Initial commit

config/delivery.yaml

@@ -0,0 +1,100 @@
+version: 1
+name: Daily News for Markyan04 Delivery Configuration
+timezone: Asia/Shanghai
+
+recipient:
+  email: markyan04@163.com
+  display_name: Hongyu Yan
+
+archive:
+  directory: newspaper
+  write_before_send: true
+  mark_sent_after_success: true
+  formats:
+    - markdown
+    - html
+    - metadata_json
+  naming:
+    markdown: "{YYYY}-{MM}-{DD}-daily-news-for-markyan04.md"
+    html: "{YYYY}-{MM}-{DD}-daily-news-for-markyan04.html"
+    metadata_json: "{YYYY}-{MM}-{DD}-daily-news-for-markyan04.meta.json"
+  metadata_fields:
+    - date
+    - subject
+    - recipient
+    - generated_at
+    - sent_at
+    - delivery_status
+    - source_item_count
+    - filtered_recent_source_item_count
+    - source_error_count
+    - source_errors
+    - source_items
+    - content_hash
+
+email:
+  transport: smtp
+  subject_format_ref: config/newspaper.yaml:title_format
+  body:
+    primary_format: html
+    include_plain_text_fallback: true
+  smtp:
+    host_env: NEWSPAPER_SMTP_HOST
+    port_env: NEWSPAPER_SMTP_PORT
+    username_env: NEWSPAPER_SMTP_USERNAME
+    password_env: NEWSPAPER_SMTP_PASSWORD
+    from_email_env: NEWSPAPER_FROM_EMAIL
+    from_name_env: NEWSPAPER_FROM_NAME
+    security_env: NEWSPAPER_SMTP_SECURITY
+    supported_security:
+      - ssl
+      - starttls
+    timeout_seconds: 30
+  secrets_policy:
+    never_commit_credentials: true
+    require_env_vars: true
+    allow_dotenv_for_local_dev: true
+    dotenv_file: .env
+    dotenv_should_be_gitignored: true
+
+delivery_policy:
+  send_only_after_successful_generation: true
+  do_not_send_if_required_sections_missing: true
+  do_not_send_if_news_items_lack_sources: true
+  max_send_attempts: 3
+  retry_backoff_seconds:
+    - 60
+    - 300
+  failure_behavior:
+    - keep_archived_draft
+    - write_failure_metadata
+    - do_not_mark_sent
+
+automation:
+  preferred_time_local: "08:00"
+  preferred_runner: docker_compose_scheduler
+  timezone: Asia/Shanghai
+  docker_compose_scheduler:
+    schedule_local: "08:00"
+    note: "Run the scheduler service on the Debian server with docker compose. It loops and runs once per local day."
+    required_secrets:
+      - DEEPSEEK_API_KEY
+      - DEEPSEEK_BASE_URL
+      - DEEPSEEK_MODEL
+      - NEWSPAPER_SMTP_HOST
+      - NEWSPAPER_SMTP_PORT
+      - NEWSPAPER_SMTP_USERNAME
+      - NEWSPAPER_SMTP_PASSWORD
+      - NEWSPAPER_FROM_EMAIL
+      - NEWSPAPER_FROM_NAME
+      - NEWSPAPER_SMTP_SECURITY
+  debian_host_cron:
+    cron_local: "0 8 * * *"
+    command: "cd /srv/apps/newspaper && docker compose run --rm newspaper hongyu-daily run"
+    note: "Use this instead of the scheduler service if you prefer host-level cron."
+
+sender_notes:
+  - "The recipient is fixed as markyan04@163.com."
+  - "The sender account is intentionally not fixed here. Use any SMTP-capable mailbox or transactional email provider."
+  - "If a 163 mailbox is used as the sender, enable SMTP/IMAP service in the mailbox settings and use an authorization code rather than the normal login password."
+  - "Keep provider-specific SMTP host and port in environment variables, not in committed code."

