iomgaa/Video-Tree-TRM5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
367 Commits 2 Branches 0 Tags
4d60a545f6b3a4077b68f93a0133606772d0881f
Commit Graph

181 Commits

Author SHA1 Message Date
iomgaa 6d6eb8e3a3 refactor(question_gen): extract _validate_parsed_fields to reduce CC 
Split field validation logic out of _parse_v2_response into a dedicated
_validate_parsed_fields helper. This brings _parse_v2_response from CC=11
(grade C) down to CC=3 (grade A). The extracted validator is CC=9 (grade B).
No grade-C functions remain.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:43:35 -04:00
iomgaa cf51d2de9d feat(question_gen): add v2 generator with per-family prompt templates 
Implement generator_v2.py with:
- CandidateQuestion dataclass (canonical location)
- _load_prompt_template: loads per-family .md from store/prompts/
- _build_v2_prompt: constructs system+user messages with material context
- _parse_v2_response: JSON extraction, json_repair, field validation
- generate_one_v2: async VLM call orchestration with reject_reason support

Add 5 family-specific prompt templates:
- retrieval.md: factual recall from visible content
- reasoning.md: multi-hop inference across segments
- enumeration.md: counting/listing entities and actions
- visual.md: visual details requiring frame observation
- spatial.md: spatial relationships between objects/people

Tests: 11 unit tests covering prompt build, parse, and e2e generation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:41:36 -04:00
iomgaa 9053233f99 fix(question_gen): gates reject_reason returns raw reason; short-circuit skips LLM 
- GateReport.reject_reason now returns gate.reason directly (no [name] prefix)
- verbatim short-circuit sets other 3 gates to SKIP without calling LLM
- test_high_verbatim_shortcircuits asserts zero LLM calls and SKIP verdicts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:33:57 -04:00
iomgaa 9f739e831d refactor(question_gen): reduce cyclomatic complexity in sampler_v2 
Extract shared _resolve_subtree helper to eliminate repeated tri-level
node resolution. Break _validate_sampling_constraints into focused
single-purpose helpers:
- _count_l3_descendants
- _has_frames
- _count_subtitles
- _resolve_subtree / _find_l3_parent

Extract _subtitles_from_l2_list and _frames_from_l2_list to simplify
collection functions.

Complexity improvements:
- _validate_sampling_constraints: D(23) -> B(8)
- _collect_subtitle_sentences: C(16) -> A(3)
- _collect_frame_paths: C(13) -> A(2)

All functions now grade B or better per radon cc.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:33:48 -04:00
iomgaa f74711cd11 feat(question_gen): add v2 material sampler with family constraints 
Implement sample_material_v2 module that samples tree nodes with
QuestionFamilySpec-aware constraint validation, providing richer
MaterialContext output (subtitles, cross-L2 context, frame paths).

Key components:
- AnchorContext/MaterialContext frozen dataclasses
- _validate_sampling_constraints: multi-level constraint checking
- _collect_subtitle_sentences: subtree subtitle extraction
- _collect_cross_l2_context: peer L2 event descriptions
- sample_material_v2: main entry with retry-on-constraint-violation

Tests: 11 unit tests covering normal sampling, used-node exclusion,
constraint violation retries, cross-L2 population, and subtitle
collection.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:30:56 -04:00
iomgaa 271d1682c9 feat(question_gen): add lightweight 4-gate quality check 
Implement 4 concurrent LLM-based quality gates for generated questions:
- key_verify: validates answer evidence in source material
- blind_answer: rejects questions answerable without video context
- multi_true: detects ambiguous multi-correct options
- leak_test: per-family shortcut detection (5 probe templates)

Includes run_gates orchestrator with verbatim_ratio short-circuit,
JSON response parsing with fallback, and 9 unit tests (all passing).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:30:13 -04:00
iomgaa 9627ac9cf9 fix(question_gen): raise ValueError on UPDATE of missing rows 
record_run_end, update_gates, and update_difficulty now check
cursor.rowcount after UPDATE+commit and raise ValueError if 0 rows
were affected. Prevents silent telemetry loss.

