clawfeedradar 0.1.0__tar.gz

clawfeedradar-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

clawfeedradar-0.1.0/PKG-INFO

@@ -0,0 +1,218 @@
+Metadata-Version: 2.4
+Name: clawfeedradar
+Version: 0.1.0
+Summary: Personal feed radar built on clawsqlite interest clusters
+Author: Ernest Yu
+License: MIT
+Project-URL: Homepage, https://github.com/ernestyu/clawfeedradar
+Project-URL: Repository, https://github.com/ernestyu/clawfeedradar.git
+Keywords: rss,recommendation,clawsqlite,feed
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# clawfeedradar
+
+Personal "reading radar" built on top of `clawsqlite`: it pulls articles from Hacker News / RSS / arXiv and ranks them against your existing knowledge base, generating a personalized RSS feed with optional bilingual summaries.
+
+> Goal: simple, controllable, auditable, and loosely coupled with `clawsqlite`. This document describes the **current v1 implementation** (branch `bot/20260402-embedding`).
+
+---
+
+## When running inside OpenClaw
+
+clawfeedradar expects an existing `clawsqlite` knowledge base with interest clusters.
+
+In an OpenClaw workspace, the recommended way to set this up is:
+
+1. **Install the `clawsqlite-knowledge` skill** (if not already installed):
+
+   ```bash
+   openclaw skills add clawsqlite-knowledge
+   ```
+
+   Or via the web catalog:
+
+   - <https://clawhub.ai/skills/clawsqlite-knowledge>
+
+2. **Initialize and build interest clusters** using that skill (see the skill README for the exact commands).
+
+Once `clawsqlite-knowledge` is installed and has built `interest_clusters`, clawfeedradar can attach to the same DB and reuse the interest space for scoring.
+
+---
+
+## Overview
+
+clawfeedradar does three things:
+
+1. **Fetch candidates from external sources**  
+   Currently HN RSS and generic RSS are supported; arXiv and others can be added later.
+2. **Score candidates using `clawsqlite` interest clusters**  
+   It uses embeddings + interest clusters to estimate how well each candidate matches your long-term interests, then applies light recency / popularity bias.
+3. **Generate an RSS feed with optional bilingual content**  
+   For selected items it scrapes fulltext, calls a small LLM to produce preview summary + bilingual body, and writes an XML + JSON pair.
+
+In short: **`clawsqlite` knows what you like; `clawfeedradar` goes out, finds similar content, and feeds it to your RSS reader.**
+
+---
+
+## Quick start
+
+### 1. Prepare environment
+
+Assume a workspace like:
+
+```text
+~/.openclaw/workspace/
+  ├── clawsqlite          # clawsqlite repo
+  ├── knowledge_data      # your clawsqlite-knowledge DB
+  ├── clawfeedradar       # this repo
+  └── clawfetch / ...     # fulltext scraper + wrapper
+```
+
+Make sure `clawsqlite` has built interest clusters:
+
+```bash
+cd ~/.openclaw/workspace/clawsqlite
+clawsqlite knowledge build-interest-clusters \
+  --root ~/.openclaw/workspace/knowledge_data
+```
+
+### 2. Configure clawfeedradar
+
+```bash
+cd ~/.openclaw/workspace/clawfeedradar
+cp ENV.example .env
+# edit .env for your local setup
+```
+
+You need to configure at least:
+
+- clawsqlite knowledge base
+  - `CLAWSQLITE_ROOT` pointing to `knowledge_data`
+  - `CLAWSQLITE_DB` if you want an explicit sqlite path
+- Embedding service (shared with clawsqlite)
+  - `EMBEDDING_BASE_URL` / `EMBEDDING_MODEL` / `EMBEDDING_API_KEY`
+  - `CLAWSQLITE_VEC_DIM` must match the embedding model dimension
+- Output directory
+  - `CLAWFEEDRADAR_OUTPUT_DIR` for XML/JSON output
+- Fulltext scraping
+  - `CLAWFEEDRADAR_SCRAPE_CMD` pointing to a wrapper that calls `clawfetch`
+  - `CLAWFEEDRADAR_SCRAPE_WORKERS` controlling parallelism (per-host serialization still applies)
+- Small LLM (summaries + bilingual body)
+  - `SMALL_LLM_BASE_URL` / `SMALL_LLM_MODEL` / `SMALL_LLM_API_KEY`
+  - `CLAWFEEDRADAR_LLM_CONTEXT_TOKENS` (approx token budget, internally converted to char budget)
+  - `CLAWFEEDRADAR_LLM_MAX_PARAGRAPH_CHARS` (screen-sized bilingual segments)
+  - `CLAWFEEDRADAR_LLM_SLEEP_BETWEEN_MS`
+  - `CLAWFEEDRADAR_LLM_SOURCE_LANG` / `CLAWFEEDRADAR_LLM_TARGET_LANG`
+- Scoring weights
+  - `CLAWFEEDRADAR_W_RECENCY`
+  - `CLAWFEEDRADAR_W_POPULARITY`
+  - `CLAWFEEDRADAR_RECENCY_HALF_LIFE_DAYS`
+  - `CLAWFEEDRADAR_INTEREST_SIGMOID_K` (steepness of S-shaped stretching around 0.5)
+- Default item count
+  - `CLAWFEEDRADAR_MAX_ITEMS` as the default when `--max-items` is omitted
+
+### 3. Run a single feed (debug)
+
+```bash
+cd ~/.openclaw/workspace/clawfeedradar
+python -m clawfeedradar.cli run \
+  --root ~/.openclaw/workspace/orgmode/clawsqlite/data \
+  --url https://feeds.bbci.co.uk/news/technology/rss.xml \
+  --output ./feeds/bbc-tech.xml \
+  --max-source-items 15 \
+  --score-threshold 0.4 \
+  --max-items 12 \
+  --source-lang en \
+  --target-lang zh
+```
+
+This produces:
+
+- `./feeds/bbc-tech.xml`  
+  RSS feed where `<description>` combines:
+  - `summary_preview` (short summary in target language) and
+  - `body_bilingual` (full bilingual body, screen-sized segments).
+- `./feeds/bbc-tech.json`  
+  Sidecar JSON containing `fulltext`, `summary_preview`, `body_bilingual`, and scoring details including:
+  - `interest_score` (S-shaped stretched score)
+  - `interest_score_raw` (linear interest score)
+  - `final_score`
+  - `best_cluster_id` / `best_cluster_weight`
+
+---
+
+## Publishing feeds via Git (GitHub Pages / Gitee Pages)
+
+clawfeedradar can optionally push the generated XML/JSON to a git repository,
+so that GitHub Pages or Gitee Pages can host your feed at a stable HTTPS URL.