config/newspaper.yaml

@@ -0,0 +1,211 @@
+title_format: "Daily News for Markyan04 | YYYY - MM - DD"
+language: zh-CN
+timezone: Asia/Shanghai
+target_reading_minutes: 8-12
+sources_config: config/sources.yaml
+delivery_config: config/delivery.yaml
+archive_dir: newspaper
+
+output_language_policy:
+  newspaper_body: Chinese
+  preserve_common_english_terms: true
+  examples:
+    - RAG
+    - agent
+    - vibe coding
+    - LLMOps
+    - MCP
+    - eBPF
+    - KYC / AML
+
+freshness_policy:
+  daily_collection_required: true
+  do_not_use_model_memory_as_news_source: true
+  news_items_require_source_url: true
+  news_items_require_date_or_collected_at: true
+  default_recent_window_hours: 72
+  prefer_recent_window_hours: 24
+  allow_evergreen_background_when_labeled: true
+  no_fresh_item_behavior: state_no_high_signal_update
+
+sections:
+  summary:
+    weight: 0.05
+    title: 今日汇总
+  general_news:
+    weight: 0.15
+    title: 传统新闻
+  ai:
+    weight: 0.35
+    title: AI领域
+  software_engineering:
+    weight: 0.15
+    title: 传统软工
+  security_performance:
+    weight: 0.12
+    title: 安全与性能工程
+  github:
+    weight: 0.10
+    title: GitHub / 开源项目跟踪
+  finance:
+    weight: 0.08
+    title: 金融领域
+
+general_news:
+  target_items_per_issue:
+    min: 3
+    max: 5
+  priority_topics:
+    - international_politics
+    - us_china_relations
+    - china_hong_kong_policy
+    - russia_ukraine_war
+    - asia_pacific
+    - macroeconomy
+    - market_regulation
+    - financial_regulation
+  style:
+    - summarize_events_before_interpretation
+    - prefer_primary_or_established_newsroom_sources
+    - include_source_metadata_under_title
+
+ai:
+  discovery_map_not_daily_quota: true
+  target_items_per_issue:
+    min: 5
+    max: 8
+  freshness_rules:
+    min_recent_items_when_available: 4
+    recent_window_hours: 72
+    max_evergreen_or_background_items: 2
+    include_fresh_discovery_slot: true
+    do_not_repackage_old_concepts_as_today_news: true
+  priority_topics:
+    - large_language_models
+    - ai_coding_tools
+    - coding_agents
+    - vibe_coding
+    - agent_frameworks
+    - model_context_protocol
+    - multi_agent_systems
+    - llmops
+    - evaluation
+    - evaluation_harness
+    - agent_harness
+    - context_engineering
+    - observability
+    - guardrails
+    - inference_optimization
+    - rag
+    - graphrag
+    - long_context
+    - memory_systems
+    - multimodal_ai
+    - open_source_models
+    - ai_security
+    - new_ai_terms
+    - high_value_papers_and_technical_reports
+  item_template:
+    - what_happened
+    - context
+    - concrete_update
+    - possible_impact
+    - source
+    - published_or_collected_at
+
+software_engineering:
+  priority_topics:
+    - backend_architecture
+    - spring_boot
+    - fastapi
+    - api_design
+    - frontend_engineering
+    - vue
+    - typescript
+    - databases
+    - postgresql
+    - mysql
+    - caching
+    - docker
+    - ci_cd
+    - observability
+    - testing
+    - incident_reviews
+    - maintainability
+
+security_performance:
+  priority_topics:
+    - cve
+    - nvd
+    - cisa_kev
+    - vendor_advisories
+    - exploited_in_the_wild
+    - supply_chain_security
+    - gfw_measurement
+    - network_censorship_research
+    - linux_performance
+    - ebpf
+    - perf
+    - flamegraph
+    - android_performance
+    - systrace
+    - perfetto
+    - database_performance
+  safety_constraints:
+    - do_not_provide_censorship_evasion_tutorials
+    - do_not_provide_operational_bypass_guidance
+
+github:
+  track_user_projects: false
+  priority_topics:
+    - ai_agents
+    - coding_agents
+    - llm_infrastructure
+    - rag_tools
+    - evaluation_tools
+    - developer_tools
+    - security_tools
+    - performance_tools
+    - fintech_infrastructure
+  selection_criteria:
+    - recent_star_growth
+    - active_commits_or_releases
+    - practical_use_case
+    - technical_learning_value
+  exclude:
+    - low_quality_prompt_collections
+    - thin_wrappers
+    - marketing_demos
+    - abandoned_repositories
+
+finance:
+  not_investment_advice: true
+  priority_topics:
+    - interest_rates
+    - bonds
+    - yield_curve
+    - etf
+    - liquidity
+    - market_makers
+    - clearing
+    - settlement
+    - payments
+    - risk_control
+    - anti_fraud
+    - kyc_aml
+    - open_banking
+    - stablecoins
+    - tokenization
+    - ai_in_finance
+    - financial_regulation
+
+negative_constraints:
+  - no_daily_action_checklist
+  - no_internship_or_job_section
+  - no_english_writing_section
+  - no_separate_research_section
+  - no_phd_or_mphil_content
+  - no_supervisor_matching
+  - no_cold_email_content
+  - no_user_project_github_tracking
+  - no_personalized_investment_advice

config/sources.yaml

@@ -0,0 +1,875 @@
+version: 1
+name: Daily News for Markyan04 Source Configuration
+language: zh-CN
+timezone: Asia/Shanghai
+
+purpose:
+  - Provide stable source rules for Daily News for Markyan04.
+  - Separate timely news from evergreen explanation.
+  - Make every newspaper item answer the basic journalistic questions when applicable.
+  - Prefer primary sources and fresh collection over model memory.