Adds three negative-path tests:
- test_record_run_end_missing_run_raises
- test_update_gates_missing_item_raises
- test_update_difficulty_missing_item_raises

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:23:48 -04:00
iomgaa 7abe92eb1c fix(question_gen): check_verbatim covers question_text + add missing blacklist patterns 
- check_verbatim now computes n-gram overlap for BOTH question_text and
  correct_option vs source texts, returning max(question_ratio, option_ratio).
  Extracted _ngram_overlap_ratio helper for reuse.

- Added 4 missing blacklist patterns: 'this segment', 'this frame',
  'the current frame', 'frame summary'.

- Added 5 new test cases covering the above changes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:23:37 -04:00
iomgaa 9525726133 fix(question_gen): rename finished_at to ended_at per schema spec 
Aligns DDL column name with research-wiki/schemas/question-gen-runs.md
which specifies 'ended_at' (not 'finished_at').

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:18:52 -04:00
iomgaa 74686dde68 refactor(question_gen): reduce check_forbidden_material complexity to A(3) 
Extract _match_any helper and declarative _FORBIDDEN_MATERIAL_RULES table
to replace repetitive per-category for-loops. Reduces cyclomatic complexity
from C(11) to A(3).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:16:34 -04:00
iomgaa 6a5424a618 feat(question_gen): add SQLite run store for generation telemetry 
Implements QuestionGenStore with:
- Idempotent schema initialization (question_gen_runs + question_gen_items)
- Run lifecycle: record_run_start / record_run_end / get_run_stats
- Per-item recording: record_item / update_gates / update_difficulty
- GateReportLike Protocol for duck-type gate report compatibility
- WAL mode + foreign keys + check_same_thread=False

DDL aligns with research-wiki/schemas/question-gen-{runs,items}.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:15:53 -04:00
iomgaa c83d771923 feat(question_gen): add deterministic postprocess layer 
Add app/question_gen/postprocess.py with zero-LLM deterministic
post-processing for generated questions:

- shuffle_options: deterministic option permutation with answer remapping
- check_referent_blacklist: detect self-referential language (this clip, etc.)
- check_verbatim: word-level n-gram overlap ratio measurement
- has_time_anchor: timestamp and temporal phrase detection
- check_forbidden_material: T1/T7 source material validation
- run_postprocess: orchestration returning PostprocessResult

Tests: 31 unit tests covering all functions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:14:43 -04:00
iomgaa 75e6d8c550 feat(question_gen): add 5 question family specs with sampling constraints 
Define QuestionFamilySpec, LeakTestProfile, SamplingConstraint dataclasses
and instantiate 5 families (RETRIEVAL/REASONING/ENUMERATION/VISUAL/SPATIAL)
targeting failure mechanisms M1-M5. Implement get_family_for_slot with
legal-type filtering + weighted random selection.

13 unit tests cover: full task-type coverage, skill_target uniqueness,
deterministic seeding, invalid input errors, and chi-square distribution.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:14:22 -04:00
iomgaa 811ffa648b feat(types): extend GeneratedQuestion with skill_target & difficulty_steps 
- Add skill_target (str | None) and difficulty_steps (int | None) fields
  to GeneratedQuestion dataclass with field(default=None)
- Update loader.py to pass new fields from JSON (backward-compatible)
- Update pools.py _q_to_dict/_dict_to_q for serialization compat
- Add question_gen_v2 config section to default.yaml
- Add comprehensive test coverage (7 tests)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-11 23:05:38 -04:00
iomgaa e9073bfdc2 feat(tree): expose build_async and accept injected API semaphore 
Core algorithms #1/#2/#3 unchanged: only entry wrapping and semaphore
source switch (injected vs self-built); build logic untouched.
- rename _build_async to public build_async (body unchanged)
- __init__ accepts keyword-only api_semaphore for cross-video sharing
- default path (no injection) is verbatim-equivalent to previous code
 2026-07-11 11:14:45 -04:00
iomgaa ebbd112d50 fix(tree): move Iterable import into type-checking block 2026-07-11 09:05:04 -04:00
iomgaa f0284199b8 refactor(tree): narrow _clean_join parameter type to Iterable 2026-07-11 09:04:25 -04:00
iomgaa a2c6a97621 refactor(tree): extract _clean_join to keep entity-fields complexity at B 
质量门要求新增代码复杂度不超过 B 级：将 node_entity_fields 中重复的
"清洗-去重-拼接"逻辑抽为模块级纯函数 _clean_join，主体收敛为两次
调用。radon：node_entity_fields C(13) → B(6)，_clean_join A(5)。

