 17.572ms (SLO: <19.650ms 📉 -10.6%) vs baseline: -0.5%

Memory: ✅ 67.928MB (SLO: <70.000MB -3.0%) vs baseline: +4.8%

✅ tracer-no-databases

Time: ✅ 19.078ms (SLO: <20.100ms -5.1%) vs baseline: -0.1%

Memory: ✅ 67.790MB (SLO: <70.000MB -3.2%) vs baseline: +4.8%

✅ tracer-no-middleware

Time: ✅ 19.238ms (SLO: <21.500ms 📉 -10.5%) vs baseline: -0.1%

Memory: ✅ 68.085MB (SLO: <70.000MB -2.7%) vs baseline: +5.1%

✅ tracer-no-templates

Time: ✅ 19.596ms (SLO: <22.000ms 📉 -10.9%) vs baseline: +1.1%

Memory: ✅ 68.182MB (SLO: <70.500MB -3.3%) vs baseline: +4.9%

🟡 errortrackingdjangosimple - 6/6

✅ errortracking-enabled-all

Time: ✅ 16.230ms (SLO: <19.850ms 📉 -18.2%) vs baseline: -0.4%

Memory: ✅ 69.828MB (SLO: <70.000MB 🟡 -0.2%) vs baseline: +4.8%

✅ errortracking-enabled-user

Time: ✅ 16.296ms (SLO: <19.400ms 📉 -16.0%) vs baseline: -0.4%

Memory: ✅ 69.776MB (SLO: <70.000MB 🟡 -0.3%) vs baseline: +4.9%

✅ tracer-enabled

Time: ✅ 16.389ms (SLO: <19.450ms 📉 -15.7%) vs baseline: +0.3%

Memory: ✅ 69.840MB (SLO: <70.000MB 🟡 -0.2%) vs baseline: +4.9%

🟡 errortrackingflasksqli - 6/6

✅ errortracking-enabled-all

Time: ✅ 2.070ms (SLO: <2.300ms -10.0%) vs baseline: +0.1%

Memory: ✅ 55.679MB (SLO: <56.500MB 🟡 -1.5%) vs baseline: +4.7%

✅ errortracking-enabled-user

Time: ✅ 2.079ms (SLO: <2.250ms -7.6%) vs baseline: +0.5%

Memory: ✅ 55.758MB (SLO: <56.500MB 🟡 -1.3%) vs baseline: +4.8%

✅ tracer-enabled

Time: ✅ 2.065ms (SLO: <2.300ms 📉 -10.2%) vs baseline: ~same

Memory: ✅ 55.719MB (SLO: <56.500MB 🟡 -1.4%) vs baseline: +4.7%

🟡 flasksimple - 18/18

✅ appsec-get

Time: ✅ 3.362ms (SLO: <4.750ms 📉 -29.2%) vs baseline: -0.6%

Memory: ✅ 55.467MB (SLO: <66.500MB 📉 -16.6%) vs baseline: +4.9%

✅ appsec-post

Time: ✅ 2.857ms (SLO: <6.750ms 📉 -57.7%) vs baseline: ~same

Memory: ✅ 55.625MB (SLO: <66.500MB 📉 -16.4%) vs baseline: +4.7%

✅ appsec-telemetry

Time: ✅ 3.383ms (SLO: <4.750ms 📉 -28.8%) vs baseline: +0.3%

Memory: ✅ 55.333MB (SLO: <66.500MB 📉 -16.8%) vs baseline: +4.6%

✅ debugger

Time: ✅ 1.871ms (SLO: <2.000ms -6.4%) vs baseline: +0.3%

Memory: ✅ 47.898MB (SLO: <49.500MB -3.2%) vs baseline: +4.8%

✅ iast-get

Time: ✅ 1.861ms (SLO: <2.000ms -6.9%) vs baseline: +0.2%

Memory: ✅ 44.577MB (SLO: <49.000MB -9.0%) vs baseline: +4.8%

✅ profiler

Time: ✅ 1.908ms (SLO: <2.100ms -9.1%) vs baseline: -0.1%

Memory: ✅ 48.803MB (SLO: <50.000MB -2.4%) vs baseline: +4.9%

✅ resource-renaming

Time: ✅ 3.355ms (SLO: <3.650ms -8.1%) vs baseline: -0.1%

Memory: ✅ 55.470MB (SLO: <56.000MB 🟡 -0.9%) vs baseline: +4.9%

✅ tracer

Time: ✅ 3.368ms (SLO: <3.650ms -7.7%) vs baseline: -0.2%

Memory: ✅ 55.408MB (SLO: <56.500MB 🟡 -1.9%) vs baseline: +4.8%

✅ tracer-native

Time: ✅ 3.378ms (SLO: <3.650ms -7.4%) vs baseline: +0.4%

Memory: ✅ 55.469MB (SLO: <60.000MB -7.6%) vs baseline: +4.8%

🟡 flasksqli - 6/6

✅ appsec-enabled

Time: ✅ 2.057ms (SLO: <4.200ms 📉 -51.0%) vs baseline: -0.4%

Memory: ✅ 55.660MB (SLO: <66.000MB 📉 -15.7%) vs baseline: +4.7%

✅ iast-enabled

Time: ✅ 2.075ms (SLO: <2.800ms 📉 -25.9%) vs baseline: +0.4%

Memory: ✅ 55.797MB (SLO: <62.500MB 📉 -10.7%)

✅ tracer-enabled

Time: ✅ 2.060ms (SLO: <2.250ms -8.5%) vs baseline: ~same

Memory: ✅ 55.797MB (SLO: <56.500MB 🟡 -1.2%) vs baseline: +4.9%

🟡 httppropagationextract - 60/60

✅ all_styles_all_headers

Time: ✅ 79.300µs (SLO: <100.000µs 📉 -20.7%) vs baseline: +0.5%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.4%

✅ b3_headers

Time: ✅ 13.704µs (SLO: <20.000µs 📉 -31.5%) vs baseline: -0.2%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +4.9%

✅ b3_single_headers

Time: ✅ 12.831µs (SLO: <20.000µs 📉 -35.8%) vs baseline: -0.5%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.5%

✅ datadog_tracecontext_tracestate_not_propagated_on_trace_id_no_match

Time: ✅ 61.582µs (SLO: <80.000µs 📉 -23.0%) vs baseline: ~same

Memory: ✅ 34.957MB (SLO: <35.500MB 🟡 -1.5%) vs baseline: +5.1%

✅ datadog_tracecontext_tracestate_propagated_on_trace_id_match

Time: ✅ 64.156µs (SLO: <80.000µs 📉 -19.8%) vs baseline: +0.2%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ empty_headers

Time: ✅ 1.580µs (SLO: <10.000µs 📉 -84.2%) vs baseline: +0.2%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +4.9%

✅ full_t_id_datadog_headers

Time: ✅ 21.642µs (SLO: <30.000µs 📉 -27.9%) vs baseline: +0.9%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ invalid_priority_header

Time: ✅ 6.453µs (SLO: <10.000µs 📉 -35.5%) vs baseline: +0.6%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +4.8%

✅ invalid_span_id_header

Time: ✅ 6.430µs (SLO: <10.000µs 📉 -35.7%) vs baseline: +0.2%

Memory: ✅ 34.937MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.1%

✅ invalid_tags_header

Time: ✅ 6.476µs (SLO: <10.000µs 📉 -35.2%) vs baseline: +0.6%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +5.2%

✅ invalid_trace_id_header

Time: ✅ 6.440µs (SLO: <10.000µs 📉 -35.6%) vs baseline: +0.4%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +4.7%

✅ large_header_no_matches

Time: ✅ 27.458µs (SLO: <30.000µs -8.5%) vs baseline: -0.3%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.2%

✅ large_valid_headers_all

Time: ✅ 28.550µs (SLO: <40.000µs 📉 -28.6%) vs baseline: +0.3%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.2%

✅ medium_header_no_matches

Time: ✅ 9.780µs (SLO: <20.000µs 📉 -51.1%) vs baseline: +0.3%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.1%

✅ medium_valid_headers_all

Time: ✅ 11.163µs (SLO: <20.000µs 📉 -44.2%) vs baseline: -0.3%

Memory: ✅ 34.977MB (SLO: <35.500MB 🟡 -1.5%) vs baseline: +5.5%

✅ none_propagation_style

Time: ✅ 1.677µs (SLO: <10.000µs 📉 -83.2%) vs baseline: +1.1%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.0%

✅ tracecontext_headers

Time: ✅ 33.563µs (SLO: <40.000µs 📉 -16.1%) vs baseline: +0.6%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +5.0%

✅ valid_headers_all

Time: ✅ 6.436µs (SLO: <10.000µs 📉 -35.6%) vs baseline: ~same

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.6%

✅ valid_headers_basic

Time: ✅ 6.032µs (SLO: <10.000µs 📉 -39.7%) vs baseline: ~same

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.7%

✅ wsgi_empty_headers

Time: ✅ 1.581µs (SLO: <10.000µs 📉 -84.2%) vs baseline: +0.3%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.3%

✅ wsgi_invalid_priority_header

Time: ✅ 6.487µs (SLO: <10.000µs 📉 -35.1%) vs baseline: -0.6%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +4.9%

✅ wsgi_invalid_span_id_header

Time: ✅ 1.576µs (SLO: <10.000µs 📉 -84.2%) vs baseline: ~same

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.9%

✅ wsgi_invalid_tags_header

Time: ✅ 6.535µs (SLO: <10.000µs 📉 -34.7%) vs baseline: +0.6%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_invalid_trace_id_header

Time: ✅ 6.491µs (SLO: <10.000µs 📉 -35.1%) vs baseline: +0.2%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_large_header_no_matches

Time: ✅ 28.659µs (SLO: <40.000µs 📉 -28.4%) vs baseline: ~same

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_large_valid_headers_all

Time: ✅ 29.774µs (SLO: <40.000µs 📉 -25.6%) vs baseline: +0.5%

Memory: ✅ 35.036MB (SLO: <35.500MB 🟡 -1.3%) vs baseline: +5.3%

✅ wsgi_medium_header_no_matches

Time: ✅ 10.044µs (SLO: <20.000µs 📉 -49.8%) vs baseline: ~same

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +4.9%

✅ wsgi_medium_valid_headers_all

Time: ✅ 11.402µs (SLO: <20.000µs 📉 -43.0%) vs baseline: -0.6%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.2%

✅ wsgi_valid_headers_all

Time: ✅ 6.593µs (SLO: <10.000µs 📉 -34.1%) vs baseline: +1.8%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.1%

✅ wsgi_valid_headers_basic

Time: ✅ 6.024µs (SLO: <10.000µs 📉 -39.8%) vs baseline: ~same

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.6%

🟡 httppropagationinject - 16/16

✅ ids_only

Time: ✅ 21.502µs (SLO: <30.000µs 📉 -28.3%) vs baseline: +5.5%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.8%

✅ with_all

Time: ✅ 26.742µs (SLO: <40.000µs 📉 -33.1%) vs baseline: +0.8%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.1%

✅ with_dd_origin

Time: ✅ 23.865µs (SLO: <30.000µs 📉 -20.5%) vs baseline: +0.1%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.6%

✅ with_priority_and_origin

Time: ✅ 23.410µs (SLO: <40.000µs 📉 -41.5%) vs baseline: -0.4%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.0%

✅ with_sampling_priority

Time: ✅ 20.551µs (SLO: <30.000µs 📉 -31.5%) vs baseline: +0.4%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +4.8%

✅ with_tags

Time: ✅ 24.877µs (SLO: <40.000µs 📉 -37.8%) vs baseline: +0.3%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.6%

✅ with_tags_invalid

Time: ✅ 26.248µs (SLO: <40.000µs 📉 -34.4%) vs baseline: ~same

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ with_tags_max_size

Time: ✅ 25.423µs (SLO: <40.000µs 📉 -36.4%) vs baseline: +0.3%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +4.9%

🟡 iast_aspects - 40/40

✅ re_expand_aspect

Time: ✅ 33.196µs (SLO: <40.000µs 📉 -17.0%) vs baseline: +6.8%

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.1%

✅ re_expand_noaspect

Time: ✅ 27.815µs (SLO: <40.000µs 📉 -30.5%) vs baseline: -1.4%

Memory: ✅ 40.383MB (SLO: <41.000MB 🟡 -1.5%) vs baseline: +5.2%

✅ re_findall_aspect

Time: ✅ 2.887µs (SLO: <10.000µs 📉 -71.1%) vs baseline: -0.1%

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.0%

✅ re_findall_noaspect

Time: ✅ 1.397µs (SLO: <10.000µs 📉 -86.0%) vs baseline: -0.5%

Memory: ✅ 40.423MB (SLO: <41.000MB 🟡 -1.4%) vs baseline: +5.2%

✅ re_finditer_aspect

Time: ✅ 4.206µs (SLO: <10.000µs 📉 -57.9%) vs baseline: -1.1%

Memory: ✅ 40.324MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +4.8%

✅ re_finditer_noaspect

Time: ✅ 1.384µs (SLO: <10.000µs 📉 -86.2%) vs baseline: ~same

Memory: ✅ 40.482MB (SLO: <41.000MB 🟡 -1.3%) vs baseline: +5.6%

✅ re_fullmatch_aspect

Time: ✅ 2.676µs (SLO: <10.000µs 📉 -73.2%) vs baseline: +0.3%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.4%

✅ re_fullmatch_noaspect

Time: ✅ 1.321µs (SLO: <10.000µs 📉 -86.8%) vs baseline: +1.3%

Memory: ✅ 40.246MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.7%

✅ re_group_aspect

Time: ✅ 2.945µs (SLO: <10.000µs 📉 -70.5%) vs baseline: -0.4%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.1%

✅ re_group_noaspect

Time: ✅ 1.594µs (SLO: <10.000µs 📉 -84.1%) vs baseline: -1.6%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.8%

✅ re_groups_aspect

Time: ✅ 3.077µs (SLO: <10.000µs 📉 -69.2%) vs baseline: -0.2%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.9%

✅ re_groups_noaspect

Time: ✅ 1.697µs (SLO: <10.000µs 📉 -83.0%) vs baseline: -0.9%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.7%

✅ re_match_aspect

Time: ✅ 2.721µs (SLO: <10.000µs 📉 -72.8%) vs baseline: +1.3%

Memory: ✅ 40.364MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +5.0%

✅ re_match_noaspect

Time: ✅ 1.306µs (SLO: <10.000µs 📉 -86.9%) vs baseline: -1.0%

Memory: ✅ 40.324MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +5.2%

✅ re_search_aspect

Time: ✅ 2.544µs (SLO: <10.000µs 📉 -74.6%) vs baseline: -0.2%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +5.1%

✅ re_search_noaspect

Time: ✅ 1.189µs (SLO: <10.000µs 📉 -88.1%) vs baseline: -1.3%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.1%

✅ re_sub_aspect

Time: ✅ 3.371µs (SLO: <10.000µs 📉 -66.3%) vs baseline: -0.3%

Memory: ✅ 40.442MB (SLO: <41.000MB 🟡 -1.4%) vs baseline: +5.2%

✅ re_sub_noaspect

Time: ✅ 1.532µs (SLO: <10.000µs 📉 -84.7%) vs baseline: +1.9%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.4%

✅ re_subn_aspect

Time: ✅ 3.611µs (SLO: <10.000µs 📉 -63.9%) vs baseline: -0.7%

Memory: ✅ 40.246MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.6%

✅ re_subn_noaspect

Time: ✅ 1.575µs (SLO: <10.000µs 📉 -84.2%) vs baseline: +0.2%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.3%

🟡 iastaspectssplit - 12/12

✅ rsplit_aspect

Time: ✅ 1.551µs (SLO: <10.000µs 📉 -84.5%) vs baseline: +6.1%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.0%

✅ rsplit_noaspect

Time: ✅ 0.579µs (SLO: <10.000µs 📉 -94.2%) vs baseline: +0.1%

Memory: ✅ 40.088MB (SLO: <41.000MB -2.2%) vs baseline: +4.4%

✅ split_aspect

Time: ✅ 1.425µs (SLO: <10.000µs 📉 -85.7%) vs baseline: +0.9%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.5%

✅ split_noaspect

Time: ✅ 0.566µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -0.8%

Memory: ✅ 40.364MB (SLO: <41.000MB 🟡 -1.6%) vs baseline: +4.9%

✅ splitlines_aspect

Time: ✅ 1.423µs (SLO: <10.000µs 📉 -85.8%) vs baseline: ~same

Memory: ✅ 40.383MB (SLO: <41.000MB 🟡 -1.5%) vs baseline: +5.1%

✅ splitlines_noaspect

Time: ✅ 0.581µs (SLO: <10.000µs 📉 -94.2%) vs baseline: -0.1%

Memory: ✅ 40.088MB (SLO: <41.000MB -2.2%) vs baseline: +4.3%

🟡 otelspan - 22/22

✅ add-event

Time: ✅ 39.664ms (SLO: <47.150ms 📉 -15.9%) vs baseline: -0.3%

Memory: ✅ 39.437MB (SLO: <47.000MB 📉 -16.1%) vs baseline: +4.7%

✅ add-metrics

Time: ✅ 263.128ms (SLO: <344.800ms 📉 -23.7%) vs baseline: +1.2%

Memory: ✅ 43.844MB (SLO: <47.500MB -7.7%) vs baseline: +5.3%

✅ add-tags

Time: ✅ 318.467ms (SLO: <321.000ms 🟡 -0.8%) vs baseline: +0.3%

Memory: ✅ 43.747MB (SLO: <47.500MB -7.9%) vs baseline: +4.9%

✅ get-context

Time: ✅ 79.824ms (SLO: <92.350ms 📉 -13.6%) vs baseline: -0.2%

Memory: ✅ 39.656MB (SLO: <46.500MB 📉 -14.7%) vs baseline: +4.8%

✅ is-recording

Time: ✅ 37.264ms (SLO: <44.500ms 📉 -16.3%) vs baseline: ~same

Memory: ✅ 39.450MB (SLO: <47.500MB 📉 -16.9%) vs baseline: +5.1%

✅ record-exception

Time: ✅ 58.404ms (SLO: <67.650ms 📉 -13.7%) vs baseline: +0.1%

Memory: ✅ 39.985MB (SLO: <47.000MB 📉 -14.9%) vs baseline: +4.8%

✅ set-status

Time: ✅ 43.688ms (SLO: <50.400ms 📉 -13.3%) vs baseline: -0.3%

Memory: ✅ 39.384MB (SLO: <47.000MB 📉 -16.2%) vs baseline: +4.2%

✅ start

Time: ✅ 37.293ms (SLO: <43.450ms 📉 -14.2%) vs baseline: +2.1%

Memory: ✅ 39.407MB (SLO: <47.000MB 📉 -16.2%) vs baseline: +4.5%

✅ start-finish

Time: ✅ 82.129ms (SLO: <88.000ms -6.7%) vs baseline: +0.2%

Memory: ✅ 37.257MB (SLO: <46.500MB 📉 -19.9%) vs baseline: +4.8%

✅ start-finish-telemetry

Time: ✅ 83.332ms (SLO: <89.000ms -6.4%) vs baseline: -0.2%

Memory: ✅ 37.356MB (SLO: <46.500MB 📉 -19.7%) vs baseline: +4.6%

✅ update-name

Time: ✅ 38.078ms (SLO: <45.150ms 📉 -15.7%) vs baseline: ~same

Memory: ✅ 39.544MB (SLO: <47.000MB 📉 -15.9%) vs baseline: +4.5%

🟡 packagespackageforrootmodulemapping - 4/4

✅ cache_off

Time: ✅ 343.019ms (SLO: <354.300ms -3.2%) vs baseline: -1.3%

Memory: ✅ 40.712MB (SLO: <41.500MB 🟡 -1.9%) vs baseline: +4.8%

✅ cache_on

Time: ✅ 0.384µs (SLO: <10.000µs 📉 -96.2%) vs baseline: +1.4%

Memory: ✅ 39.924MB (SLO: <41.000MB -2.6%) vs baseline: +4.7%

🟡 ratelimiter - 12/12

✅ defaults

Time: ✅ 2.334µs (SLO: <10.000µs 📉 -76.7%) vs baseline: -0.1%

Memory: ✅ 35.055MB (SLO: <35.500MB 🟡 -1.3%) vs baseline: +4.7%

✅ high_rate_limit

Time: ✅ 2.406µs (SLO: <10.000µs 📉 -75.9%) vs baseline: -0.4%

Memory: ✅ 35.154MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +4.7%

✅ long_window

Time: ✅ 2.343µs (SLO: <10.000µs 📉 -76.6%) vs baseline: ~same

Memory: ✅ 35.134MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +5.0%

✅ low_rate_limit

Time: ✅ 2.337µs (SLO: <10.000µs 📉 -76.6%) vs baseline: ~same

Memory: ✅ 35.134MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +4.9%

✅ no_rate_limit

Time: ✅ 0.818µs (SLO: <10.000µs 📉 -91.8%) vs baseline: -1.2%

Memory: ✅ 34.977MB (SLO: <35.500MB 🟡 -1.5%) vs baseline: +4.6%

✅ short_window

Time: ✅ 2.456µs (SLO: <10.000µs 📉 -75.4%) vs baseline: -0.4%

Memory: ✅ 35.095MB (SLO: <35.500MB 🟡 -1.1%) vs baseline: +4.9%

🟡 recursivecomputation - 8/8

✅ deep

Time: ✅ 308.532ms (SLO: <320.950ms -3.9%) vs baseline: -0.1%

Memory: ✅ 35.881MB (SLO: <36.500MB 🟡 -1.7%) vs baseline: +4.7%

✅ deep-profiled

Time: ✅ 329.179ms (SLO: <359.150ms -8.3%) vs baseline: +0.4%

Memory: ✅ 39.715MB (SLO: <40.500MB 🟡 -1.9%) vs baseline: +4.8%

✅ medium

Time: ✅ 6.994ms (SLO: <7.400ms -5.5%) vs baseline: ~same

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

✅ shallow

Time: ✅ 0.947ms (SLO: <1.050ms -9.8%) vs baseline: +1.3%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

