iomgaa/Video-Tree-TRM5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
219 Commits 2 Branches 0 Tags
e5b07ac974a1f2e9cc480ea663bc1cf996a0d995
Commit Graph

219 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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 0b48b889e0 docs(wiki): 赛题生成工具设计 + 实现计划 
design: synthesizer + factory + CLI 三模块架构
plan: 9 个 Task（前置修复 + synthesizer 4 步 + factory + CLI generate/calibrate + re-export）
calibrate: Fisher exact test 组合判定替代固定阈值

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 05:05:57 -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 86573735aa docs(wiki): apply Codex review fixes to main-figure design 2026-07-09 00:46:08 -04:00
iomgaa 8cb1158a2d docs(wiki): paper main-figure design — self-evolving loop layout 2026-07-09 00:39:45 -04:00
iomgaa d6bcf41336 fix(repair): Codex 审查修正 — progress 完成判据加严 + load_progress 防御增强 
1. 保存 progress 前重新 detect_issues，只有 empty_field 清零才记 finished
   （修复 L2/L1 空字段被检测但未修复仍写 finished 的问题）
2. load_progress 增加 AttributeError 捕获（防 JSON 非 dict 形态崩溃）
 2026-07-09 00:30:23 -04:00
iomgaa 4612123ec4 style: ruff format telemetry + repair_trees, remove unused SRTEntry import 2026-07-09 00:25:36 -04:00
iomgaa 847def4a03 feat(repair): asyncio.Semaphore 并发 + 断点续跑 + CLI 参数 
--concurrency 默认 16，--reaggregate-all 强制全量重聚合。
Semaphore 限视频并发数，视频内四步串行。progress 文件
asyncio.Lock + os.replace 原子写入。熔断阈值 max(.env, concurrency*2)。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 00:23:40 -04:00
iomgaa afe80a8b32 feat(repair): 断点续跑 progress 文件管理 
load_progress / save_progress(asyncio.Lock + os.replace 原子写入)
/ should_skip_video。支持并发安全的读改写和 --reaggregate-all 兜底。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 00:23:04 -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 f733c13dd1 fix(llm): call_id 移入重试循环，每 attempt 独立 
消除重试时遥测主键冲突的根因。每次 attempt 独立记录，
parent_call_id 不受影响（循环外固定），更利于事后诊断重试轨迹。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 00:12:38 -04:00
iomgaa 5a91f392f0 fix(telemetry): INSERT OR IGNORE + WAL + try/except 三层防御加固 
根治遥测写入主键冲突(UNIQUE constraint)和并发写锁(database is locked)
导致的异常冒泡，遥测侧信道错误不再污染 LLM 重试链。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-09 00:11:54 -04:00
iomgaa dbc9d38cd7 plan(tree/repair): 三项改造实现计划(遥测加固+断点续跑+并发) 
6 个 Task: telemetry 防御加固 → call_id 根因修复 → detector L2/L1 扩展
→ progress 管理 → 并发编排+CLI → lint+全量测试
 2026-07-09 00:08:23 -04:00
iomgaa 8a49ef18e6 design(tree/repair): 建树修复管线熔断根因修复+断点续跑+并发改造设计 
三事: (1)遥测防御性加固(INSERT OR IGNORE+WAL+busy_timeout+try/except不冒泡)
根治call_id重试复用导致的主键冲突污染重试与熔断器; (2)判据双轨
(detect重扫empty_field+progress文件)视频级断点续跑,首次用detect
自动接历史无需手补状态; (3)asyncio.Semaphore并发默认16,熔断阈值
max(5,concurrency*2),--concurrency走CLI避免与tree.concurrency串台
 2026-07-08 23:52:48 -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 91281cb995 merge: feat/app-harness — app/harness/ 训练循环编排层（14 文件, 算法保真 #6/#10/#13） 2026-07-07 20:35:04 -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
iomgaa 461abf0329 feat(harness): workspace.py — Workspace lifecycle + VersionedSkillStore/PromptStore 
- ResolvedPaths frozen dataclass: store_dir, videos_dir, questions_dir,
  skills_dir, prompts_dir, workspace_dir, db_path, analyses_dir, runs_dir
- init_workspace: create ws + copy seed weights from store
- init_workspace_from_seed: create from seed with fail-fast questions check
- load_manifest / resolve_paths: manifest I/O + path resolution
  (skills/prompts resolve to workspace, videos/questions to store)
- update_manifest: key whitelist validation
- record_run: idempotent history append + per-video wiki dirs
- read_best / update_best: best pointer independent of current
- list_video_ids: videos with tree.json
- archive_workspace: move to .archive/<name>-<ts>
- VersionedSkillStore: implements core/evolution/protocols.py::SkillStore
- VersionedPromptStore: implements core/evolution/protocols.py::PromptStore
- 21 tests all passing (incl. Protocol compliance checks)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:41:59 -04:00
iomgaa 6858da80c7 feat(harness): store.py — Store 版本操作 + Seed 管理 
从 TRM4 core/workspace.py 拆出 Store + Seed 相关函数：
- _parse_version / list_versions / next_version / advance_version
- _write_meta / init_store
- init_seed / list_seeds / read_seed
- extract_run_db（保留原始 CREATE 语句重建主键约束）
- promote_to_seed（强校验版本一致 + 非 NULL + finally 清理）