算法 #11（树环境语义搜索）数据访问层，行为不变（既有 4 测试未改全绿）。
 2026-07-11 08:56:17 -04:00
iomgaa 4e0e05210d feat(search): append raw entity fields after view_node summary 
view_node 按题两轮摘要（summarize_node）会吞掉 entities/visible_text
字段信号，Agent 站在证据节点上仍漏读实体（benchmark 错题 M1，案例
786-2、872-3、750-1）。dispatcher 侧在摘要后确定性追加 [实体]/[画面
文字] 原文区块，LLM 无法吞掉。

- TreeEnvironment.node_entity_fields：按层级取 card 实体字段原文，
  去空白、去重、分号拼接；空字段省键；未知节点抛 KeyError
- _handle_view_node Phase 2.5：摘要后、子节点概览前追加实体区块
- 附带 ruff format 修正 test_tree_environment.py 两处既有格式

算法 #11（树环境语义搜索）数据访问层扩展，不改搜索算法本身。
 2026-07-11 08:53:56 -04:00
iomgaa 307c64c388 fix(harness): infer mode honors CLI --questions over manifest 2026-07-11 07:45:33 -04:00
iomgaa 5b51f4bd0c fix(synthesizer): generate_one 捕获所有异常避免 VLM 超时穿透崩溃 
except (ValueError, KeyError) → except Exception，
覆盖 StreamLivenessTimeout 等网络/超时异常。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-10 01:08:03 -04:00
iomgaa a7ca6d15ed feat(harness): InferenceDepsRouter per-video 路由器 
按 video_id 懒加载 InferenceDeps 并缓存，路由 dispatch/prompt_builder:
- create_dispatch: 按 session_id 路由到对应视频的工具调度
- create_prompt_builder: 自动注册 qid→vid 映射并路由 prompt 构建
- 三元组 (video_id, skills_dir, prompts_dir) 缓存键

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 12:20:32 -04:00
iomgaa f21bf345a6 feat(runner): 注入 tool_dispatch_factory/prompt_builder_factory + fail-fast 
Runner.__init__ 新增 2 个可选参数:
- tool_dispatch_factory: 工具调度工厂
- prompt_builder_factory: prompt 构建工厂

infer/eval/train 模式缺少工厂时 fail-fast 抛 ValueError。
_make_tool_dispatch_fn/_make_prompt_builder 优先使用注入工厂。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 12:20:25 -04:00
iomgaa 924160c779 feat(ports): 新增 ToolDispatchFactory/PromptBuilderFactory Protocol 
4 个新 Protocol 类型:
- ToolDispatchFn: 工具调度函数签名
- ToolDispatchFactory: per-version 工具调度工厂
- PromptBuilderFn: Prompt 构建函数签名
- PromptBuilderFactory: per-version prompt 构建工厂

含 runtime_checkable isinstance 测试。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 12:20:16 -04:00
iomgaa 16140cafcc fix(tree): from_dict L2 subtitle 旧格式兼容 fallback 
旧格式 tree.json 无 card-level L2 subtitle 时，从已构造的 L3
children 聚合 subtitle，避免运行时加载静默丢失 L2 字幕。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 12:04:36 -04:00
iomgaa d3be9b1322 refactor(tree): subtitle 迁入 L3Card/L2Card + 建树管线修正 
- L3Card/L2Card 新增 subtitle: str 字段（L1Card 不加）
- L3Node 移除 subtitle 字段（数据迁入 Card）
- assign_subtitles_voronoi 改写 Card.subtitle + L2 聚合
- _collect_card_strings 增加 skip_fields 排除 subtitle
- _node_full_text/_node_anchored_text 保持 字幕:/[sN] 语义
- get_subtitle 读 Card.subtitle（L2/L3）
- verify.py/synthesizer.py: l3.subtitle → l3.card.subtitle
- 迁移脚本 tools/migrate_subtitle_to_card.py（幂等，300 棵树已迁移）
- 9→6 个测试文件适配（3 个无需改动）

