osiman/reader
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity
67 Commits 1 Branch 0 Tags
6dd8cef347d7a6ed95d545998ef501cb772fc662
Commit Graph
38 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
root 5eb390e3ed docs: 添加 Agent Skill 到项目仓库 
- 复制 reader-digest-flow skill 到 skills/ 目录（含 SKILL.md + references/）
- README 新增 Agent Skill 章节说明供 Agent 使用的工作流
 2026-07-28 18:38:54 +08:00
root 7b791ac947 docs: 重写 README 为项目介绍 
从 MCP 集成技术文档改为完整项目 README，包含：
- 项目定位与核心能力
- 架构概览（流程图 + MCP 工具层 + CLI）
- 快速开始与环境变量
- 项目结构一览
- 关键技术决策说明
- 关键词治理流程
 2026-07-28 16:26:34 +08:00
root cdbcdcd485 feat: pipeline 并行摘要 + 子进程 env 注入 + 循环导入修复 
源码：
- runtime/__init__.py: resume_jobs/resume_service 改为懒加载，打破循环导入
- freshrss_pipeline_jobs.py / resume_jobs.py: 子进程注入 .env 环境变量
- freshrss_pipeline.py: LLM 摘要串行改并行 (ThreadPoolExecutor, max_workers=4)

配置：
- term_aliases: 19→149 条，大幅扩充别名映射
- term_stopwords: 19→132 条，增加过滤规则
- filter_context.personal.json: +7 个兴趣关键词
 2026-07-28 16:24:31 +08:00
root 590d050218 keyword cleanup: v2 engine, alias rule layer, LLM semantic suggestions 
- build_review_bundle.py: 新增 _compute_percentile/_compute_growth,
  候选池从固定阈值改为百分位排名 + 增速因子 (v2 policy)
- term_cleanup_policy.json: 升级 v2 schema
- generate_term_cleanup_suggestions.py: 新增 _prepare_alias_suggestions,
  规则层输出 alias (大小写/单复数/分词变体)
- generate_term_cleanup_semantic_suggestions.py: 新增 LLM 语义建议脚本
  (DeepSeek API, 产出 semantic alias/stopword/promote)
- SKILL.md: 更新为 5 Phase 工作流程
- 首轮清洗 apply: interest 54, aliases 17组, stopwords 17个
- docs/design/keyword-cleanup-flow-overview.md: 流程文档
- plans/: 引擎设计方案
 2026-05-14 17:17:49 +08:00
root 4399c9ca90 feat: digest-brief now includes review candidates (not just keep) 2026-04-28 10:39:54 +08:00
root b29cd8f934 docs: add issue - MCP start_article_summary_job timeout but job actually runs 2026-04-16 11:22:04 +08:00
root 4c4d1a45e6 docs: narrow keyword cleanup skill boundaries 2026-04-14 17:09:23 +08:00
root b8727f1885 feat: add async resume jobs and doc navigation 2026-04-14 15:55:02 +08:00
root 6705613aa4 fix(reader): include all keep candidates in digest brief 2026-04-14 10:10:25 +08:00
root 416414ae1d chore: normalize term stopwords ordering 2026-04-14 09:51:57 +08:00
root f3e7488fc8 docs: add reference templates for IMA notes and public digest 2026-04-14 09:51:57 +08:00
root e3663f681d feat: add keyword cleanup docs, skill updates, and delivery compatibility fix 2026-04-14 09:51:57 +08:00
root a06f2a1d08 chore: update term configs, skill docs and Python 3.10 compat 
- term_change_log: record watch term add history
- term_watchlist: add initial watch terms from cleanup review
- term_aliases: minor update
- filter_context.personal: reorganize interest keywords
- keyword-cleanup-review skill: clarify JSON as formal artifact, markdown as temp review copy
- openclaw_delivery: add Python <3.11 UTC import compat
- daily-keyword-index-design: update suggestion artifact semantics
 2026-04-14 09:51:57 +08:00
root c528e0abc7 fix(article-summary): 修复 article_summary pipeline 的 3 个 bug 
1. Bug 3 (文件名含斜杠导致路径错误):
   - safe_title 生成时用 .replace('/', '-') 处理 '/' 字符
   - 同时清理连续 dash (--+) 和首尾 dash
   - 原本只处理空格，导致含 '/' 的标题写出路径错误

2. Bug 2 (delivery payload 格式不匹配):
   - 新增 '_iter_selected_items' 对 'candidates' 数组格式的支持
   - 自动 normalize selected_ids 的 'cand:' 前缀
   - candidate 条目同时支持 item_id 字段(新增)和 candidate_id(兼容)
   - 传入 delivery payload + candidate_id 时可正常匹配

3. Pipeline 补充 item_id 字段:
   - OpenClawCandidateInput 加 item_id 字段
   - build_openclaw_candidate_input 填充 item_id
   - 使得后续 article-summary 可通过 item_id 关联 extracted 文件
 2026-04-13 17:38:40 +08:00
root 52ce6bfdf5 fix: validate article summary extracted path input 2026-04-11 23:04:13 +08:00
root c58d8114cd feat: add async job entrypoint for freshrss pipeline 2026-04-11 22:12:11 +08:00
root 10f9cd088f fix: fallback to repo .env for reader pipeline settings 2026-04-11 16:29:19 +08:00
root 2053cccfef feat(reader): add async article summary jobs 2026-04-10 16:37:43 +08:00
root 87d18e4263 feat: harden article summary timeout and fallback 2026-04-07 21:08:06 +08:00
root 2df0af5b82 docs: add openclaw orchestration flow for reader MCP 2026-04-07 15:57:39 +08:00
root 4f219ef92f docs: formalize reader MCP workflow service handoff 2026-04-07 15:32:46 +08:00
root c622bc6247 Implement minimal resume_run for freshrss runs 2026-04-07 15:19:44 +08:00
root d91cdbc6c9 docs: narrow resume_run minimal recovery design 2026-04-07 15:00:19 +08:00
root 4a02894c43 Add MCP delivery payload and run report queries 2026-04-07 13:49:06 +08:00
root d9173fbe0f feat: add MCP run status query tools 2026-04-07 11:17:05 +08:00
root 7563aa8fea docs: add reader MCP architecture and implementation plan 2026-04-07 10:57:46 +08:00
root 72a6853c03 Add run-state persistence for FreshRSS pipeline 2026-04-07 10:48:00 +08:00
root 3a85d47f00 docs: record formal digest artifact workflow 2026-04-01 18:32:25 +08:00
root b5ec58cd6a feat: add public digest brief output for openclaw 2026-04-01 16:48:03 +08:00
root 5b51332075 docs: clarify openclaw handoff boundaries 2026-03-31 18:55:15 +08:00
root f72c9ad2b1 docs: translate README to Chinese 2026-03-31 16:05:50 +08:00
root 660f03674b docs: align reader docs with digest SOP defaults 2026-03-31 15:55:15 +08:00
root 7bb9bef12f prd: add article summary prompt independent PRD 2026-03-29 16:10:43 +08:00
root 7dd0894a35 prd: add article summary prompt independent PRD 2026-03-29 16:08:19 +08:00
root 15bbbd9809 Merge branch 'main' of http://119.29.78.52:3000/osiman/reader 2026-03-29 00:54:57 +08:00
root a111c3ddd7 docs: document default daily knowledge base 2026-03-29 00:51:43 +08:00
root 9fd21c59f5 feat: keep per-item extracted outputs by default 2026-03-28 23:14:18 +08:00
root 0a00a97724 feat: add article summary post-processing flow 2026-03-28 00:08:38 +08:00