+
+journalism_contract:
+  news_questions:
+    who: "谁发布、谁受影响、谁参与"
+    what: "发生了什么具体变化"
+    when: "发布日期、更新时间、事件发生时间或采集时间"
+    where: "发生在哪个机构、产品、地区、生态或仓库"
+    why: "事件的背景、影响范围和后续观察点"
+    how: "证据、机制、技术路径、影响方式或复现条件"
+  required_fields_for_news_like_items:
+    - title
+    - content_class
+    - section
+    - source_name
+    - source_url
+    - source_tier
+    - published_at_or_updated_at
+    - collected_at
+    - who
+    - what
+    - when
+    - where
+    - context_and_impact
+    - how_or_evidence
+  required_fields_for_background_items:
+    - title
+    - content_class
+    - section
+    - trigger_reason
+    - source_name
+    - source_url
+    - explanation
+    - relation_to_section_topic
+  background_items:
+    allowed: true
+    max_per_issue: 3
+    rule: "Background explanations are allowed only when they help understand a fresh item or a recurring important concept."
+    label: "背景理解"
+
+content_classes:
+  breaking_news:
+    time_sensitive: true
+    freshness_window_hours: 24
+    requires_news_questions: true
+  official_release:
+    time_sensitive: true
+    freshness_window_hours: 72
+    requires_news_questions: true
+  technical_report:
+    time_sensitive: true
+    freshness_window_hours: 168
+    requires_news_questions: true
+  paper:
+    time_sensitive: true
+    freshness_window_hours: 168
+    requires_news_questions: true
+    belongs_under_section: ai
+  vulnerability:
+    time_sensitive: true
+    freshness_window_hours: 72
+    requires_news_questions: true
+  github_project_signal:
+    time_sensitive: true
+    freshness_window_hours: 72
+    requires_growth_signal: true
+    requires_news_questions: true
+  explainer:
+    time_sensitive: false
+    requires_trigger_reason: true
+    requires_news_questions: false
+  concept_note:
+    time_sensitive: false
+    requires_trigger_reason: true
+    requires_news_questions: false
+
+source_tiers:
+  official_primary:
+    description: "Official pages, official blogs, official docs, official APIs, university pages, regulator pages."
+    default_weight: 1.0
+  technical_primary:
+    description: "Project repos, release notes, engineering blogs, model cards, arXiv papers, benchmark pages."
+    default_weight: 0.9
+  reputable_secondary:
+    description: "High-quality technical newsletters, established security research, respected independent experts."
+    default_weight: 0.75
+  community_signal:
+    description: "GitHub Trending, Hacker News, social discovery pages. Use for discovery, then verify with primary source."
+    default_weight: 0.55
+  background_reference:
+    description: "Evergreen docs and explainers. Use only as background, not as today's news."
+    default_weight: 0.4
+
+collection_policy:
+  daily_collection_required: true
+  prefer_recent_window_hours: 24
+  default_recent_window_hours: 72
+  collect_before_generate: true
+  no_model_memory_as_news_source: true
+  store_raw_items: true
+  store_normalized_items: true
+  store_snapshots_for_change_only_sources: true
+  deduplicate_by:
+    - canonical_url
+    - normalized_title
+    - source_item_id
+  if_source_unavailable:
+    - retry_once
+    - use_fallback_url_if_configured
+    - mark_source_error
+    - do_not_invent_item
+  if_no_fresh_high_signal_item:
+    behavior: "state_no_high_signal_update"
+    text: "今日未发现高信号更新。"
+
+ranking_policy:
+  score_fields:
+    source_tier: 0.25
+    freshness: 0.20
+    relevance_to_sections: 0.25
+    novelty: 0.15
+    technical_depth: 0.10
+    practical_value: 0.05
+  demote:
+    - no_source_url
+    - no_publication_or_collection_time
+    - repost_without_primary_source
+    - generic_commentary
+    - marketing_without_technical_detail
+    - low_quality_ai_listicle
+  promote:
+    - primary_source
+    - official_release_with_technical_detail
+    - useful_engineering_lessons
+    - affects_ai_engineering_workflow
+    - affects_general_news_or_financial_regulation
+    - active_exploitation_or_urgent_patch
+    - fast_github_growth_with_real_utility
+
+sections:
+  summary:
+    source_strategy: "Use selected high-score items from all sections."
+    max_items: 5
+
+  general_news:
+    source_strategy: "Use established newsrooms plus official regulators for international politics, China/Hong Kong policy, war, and market regulation."
+    recent_window_hours: 72
+    target_items_per_issue:
+      min: 3
+      max: 5
+    allowed_item_classes:
+      - breaking_news
+      - official_release
+      - technical_report
+    priority_topics:
+      - us_china_relations
+      - russia_ukraine_war
+      - china_hong_kong_policy
+      - financial_regulation
+      - macroeconomy
+      - asia_pacific
+    sources:
+      - id: bbc_world
+        name: "BBC World"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.bbc.com/news/world"
+        feed_url: "https://feeds.bbci.co.uk/news/world/rss.xml"
+        access_status: seed
+        tags: [general_news, world, politics]
+      - id: bbc_business
+        name: "BBC Business"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.bbc.com/news/business"
+        feed_url: "https://feeds.bbci.co.uk/news/business/rss.xml"
+        access_status: seed
+        tags: [general_news, business, economy]
+      - id: guardian_world
+        name: "The Guardian World"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.theguardian.com/world"
+        feed_url: "https://www.theguardian.com/world/rss"
+        access_status: seed
+        tags: [general_news, world, politics]
+      - id: guardian_us_news
+        name: "The Guardian US News"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.theguardian.com/us-news"
+        feed_url: "https://www.theguardian.com/us-news/rss"
+        access_status: seed
+        tags: [general_news, US, politics, Trump]
+      - id: aljazeera_all
+        name: "Al Jazeera"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.aljazeera.com/"
+        feed_url: "https://www.aljazeera.com/xml/rss/all.xml"
+        access_status: seed
+        tags: [general_news, world, war, middle_east]
+      - id: nytimes_world
+        name: "The New York Times World"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.nytimes.com/section/world"
+        feed_url: "https://rss.nytimes.com/services/xml/rss/nyt/World.xml"
+        access_status: seed
+        tags: [general_news, world, politics]
+      - id: nytimes_asia_pacific
+        name: "The New York Times Asia Pacific"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.nytimes.com/section/world/asia"
+        feed_url: "https://rss.nytimes.com/services/xml/rss/nyt/AsiaPacific.xml"
+        access_status: seed
+        tags: [general_news, Asia, China, Hong_Kong]
+      - id: npr_world
+        name: "NPR World"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.npr.org/sections/world/"
+        feed_url: "https://feeds.npr.org/1004/rss.xml"
+        access_status: seed
+        tags: [general_news, world, politics]
+      - id: un_news
+        name: "UN News"
+        kind: rss
+        source_tier: official_primary
+        url: "https://news.un.org/en/"
+        feed_url: "https://news.un.org/feed/subscribe/en/news/all/rss.xml"
+        access_status: seed
+        tags: [general_news, UN, war, humanitarian]
+      - id: google_news_trump_china_visit
+        name: "Google News Search - Trump China Visit"
+        kind: rss
+        source_tier: community_signal
+        url: "https://news.google.com/search?q=Trump%20China%20visit"
+        feed_url: "https://news.google.com/rss/search?q=Trump%20China%20visit&hl=zh-CN&gl=US&ceid=US:zh-Hans"
+        access_status: seed
+        tags: [general_news, US_China, Trump, discovery]
+      - id: google_news_russia_ukraine
+        name: "Google News Search - Russia Ukraine War"
+        kind: rss
+        source_tier: community_signal
+        url: "https://news.google.com/search?q=Russia%20Ukraine%20war"
+        feed_url: "https://news.google.com/rss/search?q=Russia%20Ukraine%20war&hl=zh-CN&gl=US&ceid=US:zh-Hans"
+        access_status: seed
+        tags: [general_news, Russia, Ukraine, war, discovery]
+      - id: google_news_csrc_hk_brokers
+        name: "Google News Search - CSRC Hong Kong Brokers"
+        kind: rss
+        source_tier: community_signal
+        url: "https://news.google.com/search?q=CSRC%20Hong%20Kong%20brokers"
+        feed_url: "https://news.google.com/rss/search?q=CSRC%20Hong%20Kong%20brokers%20OR%20%E4%B8%AD%E5%9B%BD%E8%AF%81%E7%9B%91%E4%BC%9A%20%E9%A6%99%E6%B8%AF%E5%88%B8%E5%95%86&hl=zh-CN&gl=HK&ceid=HK:zh-Hans"
+        access_status: seed
+        tags: [general_news, China, Hong_Kong, securities, regulation, discovery]
+      - id: china_csrc_news
+        name: "China Securities Regulatory Commission"
+        kind: official_html
+        source_tier: official_primary
+        url: "http://www.csrc.gov.cn/csrc/c100028/common_list.shtml"
+        access_status: seed
+        tags: [general_news, China, securities, regulation]
+      - id: hong_kong_sfc_news
+        name: "Hong Kong SFC News"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.sfc.hk/en/News-and-announcements/News"
+        access_status: seed
+        tags: [general_news, Hong_Kong, securities, regulation]
+      - id: china_mfa_news
+        name: "China MFA News"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.mfa.gov.cn/eng/xw/"
+        access_status: seed
+        tags: [general_news, China, diplomacy, US_China]
+
+  ai:
+    source_strategy: "Broad fresh scan, then selective reporting. Topic list is a discovery map, not a quota."
+    target_items_per_issue:
+      min: 5
+      max: 8
+    min_recent_items_when_available: 4
+    recent_window_hours: 72
+    max_background_items: 2
+    include_fresh_discovery_slot: true
+    allowed_item_classes:
+      - breaking_news
+      - official_release
+      - technical_report
+      - paper
+      - github_project_signal
+      - explainer
+      - concept_note
+    sources:
+      - id: openai_news
+        name: "OpenAI News"
+        kind: rss
+        source_tier: official_primary
+        url: "https://openai.com/news/"
+        feed_url: "https://openai.com/news/rss.xml"
+        access_status: verified_2026_07_04
+        tags: [AI, LLM, agents, models, product]
+      - id: anthropic_news
+        name: "Anthropic News"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.anthropic.com/news"
+        access_status: verified_2026_07_04
+        tags: [AI, LLM, Claude, agents, safety]
+      - id: google_deepmind_blog
+        name: "Google DeepMind Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://deepmind.google/discover/blog/"
+        access_status: seed
+        tags: [AI, LLM, multimodal, research, agents]
+      - id: google_ai_blog
+        name: "Google AI Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://blog.google/technology/ai/"
+        access_status: seed
+        tags: [AI, LLM, Gemini, product, engineering]
+      - id: meta_ai_blog
+        name: "Meta AI Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://ai.meta.com/blog/"
+        access_status: seed
+        tags: [AI, Llama, open_source_models, multimodal]
+      - id: microsoft_ai_blog
+        name: "Microsoft AI Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://blogs.microsoft.com/ai/"
+        access_status: seed
+        tags: [AI, Copilot, agents, enterprise_ai]
+      - id: microsoft_research_blog
+        name: "Microsoft Research Blog"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://www.microsoft.com/en-us/research/blog/"
+        feed_url: "https://www.microsoft.com/en-us/research/feed/"
+        access_status: seed
+        tags: [AI, research, agents, systems, engineering]
+      - id: mistral_news
+        name: "Mistral AI News"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://mistral.ai/news/"
+        access_status: seed
+        tags: [AI, LLM, open_models, agents]
+      - id: cohere_blog
+        name: "Cohere Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://cohere.com/blog"
+        access_status: seed
+        tags: [AI, LLM, enterprise_ai, RAG]
+      - id: qwen_blog
+        name: "Qwen Blog"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://qwenlm.github.io/blog/"
+        access_status: seed
+        tags: [AI, LLM, open_source_models, multimodal]
+      - id: huggingface_blog
+        name: "Hugging Face Blog"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://huggingface.co/blog"
+        feed_url: "https://huggingface.co/blog/feed.xml"
+        access_status: slow_or_unverified_2026_07_04
+        tags: [AI, open_source_models, datasets, inference, tooling]
+      - id: aws_ml_blog
+        name: "AWS Machine Learning Blog"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://aws.amazon.com/blogs/machine-learning/"
+        feed_url: "https://aws.amazon.com/blogs/machine-learning/feed/"
+        access_status: seed
+        tags: [AI, LLMOps, deployment, inference, cloud]
+      - id: nvidia_ai_blog
+        name: "NVIDIA Technical Blog - Generative AI"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://developer.nvidia.com/blog/category/generative-ai/"
+        feed_url: "https://developer.nvidia.com/blog/category/generative-ai/feed/"
+        access_status: seed
+        tags: [AI, inference, GPU, deployment, multimodal]
+      - id: langchain_blog
+        name: "LangChain Blog"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://blog.langchain.com/"
+        feed_url: "https://blog.langchain.com/rss/"
+        access_status: seed
+        tags: [AI, agents, RAG, LLMOps, evaluation]
+      - id: llamaindex_blog
+        name: "LlamaIndex Blog"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://www.llamaindex.ai/blog"
+        access_status: seed
+        tags: [AI, RAG, agents, data_frameworks]
+      - id: vllm_blog
+        name: "vLLM Blog"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://blog.vllm.ai/"
+        access_status: seed
+        tags: [AI, inference, serving, open_source_models]
+      - id: ollama_blog
+        name: "Ollama Blog"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://ollama.com/blog"
+        access_status: seed
+        tags: [AI, local_models, developer_tools, open_source_models]
+      - id: vercel_ai_blog
+        name: "Vercel AI Blog"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://vercel.com/blog/category/ai"
+        access_status: seed
+        tags: [AI, frontend_ai, ai_sdk, agents, engineering]
+      - id: cursor_changelog
+        name: "Cursor Changelog"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://cursor.com/changelog"
+        access_status: seed
+        tags: [AI, coding_agent, vibe_coding, developer_tools]
+      - id: arxiv_cs_cl
+        name: "arXiv cs.CL"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://arxiv.org/list/cs.CL/recent"
+        feed_url: "https://export.arxiv.org/rss/cs.CL"
+        access_status: seed
+        tags: [AI, NLP, LLM, papers]
+      - id: arxiv_cs_ai
+        name: "arXiv cs.AI"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://arxiv.org/list/cs.AI/recent"
+        feed_url: "https://export.arxiv.org/rss/cs.AI"
+        access_status: seed
+        tags: [AI, agents, reasoning, papers]
+      - id: arxiv_cs_lg
+        name: "arXiv cs.LG"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://arxiv.org/list/cs.LG/recent"
+        feed_url: "https://export.arxiv.org/rss/cs.LG"
+        access_status: seed
+        tags: [AI, machine_learning, papers]
+      - id: simon_willison
+        name: "Simon Willison"
+        kind: atom
+        source_tier: reputable_secondary
+        url: "https://simonwillison.net/"
+        feed_url: "https://simonwillison.net/atom/everything/"
+        access_status: verified_2026_07_04
+        tags: [AI, LLM, tools, agents, engineering]
+      - id: latent_space
+        name: "Latent Space"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://www.latent.space/"
+        feed_url: "https://www.latent.space/feed"
+        access_status: seed
+        tags: [AI, LLM, agents, industry_analysis]
+      - id: deeplearning_ai_the_batch
+        name: "The Batch by DeepLearning.AI"
+        kind: rss_or_html
+        source_tier: reputable_secondary
+        url: "https://www.deeplearning.ai/the-batch/"
+        access_status: seed
+        tags: [AI, weekly_news, explainers]
+
+  software_engineering:
+    source_strategy: "Prefer engineering blogs, release notes, incident reviews, and deep technical writeups."
+    recent_window_hours: 168
+    allowed_item_classes:
+      - official_release
+      - technical_report
+      - explainer
+      - concept_note
+    sources:
+      - id: github_engineering
+        name: "GitHub Engineering"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://github.blog/engineering/"
+        feed_url: "https://github.blog/engineering/feed/"
+        access_status: seed
+        tags: [software_engineering, developer_tools, scaling, devops]
+      - id: cloudflare_blog
+        name: "Cloudflare Blog"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://blog.cloudflare.com/"
+        feed_url: "https://blog.cloudflare.com/rss/"
+        access_status: verified_2026_07_04
+        tags: [software_engineering, networking, security, performance]
+      - id: netflix_techblog
+        name: "Netflix TechBlog"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://netflixtechblog.com/"
+        feed_url: "https://netflixtechblog.com/feed"
+        access_status: seed
+        tags: [software_engineering, distributed_systems, reliability]
+      - id: uber_engineering
+        name: "Uber Engineering"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://www.uber.com/blog/engineering/"
+        access_status: seed
+        tags: [software_engineering, backend, data, platform]
+      - id: stripe_engineering
+        name: "Stripe Engineering"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://stripe.com/blog/engineering"
+        access_status: seed
+        tags: [software_engineering, fintech, infrastructure, reliability]
+      - id: martin_fowler
+        name: "Martin Fowler"
+        kind: atom
+        source_tier: reputable_secondary
+        url: "https://martinfowler.com/"
+        feed_url: "https://martinfowler.com/feed.atom"
+        access_status: seed
+        tags: [software_design, architecture, refactoring]
+      - id: acm_queue
+        name: "ACM Queue"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://queue.acm.org/"
+        feed_url: "https://queue.acm.org/rss/feeds/queuecontent.xml"
+        access_status: seed
+        tags: [software_engineering, systems, architecture]
+      - id: spring_blog
+        name: "Spring Blog"
+        kind: atom
+        source_tier: technical_primary
+        url: "https://spring.io/blog"
+        feed_url: "https://spring.io/blog.atom"
+        access_status: seed
+        tags: [software_engineering, Java, Spring_Boot, backend]
+      - id: vue_blog
+        name: "Vue Blog"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://blog.vuejs.org/"
+        feed_url: "https://blog.vuejs.org/feed.rss"
+        access_status: seed
+        tags: [software_engineering, Vue, frontend, TypeScript]
+      - id: postgresql_news
+        name: "PostgreSQL News"
+        kind: rss
+        source_tier: official_primary
+        url: "https://www.postgresql.org/about/news/"
+        feed_url: "https://www.postgresql.org/about/news/rss/"
+        access_status: seed
+        tags: [software_engineering, database, PostgreSQL]
+
+  security_performance:
+    source_strategy: "Prioritize official advisories for urgent risk and deep technical sources for learning."
+    recent_window_hours: 72
+    allowed_item_classes:
+      - vulnerability
+      - breaking_news
+      - official_release
+      - technical_report
+      - explainer
+      - concept_note
+    safety_constraints:
+      - do_not_provide_censorship_evasion_tutorials
+      - do_not_provide_operational_bypass_guidance
+    sources:
+      - id: cisa_kev
+        name: "CISA Known Exploited Vulnerabilities Catalog"
+        kind: json
+        source_tier: official_primary
+        url: "https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json"
+        access_status: verified_2026_07_04
+        tags: [security, CVE, exploited_in_the_wild, urgent_patch]
+      - id: cisa_advisories
+        name: "CISA Cybersecurity Advisories"
+        kind: rss_or_html
+        source_tier: official_primary
+        url: "https://www.cisa.gov/news-events/cybersecurity-advisories"
+        feed_url: "https://www.cisa.gov/cybersecurity-advisories/all.xml"
+        access_status: seed
+        tags: [security, advisories, vulnerability]
+      - id: nvd_cve_api
+        name: "NVD CVE API"
+        kind: api
+        source_tier: official_primary
+        url: "https://services.nvd.nist.gov/rest/json/cves/2.0"
+        access_status: seed
+        tags: [security, CVE, vulnerability]
+      - id: github_advisory_api
+        name: "GitHub Security Advisory API"
+        kind: api
+        source_tier: official_primary
+        url: "https://api.github.com/advisories"
+        access_status: seed
+        tags: [security, supply_chain, dependencies]
+      - id: google_project_zero
+        name: "Google Project Zero"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://googleprojectzero.blogspot.com/"
+        feed_url: "https://googleprojectzero.blogspot.com/feeds/posts/default"
+        access_status: seed
+        tags: [security, vulnerability_research, browser, OS]
+      - id: trail_of_bits_blog
