Repository navigation
[fix] reject video changelog entries without scenario-type / [fix] 拒绝缺少 scenario-type 的视频 changelog 条目 - #4848
Conversation
|
Generally most InferenceX submissions don't need to add changes to the infx package. On the off chance they do, generally the diff is small. Please prompt your agent to clean your PR to keep your diff to only necessary & minimal changes too. We have an increased code quality bar for changes to the infx package. 中文大多数 InferenceX 提交通常不需要修改 infx 包。即使确实需要,改动通常也很小。请让你的 agent 清理 PR,使改动只包含必要且最小的内容。infx 包的改动有更高的代码质量要求。 |
There was a problem hiding this comment.
Beyond the inline findings, I also checked whether the new master_config[c]["scenarios"] lookup in plan.py can raise KeyError. It can't: the head master config is loaded with validation on (plan.py:354), and scenarios is a required field in both the single-node and multi-node schemas (validation.py:1066 and 1106).
Extended reasoning...
The change adds a scenario-type guard to build_plan in inferencex-e2e/infx/matrix/plan.py, along with a test and a docs note. The direct scenarios lookup was ruled out as a KeyError risk because build_plan validates the head config before it reaches the guard, and the schema requires that field.
Summary
Video sweeps are opt-in: a
perf-changelog.yamlentry plans video jobs only when itsscenario-typelistsvideo-generation. An entry that named a*-videoconfig but left video out, either by omittingscenario-typeor by listing only LLM scenarios, still validated and planned an empty sweep, so a contributor would get a green run that measured nothing.build_plannow rejects an entry when a config it names explicitly hasvideo-generationand shares no scenario with the entry's selection. The message names those configs and, when the entry also covers other configs, says to keepfixed-seq-lenandagentic-codingso their jobs are not dropped. Wildcard matches such as"*"keep skipping video as before, and every non-video entry plans exactly as on main. The video contribution steps ininferencex-e2e/docs/video-generation.mdstate the requirement.Testing: the new
test_video_matrix.pycase covers an omitted and an LLM-onlyscenario-type(both fail on main with no error and an empty plan) and a"*"entry that must still plan. The rest ofinfx/tests/matrix/passes apart from the threetest_revision.pybatch-generation cases that fail in this sandbox on every branch. With real configs, #2916's entry still yields its two H100/B200 video jobs and fails with the new message oncescenario-typeis removed; a"*"entry's plan (1055 single-node rows, no video) and 81 non-video changelog plans are byte-identical to main. Planner and docs only:infx.matrix.changedlists no config keys, so there is no changelog entry and no sweep.PR checklist and change type
Type of Change
Checklist
python -m infx.matrix.changed --base origin/mainlists affected config keys, I have appended one new entry covering them to the physical end ofinferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entriesinferencex-e2e/perf-changelog.yamlentry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs):full-sweep-fail-fast(recommended),full-sweep-enabled, ornon-canary-full-sweep-enabled. Optional modifiersall-evals,evals-only, andagentx-fastrequire a primary label; the last two block reuse while applied.OWNER/MEMBER/COLLABORATOR) has commented/use <run_id>(or the legacy/reuse-sweep-run) on this PR. Do this only once there is a final full sweep that is all green with evals passing, since after this comment the primary sweep label will no longer automatically kick off new sweeps. Remove and re-add the primary sweep label to force a new sweep.