+
+### 1) GitHub Pages example
+
+1. 创建一个公开仓库，例如：`github.com/yourname/clawfeedradar-feed`，在 Settings → Pages 中
+   启用 Pages 功能，选择：
+
+   - Branch: `gh-pages`
+   - Directory: `/` 或 `feeds/`（下面示例使用 `feeds/`）
+
+2. 在运行 clawfeedradar 的机器上，配置好 git 访问 GitHub 的方式（SSH key 或 HTTPS+PAT）。
+
+3. 在 `.env` 中添加：
+
+   ```env
+   CLAWFEEDRADAR_PUBLISH_GIT_REPO=git@github.com:yourname/clawfeedradar-feed.git
+   CLAWFEEDRADAR_PUBLISH_GIT_BRANCH=gh-pages
+   CLAWFEEDRADAR_PUBLISH_GIT_PATH=feeds
+   ```
+
+4. 之后每次运行 `clawfeedradar run` / `schedule`：
+
+   - clawfeedradar 会在本地 `./.publish/yourname-clawfeedradar-feed/` 下维护一个 clone；
+   - 将生成的 `*.xml` / `*.json` 拷贝到该 clone 的 `feeds/` 目录；
+   - 自动执行 `git add` / `git commit` / `git push`。
+
+5. 最终订阅地址类似于：
+
+   ```text
+   https://yourname.github.io/clawfeedradar-feed/feeds/bbc-tech.xml
+   ```
+
+### 2) Gitee Pages example（适合国内网络）
+
+步骤与 GitHub 类似，只是把远端换成 Gitee：
+
+1. 创建 Gitee 仓库，例如：`gitee.com/yourname/clawfeedradar-feed`，在 Pages 设置中
+   启用 Gitee Pages（选择对应分支和目录）。
+
+2. 在运行环境中配置好访问 `git@gitee.com:...` 的 SSH key。
+
+3. 在 `.env` 中添加：
+
+   ```env
+   CLAWFEEDRADAR_PUBLISH_GIT_REPO=git@gitee.com:yourname/clawfeedradar-feed.git
+   CLAWFEEDRADAR_PUBLISH_GIT_BRANCH=gh-pages
+   CLAWFEEDRADAR_PUBLISH_GIT_PATH=feeds
+   ```
+
+4. 之后 clawfeedradar 的行为与 GitHub 情况一致：每次生成 XML/JSON 后自动
+   `git add` / `commit` / `push` 到 Gitee 仓库。
+
+5. Gitee Pages 的订阅地址通常类似：
+
+   ```text
+   https://yourname.gitee.io/clawfeedradar-feed/feeds/bbc-tech.xml
+   ```
+
+如未配置 `CLAWFEEDRADAR_PUBLISH_GIT_REPO`，clawfeedradar 仅在本地写 XML/JSON，
+不会尝试推送任何远端仓库。
+
+---
+
+## Configuration (env overview)
+
+（其余章节与之前相同，略）

clawfeedradar-0.1.0/README.md

@@ -0,0 +1,201 @@
+# clawfeedradar
+
+Personal "reading radar" built on top of `clawsqlite`: it pulls articles from Hacker News / RSS / arXiv and ranks them against your existing knowledge base, generating a personalized RSS feed with optional bilingual summaries.
+
+> Goal: simple, controllable, auditable, and loosely coupled with `clawsqlite`. This document describes the **current v1 implementation** (branch `bot/20260402-embedding`).
+
+---
+
+## When running inside OpenClaw
+
+clawfeedradar expects an existing `clawsqlite` knowledge base with interest clusters.
+
+In an OpenClaw workspace, the recommended way to set this up is:
+
+1. **Install the `clawsqlite-knowledge` skill** (if not already installed):
+
+   ```bash
+   openclaw skills add clawsqlite-knowledge
+   ```
+
+   Or via the web catalog:
+
+   - <https://clawhub.ai/skills/clawsqlite-knowledge>
+
+2. **Initialize and build interest clusters** using that skill (see the skill README for the exact commands).
+
+Once `clawsqlite-knowledge` is installed and has built `interest_clusters`, clawfeedradar can attach to the same DB and reuse the interest space for scoring.
+
+---
+
+## Overview
+
+clawfeedradar does three things:
+
+1. **Fetch candidates from external sources**  
+   Currently HN RSS and generic RSS are supported; arXiv and others can be added later.
+2. **Score candidates using `clawsqlite` interest clusters**  
+   It uses embeddings + interest clusters to estimate how well each candidate matches your long-term interests, then applies light recency / popularity bias.
+3. **Generate an RSS feed with optional bilingual content**  
+   For selected items it scrapes fulltext, calls a small LLM to produce preview summary + bilingual body, and writes an XML + JSON pair.
+
+In short: **`clawsqlite` knows what you like; `clawfeedradar` goes out, finds similar content, and feeds it to your RSS reader.**
+
+---
+
+## Quick start
+
+### 1. Prepare environment
+
+Assume a workspace like:
+
+```text
+~/.openclaw/workspace/
+  ├── clawsqlite          # clawsqlite repo
+  ├── knowledge_data      # your clawsqlite-knowledge DB
+  ├── clawfeedradar       # this repo
+  └── clawfetch / ...     # fulltext scraper + wrapper
+```
+
+Make sure `clawsqlite` has built interest clusters:
+
+```bash
+cd ~/.openclaw/workspace/clawsqlite
+clawsqlite knowledge build-interest-clusters \
+  --root ~/.openclaw/workspace/knowledge_data
+```
+
+### 2. Configure clawfeedradar
+
+```bash
+cd ~/.openclaw/workspace/clawfeedradar
+cp ENV.example .env
+# edit .env for your local setup
+```
+
+You need to configure at least:
+
+- clawsqlite knowledge base
+  - `CLAWSQLITE_ROOT` pointing to `knowledge_data`
+  - `CLAWSQLITE_DB` if you want an explicit sqlite path
+- Embedding service (shared with clawsqlite)
+  - `EMBEDDING_BASE_URL` / `EMBEDDING_MODEL` / `EMBEDDING_API_KEY`
+  - `CLAWSQLITE_VEC_DIM` must match the embedding model dimension
+- Output directory
+  - `CLAWFEEDRADAR_OUTPUT_DIR` for XML/JSON output
+- Fulltext scraping
+  - `CLAWFEEDRADAR_SCRAPE_CMD` pointing to a wrapper that calls `clawfetch`
+  - `CLAWFEEDRADAR_SCRAPE_WORKERS` controlling parallelism (per-host serialization still applies)
+- Small LLM (summaries + bilingual body)
+  - `SMALL_LLM_BASE_URL` / `SMALL_LLM_MODEL` / `SMALL_LLM_API_KEY`
+  - `CLAWFEEDRADAR_LLM_CONTEXT_TOKENS` (approx token budget, internally converted to char budget)
+  - `CLAWFEEDRADAR_LLM_MAX_PARAGRAPH_CHARS` (screen-sized bilingual segments)
+  - `CLAWFEEDRADAR_LLM_SLEEP_BETWEEN_MS`
+  - `CLAWFEEDRADAR_LLM_SOURCE_LANG` / `CLAWFEEDRADAR_LLM_TARGET_LANG`
+- Scoring weights
+  - `CLAWFEEDRADAR_W_RECENCY`
+  - `CLAWFEEDRADAR_W_POPULARITY`
+  - `CLAWFEEDRADAR_RECENCY_HALF_LIFE_DAYS`
+  - `CLAWFEEDRADAR_INTEREST_SIGMOID_K` (steepness of S-shaped stretching around 0.5)
+- Default item count
+  - `CLAWFEEDRADAR_MAX_ITEMS` as the default when `--max-items` is omitted
+
+### 3. Run a single feed (debug)
+
+```bash
+cd ~/.openclaw/workspace/clawfeedradar
+python -m clawfeedradar.cli run \
+  --root ~/.openclaw/workspace/orgmode/clawsqlite/data \
+  --url https://feeds.bbci.co.uk/news/technology/rss.xml \
+  --output ./feeds/bbc-tech.xml \
+  --max-source-items 15 \
+  --score-threshold 0.4 \
+  --max-items 12 \
+  --source-lang en \
+  --target-lang zh
+```
+
+This produces:
+
+- `./feeds/bbc-tech.xml`  
+  RSS feed where `<description>` combines:
+  - `summary_preview` (short summary in target language) and
+  - `body_bilingual` (full bilingual body, screen-sized segments).
