Trace tokenization and propagate request context#679
Open
satyamg1620 wants to merge 2 commits into
Open
Conversation
Signed-off-by: satyamg1620 <Satyam.Gupta.3@ibm.com>
satyamg1620
requested review from
dannyharnik,
kfirtoledo,
liu-cong and
vMaroon
as code owners
June 22, 2026 17:56
github-actions
Bot
added
the
size/L
gyliu513
reviewed
Jun 22, 2026
Signed-off-by: satyamg1620 <Satyam.Gupta.3@ibm.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR extends OpenTelemetry trace context propagation into the tokenization worker pool so the tokenization work is parented to the originating request span, closing the “tokenization” observability gap called out in #644.
Changes:
- Add
context.Contextpropagation across the tokenization workqueue boundary and start allm_d.kv_cache.tokenizationspan in the worker. - Emit tokenization span attributes (mode, prompt length, token count, multimodal flag) and set span status on errors.
- Update the
TokenizersPoolinterface + Indexer callers to pass request context, and add span-focused tests for the worker path.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| pkg/tokenization/pool.go | Propagates caller context via Task.Ctx and creates a tokenization span with attributes/status. |
| pkg/tokenization/pool_trace_test.go | Adds tests validating parent/child span linkage and span attributes/status. |
| pkg/kvcache/types.go | Updates TokenizersPool.Tokenize signature to accept context.Context. |
| pkg/kvcache/indexer.go | Passes request ctx into tokenization so spans parent correctly. |
| pkg/kvcache/indexer_test.go | Updates mock TokenizersPool implementation to match new interface. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+208
to
+210
| // chatPromptLen returns the combined character length of the conversation's | ||
| // text content. It is used as an approximate prompt size for chat-mode | ||
| // tokenization spans, where task.Prompt is empty. |
| limitations under the License. | ||
| */ | ||
|
|
||
| package tokenization |
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
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.
Part of #644 ("Extend OTel Tracing Coverage: kvevents + tokenization"). This PR covers the tokenization sub-task
only; the kvevents event-processing span is handled separately in #678
@gyliu513