[None][fixes] Add tool call parsing fixes and Qwen3 coder parser #8817
Conversation
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
025b056 to
a76dea0
Compare
|
verified it can work well with nano-v3, thanks for the help! |
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
a76dea0 to
c5385a0
Compare
📝 WalkthroughWalkthroughAdds a new Qwen3 Coder tool parser with streaming support for parsing structured tool-call blocks, normalizes JSON tool call arguments in assistant messages, enables extra fields in protocol messages, enhances test infrastructure for tool parsers, and includes comprehensive test coverage for chat message parsing. Changes
Sequence Diagram(s)sequenceDiagram
actor User
participant QwenParser as Qwen3CoderToolParser
participant State as Streaming State
participant Output as Result
User->>QwenParser: parse_streaming_increment(text_chunk)
QwenParser->>QwenParser: _extract(text_chunk)
note over QwenParser: Split normal text from<br/><tool_call> blocks
QwenParser->>QwenParser: _parse_block(tool_call_block)
note over QwenParser: Reconstruct tool name<br/>and arguments
QwenParser->>State: Track function name,<br/>parameters, content
QwenParser->>QwenParser: _parse_and_stream_parameters()
note over QwenParser: Extract <parameter> blocks,<br/>convert values, diff against<br/>current parameters
QwenParser->>Output: Emit ToolCallItem objects<br/>with incremental JSON fragments
QwenParser->>Output: Return (normalized_text, tool_calls)
Output-->>User: Streaming output
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 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: 4
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (8)
tensorrt_llm/serve/chat_utils.py(2 hunks)tensorrt_llm/serve/openai_protocol.py(1 hunks)tensorrt_llm/serve/openai_server.py(1 hunks)tensorrt_llm/serve/tool_parser/qwen3_coder_parser.py(1 hunks)tensorrt_llm/serve/tool_parser/tool_parser_factory.py(1 hunks)tests/integration/test_lists/test-db/l0_a10.yml(1 hunks)tests/unittest/llmapi/apps/test_chat_utils.py(1 hunks)tests/unittest/llmapi/apps/test_tool_parsers.py(8 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use only spaces, no tabs; indent with 4 spaces.
Files:
tensorrt_llm/serve/openai_protocol.pytensorrt_llm/serve/openai_server.pytests/unittest/llmapi/apps/test_chat_utils.pytensorrt_llm/serve/tool_parser/qwen3_coder_parser.pytests/unittest/llmapi/apps/test_tool_parsers.pytensorrt_llm/serve/chat_utils.pytensorrt_llm/serve/tool_parser/tool_parser_factory.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.
Files:
tensorrt_llm/serve/openai_protocol.pytensorrt_llm/serve/openai_server.pytests/unittest/llmapi/apps/test_chat_utils.pytensorrt_llm/serve/tool_parser/qwen3_coder_parser.pytests/unittest/llmapi/apps/test_tool_parsers.pytensorrt_llm/serve/chat_utils.pytensorrt_llm/serve/tool_parser/tool_parser_factory.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).
Files:
tensorrt_llm/serve/openai_protocol.pytensorrt_llm/serve/openai_server.pytests/unittest/llmapi/apps/test_chat_utils.pytensorrt_llm/serve/tool_parser/qwen3_coder_parser.pytests/unittest/llmapi/apps/test_tool_parsers.pytensorrt_llm/serve/chat_utils.pytensorrt_llm/serve/tool_parser/tool_parser_factory.py
🧠 Learnings (5)
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 Learning: 2025-08-06T13:58:07.506Z
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.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 Learning: 2025-10-22T06:53:47.017Z
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.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 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.yml
🧬 Code graph analysis (5)
tensorrt_llm/serve/openai_server.py (1)
tensorrt_llm/logger.py (1)
debug(144-145)
tests/unittest/llmapi/apps/test_chat_utils.py (1)
tensorrt_llm/serve/chat_utils.py (1)
parse_chat_message_content(170-193)
tensorrt_llm/serve/tool_parser/qwen3_coder_parser.py (3)
tensorrt_llm/serve/openai_protocol.py (1)
ChatCompletionToolsParam(492-494)tensorrt_llm/serve/tool_parser/base_tool_parser.py (3)
BaseToolParser(16-324)_get_tool_indices(43-60)parse_base_json(62-86)tensorrt_llm/serve/tool_parser/core_types.py (2)