🟡 sethttpmeta - 32/32

✅ all-disabled

Time: ✅ 10.613µs (SLO: <20.000µs 📉 -46.9%) vs baseline: +0.3%

Memory: ✅ 35.232MB (SLO: <36.000MB -2.1%) vs baseline: +4.7%

✅ all-enabled

Time: ✅ 41.083µs (SLO: <50.000µs 📉 -17.8%) vs baseline: +2.0%

Memory: ✅ 35.232MB (SLO: <36.000MB -2.1%) vs baseline: +4.7%

✅ collectipvariant_exists

Time: ✅ 40.839µs (SLO: <50.000µs 📉 -18.3%) vs baseline: -0.1%

Memory: ✅ 35.409MB (SLO: <36.000MB 🟡 -1.6%) vs baseline: +5.0%

✅ no-collectipvariant

Time: ✅ 40.162µs (SLO: <50.000µs 📉 -19.7%) vs baseline: +0.4%

Memory: ✅ 35.232MB (SLO: <36.000MB -2.1%) vs baseline: +4.6%

✅ no-useragentvariant

Time: ✅ 38.871µs (SLO: <50.000µs 📉 -22.3%) vs baseline: ~same

Memory: ✅ 35.291MB (SLO: <36.000MB 🟡 -2.0%) vs baseline: +4.3%

✅ obfuscation-no-query

Time: ✅ 40.625µs (SLO: <50.000µs 📉 -18.8%) vs baseline: +0.2%

Memory: ✅ 35.468MB (SLO: <36.000MB 🟡 -1.5%) vs baseline: +5.1%

✅ obfuscation-regular-case-explicit-query

Time: ✅ 75.965µs (SLO: <90.000µs 📉 -15.6%) vs baseline: ~same

Memory: ✅ 35.507MB (SLO: <36.500MB -2.7%) vs baseline: +4.4%

✅ obfuscation-regular-case-implicit-query

Time: ✅ 76.319µs (SLO: <90.000µs 📉 -15.2%) vs baseline: -1.1%

Memory: ✅ 35.665MB (SLO: <36.500MB -2.3%) vs baseline: +4.8%

✅ obfuscation-send-querystring-disabled

Time: ✅ 154.264µs (SLO: <170.000µs -9.3%) vs baseline: -0.2%

Memory: ✅ 35.724MB (SLO: <36.500MB -2.1%) vs baseline: +4.9%

✅ obfuscation-worst-case-explicit-query

Time: ✅ 148.532µs (SLO: <160.000µs -7.2%) vs baseline: -0.2%

Memory: ✅ 35.645MB (SLO: <36.500MB -2.3%) vs baseline: +4.9%

✅ obfuscation-worst-case-implicit-query

Time: ✅ 154.562µs (SLO: <170.000µs -9.1%) vs baseline: -0.4%

Memory: ✅ 35.684MB (SLO: <36.500MB -2.2%) vs baseline: +5.1%

✅ useragentvariant_exists_1

Time: ✅ 39.553µs (SLO: <50.000µs 📉 -20.9%) vs baseline: -1.4%

Memory: ✅ 35.350MB (SLO: <36.000MB 🟡 -1.8%) vs baseline: +4.9%

✅ useragentvariant_exists_2

Time: ✅ 40.772µs (SLO: <50.000µs 📉 -18.5%) vs baseline: +0.2%

Memory: ✅ 35.409MB (SLO: <36.000MB 🟡 -1.6%) vs baseline: +5.2%

✅ useragentvariant_exists_3

Time: ✅ 40.279µs (SLO: <50.000µs 📉 -19.4%) vs baseline: +0.3%

Memory: ✅ 35.389MB (SLO: <36.000MB 🟡 -1.7%) vs baseline: +5.0%

✅ useragentvariant_not_exists_1

Time: ✅ 39.799µs (SLO: <50.000µs 📉 -20.4%) vs baseline: +0.3%

Memory: ✅ 35.370MB (SLO: <36.000MB 🟡 -1.8%) vs baseline: +4.2%

✅ useragentvariant_not_exists_2

Time: ✅ 39.582µs (SLO: <50.000µs 📉 -20.8%) vs baseline: +0.3%

Memory: ✅ 35.330MB (SLO: <36.000MB 🟡 -1.9%) vs baseline: +4.7%

🟡 tracer - 6/6

✅ large

Time: ✅ 29.213ms (SLO: <32.950ms 📉 -11.3%) vs baseline: -0.1%

Memory: ✅ 35.901MB (SLO: <36.500MB 🟡 -1.6%) vs baseline: +4.6%

✅ medium

Time: ✅ 2.882ms (SLO: <3.200ms -9.9%) vs baseline: +0.1%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ small

Time: ✅ 330.872µs (SLO: <370.000µs 📉 -10.6%) vs baseline: +1.0%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +5.1%

⚠️ Unstable Tests (1 suite)

⚠️

packagesupdateimporteddependencies - 24/24 (1 unstable)