+- `./feeds/bbc-tech.json`  
+  Sidecar JSON containing `fulltext`, `summary_preview`, `body_bilingual`, and scoring details including:
+  - `interest_score` (S-shaped stretched score)
+  - `interest_score_raw` (linear interest score)
+  - `final_score`
+  - `best_cluster_id` / `best_cluster_weight`
+
+---
+
+## Publishing feeds via Git (GitHub Pages / Gitee Pages)
+
+clawfeedradar can optionally push the generated XML/JSON to a git repository,
+so that GitHub Pages or Gitee Pages can host your feed at a stable HTTPS URL.
+
+### 1) GitHub Pages example
+
+1. 创建一个公开仓库，例如：`github.com/yourname/clawfeedradar-feed`，在 Settings → Pages 中
+   启用 Pages 功能，选择：
+
+   - Branch: `gh-pages`
+   - Directory: `/` 或 `feeds/`（下面示例使用 `feeds/`）
+
+2. 在运行 clawfeedradar 的机器上，配置好 git 访问 GitHub 的方式（SSH key 或 HTTPS+PAT）。
+
+3. 在 `.env` 中添加：
+
+   ```env
+   CLAWFEEDRADAR_PUBLISH_GIT_REPO=git@github.com:yourname/clawfeedradar-feed.git
+   CLAWFEEDRADAR_PUBLISH_GIT_BRANCH=gh-pages
+   CLAWFEEDRADAR_PUBLISH_GIT_PATH=feeds
+   ```
+
+4. 之后每次运行 `clawfeedradar run` / `schedule`：
+
+   - clawfeedradar 会在本地 `./.publish/yourname-clawfeedradar-feed/` 下维护一个 clone；
+   - 将生成的 `*.xml` / `*.json` 拷贝到该 clone 的 `feeds/` 目录；
+   - 自动执行 `git add` / `git commit` / `git push`。
+
+5. 最终订阅地址类似于：
+
+   ```text
+   https://yourname.github.io/clawfeedradar-feed/feeds/bbc-tech.xml
+   ```
+
+### 2) Gitee Pages example（适合国内网络）
+
+步骤与 GitHub 类似，只是把远端换成 Gitee：
+
+1. 创建 Gitee 仓库，例如：`gitee.com/yourname/clawfeedradar-feed`，在 Pages 设置中
+   启用 Gitee Pages（选择对应分支和目录）。
+
+2. 在运行环境中配置好访问 `git@gitee.com:...` 的 SSH key。
+
+3. 在 `.env` 中添加：
+
+   ```env
+   CLAWFEEDRADAR_PUBLISH_GIT_REPO=git@gitee.com:yourname/clawfeedradar-feed.git
+   CLAWFEEDRADAR_PUBLISH_GIT_BRANCH=gh-pages
+   CLAWFEEDRADAR_PUBLISH_GIT_PATH=feeds
+   ```
+
+4. 之后 clawfeedradar 的行为与 GitHub 情况一致：每次生成 XML/JSON 后自动
+   `git add` / `commit` / `push` 到 Gitee 仓库。
+
+5. Gitee Pages 的订阅地址通常类似：
+
+   ```text
+   https://yourname.gitee.io/clawfeedradar-feed/feeds/bbc-tech.xml
+   ```
+
+如未配置 `CLAWFEEDRADAR_PUBLISH_GIT_REPO`，clawfeedradar 仅在本地写 XML/JSON，
+不会尝试推送任何远端仓库。
+
+---
+
+## Configuration (env overview)
+
+（其余章节与之前相同，略）

clawfeedradar-0.1.0/clawfeedradar/__init__.py

@@ -0,0 +1,8 @@
+# -*- coding: utf-8 -*-
+"""clawfeedradar package.
+
+v0 目标：
+- 从配置和 SQLite 知识库中构建兴趣簇视图；
+- 接收一批 Candidate（可先用假数据），跑打分 + 多样性 + 探索逻辑；
+- 输出 JSON（后续再接真实源、RSS 和 LLM）。
+"""