Skip to content

Forward-merge release/0.3 into main#192

Merged
GPUtester merged 1 commit into
mainfrom
release/0.3
May 29, 2026
Merged

Forward-merge release/0.3 into main#192
GPUtester merged 1 commit into
mainfrom
release/0.3

Conversation

@rapids-bot
Copy link
Copy Markdown

@rapids-bot rapids-bot Bot commented May 29, 2026

Forward-merge triggered by push to release/0.3 that creates a PR to keep main up-to-date. If this PR is unable to be immediately merged due to conflicts, it will remain open for the team to manually merge. See forward-merger docs for more info.

#### Overview

Fixes the Hermes gateway session fallback and tightens ATIF LLM dedupe so complementary hook/gateway spans are only collapsed when they represent the same physical request.

- [x] I confirm this contribution is my own work, or I have the right to submit it under this project's license.
- [x] I searched existing issues and open pull requests, and this does not duplicate existing work.

#### Details

- Uses the OpenAI-compatible request body session_id as a gateway fallback when explicit session headers are absent.
- Keeps the existing explicit Claude/Codex session fallbacks ahead of the OpenAI body fallback.
- Requires complementary hook/gateway LLM spans to share a request signature or strong request correlation key before ATIF dedupes them.
- Adds regression coverage for gateway fallback selection and concurrent overlapping LLM spans that should remain distinct.

#### Where should the reviewer start?

Start with `crates/cli/src/alignment/mod.rs` for the gateway fallback behavior, then review `crates/core/src/observability/atif.rs` for the strengthened complementary hook/gateway dedupe guard. The focused regression tests are in `crates/cli/tests/coverage/alignment_tests.rs`, `crates/cli/tests/coverage/gateway_tests.rs`, and `crates/core/tests/unit/atif_tests.rs`.

#### Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

- Closes #176




## Summary by CodeRabbit

* **Bug Fixes**
  * Session ID resolution enhanced to properly support OpenAI-compatible API request formats, including additional fallback to request body identifiers
  * LLM span correlation and deduplication logic improved with request-level identifier matching, enabling more accurate observability tracking and better event correlation for request tracing



[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/NVIDIA/NeMo-Relay/pull/189?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

Authors:
  - Bryan Bednarski (https://github.com/bbednarski9)

Approvers:
  - Will Killian (https://github.com/willkill07)

URL: #189
@rapids-bot rapids-bot Bot requested a review from a team as a code owner May 29, 2026 21:48
@GPUtester GPUtester merged commit 3842b6a into main May 29, 2026
@rapids-bot
Copy link
Copy Markdown
Author

rapids-bot Bot commented May 29, 2026

SUCCESS - forward-merge complete.

@github-actions github-actions Bot added size:M PR is medium lang:rust PR changes/introduces Rust code labels May 29, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

lang:rust PR changes/introduces Rust code size:M PR is medium

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants