Reword as intelligent advisory research system

Author: Pigbibi

.github/workflows/monthly_advisory_review.yml

@@ -1,4 +1,4 @@
-name: Monthly Advisory Review
+name: Monthly Intelligent Advisory Review
 
 on:
   workflow_dispatch:

.github/workflows/publish_advisory_site.yml

@@ -1,4 +1,4 @@
-name: Publish Model Recommendations Site
+name: Publish Intelligent Advisory Site
 
 on:
   workflow_dispatch:
@@ -142,7 +142,7 @@ jobs:
             --reports "data/output/published/advisory_report_${AS_OF}.json" \
             --output-dir site \
             --site-url "${SITE_URL}" \
-            --feed-title "量化模型推荐"
+            --feed-title "智慧投顾研究系统"
           cp "data/output/published/advisory_report_${AS_OF}.json" site/
           cp "data/output/published/advisory_report_${AS_OF}.md" site/
           cp "data/output/published/advisory_report_${AS_OF}.json.manifest.json" site/

.github/workflows/weekly_advisory_review.yml

@@ -1,4 +1,4 @@
-name: Weekly Model Recommendations
+name: Weekly Intelligent Advisory Review
 
 on:
   workflow_dispatch:
@@ -69,7 +69,7 @@ jobs:
       - name: Install advisor package
         working-directory: advisor
         run: python -m pip install -e .
-      - name: Build model recommendation report
+      - name: Build intelligent advisory report
         working-directory: advisor
         env:
           INPUT_AS_OF: ${{ github.event.inputs.as_of || '' }}
@@ -123,7 +123,7 @@ jobs:
             "${MARKET_ARGS[@]}" \
             --output-json "data/output/weekly_advisory_review/advisory_report_${AS_OF}.json" \
             --output-md "data/output/weekly_advisory_review/advisory_report_${AS_OF}.md"
-      - name: Upload model recommendation artifact
+      - name: Upload intelligent advisory artifact
         uses: actions/upload-artifact@v7
         with:
           name: weekly-model-recommendations

README.md

@@ -2,24 +2,24 @@
 
 [English](README.md) | [简体中文](README.zh-CN.md)
 
-Non-personalized model recommendation orchestration for QuantStrategyLab.
+Intelligent advisory research system for QuantStrategyLab.
 
-This repository combines deterministic event evidence and saved AI shadow context
-into audit-ready model recommendation reports. It does not place orders, store
-broker credentials, manage portfolios, or personalize advice for a specific
-investor.
+This repository combines deterministic event evidence, theme momentum, market
+confirmation, and saved AI shadow context into investor-readable advisory
+research reports. It does not place orders, store broker credentials, manage
+portfolios, or personalize advice for a specific investor.
 
 ## Repository Role
 
-`QuantAdvisorResearch` is the coordinator for a future smart advisory research
-system:
+`QuantAdvisorResearch` is the coordinator for the Intelligent Advisory Research
+System:
 
 - consume political/public-event context from `PoliticalEventTrackingResearch`
 - consume saved AI shadow context from `ResearchSignalContextPipelines`
 - keep other strategy and snapshot repositories independent from this pipeline
 - leave broker execution in platform repositories
 
-The current operating cadence is a weekly public recommendation snapshot,
+The current operating cadence is a weekly public intelligent-advisory snapshot,
 supported by weekly event/theme refreshes and monthly long-horizon AI shadow
 context. Monthly review reports are generated separately for change review and
 month-end inspection. They do not replace the weekly publication while
@@ -45,17 +45,17 @@ Advisor is the final composition layer. Source ownership by horizon is:
 - Medium term (`2-12 weeks`): `theme_momentum_snapshot.json` from `ResearchSignalContextPipelines`, now explicitly marked as `medium_horizon_theme_context`, focused on theme momentum and symbol momentum.
 - Long term (`1-3 years`): `latest_signal.json` / `signal_history/*.json` from `ResearchSignalContextPipelines` as AI shadow context.
 
-Final recommendations are still deterministic Advisor outputs. The signal context repository does not directly produce short-term recommendations or replace the final decision engine. Advisor now records separate short/medium/long horizon scores and gates for each final pick; public pages keep the simpler final recommendation layout.
+Final recommendations are still deterministic Intelligent Advisory outputs. The signal context repository does not directly produce short-term recommendations or replace the final decision engine. Advisor now records separate short/medium/long horizon scores and gates for each final pick; public pages keep the simpler final recommendation layout.
 
 ## Boundary
 
 This repository owns:
 
-- model recommendation artifact schemas
+- intelligent advisory artifact schemas
 - deterministic scoring and review policy
 - daily/weekly/monthly report generation
 - evidence and risk summaries
-- model recommendation history for later review
+- intelligent advisory history for later review
 
 This repository does not own:
 
@@ -114,7 +114,7 @@ files, create orders, or notify investors.
 
 `.github/workflows/publish_advisory_site.yml` publishes the HTML/JSON/RSS site on
 a weekly schedule. If `TELEGRAM_BOT_TOKEN` and `TELEGRAM_CHAT_ID` are configured
-as repository secrets, the workflow sends a short non-personalized Telegram
+as repository secrets, the workflow sends a short intelligent-advisory Telegram
 summary after a successful Pages deployment. If either secret is missing, the
 notification step is skipped without failing the publication. Telegram delivery
 errors are logged and do not block Pages/RSS output.
@@ -154,15 +154,14 @@ GitHub Pages:
 <https://quantstrategylab.github.io/QuantAdvisorResearch/>
 
 The published HTML, RSS feed title, and Telegram summary default to Simplified
-Chinese (`zh-CN`) because the current audience is Chinese-language retail
-research readers. JSON field names remain stable English contract keys.
+Chinese (`zh-CN`) and use the public-facing Intelligent Advisory Research System wording because the current audience is Chinese-language retail research readers. JSON field names remain stable English contract keys.
 
 The scheduled publish workflow defaults to live source artifacts inside sibling
 repositories. Manual dispatch can normally pass only `as_of`; override paths only
 when intentionally testing a different artifact:
 
 ```bash
-gh workflow run "Publish Model Recommendations Site" \
+gh workflow run "Publish Intelligent Advisory Site" \
   --repo QuantStrategyLab/QuantAdvisorResearch \
   -f as_of=2026-05-30
 ```
@@ -269,7 +268,7 @@ Default horizon windows:
 
 ## Versioning
 
-The Python package version is `0.1.2`. Report artifacts are versioned separately:
+The Python package version is `0.1.3`. Report artifacts are versioned separately:
 
 - report schema: `schema_version = 5`
 - report contract: `model_recommendations.v5`

README.zh-CN.md

@@ -2,7 +2,7 @@
 
 [English](README.md) | [简体中文](README.zh-CN.md)
 
-QuantStrategyLab 的“智慧顾投”研究协调仓库。它生成非个性化模型推荐、推荐理由、适合周期和日/周/月复盘，不下单、不管理仓位、不接券商凭证。
+QuantStrategyLab 的“智慧投顾研究系统”协调仓库。它把事件证据、主题动量、市场确认和 AI shadow 背景整理成普通投资者能读懂的研究结论；不下单、不管理仓位、不接券商凭证，也不做账户级个性化建议。
 
 线上站点：<https://quantstrategylab.github.io/QuantAdvisorResearch/>
 
@@ -13,11 +13,11 @@ QuantStrategyLab 的“智慧顾投”研究协调仓库。它生成非个性化
 - [通知格式](docs/notification_format.zh-CN.md) / [Notification format](docs/notification_format.md)
 - [Artifact contract](docs/advisory_contract.md)
 
-当前运行节奏是：**周度公开推荐 + 周度事件/主题刷新 + 月度 AI shadow 背景 + 单独月度复盘 artifact**。月度复盘只做变化回顾和月末检查；只要报告里仍保留短线 `1-10个交易日` 和中线 `2-12周` 窗口，公开推荐就不应改成月更。
+当前运行节奏是：**周度公开智慧投顾研究 + 周度事件/主题刷新 + 月度 AI shadow 背景 + 单独月度复盘 artifact**。月度复盘只做变化回顾和月末检查；只要报告里仍保留短线 `1-10个交易日` 和中线 `2-12周` 窗口，公开推荐就不应改成月更。
 
 ## 仓库定位
 
-这个仓库把事件研究和 AI shadow 产物组合成 model recommendation artifact：
+这个仓库把事件研究、主题动量、市场确认和 AI shadow 产物组合成智慧投顾研究 artifact：
 
 - `PoliticalEventTrackingResearch`：政治/公开事件事实、催化剂、来源置信度。
 - `ResearchSignalContextPipelines`：已保存的长周期 AI shadow context。
@@ -27,17 +27,17 @@ QuantStrategyLab 的“智慧顾投”研究协调仓库。它生成非个性化
 
 ## 短中长线来源分工
 
-Advisor 是最终合成层，三个周期的输入分工如下：
+智慧投顾研究系统由本仓库做最终合成，三个周期的输入分工如下：
 
 - 短线（1-10 个交易日）：事件/新闻政策催化 + 自动生成的 `market_confirmation.csv`，重点看相对强度、成交量、回撤和波动。
 - 中线（2-12 周）：`ResearchSignalContextPipelines` 的 `theme_momentum_snapshot.json`，现在明确标记为 `medium_horizon_theme_context`，重点看主题动量和个股动量。
 - 长线（1-3 年）：`ResearchSignalContextPipelines` 的 `latest_signal.json` / `signal_history/*.json`，作为 AI shadow 背景。
 
-最终推荐仍由本仓库确定性合成。信号上下文仓库不直接输出短线推荐，也不替代本仓库的最终决策。本仓库会为最终推荐记录短/中/长线独立评分和独立门槛，但公开页面仍保持简洁，只展示最终列表、背景、理由和风险。
+最终研究结论仍由本仓库确定性合成。信号上下文仓库不直接输出短线推荐，也不替代本仓库的最终决策。本仓库会为最终推荐记录短/中/长线独立评分和独立门槛，但公开页面仍保持简洁，只展示最终列表、背景、理由和风险。
 
 ## 当前 MVP
 
-当前实现一个确定性报告生成器：
+当前实现一个确定性的智慧投顾研究报告生成器：
 
 ```bash
 python scripts/build_advisory_report.py \
@@ -85,10 +85,10 @@ manifest 会记录 JSON/Markdown 的 SHA256、`as_of`、cadence、来源 artifac
 
 本仓库负责：
 
-- model recommendation artifact schema
+- 智慧投顾研究 artifact schema
 - 确定性评分和复核规则
 - 日/周/月报告生成
-- 历史模型推荐记录和后续复盘入口
+- 历史智慧投顾研究记录和后续复盘入口
 
 本仓库不负责：
 
@@ -126,11 +126,11 @@ python -m pytest -q
 ## 周度复盘
 
 `.github/workflows/weekly_advisory_review.yml` 会 checkout 本仓库、`PoliticalEventTrackingResearch`
-和 `ResearchSignalContextPipelines`，生成周度 `model_recommendations` 报告并上传为 GitHub Actions artifact。
+和 `ResearchSignalContextPipelines`，生成周度 `model_recommendations` 智慧投顾研究报告并上传为 GitHub Actions artifact。
 
 它不会提交文件、不会通知投资者、不会创建订单。
 
-`.github/workflows/publish_advisory_site.yml` 会每周发布 HTML/JSON/RSS 站点。如果仓库 secrets 配置了 `TELEGRAM_BOT_TOKEN` 和 `TELEGRAM_CHAT_ID`，Pages 部署成功后会发送一条非个性化 Telegram 摘要；如果没配置，通知步骤会跳过；Telegram 发送异常会记录在日志里，但不阻断网页/RSS 发布。
+`.github/workflows/publish_advisory_site.yml` 会每周发布 HTML/JSON/RSS 站点。如果仓库 secrets 配置了 `TELEGRAM_BOT_TOKEN` 和 `TELEGRAM_CHAT_ID`，Pages 部署成功后会发送一条智慧投顾研究 Telegram 摘要；如果没配置，通知步骤会跳过；Telegram 发送异常会记录在日志里，但不阻断网页/RSS 发布。
 
 周度发布是有意保留的：短线结论如果只月更会过期；月度 AI shadow 只提供长周期背景，不作为每周追热点的模型输入。
 
@@ -164,13 +164,13 @@ python scripts/publish_advisory_site.py \
 `.github/workflows/publish_advisory_site.yml` 会部署到 GitHub Pages：
 <https://quantstrategylab.github.io/QuantAdvisorResearch/>
 
-当前公开页面、RSS 标题和 Telegram 摘要默认使用简体中文（`zh-CN`）。
+当前公开页面、RSS 标题和 Telegram 摘要默认使用简体中文（`zh-CN`），并统一使用“智慧投顾研究系统”的对外表述。
 JSON 字段名继续保持英文契约键，避免破坏下游程序读取。
 
 发布 workflow 默认已经读取 `PoliticalEventTrackingResearch` 内的真实 CSV。手工触发通常只需要传日期；只有刻意测试其他 artifact 时才覆盖路径：
 
 ```bash
-gh workflow run "Publish Model Recommendations Site" \
+gh workflow run "Publish Intelligent Advisory Site" \
   --repo QuantStrategyLab/QuantAdvisorResearch \
   -f as_of=2026-05-30
 ```

docs/advisory_contract.md

@@ -1,4 +1,4 @@
-# Model Recommendation Artifact Contract
+# Intelligent Advisory Artifact Contract
 
 ## Report
 
@@ -21,7 +21,7 @@ policy: object
 
 ## Policy
 
-The policy block allows non-personalized model recommendations but keeps account
+The policy block allows non-personalized intelligent-advisory research output but keeps account
 actions and execution disabled:
 
 ```json
@@ -31,7 +31,7 @@ actions and execution disabled:
   "portfolio_allocation_allowed": false,
   "personalized_advice_allowed": false,
   "account_specific_advice_allowed": false,
-  "downstream_use": "Model recommendation research only; do not route to broker execution or account-level allocation."
+  "downstream_use": "Intelligent advisory research only; do not route to broker execution or account-level allocation."
 }
 ```
 
@@ -148,7 +148,7 @@ risk_notes
 
 ## Final Decisions
 
-`final_decisions` is the public recommendation layer. It keeps the simple public
+`final_decisions` is the public Intelligent Advisory recommendation layer. It keeps the simple public
 list while preserving audit details in JSON:
 
 ```text

docs/data_factor_roadmap.md

@@ -4,15 +4,15 @@
 
 ## Current Direction
 
-`QuantAdvisorResearch` should remain the final recommendation repository instead
-of becoming a full multi-factor trading platform.
+`QuantAdvisorResearch` should remain the Intelligent Advisory Research System
+coordinator instead of becoming a full multi-factor trading platform.
 
 Two different research paths should stay separated:
 
 - Backtestable/executable path: price, technical, momentum, volatility, snapshot,
   and strategy repositories that may eventually connect to broker platforms.
 - Event/policy/news/AI-shadow path: less stable evidence that should only produce
-  non-personalized recommendation reports and review artifacts.
+  non-personalized intelligent-advisory reports and review artifacts.
 
 For now, this repository consumes only:
 
@@ -56,7 +56,7 @@ must not directly generate orders, target weights, or account actions.
 
 ### QuantAdvisorResearch
 
-Owns final non-personalized model recommendations:
+Owns final non-personalized intelligent-advisory research output:
 
 - inputs: event CSV, watchlist CSV, saved AI shadow JSON, optional theme momentum, optional market confirmation CSV;
 - outputs: JSON, Markdown, HTML, RSS, and optional Telegram summary;

docs/data_factor_roadmap.zh-CN.md

@@ -4,10 +4,10 @@
 
 ## 当前结论
 
-`QuantAdvisorResearch` 当前应该继续做推荐结论仓库，而不是把所有量化因子仓库接进来。原因是现有组织里已经有两条性质不同的链路：
+`QuantAdvisorResearch` 当前应该继续做智慧投顾研究系统的最终合成仓库，而不是把所有量化因子仓库接进来。原因是现有组织里已经有两条性质不同的链路：
 
 - 可回测、可执行链路：价格、技术、动量、波动、快照和策略仓库，最后可进入券商平台。
-- 新闻、政策、公开事件、AI shadow 链路：证据不稳定、样本少、回测难，应该只进入非个性化模型推荐和复盘。
+- 新闻、政策、公开事件、AI shadow 链路：证据不稳定、样本少、回测难，应该只进入非个性化智慧投顾研究和复盘。
 
 因此本仓库短期只消费 `PoliticalEventTrackingResearch` 和 `ResearchSignalContextPipelines` 的研究产物；`UsEquitySnapshotPipelines`、`UsEquityStrategies`、`CryptoSnapshotPipelines`、`CryptoStrategies` 保持独立，只作为方法参考和未来人工复核资料来源。
 
@@ -51,7 +51,7 @@
 
 ### QuantAdvisorResearch
 
-当前负责最终非个性化模型推荐：
+当前负责最终非个性化智慧投顾研究输出：
 
 - 输入：事件 CSV、watchlist CSV、AI shadow JSON、可选主题动量、可选市场确认 CSV。
 - 输出：`model_recommendations` JSON、Markdown、HTML、RSS。

docs/notification_format.md

@@ -1,4 +1,4 @@
-# Model Recommendation Notification Format
+# Intelligent Advisory Notification Format
 
 ## Implemented Channels
 
@@ -14,7 +14,7 @@
 
 ## Boundary
 
-Default notifications show final recommendations, stock background,
+Default Intelligent Advisory notifications show final recommendations, stock background,
 recommendation reasons, horizon, combined score, and the full report link. Theme
 candidates stay in JSON/Markdown audit material and are not included in the
 default notification summary. Notifications must not show orders, target
@@ -24,7 +24,7 @@ allocation advice.
 ## Telegram Summary Shape
 
 ```text
-量化模型推荐 | 周度 | 2026-05-31
+智慧投顾研究系统 | 周度 | 2026-05-31
 
 本期推荐：
 - MU | 中线 | 综合分=0.85 | 股票背景：Micron 主要做 DRAM、NAND 和 HBM 等存储芯片。
@@ -42,5 +42,5 @@ RSS remains intentionally short for feed readers:
 
 ```text
 主要信号=HBM / 存储, AI 算力平台；推荐=MU, INTC, AMD, VRT, DELL。
-非个性化模型输出；不包含下单、仓位配置或账户级建议。
+智慧投顾研究输出；不包含下单、仓位配置或账户级建议。
 ```

docs/notification_format.zh-CN.md

@@ -1,10 +1,10 @@
-# 模型推荐通知格式
+# 智慧投顾研究通知格式
 
 ## 设计原则
 
-通知可以明确展示“推荐什么标的、为什么、适合短中长哪类周期”。边界不是禁止推荐，而是禁止把模型推荐变成账户级操作：
+通知可以明确展示“推荐什么标的、为什么、适合短中长哪类周期”。边界不是禁止推荐，而是禁止把智慧投顾研究结论变成账户级操作：
 
-- 可以输出非个性化模型推荐、观察、来源核验、暂缓。
+- 可以输出非个性化智慧投顾研究结论、观察、来源核验、暂缓。
 - 可以输出适合周期：短线、中线、长线。
 - 可以输出理由、风险、证据来源和模型分数。
 - 不输出目标仓位、股数、订单类型、账户调仓或个性化适当性结论。
@@ -56,9 +56,9 @@ review_checklist[]
 RSS 只放最短摘要，适合订阅器扫一眼：
 
 ```text
-标题：2026-05-30 周度模型推荐
+标题：2026-05-30 周度智慧投顾研究
 摘要：主要信号=HBM / 存储, AI 算力平台；推荐=MU, INTC, AMD, VRT, DELL。
-     非个性化模型输出；不包含下单、仓位配置或账户级建议。
+     智慧投顾研究输出；不包含下单、仓位配置或账户级建议。
 链接：完整 HTML 报告
 ```
 
@@ -67,7 +67,7 @@ RSS 只放最短摘要，适合订阅器扫一眼：
 Telegram 适合中等长度，最多展示前 3-5 个推荐：
 
 ```text
-量化模型推荐 | 周度 | 2026-05-30
+智慧投顾研究系统 | 周度 | 2026-05-30
 
 本期推荐：
 - MU | 中线 | 综合分=0.85 | 股票背景：Micron 主要做 DRAM、NAND 和 HBM 等存储芯片。
@@ -84,7 +84,7 @@ Telegram 适合中等长度，最多展示前 3-5 个推荐：
 邮件可以放完整列表和复核清单，结构建议：
 
 ```text
-Subject: 量化模型推荐周度复盘 - 2026-05-30
+Subject: 智慧投顾研究周度复盘 - 2026-05-30
 
 1. 本期推荐摘要
 2. 重点推荐