StreamingParseResult(16-20)ToolCallItem(8-13)
tests/unittest/llmapi/apps/test_tool_parsers.py (5)
tensorrt_llm/serve/openai_protocol.py (2)
ChatCompletionToolsParam(492-494)FunctionDefinition(486-489)tensorrt_llm/serve/tool_parser/base_tool_parser.py (4)
BaseToolParser(16-324)has_tool_call(302-306)detect_and_parse(89-96)parse_streaming_increment(111-299)tensorrt_llm/serve/tool_parser/core_types.py (1)
StructureInfo(24-27)tensorrt_llm/serve/tool_parser/qwen3_coder_parser.py (4)
Qwen3CoderToolParser(28-346)has_tool_call(62-63)detect_and_parse(65-68)parse_streaming_increment(70-198)tensorrt_llm/serve/tool_parser/qwen3_tool_parser.py (4)
has_tool_call(39-41)detect_and_parse(43-70)parse_streaming_increment(72-107)Qwen3ToolParser(13-114)
tensorrt_llm/serve/tool_parser/tool_parser_factory.py (3)
tensorrt_llm/serve/tool_parser/qwen3_coder_parser.py (1)
Qwen3CoderToolParser(28-346)tensorrt_llm/serve/tool_parser/qwen3_tool_parser.py (1)
Qwen3ToolParser(13-114)tensorrt_llm/serve/tool_parser/base_tool_parser.py (1)
BaseToolParser(16-324)
🪛 Ruff (0.14.3)
tensorrt_llm/serve/tool_parser/qwen3_coder_parser.py
21-21: Do not catch blind exception: Exception
(BLE001)
24-24: Do not catch blind exception: Exception
(BLE001)
43-43: Possible hardcoded password assigned to: "tool_call_start_token"
(S105)
44-44: Possible hardcoded password assigned to: "tool_call_end_token"
(S105)
338-338: Do not catch blind exception: Exception
(BLE001)
tests/unittest/llmapi/apps/test_tool_parsers.py
519-519: Possible hardcoded password assigned to argument: "parse_streaming_increment_partial_bot_token"
(S106)
526-526: Possible hardcoded password assigned to: "bot_token"
(S105)
527-527: Possible hardcoded password assigned to: "eot_token"
(S105)
697-697: Possible hardcoded password assigned to argument: "parse_streaming_increment_partial_bot_token"
(S106)
774-774: Unused method argument: sample_tools
(ARG002)
⏰ 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
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
2 times, most recently
from
2ec881c to
c7b630d
Compare
|
/bot run |
|
PR_Github #23822 [ run ] triggered by Bot. Commit: |
|
PR_Github #23822 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
c7b630d to
31b86a0
Compare
|
/bot run |
|
PR_Github #23882 [ run ] triggered by Bot. Commit: |
|
PR_Github #23882 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
31b86a0 to
84c97c6
Compare
|
/bot run |
|
PR_Github #23906 [ run ] triggered by Bot. Commit: |
|
PR_Github #23906 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
84c97c6 to
67267d1
Compare
|
/bot run |
|
PR_Github #23969 [ run ] triggered by Bot. Commit: |
|
PR_Github #23969 [ run ] completed with state |
|
/bot run |
|
PR_Github #24034 [ run ] triggered by Bot. Commit: |
|
PR_Github #24034 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
67267d1 to
cdf7637
Compare
|
/bot run |
|
PR_Github #24050 [ run ] triggered by Bot. Commit: |
|
PR_Github #24050 [ run ] completed with state |
|
/bot run |
|
PR_Github #24101 [ run ] triggered by Bot. Commit: |
|
PR_Github #24101 [ run ] completed with state |
Signed-off-by: William Zhang <[email protected]>
2ez4bz
force-pushed
the
dev-qwen3-coder-tool
branch
from
cdf7637 to
9a1532b
Compare
|
/bot run |
|
PR_Github #24216 [ run ] triggered by Bot. Commit: |
|
PR_Github #24216 [ run ] completed with state |
|
/bot run |
|
PR_Github #24248 [ run ] triggered by Bot. Commit: |
|
PR_Github #24248 [ run ] completed with state |
|
/bot run |
|
PR_Github #24320 [ run ] triggered by Bot. Commit: |
|
PR_Github #24320 [ run ] completed with state |
|
/bot run |
|
PR_Github #24398 [ run ] triggered by Bot. Commit: |
|
PR_Github #24398 [ run ] completed with state |
|
|
…DIA#8817) Signed-off-by: William Zhang <[email protected]>
…DIA#8817) Signed-off-by: William Zhang <[email protected]>
4 participants
Summary by CodeRabbit
New Features
Tests
[None][fixes] Add tool call parsing fixes and Qwen3 coder parser
This commit:
TODO:
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
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.