✅ import_many

Time: ✅ 154.370µs (SLO: <170.000µs -9.2%) vs baseline: -0.9%

Memory: ✅ 39.948MB (SLO: <41.000MB -2.6%) vs baseline: +5.3%

✅ import_many_cached

Time: ✅ 121.289µs (SLO: <130.000µs -6.7%) vs baseline: ~same

Memory: ✅ 39.863MB (SLO: <41.000MB -2.8%) vs baseline: +4.9%

✅ import_many_stdlib

Time: ✅ 0.755ms (SLO: <1.750ms 📉 -56.9%) vs baseline: ~same

Memory: ✅ 39.850MB (SLO: <41.000MB -2.8%) vs baseline: +5.4%

⚠️ import_many_stdlib_cached

Time: ⚠️ 0.172ms (SLO: <1.100ms 📉 -84.4%) vs baseline: -0.5%

Memory: ✅ 39.745MB (SLO: <41.000MB -3.1%) vs baseline: +4.6%

✅ import_many_unknown

Time: ✅ 831.625µs (SLO: <890.000µs -6.6%) vs baseline: ~same

Memory: ✅ 39.966MB (SLO: <41.000MB -2.5%) vs baseline: +4.9%

✅ import_many_unknown_cached

Time: ✅ 792.419µs (SLO: <870.000µs -8.9%) vs baseline: -0.9%

Memory: ✅ 40.080MB (SLO: <41.000MB -2.2%) vs baseline: +4.9%

✅ import_one

Time: ✅ 19.815µs (SLO: <30.000µs 📉 -34.0%) vs baseline: -0.3%

Memory: ✅ 39.765MB (SLO: <41.000MB -3.0%) vs baseline: +4.4%

✅ import_one_cache

Time: ✅ 6.249µs (SLO: <10.000µs 📉 -37.5%) vs baseline: -1.1%

Memory: ✅ 39.938MB (SLO: <41.000MB -2.6%) vs baseline: +5.5%

✅ import_one_stdlib

Time: ✅ 18.729µs (SLO: <20.000µs -6.4%) vs baseline: +0.8%

Memory: ✅ 39.937MB (SLO: <41.000MB -2.6%) vs baseline: +5.4%

✅ import_one_stdlib_cache

Time: ✅ 6.320µs (SLO: <10.000µs 📉 -36.8%) vs baseline: +1.2%

Memory: ✅ 39.793MB (SLO: <41.000MB -2.9%) vs baseline: +5.0%

✅ import_one_unknown

Time: ✅ 45.394µs (SLO: <50.000µs -9.2%) vs baseline: ~same

Memory: ✅ 40.003MB (SLO: <41.000MB -2.4%) vs baseline: +5.5%

✅ import_one_unknown_cache

Time: ✅ 6.273µs (SLO: <10.000µs 📉 -37.3%) vs baseline: -0.6%

Memory: ✅ 39.835MB (SLO: <41.000MB -2.8%) vs baseline: +5.2%

✅ All Tests Passing (4 suites)

✅ iastpropagation - 8/8

✅ no-propagation

Time: ✅ 48.746µs (SLO: <60.000µs 📉 -18.8%) vs baseline: +0.2%

Memory: ✅ 40.069MB (SLO: <42.000MB -4.6%) vs baseline: +4.7%

✅ propagation_enabled

Time: ✅ 173.529µs (SLO: <190.000µs -8.7%) vs baseline: -1.6%

Memory: ✅ 40.108MB (SLO: <42.000MB -4.5%) vs baseline: +4.9%

✅ propagation_enabled_100

Time: ✅ 1.924ms (SLO: <2.300ms 📉 -16.3%) vs baseline: +0.2%

Memory: ✅ 40.167MB (SLO: <42.000MB -4.4%) vs baseline: +4.9%

✅ propagation_enabled_1000

Time: ✅ 32.351ms (SLO: <34.550ms -6.4%) vs baseline: -0.4%

Memory: ✅ 40.088MB (SLO: <42.000MB -4.6%) vs baseline: +4.9%

✅ otelsdkspan - 24/24

✅ add-event

Time: ✅ 40.393ms (SLO: <42.000ms -3.8%) vs baseline: -0.3%

Memory: ✅ 37.316MB (SLO: <39.000MB -4.3%) vs baseline: +4.3%

✅ add-link

Time: ✅ 36.290ms (SLO: <38.550ms -5.9%) vs baseline: ~same

Memory: ✅ 37.395MB (SLO: <39.000MB -4.1%) vs baseline: +4.5%

✅ add-metrics

Time: ✅ 217.752ms (SLO: <232.000ms -6.1%) vs baseline: -0.8%

Memory: ✅ 37.434MB (SLO: <39.000MB -4.0%) vs baseline: +4.1%

✅ add-tags

Time: ✅ 210.582ms (SLO: <221.600ms -5.0%) vs baseline: -0.7%

Memory: ✅ 37.356MB (SLO: <39.000MB -4.2%) vs baseline: +3.8%

✅ get-context

Time: ✅ 29.118ms (SLO: <31.300ms -7.0%) vs baseline: -0.3%

Memory: ✅ 37.238MB (SLO: <39.000MB -4.5%) vs baseline: +4.7%

✅ is-recording

Time: ✅ 29.172ms (SLO: <31.000ms -5.9%) vs baseline: +0.4%

Memory: ✅ 37.336MB (SLO: <39.000MB -4.3%) vs baseline: +4.5%

✅ record-exception

Time: ✅ 63.000ms (SLO: <65.850ms -4.3%) vs baseline: ~same

Memory: ✅ 37.670MB (SLO: <39.000MB -3.4%) vs baseline: +4.7%

✅ set-status

Time: ✅ 31.919ms (SLO: <34.150ms -6.5%) vs baseline: +0.2%

Memory: ✅ 37.375MB (SLO: <39.000MB -4.2%) vs baseline: +4.9%

✅ start

Time: ✅ 29.299ms (SLO: <30.150ms -2.8%) vs baseline: +2.0%

Memory: ✅ 37.297MB (SLO: <39.000MB -4.4%) vs baseline: +4.7%

✅ start-finish

Time: ✅ 33.835ms (SLO: <35.350ms -4.3%) vs baseline: -0.8%

Memory: ✅ 37.473MB (SLO: <39.000MB -3.9%) vs baseline: +5.1%

✅ start-finish-telemetry

Time: ✅ 34.298ms (SLO: <35.450ms -3.2%) vs baseline: +0.9%

Memory: ✅ 37.316MB (SLO: <39.000MB -4.3%) vs baseline: +4.5%

✅ update-name

Time: ✅ 30.899ms (SLO: <33.400ms -7.5%) vs baseline: ~same

Memory: ✅ 37.336MB (SLO: <39.000MB -4.3%) vs baseline: +4.9%

✅ samplingrules - 8/8

✅ average_match

Time: ✅ 137.677µs (SLO: <290.000µs 📉 -52.5%) vs baseline: ~same

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.8%

✅ high_match

Time: ✅ 174.781µs (SLO: <480.000µs 📉 -63.6%) vs baseline: +0.4%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

