Repository navigation
Add QwenPaw 2.x runtime support - #994
Open
123liuziming wants to merge 10 commits into
Open
123liuziming wants to merge 10 commits into
123liuziming wants to merge 10 commits into
Conversation
Assisted-by: GPT-6.1 Sol
Pull request dashboard statusWaiting on the author · refreshed 2026-11-11 19:36 UTC Respond to 4 review items (e.g. link a commit, explain why not, ask a follow-up): Status above doesn't look right?
|
Assisted-by: GPT-6.1 Sol
Assisted-by: GPT-6.1 Sol
Assisted-by: GPT-6.1 Sol
Assisted-by: GPT-6.1 Sol
Retain hook context across stream reads, merge partial message snapshots, and use shared media conversion. Cover both runtime generations and keep fixture-specific assertions in unit tests. Assisted-by: GPT-6.1 Sol
123liuziming
changed the title
123liuziming
marked this pull request as ready for review
November 1, 2026 09:34
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
Snapshot capture overwrites valid media content when text and media block indexes collide, causing finished spans and completion hooks to lose content.
1 open issue
What changed in this PR
Extends the existing QwenPaw instrumentation to support the 2.x Runtime.run entry point while retaining 1.x runner support.
Changes:
- Adds lazy runtime tracing, conversation propagation, and streamed message capture.
- Expands unit and conformance coverage across both runtime generations.
- Updates dependency ranges, examples, and documentation for 2.x support.
Paths below are relative to instrumentation/opentelemetry-instrumentation-genai-qwenpaw/, except those marked repository root.
| File | Description |
|---|---|
uv.lock (repository root) |
Updates the supported QwenPaw range. |
tox.ini (repository root) |
Adds version-specific test environments and shared dependency constraints. |
README.md (repository root) |
Updates the instrumentation compatibility table. |
tests/test_runtime.py |
Tests runtime tracing, lifecycle, context, and message capture. |
tests/test_message_mapping.py |
Uses structured user-message content. |
tests/test_instrumentor.py |
Adjusts dependency and instrumentation lifecycle tests. |
tests/test_instrumentation_scope.py |
Removes the legacy-runner fixture requirement. |
tests/test_conformance.py |
Registers error and rich-message scenarios. |
tests/requirements.v2.txt |
Adds the QwenPaw 2.0.0 test dependencies. |
tests/requirements.v1.txt |
Adds latest-1.x test dependencies. |
tests/requirements.oldest.txt |
Uses the unreleased workspace utility package. |
tests/requirements.latest.txt |
Moves latest-version testing to QwenPaw 2.x. |
tests/harness.py |
Adds runtime and request construction helpers. |
tests/conftest.py |
Selects fixtures by runtime generation. |
tests/conformance/runtime_messages.py |
Exercises rich messages through runtime envelopes. |
tests/conformance/runtime_error.py |
Exercises failed turns in both generations. |
tests/conformance/invoke_agent.py |
Supports successful turns in both generations. |
src/opentelemetry/instrumentation/genai/qwenpaw/runtime.py |
Implements lazy runtime tracing and envelope capture. |
src/opentelemetry/instrumentation/genai/qwenpaw/package.py |
Broadens declared QwenPaw compatibility. |
src/opentelemetry/instrumentation/genai/qwenpaw/__init__.py |
Selects and unwraps version-specific instrumentation. |
README.rst |
Documents runtime support, captured content, and test environments. |
pyproject.toml |
Broadens QwenPaw support and raises the utility dependency floor. |
examples/zero-code/requirements.txt |
Updates automatic-instrumentation examples to 2.x. |
examples/manual/requirements.txt |
Updates manual-instrumentation examples to 2.x. |
.changelog/994.added |
Records added 2.x support and retained 1.x compatibility. |
Review effort: Balanced
Distinguish text and media block indexes and preserve snapshot ordering without dropping unfinished content. Cover complete, early-close, and failed streams using real QwenPaw envelopes. Assisted-by: GPT-6.1 Sol
lmolkova
reviewed
Nov 3, 2026
This comment has been minimized.
This comment has been minimized.
Assisted-by: GPT-6.1 Sol
Assisted-by: GPT-6.1 Sol
Assisted-by: GPT-6.1 Sol
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
Heartbeat handling repeatedly decodes unchanged output and completion handling synthesizes unsupported finish reasons, while rich-content tests lack required coverage assertions and public-entry-point verification.
4 open issues
1 resolved since last review
Review effort: Balanced
Comment on lines
+249
to
+251
| if invocation.should_capture_content: | ||
| for message in _items(_field(chunk, "output")): | ||
| self._capture_message(message) |
Comment on lines
+328
to
+329
| if self._self_complete: | ||
| invocation.finish_reasons = ["stop"] |
Comment on lines
+25
to
+27
| class RuntimeMessagesScenario(Scenario): | ||
| expected_spans = {"invoke_agent": 1} | ||
| expected_metrics = ("gen_ai.invoke_agent.duration",) |
Comment on lines
+903
to
+905
| stream = make_runtime_wrapper(handler)( | ||
| events, make_runtime(), (runtime_request(),), {} | ||
| ) |
This branch has not been deployed
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.
Adds QwenPaw 2.x
Runtime.runinstrumentation while retaining 1.xAgentRunner.query_handlersupport. Captures request and streamed message content, preserves lazy execution, and propagates conversation IDs.Follow-up to #969.
Requires unreleased
opentelemetry-util-genai1.4b0. The error conformance scenario declares a known registry gap forgen_ai.invoke_agent.exception, which the util emits but the pinned semantic-conventions registry does not define. The declaration fails once the gap disappears.Validated the unit suites and all 10 Weaver conformance scenarios across QwenPaw 1.1.0, 1.1.12.post3, 2.0.0, and 2.2.2.post1. Pre-commit, README rendering, and type checking pass.