[TRTLLM-8462][feat] Support GET/DELETE v1/responses/{response_id} #9937
Conversation
Signed-off-by: Junyi Xu <[email protected]>
|
/bot run |
|
PR_Github #27968 [ run ] triggered by Bot. Commit: |
📝 WalkthroughWalkthroughThe pull request introduces two new API endpoints (GET and DELETE) for retrieving and managing stored OpenAI responses. The OpenAI server now exposes these endpoints with corresponding handlers, while the response storage layer is upgraded from synchronous to asynchronous operations with support for targeted response deletion. Comprehensive integration and unit tests are added to validate the new functionality. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
tests/integration/defs/test_e2e.py (1)
1-2: Update NVIDIA copyright year to include 2025 (file modified in this PR).
As per coding guidelines.tensorrt_llm/serve/responses_utils.py (2)
200-209: Type contract mismatch:load_response()can returnNonebut return type is non-optional.
This change makes-> Optional[ResponsesResponse]the correct signature.- async def load_response(self, resp_id: str) -> ResponsesResponse: + async def load_response(self, resp_id: str) -> Optional[ResponsesResponse]: _responses_debug_log( f"ConversationHistoryStore loading resp: {resp_id}") async with self.responses_lock: if resp_id not in self.responses: return None
210-267: Avoid mutable default arg and guard against missingprev_resp_idunder concurrent DELETE.
With DELETE added,prev_resp_idcan disappear between request validation andstore_response(), causing a KeyError at Line 252. Alsoresp_msgs=[]is a shared default.async def store_response(self, resp: ResponsesResponse, - resp_msgs: Optional[ - Union[list[Message], - list[ChatCompletionMessageParam]]] = [], + resp_msgs: Optional[ + Union[list[Message], + list[ChatCompletionMessageParam]]] = None, prev_resp_id: Optional[str] = None) -> None: @@ - async with self.responses_lock: + resp_msgs = [] if resp_msgs is None else resp_msgs + + async with self.responses_lock: self.responses[resp_id] = resp if len(self.responses) > self.response_capacity: await self._pop_response() @@ elif prev_resp_id is not None: - if prev_resp_id not in self.response_to_conversation: - logger.warning( - f"Previous response id {prev_resp_id} not found in conversation store" - ) - - conversation_id = self.response_to_conversation[prev_resp_id] + conversation_id = self.response_to_conversation.get(prev_resp_id) + if conversation_id is None: + logger.warning( + f"Previous response id {prev_resp_id} not found in conversation store; starting a new conversation" + ) + conversation_id = _random_uuid() + self.conversations[conversation_id] = [] self.conversations[conversation_id].extend(resp_msgs)
🧹 Nitpick comments (2)
tensorrt_llm/serve/openai_server.py (1)
1023-1054: Prefer a public store API for deletes + align invalid-id message withresp_check.
CallingConversationHistoryStore._pop_response()fromOpenAIServercouples to internals; considerconversation_store.delete_response(resp_id)wrapper. Also_create_invalid_response_id_error()says “begins with 'resp'” but you enforceresp_.def _create_invalid_response_id_error(self, response_id: str) -> Response: return self.create_error_response( err_type="InvalidRequestError", message=(f"Invalid 'response_id': '{response_id}'. " - "Expected an ID that begins with 'resp'."), + "Expected an ID that begins with 'resp_'."), )tests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py (1)
37-46: Nice: validates retrieve returns the stored response (id + full payload).
Optional: consider a less strict comparison than fullmodel_dump()if this becomes flaky across SDK/server versions (e.g., compare stable fields only).
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
tensorrt_llm/serve/openai_server.py(2 hunks)tensorrt_llm/serve/responses_utils.py(3 hunks)tests/integration/defs/test_e2e.py(1 hunks)tests/integration/test_lists/test-db/l0_a10.yml(1 hunks)tests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM should conform to Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Always maintain the namespace when importing in Python, even if only one class or function from a module is used (e.g., usefrom package.subpackage import fooand thenfoo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python class names should use PascalCase (e.g.,class SomeClass)
Python function and method names should use snake_case (e.g.,def my_awesome_function():)
Python local variable names should use snake_case, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile = ...)