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 11:57:41 -04:00
iomgaa 45403b23b4 feat(repair): regenerator + supplement 防御修复 + 迁移脚本 
- 新增 app/tree/repair/regenerator.py（VLM 重生成 + 级联修复）
- supplement.py: deduplicate_field str() 防御 + inject_value strip
- patch.py: ruff format 格式化
- repair_trees.sh: conda source 激活修复
- 新增 migrate_from_trm4.sh 迁移工具
- enhance/__init__.py → repair/__init__.py 重命名

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 07:53:59 -04:00
iomgaa f57ee45dc0 fix: Codex 全量审查修正 
Critical:
- C1: assemble_mode 'plain' → 'ids'（合法枚举值）
- C2: question_id 加入 task_type slug 避免跨题型冲突

Important/Minor:
- generate_one 移除未用的 embed_fn/similarity_threshold 参数
- config.py 注释 11→12 同步
- 测试 question_id 断言更新

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 07:40:27 -04:00
iomgaa fad8147d71 refactor(question_gen): __init__.py 追加 synthesizer re-export 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:49:05 -04:00
iomgaa 6e46d184b8 feat(harness): add factory.py — InferenceDeps dataclass + build_inference_deps 
组装一次推理所需的全套依赖的工厂函数：
- TreeIndex 加载（FileNotFoundError if missing）
- TreeEnvironment 构建
- SkillRegistry 按需发现
- SearchToolDispatcher 装配
- PromptManager + prompt_builder 闭包

测试覆盖：正常路径、缺失树文件、skills 注入、frozen 不可变性。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:36:07 -04:00
iomgaa 5aa7cc48c5 feat(question_gen): is_duplicate + generate_one — 去重判定与单题生成编排 
- is_duplicate: 余弦相似度去重，空池短路
- generate_one: 异步重试循环，不含去重（由调用方汇总点原子执行）

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:32:39 -04:00
iomgaa 90f17e330e feat(question_gen): build_generation_prompt + parse_vlm_response 
- prompt 组装：system(角色+题型+约束+few-shot) + user(card+字幕+干扰项)
- VLM 响应解析：JSON 直接 + markdown code block 回退，四选一 schema 校验

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:28:25 -04:00
iomgaa 40b04f886e fix(question_gen): sample_anchor Codex 审查修正 
- C1/C2: Temporal Reasoning ≥3 L2 + Object Reasoning ≥2 L2 下限检查
- I1: L2 题型子帧不足时 ValueError
- I2: L3 过滤无 frame_path 的节点
- I3/I4: distractor_texts 扩展到整棵树范围
- I5-I7: 测试补强 Information Synopsis/Temporal Reasoning/Object Reasoning
- M1: Spatial Reasoning 测试断言 spatial_layout

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:24:30 -04:00
iomgaa a597a9f901 feat(question_gen): sample_anchor — 按题型层级采样锚节点 
含 6 种层级分支：L3 单帧、L2 多帧、Temporal Perception 特例、
L1 全量/采样 L2、L1-L2 混合。时间排序 + used_node_ids 排除。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:18:25 -04:00
iomgaa 9eb9b86954 feat(question_gen): AnchorContext + 12 题型-层级映射常量 
- AnchorContext frozen dataclass: 锚节点生成上下文（node_id, card_text, frame_paths, subtitle, distractor_texts）
- TaskTypeSpec frozen dataclass: 题型生成规格（level, needs_frames, frame_count, context_fields）
- TASK_TYPE_LEVEL_MAP: 12 种 Video-MME 题型 → 树层级 + 生成规格映射
- 11 项单元测试覆盖：映射完整性、值类型、层级合法性、frozen 不变性

