fix(workflow-operator): carry structured task context into chat fallback payloads

[PG1204]

What changes were proposed in this PR?

The five structured Hugging Face tasks (question-answering, table-question-answering, zero-shot-classification, sentence-similarity, text-ranking) build a native HF pipeline payload that only hf-inference understands. When the operator fell back to a third-party chat-completions provider, all three chat branches sent just the prompt cell, dropping the
context, table, candidate labels, or sentence list, so the model answered without the input that defines the task.

This adds a _chat_content_for_task helper to the generated operator that reformulates each of the five tasks into a chat prompt carrying its full context, and routes all three chat branches (zai-org, OpenAI-compatible, unknown-provider fallback) through it. Other tasks pass through unchanged. QaRankingCodegen.parsePython is also extended to read choices[0].message.content from chat responses, keeping the native {"answer": ...} shape as the primary path, the same idiom ImageTaskCodegen already uses.

Any related issues?

Closes #7195

How was this PR tested?

131 tests pass in the WorkflowOperator Hugging Face suites, PythonCodeRawInvalidTextSpec py-compiles the generated Python for all 117 operators, and scalafmtCheck is clean for main and test sources. A new spec test asserts the helper is emitted and used by every chat branch, with one assertion per task reformulation; two existing tests were updated where they pinned the old parse expression.

Was this PR authored or co-authored using generative AI tooling?

Yes, this PR was co-authored with Claude in compliance with ASF policy.

[github-actions]

Backport auto-label report

This fix: PR was checked against each actively-supported release branch. release/* labels drive the post-merge backport, so add or remove one to change where this fix lands.

Release branch

Analysis

⚠️ release/v1.2

Not labeled automatically — none of the files this PR modifies exist on this branch (common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/codegen/HuggingFaceCodegenBase.scala, common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/huggingFace/codegen/QaRankingCodegen.scala, common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceInferenceOpDescSpec.scala, common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/codegen/QaRankingCodegenSpec.scala). The fix may target code that isn't on this release, or the files were moved/renamed after the branch was cut. Please check and add release/v1.2 by hand if this fix should be backported here.

Auto-label run.

[github-actions]

Automated Reviewer Suggestions

Based on the git blame history of the changed files, we recommend the following reviewers:

• Contributors with relevant context: @anishshiva7, @Ma77Ball
  You can notify them by mentioning @anishshiva7, @Ma77Ball in a comment.

[PG1204]

/request-review @xuang7

[github-actions]

⚠️ Benchmark changes need a look

🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline

Compared against main 5f95b67 benchmarked on this same runner, so the delta is largely free of cross-runner hardware noise. The "7d avg" column still reflects the gh-pages dashboard. Treat <±5% as noise unless repeated.

Dashboard · Run

	config	throughput	MB/s	latency	max Δ latest / 7d
🔴	bs=10 sw=10 sl=64	373	0.228	28,239/33,413/33,413 us	🔴 +37.4% / 🔴 +121.5%
🔴	bs=100 sw=10 sl=64	784	0.478	125,397/170,879/170,879 us	🔴 +23.8% / 🔴 +60.0%
⚪	bs=1000 sw=10 sl=64	920	0.562	1,087,072/1,123,787/1,123,787 us	⚪ within ±5% / 🔴 +11.9%

Baseline details

Latest main 5f95b67 from same runner

config	metric	PR	latest main	7d avg	Δ latest	Δ 7d
bs=10 sw=10 sl=64	throughput	373 tuples/sec	401 tuples/sec	771.02 tuples/sec	-7.0%	-51.6%
bs=10 sw=10 sl=64	MB/s	0.228 MB/s	0.245 MB/s	0.471 MB/s	-6.9%	-51.6%
bs=10 sw=10 sl=64	p50	28,239 us	20,558 us	12,749 us	+37.4%	+121.5%
bs=10 sw=10 sl=64	p95	33,413 us	45,932 us	15,594 us	-27.3%	+114.3%
bs=10 sw=10 sl=64	p99	33,413 us	45,932 us	19,320 us	-27.3%	+72.9%
bs=100 sw=10 sl=64	throughput	784 tuples/sec	821 tuples/sec	997.05 tuples/sec	-4.5%	-21.4%
bs=100 sw=10 sl=64	MB/s	0.478 MB/s	0.501 MB/s	0.609 MB/s	-4.6%	-21.5%
bs=100 sw=10 sl=64	p50	125,397 us	121,250 us	100,339 us	+3.4%	+25.0%
bs=100 sw=10 sl=64	p95	170,879 us	138,030 us	106,781 us	+23.8%	+60.0%
bs=100 sw=10 sl=64	p99	170,879 us	138,030 us	113,101 us	+23.8%	+51.1%
bs=1000 sw=10 sl=64	throughput	920 tuples/sec	926 tuples/sec	1,037 tuples/sec	-0.6%	-11.3%
bs=1000 sw=10 sl=64	MB/s	0.562 MB/s	0.565 MB/s	0.633 MB/s	-0.5%	-11.2%
bs=1000 sw=10 sl=64	p50	1,087,072 us	1,080,533 us	971,388 us	+0.6%	+11.9%
bs=1000 sw=10 sl=64	p95	1,123,787 us	1,133,336 us	1,013,249 us	-0.8%	+10.9%
bs=1000 sw=10 sl=64	p99	1,123,787 us	1,133,336 us	1,039,879 us	-0.8%	+8.1%

Raw CSV

config_idx,batch_size,schema_width,string_len,num_batches,total_ms,total_tuples,total_bytes,tuples_per_sec,mb_per_sec,lat_p50_us,lat_p95_us,lat_p99_us
0,10,10,64,20,536.55,200,128000,373,0.228,28238.77,33412.94,33412.94
1,100,10,64,20,2552.64,2000,1280000,784,0.478,125396.95,170879.27,170879.27
2,1000,10,64,20,21728.44,20000,12800000,920,0.562,1087071.84,1123787.12,1123787.12

[xuang7]

LGTM