docs(weave): document linked agent eval traces#2930
Open
bcsherma wants to merge 5 commits into
Open
Conversation
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
Contributor
📚 Mintlify Preview Links📝 Changed (1 total)📄 Pages (1)
🤖 Generated automatically when Mintlify deployment succeeds |
Contributor
🔗 Link Checker ResultsPreview: https://wb-21fd5541-codex-link-agent-evals-docs.mintlify.site |
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 17, 2026 19:28
161e846 to
57e59ab
Compare
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 17, 2026 19:34
57e59ab to
60025ca
Compare
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 17, 2026 19:41
60025ca to
eb5685a
Compare
bcsherma
marked this pull request as ready for review
July 17, 2026 19:59
NiWaRe
reviewed
Jul 18, 2026
NiWaRe
left a comment
NiWaRe
left a comment
Contributor
There was a problem hiding this comment.
Minor feedback to make sure everyone understands - great otherwise thanks for the fast turn around!!
| | Attribute | Type | Description | | ||
| | --- | --- | --- | | ||
| | `weave.eval.run_id` | string | The call ID of the evaluation run (`Evaluation.evaluate`). Required to include the span in the evaluation-level **View spans** result. | | ||
| | `weave.eval.predict_and_score_call_id` | string | The call ID of the `Evaluation.predict_and_score` operation for a specific result and trial. Set this together with `weave.eval.run_id` to link the span to that result. | |
Contributor
There was a problem hiding this comment.
Maybe clearer if we include a quick example of how to create and propagate both IDs in above example?
Should be very similar but just to make sure the creation and propagation of the predict_and_score is also clear - from my understanding it is auto-created when a new prediction is logged and you would pass it along the external agent invocation?
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 20, 2026 18:24
eb5685a to
7fdca78
Compare
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 23, 2026 21:28
7fdca78 to
3db6fe8
Compare
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 23, 2026 21:34
3db6fe8 to
aef72a1
Compare
bcsherma
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 23, 2026 21:41
aef72a1 to
73e22e0
Compare
Apply documentation-review changes to the eval-linking guide: - standardize variable names to prediction/predictions - standardize placeholders to [YOUR-TEAM]/[YOUR-PROJECT] - replace "stamp" with "set"; label attribute table (Required)/(Optional) - restructure "Link agent traces to evaluations" with situation-led subheadings and an orienting decision paragraph - add "not available in TypeScript" tabs to Python-only examples, plus a Note clarifying the TypeScript raw-OTel path - point the destination to the /agents/otel/v1/traces endpoint and link the Export a GenAI trace reference - drop the per-example "View spans" UI step - unify terminology (linking attributes, OTel span) - focus the receiving-side example highlight on the two linking lines Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
anastasiaguspan
force-pushed
the
codex/link-agent-evals-docs
branch
from
July 24, 2026 13:53
73e22e0 to
500afaa
Compare
Add a how-to link to the newly merged 'Send OpenTelemetry spans to the Agents view' guide alongside the endpoint reference, so readers have both the conceptual pipeline setup and the endpoint spec. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Split the how-to guide and endpoint-spec links into a bulleted list and keep the attribute-propagation rule with the send-to-project instruction. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary
EvaluationLogger.log_prediction()context to link their spans to evaluation results.weave.eval.*OpenTelemetry attribute, including the two call IDs required for evaluation and result linkage.predict_and_scorecall, propagates both call IDs to an external agent service, and stamps the receiving OTel span.Validation
npx mint@latest validate