Scope RunInference model_identifier annotation and preserve ModelManager metric_tag across model updates

[AMOOOMA]

Summary

This PR addresses two related issues with model_identifier and ModelManager metrics during runtime side-input model updates in RunInference:

1. Scope model_identifier transform annotation strictly to BeamML_RunInference:

   • Previously, RunInference.annotations() attached model_identifier to the outer RunInference composite PTransform, which caused all nested sub-transforms (such as WatchFilePattern side-input polling transforms, BatchElements, preprocess/postprocess transforms, etc.) to inherit the model_identifier annotation. Runners that group steps by model_identifier to look up num_loaded_models_<model_identifier> would then fail to resolve the metric on steps that never execute _RunInferenceDoFn.
   • Remove model_identifier from RunInference.annotations() and instead attach transform_annotations(model_identifier=self._model_tag) directly around BeamML_RunInference in RunInference.expand().

2. Stick to reporting the original model_identifier (metric_tag) in ModelManager across runtime side-input model updates:

   • When RunInference updates its model via side input (ModelMetadata), _RunInferenceDoFn._load_model acquires the new model under the updated model_id tag (self._cur_tag) so ModelManager caches/evicts the new model version separately from the previous version, while the BeamML_RunInference transform annotation remains fixed at construction time (self._model_tag / model_identifier).
   • Pass metric_tag=self._model_tag through _SharedModelWrapper to ModelManager.acquire_model(..., metric_tag=...), and map metric_tag to the active version tag in ModelManager / ResourceEstimator so num_loaded_models_<metric_tag> and memory_estimate_mb_<metric_tag> strictly reuse and report under the original metric_tag rather than the new side-input version tag.

Testing

• Added test_run_inference_only_attaches_model_identifier_to_inference_step in base_test.py.
• Updated test_run_inference_dofn_model_update_acquires_and_releases_matching_tag in base_test.py to verify metric_tag preservation across model updates.
• Added test_model_manager_metrics_with_metric_tag in model_manager_test.py verifying that num_loaded_models_<metric_tag> and memory_estimate_mb_<metric_tag> report exclusively under metric_tag.
• Updated test_monitoring_outlet_clears_model_identifier_annotation in vertex_ai_model_monitoring_v2_test.py.

[codecov]

Codecov Report

❌ Patch coverage is 43.58974% with 22 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.00%. Comparing base (76f6e6d) to head (7ddd3f0).
⚠️ Report is 241 commits behind head on master.

Files with missing lines	Patch %	Lines
...s/python/apache_beam/ml/inference/model_manager.py	0.00%	20 Missing ⚠️
sdks/python/apache_beam/ml/inference/base.py	89.47%	2 Missing ⚠️

Additional details and impacted files

@@              Coverage Diff              @@
##             master   #40671       +/-   ##
=============================================
+ Coverage     56.16%   80.00%   +23.83%     
=============================================
  Files          1124      490      -634     
  Lines        178336    82827    -95509     
  Branches       1489        0     -1489     
=============================================
- Hits         100170    66268    -33902     
+ Misses        75645    16559    -59086     
+ Partials       2521        0     -2521     

Flag	Coverage Δ
go	?
java	?
python	80.00% <43.58%> (+0.45%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.