feat(wan22): add WAN 2.2 text-to-video adapter and dataset for MLPerf inference #293
feat(wan22): add WAN 2.2 text-to-video adapter and dataset for MLPerf inference #293wu6u3tw wants to merge 15 commits intomlcommons:mainfrom
Conversation
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces support for the WAN2.2 MLPerf text-to-video benchmark, including a new adapter, dataset loader, and associated Pydantic models. It also adds comprehensive documentation and an example configuration for running benchmarks on Lyris. The review feedback identifies several critical omissions and inconsistencies: the VideoPathRequest and Wan22Dataset are missing the latent_path field required for MLPerf reproducibility, and there is a mismatch between the adapter implementation and unit tests regarding the response_format and handling of VideoPayloadResponse. Additionally, the feedback suggests using None as a default for negative_prompt to allow server-side defaults and injecting the canonical MLPerf negative prompt into the dataset.
wu6u3tw
force-pushed
the
feat/wan22
branch
2 times, most recently
from
b0878b5 to
3230fec
Compare
…er, Wan22Dataset→VideoGenDataset
- Rename src/inference_endpoint/wan22/ → videogen/
- Rename tests/unit/wan22/ → tests/unit/videogen/
- Rename tests/integration/wan22/ → tests/integration/videogen/
- APIType.WAN22 → APIType.VIDEOGEN ("wan22" → "videogen")
- Wan22Adapter → VideoGenAdapter
- Wan22Dataset → VideoGenDataset
- Wan22Accumulator → VideoGenAccumulator
- Update all imports, maps, __all__, tests, docs, and example yaml
- Keep dataset_id="wan22_mlperf" and model_params.name="wan22" (MLPerf identifiers)
…bytes) encode_query: response_format defaults to "video_bytes" but can be overridden via query.data["response_format"] = "video_path" for Lustre-path mode. decode_response: dispatches on response shape — "video_bytes" key → VideoPayloadResponse, otherwise → VideoPathResponse.
There was a problem hiding this comment.
@arekay-nv Quick Q: We don't want to have this jsonl file in the PR, right?
There was a problem hiding this comment.
Here should be fine given that it is relatively small.
arekay-nv
left a comment
arekay-nv
left a comment
There was a problem hiding this comment.
Made a quick pass - will make another later.
There was a problem hiding this comment.
Revert this file to pass pre-commit.
|
|
||
| settings: | ||
| runtime: | ||
| min_duration_ms: 60000 # 1 minute warm-up |
There was a problem hiding this comment.
This isn't the warmup duration as this is counted in the performance runs.
There was a problem hiding this comment.
This shouldn't be needed. Alternatively what would be nice to have here is instructions on which model (HF link) to use and how to launch a server instance as well as the benchmark.
There was a problem hiding this comment.
Here should be fine given that it is relatively small.
There was a problem hiding this comment.
Revert this file as well - likely related to the original datasets folder.
| import pytest | ||
| from aiohttp import web | ||
|
|
||
| DUMMY_VIDEO_PATH = "/lustre/videos/mock_video_001.mp4" |
|
|
||
| @classmethod | ||
| def decode_sse_message(cls, json_bytes: bytes) -> str: | ||
| raise NotImplementedError("WAN 2.2 does not use SSE streaming") |
There was a problem hiding this comment.
Use model name or adapter name here - might be run with a different model.
| WAN 2.2 uses non-streaming HTTP. This class exists only to satisfy | ||
| the HTTPClientConfig.accumulator type contract. | ||
| """ | ||
|
|
||
| def __init__(self, query_id: str, stream_all_chunks: bool) -> None: | ||
| self.query_id = query_id | ||
| # stream_all_chunks is intentionally ignored: WAN 2.2 is non-streaming. |
| DUMMY_VIDEO_BYTES = b"\x00\x00\x00\x20ftypmp42" + b"\x00" * 24 | ||
|
|
||
|
|
||
| class MockTrtllmServe: |
There was a problem hiding this comment.
Is it possible to reuse the existing echo server with a new video-gen route. That will keep things simple and reduce replication.
There was a problem hiding this comment.
Pull request overview
Adds WAN 2.2 text-to-video (trtllm-serve) support to the inference-endpoint client by introducing a new videogen module (adapter + wire types + dataset) and wiring it into the existing endpoint client + dataset loader factory.
Changes:
- Introduce
APIType.VIDEOGENwithVideoGenAdapter/VideoGenAccumulatorand Pydantic request/response wire models forPOST /v1/videos/generations. - Add
VideoGenDatasetregistered as predefined datasetwan22_mlperf, plus unit/integration tests and example offline benchmark config/scripts. - Update dataset factory + templates/docs to recognize the new workload.
Reviewed changes
Copilot reviewed 30 out of 32 changed files in this pull request and generated 14 comments.
Show a summary per file
| File | Description |
|---|---|
| uv.lock | Bumps transformers and adds videogen extras to lock metadata. |
| pyproject.toml | Adds a videogen optional dependency group (currently empty). |
| src/inference_endpoint/videogen/types.py | Adds Pydantic wire models for video generation request/response. |
| src/inference_endpoint/videogen/adapter.py | Adds HTTP adapter + no-op accumulator for non-streaming video endpoint. |
| src/inference_endpoint/videogen/dataset.py | Adds predefined dataset wan22_mlperf (prompt text file loader). |
| src/inference_endpoint/videogen/init.py | Exposes videogen public API symbols. |
| src/inference_endpoint/core/types.py | Registers APIType.VIDEOGEN and default route /v1/videos/generations. |
| src/inference_endpoint/endpoint_client/config.py | Wires adapter/accumulator into ADAPTER_MAP/ACCUMULATOR_MAP. |
| src/inference_endpoint/dataset_manager/factory.py | Modifies predefined dataset loader invocation to pass path=. |
| src/inference_endpoint/dataset_manager/init.py | Imports VideoGenDataset so it registers into Dataset.PREDEFINED. |
| src/inference_endpoint/dataset_manager/dataset.py | Adds mypy ignore on datasets imports. |
| src/inference_endpoint/dataset_manager/predefined/shopify_product_catalogue/init.py | Adds mypy ignore on datasets import. |
| src/inference_endpoint/evaluation/livecodebench/generate.py | Adds mypy ignore on datasets import. |
| src/inference_endpoint/config/templates/online_template_full.yaml | Updates documented api_type options to include videogen. |
| src/inference_endpoint/config/templates/offline_template_full.yaml | Updates documented api_type options to include videogen. |
| src/inference_endpoint/config/templates/concurrency_template_full.yaml | Updates documented api_type options to include videogen. |
| tests/unit/videogen/test_types.py | Unit tests for videogen Pydantic wire models. |
| tests/unit/videogen/test_adapter.py | Unit tests for adapter encode/decode behavior and accumulator contract. |
| tests/unit/videogen/test_dataset.py | Unit tests for dataset loading + sample shaping. |
| tests/unit/videogen/test_factory.py | Unit tests asserting factory can create the videogen predefined dataset. |
| tests/unit/videogen/test_registration.py | Unit tests for enum + adapter/accumulator registration. |
| tests/unit/videogen/test_init.py | Unit tests for videogen module public exports. |
| tests/unit/videogen/init.py | Test package init (licensing header). |
| tests/integration/videogen/conftest.py | Adds aiohttp mock trtllm-serve fixtures for adapter integration tests. |
| tests/integration/videogen/test_adapter.py | Integration tests for encode→POST→decode round-trip and error cases. |
| tests/integration/videogen/init.py | Test package init (licensing header). |
| examples/09_Wan22_VideoGen_Example/offline_wan22.yaml | Example offline benchmark config targeting videogen endpoint. |
| examples/09_Wan22_VideoGen_Example/setup_and_test.sh | Example script to set up venv and run videogen tests. |
| examples/09_Wan22_VideoGen_Example/wan22_prompts.jsonl | Bundled 248-prompt dataset artifact for the example benchmark. |
| endpoints_changed.md | Design summary / documentation for WAN2.2 videogen integration. |
| AGENTS.md | Adds videogen module to repo architecture documentation. |
| .gitignore | Ignores .worktrees/. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| - http://localhost:8000 | ||
| api_key: null # API key | ||
| api_type: openai # API type: openai or sglang | options: openai, sglang | ||
| api_type: openai # API type: openai or sglang | options: openai, sglang, videogen |
There was a problem hiding this comment.
The inline comment still says “API type: openai or sglang” even though videogen is now supported. Update the comment text to avoid contradicting the listed options.
| api_type: openai # API type: openai or sglang | options: openai, sglang, videogen | |
| api_type: openai # API type: openai, sglang, or videogen | options: openai, sglang, videogen |
| - http://localhost:8000 | ||
| api_key: null # API key | ||
| api_type: openai # API type: openai or sglang | options: openai, sglang | ||
| api_type: openai # API type: openai or sglang | options: openai, sglang, videogen |
There was a problem hiding this comment.
The inline comment still says “API type: openai or sglang” even though videogen is now supported. Update the comment text to avoid contradicting the listed options.
| api_type: openai # API type: openai or sglang | options: openai, sglang, videogen | |
| api_type: openai # API type: openai, sglang, or videogen | options: openai, sglang, videogen |
| # exclude_none so optional fields fall back to server-side defaults | ||
| # (MLPerf: omit negative_prompt and latent_path unless explicitly set). |
There was a problem hiding this comment.
The comment here says “MLPerf: omit negative_prompt and latent_path unless explicitly set”, but this PR’s VideoGenDataset injects the MLPerf canonical negative_prompt by default (i.e., it is explicitly set for the common path). Consider rewording this comment to reflect the actual behavior: fields are omitted only when their value is None in query.data.
| # exclude_none so optional fields fall back to server-side defaults | |
| # (MLPerf: omit negative_prompt and latent_path unless explicitly set). | |
| # exclude_none so optional fields with value None fall back to | |
| # server-side defaults. In particular, negative_prompt and | |
| # latent_path are omitted only when their value in query.data is None. |
| return ds_cls.get_dataloader( | ||
| transforms=preset_transforms, | ||
| num_repeats=num_repeats, | ||
| path=dataset_path, | ||
| **kwargs, |
There was a problem hiding this comment.
DataLoaderFactory now always passes path=dataset_path into ds_cls.get_dataloader(...) for all predefined datasets. Most predefined datasets use the base Dataset.get_dataloader(), which forwards **kwargs into cls.generate(...); many generate() implementations (e.g. AIME25/CNNDailyMail/GPQA/OpenOrca) do not accept a path kwarg, so this will raise TypeError: generate() got an unexpected keyword argument 'path' whenever those datasets are loaded. Consider only passing path for dataset classes that explicitly accept it (e.g. VideoGenDataset), or mapping config.path to the existing datasets_dir parameter instead of introducing a new kwarg.
| query = Query(id="q1", data={"prompt": "a golden retriever running on a beach"}) | ||
| request_bytes = VideoGenAdapter.encode_query(query) | ||
|
|
||
| status, content = _post( | ||
| f"{mock_trtllm_serve.url}/v1/videos/generations", request_bytes | ||
| ) | ||
| assert status == 200 | ||
|
|
||
| result = VideoGenAdapter.decode_response(content, query.id) | ||
| assert result.id == "q1" | ||
| assert result.error is None | ||
| assert "video_bytes" in result.metadata | ||
| decoded = base64.b64decode(result.metadata["video_bytes"]) | ||
| assert decoded == DUMMY_VIDEO_BYTES |
There was a problem hiding this comment.
This integration test asserts that a default request returns video_bytes, but VideoGenAdapter.encode_query() defaults response_format to video_path. As written, the test only passes because the mock server always returns video_bytes, so it doesn’t reflect real server behavior. Either set response_format='video_bytes' in query.data for this test, or change the mock + assertions to expect video_path for the default case (and add a separate test for the video_bytes path).
| datasets: | ||
| - name: wan22_prompts | ||
| path: examples/09_Wan22_VideoGen_Example/wan22_prompts.jsonl | ||
| format: jsonl | ||
| type: "performance" | ||
| samples: 248 | ||
|
|
There was a problem hiding this comment.
This YAML says WAN2.2 MLPerf params are baked into VideoGenAdapter defaults and “only prompt is required from the dataset”, but the configured dataset is a JSONL file that (as provided) includes extra fields like negative_prompt/mode. Those fields will be forwarded into query.data and can override adapter defaults (e.g., empty negative_prompt). Consider either switching the example to wan22_mlperf (text prompts) so the adapter truly only receives prompt, or trimming the JSONL to only the fields you intend to send.
| # Fixed latent path is injected into every request via VideoGenDataset. | ||
| # Set latent_path in dataset config or pass it when constructing VideoGenDataset. |
There was a problem hiding this comment.
These comments state that a fixed latent path is injected “via VideoGenDataset”, but this example configuration does not use the predefined wan22_mlperf/VideoGenDataset loader (it loads a JSONL file directly). As a result, latent_path will not be injected unless it is explicitly present in the JSONL or added via a transform. Update the comments (or the dataset config) so the example reflects the actual injection mechanism.
| # Fixed latent path is injected into every request via VideoGenDataset. | |
| # Set latent_path in dataset config or pass it when constructing VideoGenDataset. | |
| # This example loads prompts directly from JSONL and does not use | |
| # `VideoGenDataset`, so `latent_path` is not injected automatically here. | |
| # If required, include `latent_path` in the JSONL or add it via a transform. |
| return web.json_response( | ||
| { | ||
| "video_id": video_id, | ||
| "video_bytes": base64.b64encode(DUMMY_VIDEO_BYTES).decode(), | ||
| } | ||
| ) | ||
|
|
||
|
|
There was a problem hiding this comment.
MockTrtllmServe claims to support both response_format='video_path' and 'video_bytes', but _handle_sync() always returns a payload containing video_bytes and never returns video_path (nor does it inspect the request’s response_format). This makes the integration suite unable to validate the adapter’s video_path decode branch and can mask regressions. Update the handler to branch on body.get('response_format') and return video_path when requested.
| return web.json_response( | |
| { | |
| "video_id": video_id, | |
| "video_bytes": base64.b64encode(DUMMY_VIDEO_BYTES).decode(), | |
| } | |
| ) | |
| response_format = body.get("response_format") | |
| response_body = {"video_id": video_id} | |
| if response_format == "video_path": | |
| response_body["video_path"] = DUMMY_VIDEO_PATH | |
| else: | |
| response_body["video_bytes"] = base64.b64encode(DUMMY_VIDEO_BYTES).decode() | |
| return web.json_response(response_body) |
| ▼ | ||
| HTTPEndpointClient | ||
| │ | ||
| │ selects adapter via APIType.WAN22 |
There was a problem hiding this comment.
The design doc refers to APIType.WAN22, but the implementation added in this PR is APIType.VIDEOGEN. This mismatch is likely to confuse readers and makes the doc inaccurate; update the diagram/text to match the actual enum value and wiring.
| │ selects adapter via APIType.WAN22 | |
| │ selects adapter via APIType.VIDEOGEN |
| videogen/ | ||
| ├── __init__.py Public exports | ||
| ├── types.py Pydantic wire models: VideoPathRequest, | ||
| │ VideoPathResponse, VideoPayloadResponse, HealthResponse |
There was a problem hiding this comment.
The “New Files” section lists a HealthResponse type in videogen/types.py, but no such model is implemented/exported in this PR. Either add the missing type or remove it from the document to keep the doc accurate.
| │ VideoPathResponse, VideoPayloadResponse, HealthResponse | |
| │ VideoPathResponse, VideoPayloadResponse |
After rebasing onto origin/main, these files needed updates from: - ruff lint/format (test imports, line wrapping) - prettier (markdown table formatting, YAML alignment) - regenerate-templates (api_type docstring now lists "videogen") - uv lock refresh (pyproject.toml now has "videogen" optional group) Also tightens an over-broad pytest.raises(Exception) in the videogen integration tests to (ValidationError, json.JSONDecodeError) for the 500-response case and json.JSONDecodeError for the malformed-JSON case (B017).
…t_path Address MR review feedback (Task 3 of wan22-trtllm-plan.md): types.py: - VideoPathRequest.negative_prompt: str = "" -> str | None = None - Add VideoPathRequest.latent_path: str | None = None field (per-request fixed latent tensor path for MLPerf reproducibility) adapter.py: - encode_query: read negative_prompt and latent_path with .get() (no default), and serialise with model_dump_json(exclude_none=True) so optional fields fall back to server-side defaults when absent. dataset.py: - Add _MLPERF_NEGATIVE_PROMPT module constant (canonical MLPerf string). - VideoGenDataset injects this negative prompt into every sample by default; pass negative_prompt=None to omit. Accepts latent_path as a per-dataset config so all samples share the same fixed latent. - load() conditionally includes negative_prompt and latent_path in each sample dict only when set, so adapter exclude_none does the right thing end-to-end. Tests: - Update test_types defaults (negative_prompt None, latent_path None) - Update test_dataset for the canonical negative-prompt default, add coverage for negative_prompt=None and latent_path propagation. - Add adapter tests for exclude_none behaviour and latent_path forwarding. Note for reviewer: the other two review comments (response_format hardcoded to video_path; decode_response only handling VideoPathResponse) are stale; both were addressed in 7a1b4d3 "fix: make response_format optional in VideoGenAdapter (default video_bytes)". Current adapter already defaults response_format to video_bytes and dispatches in decode_response on whether "video_bytes" is present in the response.