Python global variables should use upper snake_case with prefixG(e.g.,G_MY_GLOBAL = ...)
Python constants should use upper snake_case (e.g.,MY_CONSTANT = ...)
Avoid shadowing variables declared in an outer scope in Python
Initialize all externally visible members of a Python class in the constructor
For Python interfaces that may be used outside a file, prefer docstrings over comments
Python comments should be reserved for code within a function, or interfaces that are local to a file
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description (e.g.,self.x = 5followed by"""<type>: Description of 'x'""")
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of specific errors possible instead of catching all exceptions
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible and use the else block to implement the logic
Files:
tests/integration/defs/test_e2e.pytensorrt_llm/serve/openai_server.pytensorrt_llm/serve/responses_utils.pytests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the top
Files:
tests/integration/defs/test_e2e.pytensorrt_llm/serve/openai_server.pytensorrt_llm/serve/responses_utils.pytests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/integration/defs/test_e2e.pytests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py
🧬 Code graph analysis (1)
tensorrt_llm/serve/openai_server.py (1)
tensorrt_llm/serve/responses_utils.py (2)
load_response(200-208)_pop_response(403-428)
🪛 Ruff (0.14.8)
tests/integration/defs/test_e2e.py
1656-1656: Unused function argument: llm_root
(ARG001)
tests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py
72-72: Unused function argument: model
(ARG001)
78-78: Unused function argument: model
(ARG001)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (3)
tests/integration/test_lists/test-db/l0_a10.yml (1)
55-69: Good coverage wiring: new Responses API e2e is now exercised in pre-merge.tensorrt_llm/serve/openai_server.py (1)
246-274: Route wiring for GET/DELETE on/v1/responses/{response_id}looks correct.tests/unittest/llmapi/apps/_test_openai_responses_entrypoint.py (1)
1-8: Add NVIDIA copyright header (include 2025) to new Python file.
As per coding guidelines for**/*.py.⛔ Skipped due to learnings
Learnt from: galagam Repo: NVIDIA/TensorRT-LLM PR: 6487 File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12 Timestamp: 2025-08-06T13:58:07.506Z Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.Learnt from: xinhe-nv Repo: NVIDIA/TensorRT-LLM PR: 8534 File: scripts/format_test_list.py:1-6 Timestamp: 2025-10-22T06:53:47.017Z Learning: The file `scripts/format_test_list.py` in the TensorRT-LLM repository does not require the NVIDIA Apache-2.0 copyright header.Learnt from: CR Repo: NVIDIA/TensorRT-LLM PR: 0 File: CODING_GUIDELINES.md:0-0 Timestamp: 2025-11-24T17:09:17.870Z Learning: Applies to **/*.{cpp,h,cu,py} : All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the topLearnt from: EmmaQiaoCh Repo: NVIDIA/TensorRT-LLM PR: 7370 File: tests/unittest/trt/model_api/test_model_quantization.py:24-27 Timestamp: 2025-08-29T14:07:45.863Z Learning: In TensorRT-LLM's CI infrastructure, pytest skip markers (pytest.mark.skip) are properly honored even when test files have __main__ blocks that call test functions directly. The testing system correctly skips tests without requiring modifications to the __main__ block execution pattern.
Signed-off-by: Junyi Xu <[email protected]>
|
/bot run |
|
PR_Github #27973 [ run ] triggered by Bot. Commit: |
|
PR_Github #27968 [ run ] completed with state |
|
PR_Github #27973 [ run ] completed with state |
|
/bot run |
|
PR_Github #28015 [ run ] triggered by Bot. Commit: |
|
PR_Github #28015 [ run ] completed with state |
|
/bot run |
|
PR_Github #28091 [ run ] triggered by Bot. Commit: |
|
PR_Github #28091 [ run ] completed with state |
2 participants
Summary by CodeRabbit
New Features
Tests
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Support openai described entrypoints. Ref: https://platform.openai.com/docs/api-reference/responses
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.