iomgaa/Video-Tree-TRM5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
504 Commits 2 Branches 0 Tags
7386e5af5709c18be2311b6e155e4bbf6ea5268a
Commit Graph

8 Commits

Author SHA1 Message Date
iomgaa 8958eee11b refactor: remove block-sequential gate path and gate_block knob (algo #6) 
config/train_videomme.yaml 同时收录待入库的实验配置变更(run_id v2 /
concurrency 32 / batch_size 40)。tests/integration/test_v3_contract_e2e.py
的 run_id 断言按 Task 5 显式契约同步修正(原断言依赖旧隐式实例注入)。
 2026-07-17 04:40:30 -04:00
iomgaa ee69721ea3 fix: filter frozen pools by requested task_types subset 2026-07-16 07:13:31 -04:00
iomgaa e1f08dcd3b fix: count units not questions in trainability pre-flight; fail-fast when all types filtered 2026-07-16 06:45:16 -04:00
iomgaa caea9150b3 feat: pre-flight filter of untrainable task types before gate 2026-07-16 06:16:02 -04:00
iomgaa c44f6010eb fix: early_stop patience counts epochs not steps 2026-07-16 06:09:11 -04:00
iomgaa 2429dad393 feat(batching): unit 粒度切分——pair 整锁 + 单元级分桶 + 非 AR 独立 rng 
build_batches 改以 QuestionUnit 为原子调度单元：孪生对 2 题整锁进同一 batch、
按单元级正确性（双向 AND）落 correct/error 桶，不再因 P 对 Q 错被劈或被 FFD 拆箱。

- 非 AR（single）用 random.Random(seed) 复现旧逐题算法确切 draw 序列，AR（pair）
  用 _rng_ns(seed,"AR") SHA-256 派生独立流；二者 draw 流互不干扰，故 AR 折叠不改变
  非 AR 抽样/洗牌序列——纯非 AR 输入 build_batches 结果与引入 QuestionUnit 前逐字节一致。
- FFD 容量按 unit.size（pair 占 2），round-robin 遇碎片新开 bin 兜底而非报错。
- _select_mixed_by_task_type 分流各跑一次后合并，大类洗牌按 kind 拆分各用对应 rng。

新增黄金测试 test_batching_pair_lock.py 覆盖三条铁律（同 batch / 单元分桶 /
非 AR byte-identical + draw 流独立）；既有 batching 测试全绿。
 2026-07-15 06:46:28 -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 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