Aligns three previously-inconsistent statements about the request default:
- Adapter `encode_query` previously fell back to "video_bytes" when
query.data did not specify a response_format, but the Pydantic field
default on VideoPathRequest was "video_path" — the latter was dead
because the adapter always supplied a value.
- Dataset docstring claimed "always requests video_bytes"; types
docstring described a perf/accuracy split.
Pick the perf/accuracy split (Option A): default = video_path (perf),
opt-in to video_bytes via query.data["response_format"] (accuracy).
- adapter.py: flip `data.get("response_format", ...)` default to
"video_path"; rewrite class + encode_query docstrings to match.
- dataset.py: drop the "always requests video_bytes" line.
- test_adapter.py (unit + integration): split the old
test_encode_query_always_requests_video_bytes test into
default-is-video_path + accuracy-mode-override tests.
Also rewrite endpoints_changed.md:
- Replace the "always video_path" framing with the dual-mode reality.
- Document VideoPayloadResponse and the decode_response shape dispatch.
- Fix the payload-size claim (300 MB -> 3-5 MB; 300 MB was raw uncompressed).
- Drop stale "Pending" tasks 2 (latent_path -- already wired) and 3
(negative_prompt None -- already done).
- Update module name `wan22` -> `videogen` and `api_type` example.
Verified on aarch64 GB200: 58 unit+integration videogen tests pass.
…wan22 refs
Move datasets/wan22_prompts.jsonl into the example folder so the example
is self-contained and drop the absolute Lustre path baked into the setup
script.
setup_and_test.sh:
- Remove PROMPTS_TXT (hardcoded /lustre/share/... path) and the entire
prompts.txt -> JSONL conversion block. The JSONL is now bundled with
the example, so regeneration from a Lustre source is no longer needed.
- Retarget PROMPTS_JSONL to ${SCRIPT_DIR}/wan22_prompts.jsonl.
- Drop the now-orphaned PYTHON variable (only used by the conversion
heredoc).
- Fix stale post-rename references that were left over from
ddac990 (wan22 -> videogen): pip extras [wan22,test] -> [videogen,test]
and test paths tests/unit/wan22 / tests/integration/wan22 ->
tests/unit/videogen / tests/integration/videogen. Without these the
script failed on a fresh setup (no [wan22] extra) and collected zero
tests.
offline_wan22.yaml: dataset path -> examples/09_Wan22_VideoGen_Example/wan22_prompts.jsonl.
endpoints_changed.md: update bundled-dataset path reference.
…ader
VideoGenDataset duplicated functionality the generic JsonlLoader already
provides, was bugged on JSONL input (read each line as a raw text prompt
instead of parsing JSON), and wasn't actually invoked by the example
config: offline_wan22.yaml uses `name: wan22_prompts`, which doesn't
match its dataset_id (`wan22_mlperf`), so DataLoaderFactory already
routed to JsonlLoader. The class was dead code in the only path the
example exercises.
Bake the MLPerf canonical negative_prompt into every row of the bundled
JSONL so runtime injection is unnecessary, then delete the workload-
specific dataset class.
- examples/09_Wan22_VideoGen_Example/wan22_prompts.jsonl: replace
empty negative_prompt with canonical MLPerf string in all 248 rows.
- src/inference_endpoint/videogen/dataset.py: deleted.
- src/inference_endpoint/dataset_manager/__init__.py: drop the
side-effect VideoGenDataset import and __all__ entry.
- tests/unit/videogen/test_dataset.py, test_factory.py: deleted.
- src/inference_endpoint/videogen/types.py: update negative_prompt
field docstring to point at the bundled JSONL instead of
VideoGenDataset.
