Skip to content

Observability: OTel semantic conventions for agentic systems#33

Merged
k8s-ci-robot merged 19 commits intokubernetes-sigs:mainfrom
david-martin:observability-proposal
Feb 24, 2026
Merged

Observability: OTel semantic conventions for agentic systems#33
k8s-ci-robot merged 19 commits intokubernetes-sigs:mainfrom
david-martin:observability-proposal

Conversation

@david-martin
Copy link
Copy Markdown
Contributor

@david-martin david-martin commented Dec 19, 2025

What type of PR is this?

/kind documentation

What this PR does / why we need it:

Defines tracing schemas for agentic systems by following OpenTelemetry semantic conventions, with proposed extensions for permission enforcement outcomes.

@k8s-ci-robot
Copy link
Copy Markdown
Contributor

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

@k8s-ci-robot k8s-ci-robot added do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. kind/documentation Categorizes issue or PR as related to documentation. labels Dec 19, 2025
@k8s-ci-robot k8s-ci-robot added approved Indicates a PR has been approved by an approver from all required OWNERS files. size/M Denotes a PR that changes 30-99 lines, ignoring generated files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. labels Dec 19, 2025
Comment thread docs/proposals/0033-Observabilty.md Outdated
Comment thread docs/proposals/0033-Observabilty.md Outdated
Comment thread docs/proposals/0033-Observabilty.md Outdated
Comment thread docs/proposals/0033-Observabilty.md Outdated
Copy link
Copy Markdown
Contributor

@rubambiza rubambiza left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for kicking off the proposal @david-martin . I am a clean slate to the world of observability, so excuse any obvious questions in my review 😅

Comment thread docs/proposals/0033-Observabilty.md Outdated
Comment thread docs/proposals/0033-Observabilty.md Outdated
@linux-foundation-easycla
Copy link
Copy Markdown

linux-foundation-easycla Bot commented Jan 8, 2026

CLA Signed

The committers listed above are authorized under a signed CLA.

@k8s-ci-robot k8s-ci-robot added cncf-cla: no Indicates the PR's author has not signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. and removed cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/M Denotes a PR that changes 30-99 lines, ignoring generated files. cncf-cla: no Indicates the PR's author has not signed the CNCF CLA. labels Jan 8, 2026
Comment thread docs/proposals/0033-Observabilty.md Outdated
@david-martin
Copy link
Copy Markdown
Contributor Author

Capturing the outcome of conversation on slack & meet.

  • focus on schema first, with traces. API (including how to specify which fields to log/not log/redact) comes in a later proposal/addition, as will metrics
  • leaning into proxy use cases, let's iterate on an auditing example, building on something like an AccessPolicy rule that denies a tool call
  • Open q still if we want to add a schema repo. Do we have a handle on if/when https://github.com/open-telemetry/opentelemetry-specification/pull/4815/changes is going to land, and if that's a blocker for hosting our own schema?
    • that PR indeed needs to land and there's still some debate ongoing regarding SemConv V2. Once we have the schema specified we can also contribute it to the existing SemConv. We could request help from this group: https://contribute.cncf.io/community/tcgs/artificial-intelligence/
      They've been driving the SemConv for agentic workloads.

@david-martin david-martin marked this pull request as ready for review January 22, 2026 16:40
@k8s-ci-robot k8s-ci-robot removed the do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. label Jan 22, 2026
Comment thread docs/proposals/0033-Observability.md Outdated
Comment thread docs/proposals/0033-Observability.md Outdated
Comment thread docs/proposals/0033-Observability.md Outdated
Comment thread docs/proposals/0033-Observability.md
@netlify
Copy link
Copy Markdown

netlify Bot commented Jan 27, 2026

Deploy Preview for kube-agentic-networking ready!

Name Link
🔨 Latest commit 34366d4
🔍 Latest deploy log https://app.netlify.com/projects/kube-agentic-networking/deploys/699c30165ed0f900082fbca9
😎 Deploy Preview https://deploy-preview-33--kube-agentic-networking.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

david-martin and others added 6 commits January 27, 2026 14:20
Signed-off-by: David Martin <davmarti@redhat.com>
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
…n attributes from otel

Signed-off-by: David Martin <davmarti@redhat.com>
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
📝 Consolidate span attributes
…for the most part

Signed-off-by: David Martin <davmarti@redhat.com>
Simplify proposal to make it clear we're not defining new attributes …
@david-martin david-martin changed the title Add Observability auditing proposal Observability: OTel semantic conventions for agentic systems Feb 12, 2026
evaline-ju and others added 2 commits February 13, 2026 09:39
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
📝 Add alternate conventions section
@LiorLieberman
Copy link
Copy Markdown
Member

Overall this proposal looks good to me, thanks @david-martin!

/approve

/hold Will defer to @gkhom for final approval.

@k8s-ci-robot k8s-ci-robot added the do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. label Feb 19, 2026
Signed-off-by: David Martin <davmarti@redhat.com>
Signed-off-by: David Martin <davmarti@redhat.com>
@david-martin david-martin force-pushed the observability-proposal branch from 7a3c85e to cc31050 Compare February 19, 2026 15:42
Comment on lines +175 to +177
### Guardrailing

This shows a trace example of a guardrail blocking a request at a gateway.
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👋 from OpenTelemetry GenAI SIG

I don't have a ton of context on this proposal, but I wanted to share a proposal for Guardrails open-telemetry/semantic-conventions#3233

Comment thread docs/proposals/0033-Observability.md Outdated
│ POST /mcp
│ Headers:
│ traceparent: 00-c3d4e5f6a7b8c9d0e1f2a3b4c5d6e7f8-9c1d2e3f4a5b6c7d-01
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Copy Markdown
Contributor

@rubambiza rubambiza left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mostly clarifying questions, not sure if they may require any changes. They certainly do not need to block merging.

Comment thread docs/proposals/0033-Observability.md
Comment thread docs/proposals/0033-Observability.md Outdated
│ }
│ }
│ }
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this the point where the traffic hits a k8s cluster?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would say the request is inside the MCP aware router/gateway, or in the MCP Server at this point.
Either of those could be in a k8s cluster, yes.
After this point, it's up to the MCP server where that traffic goes (if anywhere), before the response is returned.

evaline-ju and others added 3 commits February 20, 2026 12:34
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
Signed-off-by: Evaline Ju <69598118+evaline-ju@users.noreply.github.com>
📝 Update traceparent and JSON-RPC bodies in examples
@LiorLieberman
Copy link
Copy Markdown
Member

@david-martin anything else thats blocking you from getting this in?

@david-martin
Copy link
Copy Markdown
Contributor Author

@LiorLieberman I think we're good to go here.

Thanks to everyone for the help and feedback on getting this to a mergable state.

@LiorLieberman
Copy link
Copy Markdown
Member

/approve
/lgtm
@david-martin please remove the hold when ready

@k8s-ci-robot k8s-ci-robot added the lgtm "Looks good to me", indicates that a PR is ready to be merged. label Feb 24, 2026
@k8s-ci-robot
Copy link
Copy Markdown
Contributor

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: david-martin, LiorLieberman

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Details Needs approval from an approver in each of these files:
  • OWNERS [LiorLieberman,david-martin]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@david-martin
Copy link
Copy Markdown
Contributor Author

/unhold

@k8s-ci-robot k8s-ci-robot removed the do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. label Feb 24, 2026
@k8s-ci-robot k8s-ci-robot merged commit f1b855d into kubernetes-sigs:main Feb 24, 2026
14 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/documentation Categorizes issue or PR as related to documentation. lgtm "Looks good to me", indicates that a PR is ready to be merged. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

9 participants