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:10:58 -04:00
iomgaa eb15ab315e fix(config): _VIDEO_MME_TASK_TYPE_COUNT 11→12，Video-MME 实际有 12 种题型 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:08:05 -04:00
iomgaa 8c383354c5 fix(detector): 移除 ongoing_actions/visible_entities 空字段检测 + 新增 repair sh 
抽检确认这两个字段为空是合法内容状态（静物/黑帧/模糊帧），
VLM 重修也修不好，保留会导致断点续跑死循环。
L3 空字段检测缩减为 frame_summary + spatial_layout。
 2026-07-09 00:54:27 -04:00
iomgaa 8182cb86b1 feat(detector): 扩展空字段检测到 L2 event_description / L1 scene_summary 
断点续跑判据需要 L2/L1 层的 empty_field 检测。零 LLM 成本。
 2026-07-09 00:12:55 -04:00
iomgaa 53286ac3ab refactor: remove deprecated retriever module 
RecursiveRetriever was a failed approach, not carried into TRM5.
- delete app/retriever/ (empty placeholder)
- drop retriever + train blocks from config/default.yaml
- renumber fidelity checklist 13->12 items (drop #4, shift up)
- sync core-goal text, dir tree, module-interaction diagrams
  across CLAUDE.md, ARCHITECTURE.md, overview.md, README.md
- reference/ kept intact as historical code
 2026-07-08 23:09:30 -04:00
iomgaa 9a42bbcf85 style(harness): ruff format batching.py + log.py 2026-07-07 20:34:48 -04:00
iomgaa a668fc173c feat(harness): __init__.py public API + lint fixes 2026-07-07 13:45:48 -04:00
iomgaa d6e74f2734 feat(harness): runner.py — train loop orchestrator (#13 algorithm fidelity) 
Three-level nesting (epoch -> step -> per-skill), slow update 10-step
sequence, checkpoint/resume, early stop, probation accept/reject/rollback.

Key TRM4->TRM5 changes:
- sync -> async (all inference/diagnosis/evolve/validate awaited)
- LLMClient.from_env -> injected LLMProvider (DI via constructor)
- Direct DB/file access -> module functions (workspace/store/log)
- _TrainState as train() local, explicit param passing to helpers

Module-level pure functions extracted for testability:
resume_plan, _guard_infra_failures, _apply_batch_correctness,
_compute_total_steps, _should_early_stop, _format_applied_edits,
_fallback_summary, _write_skip_report, _outcome_to_quadrant_pairs,
_build_comparison_pairs, _batch_from_ids, _snapshot_current_skills.

Tests: 34 unit tests covering 13a-13e sub-tasks.
Radon: all functions Grade B or better.
 2026-07-07 13:43:20 -04:00
iomgaa 6baddcc17d feat(harness): validate.py — async 块序贯验证编排 + Probation 统一定义 2026-07-07 13:20:43 -04:00
iomgaa 8c9f7d2d37 feat(harness): checkpoint.py — TrainState 序列化 + 原子写 + 指纹校验 2026-07-07 13:13:37 -04:00
iomgaa 6b56fc8f98 feat(harness): inference.py — async run_inference + DI 2026-07-07 13:04:26 -04:00
iomgaa 49e272719e feat(harness): momentum.py — async 慢更新动量生成 2026-07-07 13:01:04 -04:00
iomgaa 767ac55787 feat(harness): observation.py — 五张观测表 + step/epoch 报告 2026-07-07 12:55:12 -04:00
iomgaa d7d8633dae feat(harness): gate_ladder.py — 信息阶梯 + BaselineCache (#6 算法保真) 2026-07-07 12:55:12 -04:00
iomgaa 48b423ef35 feat(harness): pools.py — 三池切分（test→validation→diagnosis） 2026-07-07 12:48:54 -04:00
iomgaa ad8fc176d0 feat(harness): batching.py — FFD + round-robin mini-batch (#10 算法保真) 2026-07-07 12:47:33 -04:00