技能链路由引擎 — three-layer skill routing with SAD feedback and DAG composition
Project description
Changelog — Skill Weave Iteration
All notable changes to the Skill Weave project are documented in this file.
The format is based on Keep a Changelog.
[Phase 4] — 2026-07-08 — 通用化去耦合
Added
circuit_breaker.py— 纯 stdlib 实现的 CircuitBreaker 状态机(CLOSED/OPEN/HALF_OPEN),8 个公开方法完全兼容原 skill_weave 接口telemetry.py— 纯 stdlib 实现的 Telemetry JSONL 日志器,6 个公开方法(start_span/end_span/log_event/read_logs/stats/span),支持自动日志轮转tfidf_embedder.py— HashEmbedder 轻量文本嵌入(djb2 哈希 + 字符 n-gram + 128 维 + L2 归一化),作为无外部嵌入模型时的 dense fallbackchains.json/chains.yaml— 链定义配置文件,支持 JSON/YAML 两种格式,用户可通过编辑配置文件添加自定义链weave_chains.py新增_load_config()函数,模块加载时自动读取 chains.json,不存在则回退到硬编码默认值semantic_retriever.py新增_postprocess_ascii_abbrevs()后处理函数,从中英混合 token 中分离 ASCII 技术缩写(LoRA/BERT/GPT 等)_ASCII_ABBREVS集合:70+ 常见技术缩写词表
Changed
weave_chains.py导入改为本地模块:from circuit_breaker import CircuitBreaker/from telemetry import Telemetry,不再依赖skill_weave包的 CircuitBreaker/Telemetryinit_phase3()当embed_fn=None时自动创建 TF-IDF HashEmbedder 并重建 SemanticRetriever,确保 dense 检索始终可用tokenize()函数所有模式(jieba/fmm/bigram)统一应用 ASCII 缩写后处理
Renamed (去 Hermes 化)
hermes-ui-design→ui-design-systemhallmark→anti-ai-designmemory-maintenance→memory-concierge
Fixed
- Phase 3 SADFeedback bug:
confidence_threshold从 3.0 降到 2.0,单触发词匹配(score=2)不再触发不必要的 SAD 校正 - Phase 3 SADFeedback bug: 添加链切换保护,新链 score 未超过原链 +1.0 时保持原链
Performance
- Recall@10 从 93.94%(31/33)提升到 96.97%(32/33),TF-IDF 密集嵌入有效提升混合检索质量
Test Results
- Phase 3 集成测试:42/42 通过
- 基准路由测试:31/31 = 100%
- v0.4 集成测试:12/12 通过
Deliverables (6 files)
circuit_breaker.py— CircuitBreaker + CircuitStatetelemetry.py— Telemetry + RouteSpantfidf_embedder.py— HashEmbedder + create_embed_fnsemantic_retriever.py— 含 ASCII 缩写后处理weave_chains.py— 含 config loader + TF-IDF 集成 + 本地导入chains.yaml— 人类可读的链配置文件
[Phase 3] — 2026-07-08 — SAD 反馈闭环和语义检索
Added
semantic_retriever.py— FMM 分词器 + BM25 SparseIndex + 混合 SemanticRetriever(jieba/FMM/bigram 三级降级)sad_feedback.py— SADFeedback 迭代权重校正闭环dag_composer.py— TaskDecomposer + DAGComposer + DAGPlanweave_chains.py新增init_phase3()/route_task_v3()/compose_task()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
skill_weave_chains-0.1.0.tar.gz
(40.8 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file skill_weave_chains-0.1.0.tar.gz.
File metadata
- Download URL: skill_weave_chains-0.1.0.tar.gz
- Upload date:
- Size: 40.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0aa1919e60775de493dceca976316300fb5a030d606c9a9414e4ec9ab67c922a
|
|
| MD5 |
3d82c94a7956219684d37d0583b50ebb
|
|
| BLAKE2b-256 |
969966cbfb93db6367c201bae6287a0db4717b3fc984f99a10d065947ae883d7
|
File details
Details for the file skill_weave_chains-0.1.0-py3-none-any.whl.
File metadata
- Download URL: skill_weave_chains-0.1.0-py3-none-any.whl
- Upload date:
- Size: 37.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
10a10f9e7777051b614cbfbf56e33833c5fe1cc904e808cb6246e2f17f6e9090
|
|
| MD5 |
074edb21bb0bf602627db4bb082642e8
|
|
| BLAKE2b-256 |
345fdd2ba6f8d06610c127fb98c3f17748536248bbd29fd0e9d359a00e932144
|