- examples/09_Wan22_VideoGen_Example/offline_wan22.yaml: drop
`format: jsonl` (the factory tries DatasetFormat("jsonl") and
crashes because enum values are `.jsonl`; auto-detection from the
path extension works), and update the comment block.
- endpoints_changed.md: replace the dataset.py / VideoGenDataset
section with a brief note about the bundled JSONL + JsonlLoader.
Verified on aarch64 GB200:
- pre-commit run --all-files: all hooks pass
- 42 videogen tests pass (down from 58: 14 dataset tests + 3 factory
tests removed; adapter/types/init/registration tests retained)
- end-to-end smoke: DataLoaderFactory creates a Dataset with 248
samples, each carrying prompt + canonical negative_prompt;
VideoGenAdapter.encode_query produces a valid request with
response_format=video_path.
The `metrics:` top-level block was rejected by `BenchmarkConfig` (extra="forbid", no `metrics` field in the schema), so loading the YAML via `BenchmarkConfig.from_yaml_file()` failed validation. The block had no effect on metrics collection — that's controlled by `settings.runtime` and the metrics aggregator service. Caught by an end-to-end functional smoke test that loads the YAML, runs encode → POST → decode against an inline mock trtllm-serve in both perf (video_path) and accuracy (video_bytes) modes, and bulk- encodes all 248 samples.
… simplify adapter, broaden tests Five small fixes from a pre-review pass: - factory.py: drop `path=dataset_path` kwarg on the predefined-dataset branch. It was added in 9ded0e6 to feed VideoGenDataset (since deleted in 6ce6bfa); none of the remaining predefined datasets' generate() signatures accept `path`, so any user passing both `name=<predefined>` and `path=<file>` would TypeError. Restores the pre-9ded0e6 behavior. Verified the videogen example still loads end-to-end (it routes through Dataset.load_from_file, not the predefined branch). - adapter.py encode_query: replace the 12-line data.get() boilerplate with `VideoPathRequest.model_validate({k: data[k] for k in known if k in data})`. Pydantic applies defaults, eliminating the drift risk between adapter.py and types.py. Extra keys in query.data (sample_id, sample_index, mode, ...) are now ignored cleanly. - integration mock: MockTrtllmServe._handle_sync now honors body["response_format"] and routes to a VideoPathResponse when the request asks for video_path. Previously the mock always returned video_bytes regardless of the request, so the integration tests never exercised the perf-mode decode branch end-to-end. - integration tests: add test_perf_mode_round_trip_returns_video_path asserting result.metadata == {video_path: ...} via real HTTP. Rename the renamed counterpart to test_accuracy_mode_round_trip_returns_video_bytes. Replace the misleadingly named test_missing_video_bytes_field_raises_validation_error with two targeted tests, one per decode dispatch branch. - endpoints_changed.md: drop two stale references — `HealthResponse` (never existed in types.py) and `APIType.WAN22` (the actual enum is APIType.VIDEOGEN). Trim the doc from 155 → 84 lines (~46% reduction) by collapsing the architecture diagram and removing repetition; factual content is unchanged. Verified on aarch64 GB200: - pre-commit run --all-files: all hooks pass - 43 videogen tests pass (one new perf-mode round-trip test added) - end-to-end smoke (load YAML → factory → JsonlLoader → adapter → mock server) passes both perf and accuracy modes; encode_query ignores extra keys cleanly
Summary
wan22module withWan22Adapter,Wan22Accumulator,Wan22Dataset, and Pydantic wire types for the trtllm-servePOST /v1/videos/generationsendpoint.Wan22Adapterusesresponse_format=video_path: the server saves the encoded video to shared storage (Lustre) and returns only the file path, avoiding 3–5 MB of base64 video bytes per request overHTTP and ZMQ transport.
Wan22Datasetloads MLPerf WAN2.2 prompt text files (one prompt per line); dataset IDwan22_mlperfis registered withDataLoaderFactoryfor--datasetCLI use.APIType.WAN22and wiresWan22Adapter/Wan22AccumulatorintoHTTPClientConfig.with_updates()to reset adapter and accumulator whenapi_typechanges.Test plan
pytest -m unit tests/unit/wan22/— adapter, dataset, factory, types, init, registration unit testspytest -m integration tests/integration/wan22/— adapter round-trip with mock serverpre-commit run --all-filespasses cleanWhat does this PR do?
Type of change
Related issues
Testing
Checklist