26 个测试全部通过，radon 复杂度 A (2.83)。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:36:36 -04:00
iomgaa fd76720dcf feat(harness): HarnessLog SQLite wrapper + RunLogImpl readonly port 
- HarnessLog: TRM4 direct port with WAL mode, threading.Lock, INSERT OR
  IGNORE idempotent _runs, context manager (completed/failed), create_table
  with auto run_id+timestamp, insert/insert_many/execute/query/log_event
- RunLogImpl: implements core/evolution/protocols.py::RunLog Protocol with
  independent sqlite3.connect for read-only SELECT (no _runs pollution),
  asyncio.to_thread wrapping for async interface
- _read_table: shared readonly helper with optional question_ids filtering,
  graceful empty-list return for missing tables
- Tests: 17 cases covering thread safety, idempotent inserts, context
  manager status, WAL mode, protocol compliance, readonly isolation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:29:29 -04:00
iomgaa b47f634e61 fix(harness): Codex functional review 修复 — 命名/集成测试/delta_min/promote 消息 
- _apply_env_overrides → _apply_env_var_overrides，docstring 明确从 os.environ 读取
- 新增 TestLoadConfigRealYaml：用真实 config/default.yaml 验证嵌套 harness 解析
- 新增 test_delta_min_negative_rejected：覆盖 gate_delta_min >= 0 校验
- 恢复 promote 模式独立错误消息（从合并分支分离回 TRM4 原始提示）
- 77 个单元测试全部通过，radon 全部 Grade B 或更好

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:23:27 -04:00
iomgaa 535bd320b0 fix(harness): 补充 train 模式 run_id 校验 + 拆分函数保持 radon Grade B 
- _validate_mode_deps: 恢复 train 非 resume/fresh 时必须提供 run_id 校验
- 提取 _validate_train_run_id 用 early return 展平条件，避免 radon Grade C
- 合并 promote run_id 检查到 diagnose/evolve/promote 统一检查
- 新增 4 个测试：train+run_id / train+resume / train+fresh / train+baseline
- radon cc -n C 无输出（全部 Grade B 或更好）
- 74 个单元测试全部通过

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:14:28 -04:00
iomgaa 5e57cf19b6 refactor(harness): 拆分校验函数降低 radon 圈复杂度至 Grade B 
- _validate: 拆出 _validate_mode（mode 依赖校验）+ _validate_basic（标量/枚举校验）
- _validate_gate: 拆为 _validate_gate_thresholds（e 值/净胜/方向）+ _validate_gate_ladder（阶梯/块序贯）
- load_config: 提取 _apply_env_overrides 函数
- radon cc -n C 无输出（全部 Grade B 或更好）
- 70 个单元测试全部通过

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:01:46 -04:00
iomgaa ca02b5a91d feat(harness): RunConfig frozen dataclass + 四层校验 + YAML/CLI/.env 三层加载 
- RunConfig: 46 字段 frozen dataclass，从 TRM4 core/harness/config.py 迁移
- 四层校验链：_validate → _validate_edit_budget + _validate_minibatch + _validate_gate
- 新增 .env 覆盖层：工程配置（workspace_dir, store_dir）可通过 HARNESS_* 环境变量注入
- 合并优先级：CLI > .env > YAML（CLAUDE.md §4.5）
- load_config 支持嵌套 harness 段和扁平 YAML 两种格式
- run_id 改为默认空字符串（CLI-only 字段，YAML 不提供）
- resume/fresh 互斥校验不在 config 层（移至 runner.py）
- 70 个单元测试全部通过

