Video-Tree-TRM5

Files

T

iomgaa 206c553143 feat(question_gen): add v2 pipeline with retry loop and heavy check

- PipelineConfig: YAML-driven configuration with family_ratios, retry,
  concurrency, dedup threshold, and heavy sampling rate
- _assign_slots: deterministic round-robin slot assignment across videos
  with per-family weighted random selection
- _process_one_slot: full retry loop (generate → postprocess → gates →
  dedup) with reject-reason feedback to VLM on retry
- _heavy_check_one: blind LLM agent trial-answer for difficulty_steps
- run_pipeline_v2: orchestration with semaphore-bounded concurrency,
  progress/resume support, and store integration
- is_duplicate: cosine similarity dedup against embedding pool

Tests: 11 integration tests covering slot assignment, retry behavior,
max-retries exhaustion, full pipeline flow, progress resume, heavy
sampling, and store record completeness.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-07-11 23:55:15 -04:00

__init__.py

refactor(question_gen): __init__.py 追加 synthesizer re-export

2026-07-09 05:49:05 -04:00

families.py

feat(question_gen): add 5 question family specs with sampling constraints

2026-07-11 23:14:22 -04:00

gates.py

fix(question_gen): gates reject_reason returns raw reason; short-circuit skips LLM

2026-07-11 23:33:57 -04:00

generator_v2.py

refactor(question_gen): extract _validate_parsed_fields to reduce CC