+        name: "Trail of Bits Blog"
+        kind: rss
+        source_tier: technical_primary
+        url: "https://blog.trailofbits.com/"
+        feed_url: "https://blog.trailofbits.com/feed/"
+        access_status: seed
+        tags: [security, supply_chain, code_audit, vulnerability_research]
+      - id: portswigger_research
+        name: "PortSwigger Research"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://portswigger.net/research"
+        feed_url: "https://portswigger.net/research/rss"
+        access_status: seed
+        tags: [security, web_security, vulnerability_research]
+      - id: ooni_blog
+        name: "OONI Blog"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://ooni.org/blog/"
+        feed_url: "https://ooni.org/index.xml"
+        access_status: seed
+        tags: [GFW, network_measurement, censorship_research]
+      - id: citizen_lab
+        name: "Citizen Lab"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://citizenlab.ca/"
+        feed_url: "https://citizenlab.ca/feed/"
+        access_status: seed
+        tags: [GFW, censorship_research, surveillance, security]
+      - id: censored_planet
+        name: "Censored Planet Publications"
+        kind: official_html
+        source_tier: technical_primary
+        url: "https://censoredplanet.org/publications"
+        access_status: seed
+        tags: [GFW, network_measurement, censorship_research]
+      - id: lwn_headlines
+        name: "LWN Headlines"
+        kind: rss
+        source_tier: reputable_secondary
+        url: "https://lwn.net/"
+        feed_url: "https://lwn.net/headlines/rss"
+        access_status: verified_2026_07_04
+        tags: [Linux, kernel, performance, systems]
+      - id: brendan_gregg
+        name: "Brendan Gregg"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://www.brendangregg.com/blog/"
+        feed_url: "https://www.brendangregg.com/blog/rss.xml"
+        access_status: seed
+        tags: [Linux, performance, eBPF, FlameGraph, observability]
+      - id: ebpf_blog
+        name: "eBPF.io Blog"
+        kind: rss_or_html
+        source_tier: technical_primary
+        url: "https://ebpf.io/blog/"
+        access_status: seed
+        tags: [Linux, eBPF, observability, performance]
+
+  github:
+    source_strategy: "Use community signals for discovery, then verify project value on GitHub repo, releases, commits, and issues."
+    recent_window_hours: 72
+    track_user_projects: false
+    allowed_item_classes:
+      - github_project_signal
+      - technical_report
+    source_rules:
+      require_repo_url: true
+      require_growth_or_activity_signal: true
+      require_project_summary: true
+      do_not_select_prompt_collections_without_engineering_value: true
+    sources:
+      - id: github_trending_daily
+        name: "GitHub Trending Daily"
+        kind: html
+        source_tier: community_signal
+        url: "https://github.com/trending?since=daily"
+        access_status: seed
+        tags: [GitHub, open_source, discovery]
+      - id: github_trending_weekly
+        name: "GitHub Trending Weekly"
+        kind: html
+        source_tier: community_signal
+        url: "https://github.com/trending?since=weekly"
+        access_status: seed
+        tags: [GitHub, open_source, discovery]
+      - id: github_trending_python
+        name: "GitHub Trending Python"
+        kind: html
+        source_tier: community_signal
+        url: "https://github.com/trending/python?since=weekly"
+        access_status: seed
+        tags: [GitHub, Python, AI, tools]
+      - id: github_trending_typescript
+        name: "GitHub Trending TypeScript"
+        kind: html
+        source_tier: community_signal
+        url: "https://github.com/trending/typescript?since=weekly"
+        access_status: seed
+        tags: [GitHub, TypeScript, AI, developer_tools]
+      - id: github_search_api_ai_agents
+        name: "GitHub Search API - AI Agents"
+        kind: api
+        source_tier: community_signal
+        url: "https://api.github.com/search/repositories"
+        query_template: "agents ai stars:>200 pushed:>{date_minus_30d}"
+        access_status: seed
+        tags: [GitHub, AI, agents, discovery]
+      - id: github_search_api_llm_infra
+        name: "GitHub Search API - LLM Infrastructure"
+        kind: api
+        source_tier: community_signal
+        url: "https://api.github.com/search/repositories"
+        query_template: "llm inference stars:>200 pushed:>{date_minus_30d}"
+        access_status: seed
+        tags: [GitHub, LLM, inference, infrastructure]
+      - id: github_search_api_security_tools
+        name: "GitHub Search API - Security Tools"
+        kind: api
+        source_tier: community_signal
+        url: "https://api.github.com/search/repositories"
+        query_template: "security tool stars:>500 pushed:>{date_minus_30d}"
+        access_status: seed
+        tags: [GitHub, security, tools]
+
+  finance:
+    source_strategy: "Use official regulators and central banks first. Use fintech media only as discovery, not as investment advice."