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 11:57:35 -04:00
iomgaa 63ad68f737 feat(evolution): export dataclass types from __init__.py 2026-07-07 11:48:13 -04:00
iomgaa 2db612e0bb docs: app/harness/ implementation plan — 15 tasks, algorithm fidelity #6/#10/#13, 120 TRM4 tips 2026-07-07 11:45:38 -04:00
iomgaa af8081e9ed docs: app/harness/ design — 14-module training loop orchestration layer 2026-07-07 11:28:29 -04:00
iomgaa 283ea27b51 merge: feat/tree-index — core/evolution/ extractable kernel + tree/search/question_gen modules 2026-07-07 10:29:54 -04:00
iomgaa 9ab6a89298 feat(evolution): __init__.py public API + ARCHITECTURE.md Protocol update 2026-07-07 10:28:14 -04:00
iomgaa 5c42e0309b feat(evolution): evolve.py per-target evolution — skill/system/tool (#9) 2026-07-07 10:26:58 -04:00
iomgaa 2c5b4c819c feat(evolution): evolve.py validation + helpers (#9) 2026-07-07 10:12:15 -04:00
iomgaa c6a81f8504 feat(evolution): diagnose.py aggregation + case packs + run_diagnosis (#8) 2026-07-07 10:04:48 -04:00
iomgaa fdbf9222ab feat(evolution): diagnose.py metrics + attribution (Stage 1, #8) 2026-07-07 09:55:22 -04:00
iomgaa ebd83810aa feat(evolution): validate.py — pure block validation decision functions (#7) 2026-07-07 09:47:45 -04:00
iomgaa 7f8ed56428 feat(evolution): patch.py — 补丁引擎移植（算法 #9），51 测试全通过 
从 TRM4 core/harness/patch.py (427 行) 零修改移植到 core/evolution/patch.py。

包含:
- 7 个常量（APPENDIX/MOMENTUM marker + MAX_CHARS + HEADING）
- appendix 区：追加/提取/替换/边界检测，损坏态 ValueError
- momentum 区：替换/提取/边界检测，注入防护
- apply_patch_with_report：4 种 op（append/insert_after/replace/delete）
- 冻结区坐标判定（每条 edit 重算）、report 1-based index
- 51 个单元测试覆盖全部公共 API 及边缘场景

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 09:44:05 -04:00
iomgaa 57793fb0f8 feat(evolution): gate.py — CE-Gate e-process 纯函数 (#5 算法保真) 
从 TRM4 core/harness/eprocess.py 逐行迁移，零逻辑变更:
- compute_e_value: 截断 Beta 混合 e 值（log 空间 + betainc 对称性）
- gate_decision: 四出口优先级链（confirmed→directional→futility→exhaustion→continue）
- probation_verdict: 试用期非对称双向结算
- 常量保真: _WALD_WIN=ln1.4, _WALD_LOSS=ln0.6, _SHRINK_PSEUDO=4

仅变更: import 路径 + GateParams/GateVerdict 移至 types.py + 中文 docstring

14 tests 覆盖: e 值数学、边界校验、四出口路径、试用期三分支

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 09:38:21 -04:00
iomgaa 47c2de71a2 feat(core/evolution): protocols.py + types.py 基础层 — 18 个 dataclass + 3 个 Protocol 
TRM4 诊断/进化/门控数据类型迁移至 TRM5 Clean Architecture 内核。
逐字段比对 TRM4 的 eprocess.py、diagnose.py、evolve.py 保真迁移。

types.py (18 个 dataclass):
- Gate: GateParams, GateVerdict (frozen, 原样迁移)
- 诊断: SpanMetrics, SkillStepAdherence, QuestionMetrics,
  ErrorAttribution, CaseSample, SkillCasePack, SystemCasePack,
  ToolCasePack, DiagnosisResult (全部 frozen=True)
- 进化: EvolutionRecord (mutable), RejectedEdit (frozen),
  EvolutionResult (frozen, 移除 skills_version/prompts_version)
- 新增: PairResult, QuadrantClassification (块验证纯决策输出)
- 新增: DiagnosePrompts, EvolvePrompts (模板束, frozen)

protocols.py (3 个只读 Protocol):
- SkillStore, PromptStore (同步文件读取)
- RunLog (异步日志查询, 隔离 SQL)

变更理由:
- QuestionMetrics 由 TRM4 mutable 改为 frozen (一次性构造)
- ErrorAttribution 由 TRM4 mutable 改为 frozen (构造时填入全部字段)
- EvolutionResult 移除版本管理字段 (app/ 职责)

涉及算法: #5(CE-Gate), #8(诊断瀑布), #9(进化引擎)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 09:34:04 -04:00
iomgaa 8bbfbc9b8a docs: core/evolution/ implementation plan — 9 tasks, TDD, algorithm fidelity checks 2026-07-07 07:55:21 -04:00
iomgaa 2761ca3e82 docs: core/evolution/ extractable kernel design — gate, patch, diagnose, evolve 2026-07-07 07:39:24 -04:00