✅ low_match

Time: ✅ 98.915µs (SLO: <120.000µs 📉 -17.6%) vs baseline: +0.4%

Memory: ✅ 603.570MB (SLO: <700.000MB 📉 -13.8%) vs baseline: +4.9%

✅ very_low_match

Time: ✅ 2.676ms (SLO: <8.500ms 📉 -68.5%) vs baseline: +1.0%

Memory: ✅ 71.112MB (SLO: <75.000MB -5.2%) vs baseline: +5.1%

✅ span - 26/26

✅ add-event

Time: ✅ 18.270ms (SLO: <22.500ms 📉 -18.8%) vs baseline: +0.3%

Memory: ✅ 36.807MB (SLO: <53.000MB 📉 -30.6%) vs baseline: +4.7%

✅ add-metrics

Time: ✅ 88.933ms (SLO: <93.500ms -4.9%) vs baseline: +0.5%

Memory: ✅ 41.078MB (SLO: <53.000MB 📉 -22.5%) vs baseline: +5.1%

✅ add-tags

Time: ✅ 141.920ms (SLO: <155.000ms -8.4%) vs baseline: -0.5%

Memory: ✅ 41.124MB (SLO: <53.000MB 📉 -22.4%) vs baseline: +5.1%

✅ get-context

Time: ✅ 16.968ms (SLO: <20.500ms 📉 -17.2%) vs baseline: +0.5%

Memory: ✅ 36.663MB (SLO: <53.000MB 📉 -30.8%) vs baseline: +4.8%

✅ is-recording

Time: ✅ 17.289ms (SLO: <20.500ms 📉 -15.7%) vs baseline: +0.4%

Memory: ✅ 36.641MB (SLO: <53.000MB 📉 -30.9%) vs baseline: +4.7%

✅ record-exception

Time: ✅ 36.703ms (SLO: <40.000ms -8.2%) vs baseline: +0.2%

Memory: ✅ 37.235MB (SLO: <53.000MB 📉 -29.7%) vs baseline: +4.8%

✅ set-status

Time: ✅ 18.713ms (SLO: <22.000ms 📉 -14.9%) vs baseline: +0.5%

Memory: ✅ 36.625MB (SLO: <53.000MB 📉 -30.9%) vs baseline: +4.7%

✅ start

Time: ✅ 17.418ms (SLO: <20.500ms 📉 -15.0%) vs baseline: +3.1%

Memory: ✅ 36.700MB (SLO: <53.000MB 📉 -30.8%) vs baseline: +5.1%

✅ start-finish

Time: ✅ 51.155ms (SLO: <52.500ms -2.6%) vs baseline: +0.6%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.6%

✅ start-finish-telemetry

Time: ✅ 52.359ms (SLO: <54.500ms -3.9%) vs baseline: -0.1%

Memory: ✅ 34.662MB (SLO: <35.500MB -2.4%) vs baseline: +4.4%

✅ start-finish-traceid128

Time: ✅ 54.092ms (SLO: <57.000ms -5.1%) vs baseline: ~same

Memory: ✅ 34.682MB (SLO: <35.500MB -2.3%) vs baseline: +4.8%

✅ start-traceid128

Time: ✅ 17.356ms (SLO: <22.500ms 📉 -22.9%) vs baseline: +0.6%

Memory: ✅ 36.697MB (SLO: <53.000MB 📉 -30.8%) vs baseline: +5.0%

✅ update-name

Time: ✅ 17.356ms (SLO: <22.000ms 📉 -21.1%) vs baseline: -0.2%

Memory: ✅ 36.779MB (SLO: <53.000MB 📉 -30.6%) vs baseline: +5.0%

ℹ️ Scenarios Missing SLO Configuration (10 scenarios)

The following scenarios exist in candidate data but have no SLO thresholds configured:

coreapiscenario-core_dispatch_listeners
coreapiscenario-core_dispatch_no_listeners
coreapiscenario-core_dispatch_with_results_listeners
coreapiscenario-core_dispatch_with_results_no_listeners
djangosimple-baseline
errortrackingdjangosimple-baseline
errortrackingflasksqli-baseline
flasksimple-baseline
flasksqli-baseline
sethttpmeta-obfuscation-disabled

brettlangdon · 2025-10-02T18:01:58Z

@PROFeNoM probably worth updating the codeowners file as well to make llmobs the owner of this integration, will help require less people to review it (after the codeowners change is merged)

github-actions · 2025-11-18T00:08:26Z

This pull request has been automatically closed after a period of inactivity.
After this much time, it will likely be easier to open a new pull request with the
same changes than to update this one from the base branch. Please comment or reopen
if you think this pull request was closed in error.

# Conflicts: # .gitlab/testrunner.yml # scripts/ddtest # tests/llmobs/suitespec.yml

# Conflicts: # tests/llmobs/suitespec.yml

# Conflicts: # ddtrace/llmobs/_constants.py

…d improve span creation logic - Updated `traced_output_processor_process_outputs` to capture `req_state` data for all requests, not just those marked as finished. - Improved span creation logic to ensure spans are only created for requests that have actually finished processing. - Added handling for `iteration_stats` to provide additional context in spans. - Cleaned up comments for clarity and accuracy regarding request state handling. # Conflicts: # ddtrace/llmobs/_constants.py

…h wrapt proxies - Introduced `_register_wrapt_pickle_reducers` to register custom pickle reducers for wrapt proxy types. - This enables serialization of ddtrace-wrapped objects in frameworks like Ray that utilize cloudpickle. - The new reducer unwraps proxies to their underlying objects, allowing for re-patching on deserialization. - Called the new function in `_patch_all` to ensure the reducers are registered during the patching process.

- Simplified the `_register_wrapt_pickle_reducers` function to prevent multiple registrations by using a global flag. - Removed redundant comments and improved code clarity while maintaining functionality for serializing ddtrace-wrapped objects. - Ensured that the registration of pickle reducers occurs only once to enhance performance and avoid unnecessary overhead.

- Introduced `parse_prompt_to_messages` to convert formatted prompts into structured messages, supporting various chat templates. - Added role extraction patterns for common chat formats to improve message handling. - Updated `VLLMIntegration` to utilize the new message parsing function for input messages. - Refactored tests to align with the new message structure, ensuring consistency in input and output message formats.

- Updated role extraction patterns to support additional chat templates, including Llama 4, Granite, Gemma, and others. - Improved the `parse_prompt_to_messages` function to utilize quick checks for markers, enhancing performance and accuracy in message parsing. - Added comprehensive tests for various prompt formats to ensure robust handling of different message structures and roles.

