4 Commits

Author SHA1 Message Date
iomgaa ac115d96fb test: cover backfill params end-to-end (mutation isolation + seq_offset) 2026-07-14 15:44:43 -04:00
iomgaa b13eab0659 feat: wire grounded selector into AR slot processing
将 Task 5 的 grounded selector 织入 AR 出题路径(Phase 3.5,位于
record_item 与 postprocess 之间),仅在 strategy.uses_grounded_selector
为真时进入。observation 始终落库(含 hard-fail),硬失败走重出。
PipelineConfig 新增 candidate_pool_size/selector_delta_low/
selector_delta_high 三参,YAML 与 CLI seed override 同步。
2026-07-14 14:15:50 -04:00
iomgaa 36c712defa feat(pipeline): replace QuestionFamilySpec with TaskTypeStrategy
- SlotAssignment: remove family field, strategy looked up at process time
- PipelineConfig: remove family_ratios field
- _assign_slots: remove family_ratios and rng params (pure deterministic)
- _process_one_slot: use get_strategy() for sampling, generation, gates
- Add sub_pattern support (level/constraint override, instruction injection)
- Add strategy.extra_gates() check after standard gates
- load_pipeline_config: stop reading family_ratios from YAML
- Update tools/generate_questions.py seed override and dry-run log
- Update all integration tests to match new API

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-07-14 06:05:23 -04:00
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