+    recent_window_hours: 168
+    allowed_item_classes:
+      - breaking_news
+      - official_release
+      - technical_report
+      - explainer
+      - concept_note
+    not_investment_advice: true
+    sources:
+      - id: hkma_press_releases
+        name: "Hong Kong Monetary Authority Press Releases"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.hkma.gov.hk/eng/news-and-media/press-releases/"
+        access_status: verified_2026_07_04
+        tags: [finance, fintech, Hong_Kong, banking, regulation]
+      - id: mas_news
+        name: "Monetary Authority of Singapore News"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.mas.gov.sg/news"
+        access_status: verified_2026_07_04
+        tags: [finance, fintech, Singapore, banking, regulation]
+      - id: federal_reserve_press
+        name: "Federal Reserve Press Releases"
+        kind: rss
+        source_tier: official_primary
+        url: "https://www.federalreserve.gov/newsevents/pressreleases.htm"
+        feed_url: "https://www.federalreserve.gov/feeds/press_all.xml"
+        access_status: verified_2026_07_04
+        tags: [finance, rates, banking, regulation, macro]
+      - id: bis_press
+        name: "Bank for International Settlements Press Releases"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.bis.org/press/pressrels.htm"
+        access_status: verified_2026_07_04
+        tags: [finance, central_banks, payments, regulation]
+      - id: bis_innovation_hub
+        name: "BIS Innovation Hub"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.bis.org/about/bisih/"
+        access_status: seed
+        tags: [finance, fintech, CBDC, tokenization, payments]
+      - id: sec_news
+        name: "SEC Newsroom"
+        kind: official_html
+        source_tier: official_primary
+        url: "https://www.sec.gov/newsroom"
+        access_status: protected_or_dynamic_2026_07_04
+        tags: [finance, securities, regulation, fintech]
+      - id: finextra
+        name: "Finextra"
+        kind: rss_or_html
+        source_tier: reputable_secondary
+        url: "https://www.finextra.com/"
+        access_status: seed
+        tags: [finance, fintech, payments, banking]
+      - id: chainalysis_blog
+        name: "Chainalysis Blog"
+        kind: rss_or_html
+        source_tier: reputable_secondary
+        url: "https://www.chainalysis.com/blog/"
+        access_status: seed
+        tags: [finance, crypto, compliance, AML, stablecoins]
+
+global_search_queries:
+  general_news:
+    - "\"Trump\" \"China visit\" OR \"特朗普\" \"访华\""
+    - "\"Russia Ukraine war\" \"latest\" OR \"俄乌战争\""
+    - "\"CSRC\" \"Hong Kong brokers\" OR \"中国证监会\" \"香港券商\""
+    - "\"US China\" \"tariff\" OR \"中美关系\" \"关税\""
+    - "\"Hong Kong\" \"securities regulator\" OR \"香港\" \"证券监管\""
+  ai:
+    - "\"AI agent\" OR \"coding agent\" OR \"vibe coding\""
+    - "\"agent harness\" OR \"evaluation harness\" OR \"context engineering\""
+    - "\"LLMOps\" OR \"model routing\" OR \"prompt caching\" OR \"agent evaluation\""
+    - "\"MCP\" \"agent\" \"release\""
+    - "\"RAG\" \"evaluation\" OR \"GraphRAG\""
+    - "\"computer use\" \"agent\" \"AI\""
+  software_engineering:
+    - "\"incident review\" \"engineering\""
+    - "\"PostgreSQL\" \"performance\" \"release\""
+    - "\"Spring Boot\" \"release\""
+    - "\"Vue\" \"TypeScript\" \"release\""
+  security_performance:
+    - "\"CVE\" \"exploited in the wild\""
+    - "\"CISA KEV\" \"added\""
+    - "\"eBPF\" \"performance\""
+    - "\"Linux perf\" \"FlameGraph\""
+    - "\"network censorship measurement\" OR \"GFW measurement\""
+  github:
+    - "\"GitHub\" \"AI agent\" \"stars\""
+    - "\"open source\" \"LLM infrastructure\""
+    - "\"RAG\" \"GitHub\" \"release\""
+  finance:
+    - "\"fintech\" \"HKMA\""
+    - "\"fintech\" \"MAS\""
+    - "\"stablecoin\" \"regulation\""
+    - "\"tokenization\" \"BIS\""
+
+output_rules:
+  cite_every_news_item: true
+  cite_background_items: true
+  show_dates_for_news_items: true
+  source_label_format: "{source_name}, {published_at_or_updated_at}"
+  stale_item_policy: "Do not include stale news unless explicitly labeled as background."
+  primary_source_verification_for_secondary_items: "Required when item makes factual claims about releases, vulnerabilities, market regulation, or official policy."
+  metadata_placement: "Put source, date, and link directly under each item title."
+  prose_style: "Write paragraphs. Do not use formulaic labels such as 为何重要, 学习启示, 对你来说, 来源, 时间 as sectioned bullets inside the body."