# Conflicts: # ddtrace/llmobs/_constants.py

…y metrics - Refactored GPU test configurations in `.gitlab/testrunner.yml` and `.gitlab/tests.yml` to utilize shared templates for improved maintainability. - Removed redundant GPU variant definitions and consolidated before scripts. - Enhanced latency metrics tracking in `vllm` integration by adding `set_latency_metrics` to capture detailed performance data. - Updated test snapshots to reflect changes in latency metrics and ensure consistency across tests.

- consolidate latency metrics calculation - extract magic strings to constants - split large output processor function - add complete type hints - improve error handling specificity

PROFeNoM · 2025-12-09T08:58:42Z

@codex review

chatgpt-codex-connector · 2025-12-09T09:06:35Z

Codex Review: Didn't find any major issues. What shall we delve into next?

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

PROFeNoM self-assigned this Sep 30, 2025

PROFeNoM force-pushed the alex/feat/vllm branch 4 times, most recently from bf30414 to 0af046e Compare September 30, 2025 14:00

PROFeNoM added integrations Tracing Distributed Tracing CI MLObs ML Observability (LLMObs) labels Oct 2, 2025

PROFeNoM force-pushed the alex/feat/vllm branch 3 times, most recently from 5627244 to 494f936 Compare October 2, 2025 13:09

PROFeNoM marked this pull request as ready for review October 2, 2025 13:58

PROFeNoM requested review from a team as code owners October 2, 2025 13:58

PROFeNoM requested review from juanjux, vlad-scherbich and wconti27 October 2, 2025 13:58

PROFeNoM force-pushed the alex/feat/vllm branch 3 times, most recently from d970650 to 2c22b68 Compare October 2, 2025 14:20

PROFeNoM force-pushed the alex/feat/vllm branch 2 times, most recently from 23026f8 to e64073f Compare October 6, 2025 13:17

github-actions bot closed this Nov 18, 2025

PROFeNoM reopened this Dec 3, 2025

PROFeNoM marked this pull request as draft December 3, 2025 08:41

github-actions bot removed the stale label Dec 4, 2025

PROFeNoM added 16 commits December 8, 2025 15:27

feat(vllm): add vLLM integration

df81012

# Conflicts: # .gitlab/testrunner.yml # scripts/ddtest # tests/llmobs/suitespec.yml

Rework the integration for 0.10.2+ V1 engine support only

a3d64f7

# Conflicts: # tests/llmobs/suitespec.yml

chore: Update the CODEOWNERS file

06a1257

chore: Update registry.yaml

00d20a0

migrate latency metrics to span events

e7e976f

# Conflicts: # ddtrace/llmobs/_constants.py

lint

2c151d4

less invasive fix

6d73c6c

fix(vllm): update tokenizer decoding to preserve chat template markers

c0ab80c

style: lint

aa45e29

# Conflicts: # ddtrace/llmobs/_constants.py

lint

0beb49a

PROFeNoM force-pushed the alex/feat/vllm branch from 5c940b1 to 0beb49a Compare December 8, 2025 14:34

PROFeNoM added 2 commits December 8, 2025 16:47

refactor

f0ca0d5

- consolidate latency metrics calculation - extract magic strings to constants - split large output processor function - add complete type hints - improve error handling specificity

lint

58b6893

PROFeNoM marked this pull request as ready for review December 8, 2025 16:07

PROFeNoM requested a review from a team as a code owner December 8, 2025 16:07

PROFeNoM requested a review from mabdinur December 8, 2025 16:07

ZStriker19 self-requested a review December 9, 2025 15:56

feat(vllm): add vLLM integration #14732

Are you sure you want to change the base?

feat(vllm): add vLLM integration #14732

Conversation

PROFeNoM commented Sep 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Request Flow and Instrumentation Points

Version Support

Metadata Captured

Chat Template Parsing

FastAPI Pickle Fix for Ray Serve Compatibility

Problem

Solution

Why This Works

Reproducer

Testing

Risks

Additional Notes

Main Files

Uh oh!

github-actions bot commented Sep 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Sep 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Bootstrap import analysis

Summary

Import time breakdown

Uh oh!

pr-commenter bot commented Sep 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Performance SLOs

✅ add_aspect

✅ add_inplace_aspect

✅ add_inplace_noaspect

✅ add_noaspect

✅ bytearray_aspect

✅ bytearray_extend_aspect

✅ bytearray_extend_noaspect

✅ bytearray_noaspect

✅ bytes_aspect

✅ bytes_noaspect

✅ bytesio_aspect

✅ bytesio_noaspect

✅ capitalize_aspect

✅ capitalize_noaspect

✅ casefold_aspect

✅ casefold_noaspect

✅ decode_aspect

✅ decode_noaspect

✅ encode_aspect

✅ encode_noaspect

✅ format_aspect

✅ format_map_aspect

✅ format_map_noaspect

✅ format_noaspect

✅ index_aspect

✅ index_noaspect

✅ join_aspect

✅ join_noaspect

✅ ljust_aspect

✅ ljust_noaspect

✅ lower_aspect

✅ lower_noaspect

✅ lstrip_aspect

✅ lstrip_noaspect

✅ modulo_aspect

✅ modulo_aspect_for_bytearray_bytearray

✅ modulo_aspect_for_bytes

✅ modulo_aspect_for_bytes_bytearray

✅ modulo_noaspect

✅ replace_aspect

✅ replace_noaspect

✅ repr_aspect

✅ repr_noaspect

✅ rstrip_aspect

✅ rstrip_noaspect

✅ slice_aspect

✅ slice_noaspect

PROFeNoM commented Sep 30, 2025 •

edited

Loading

github-actions bot commented Sep 30, 2025 •

edited

Loading

github-actions bot commented Sep 30, 2025 •

edited

Loading

pr-commenter bot commented Sep 30, 2025 •

edited

Loading