otel-eval-bridge
otel-eval-bridge converts exported OpenTelemetry or Phoenix-style GenAI spans
into local eval cases while preserving trace and span references.
At a Glance
| Job | Extract trace-linked eval inputs, expected values, observations, and provider/model metadata. |
| Built for | Eval engineers and observability teams turning recorded traces into regression inputs. |
| Differentiator | Dependency-free file bridge with default secret and email redaction. |
| Produces | JSONL eval cases, a trace-reference manifest, and eval results attached back to cases. |
Install
python -m pip install "otel-eval-bridge==0.1.2"
Verified Quickstart
Run from a source checkout:
otel-eval-bridge extract examples/genai_trace.json \
--out /tmp/eval-cases.jsonl
otel-eval-bridge manifest /tmp/eval-cases.jsonl \
--out /tmp/eval-manifest.json
otel-eval-bridge attach /tmp/eval-cases.jsonl examples/eval_results.json \
--out /tmp/trace-linked-results.json
The bundled trace export produces two eval cases and an
auraone.eval-run-manifest.v1 manifest.
Input and Output Contract
The reader accepts a JSON list, a top-level spans list, or OTLP JSON
resourceSpans[].scopeSpans[].spans[]. Phoenix-style input.value,
output.value, llm.provider, and llm.model_name attributes are normalized
to the bridge's GenAI fields.
Each emitted case can include:
- trace ID, span ID, and span name;
- prompt/input, expected value, and observed completion;
- provider and model metadata.
attach matches result entries by trace ID first and span ID second.
Runtime, Data, and Network Boundary
- All commands read and write local JSON or JSONL files.
- The CLI does not receive OTLP traffic, export telemetry, call an observability backend, run an eval, or make network requests.
- Redaction is enabled by default for sensitive keys,
sk-...,pypi-..., bearer tokens, and email addresses. --no-redactdisables that protection. Default redaction is pattern-based and is not a comprehensive privacy or compliance control.
Limitations
- The bridge extracts eval inputs from exported trace data only. It does not run a scorer, validate observability semantics, or prove trace completeness.
- Redaction is pattern-based and intentionally small. Review emitted cases before sharing them outside the originating environment.
Compatibility
The published auraone-agent-studio-open CLI declares
otel-eval-bridge>=0.1.0 as a runtime dependency and exposes local trace import
and eval-case extraction paths. The JSONL output can also be adapted by an
in-house eval runner.
Publication Status
Verified on 2026-07-13:
- PyPI:
otel-eval-bridge==0.1.2 - GitHub release:
v0.1.2 - The source, wheel, source distribution, and release tag are aligned on
0.1.2.
Next Action
Export a sanitized trace sample, inspect the generated cases for residual sensitive data, then connect the JSONL file to the eval runner that owns scoring.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file otel_eval_bridge-0.1.2.tar.gz.
File metadata
- Download URL: otel_eval_bridge-0.1.2.tar.gz
- Upload date:
- Size: 8.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
09c78a473f970ca5951f5660f145abef714ca39a25ecb272faf627e50161d7d6
|
|
| MD5 |
a376e9797d3b99b509d9633dd1b0927b
|
|
| BLAKE2b-256 |
41ca54dfce63295375e38b7cdbe71c9ad426e9e3907cd4890c9ae7684a2d8a97
|
Provenance
The following attestation bundles were made for otel_eval_bridge-0.1.2.tar.gz:
Publisher:
release-python.yml on auraoneai/otel-eval-bridge
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
otel_eval_bridge-0.1.2.tar.gz -
Subject digest:
09c78a473f970ca5951f5660f145abef714ca39a25ecb272faf627e50161d7d6 - Sigstore transparency entry: 2165376302
- Sigstore integration time:
-
Permalink:
auraoneai/otel-eval-bridge@05da6820f4366afca346ec55010738b5fd20b9bf -
Branch / Tag:
refs/tags/v0.1.2 - Owner: https://github.com/auraoneai
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release-python.yml@05da6820f4366afca346ec55010738b5fd20b9bf -
Trigger Event:
release
-
Statement type:
File details
Details for the file otel_eval_bridge-0.1.2-py3-none-any.whl.
File metadata
- Download URL: otel_eval_bridge-0.1.2-py3-none-any.whl
- Upload date:
- Size: 8.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8e4ed73eee7fccef66f7fedf20a1666c654d33d7a3add96a1e7c541fb49b1ad3
|
|
| MD5 |
5a55fe64bc241a3c63f9811fd0f3b832
|
|
| BLAKE2b-256 |
f8b863185b4461fac24e3cff5af88d7ac7219b358461aa2b55d8704262921614
|
Provenance
The following attestation bundles were made for otel_eval_bridge-0.1.2-py3-none-any.whl:
Publisher:
release-python.yml on auraoneai/otel-eval-bridge
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
otel_eval_bridge-0.1.2-py3-none-any.whl -
Subject digest:
8e4ed73eee7fccef66f7fedf20a1666c654d33d7a3add96a1e7c541fb49b1ad3 - Sigstore transparency entry: 2165376305
- Sigstore integration time:
-
Permalink:
auraoneai/otel-eval-bridge@05da6820f4366afca346ec55010738b5fd20b9bf -
Branch / Tag:
refs/tags/v0.1.2 - Owner: https://github.com/auraoneai
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release-python.yml@05da6820f4366afca346ec55010738b5fd20b9bf -
Trigger Event:
release
-
Statement type:
