focus-feed 1.0__tar.gz

focus_feed-1.0/.github/workflows/publish-to-pypi.yml

@@ -0,0 +1,53 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    name: Build distributions
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+
+      - name: Set up Python
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.x"
+
+      - name: Install build frontend
+        run: python -m pip install --upgrade build
+
+      - name: Build source distribution and wheel
+        run: python -m build
+
+      - name: Store distributions
+        uses: actions/upload-artifact@v7
+        with:
+          name: pypi-distributions
+          path: dist/
+          if-no-files-found: error
+
+  publish:
+    name: Publish distributions to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/focus-feed
+    permissions:
+      id-token: write
+    steps:
+      - name: Retrieve distributions
+        uses: actions/download-artifact@v8
+        with:
+          name: pypi-distributions
+          path: dist/
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@v1.14.3

focus_feed-1.0/.gitignore

@@ -0,0 +1,67 @@
+data/
+__pycache__/
+scripts/
+.env
+*.log
+
+# Python bytecode and native extensions
+*.py[cod]
+*$py.class
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+pip-wheel-metadata/
+share/python-wheels/
+
+# Virtual environments
+.venv/
+venv/
+env/
+ENV/
+
+# Test and type-check caches
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+*.pyc
+
+# Coverage
+.coverage
+.coverage.*
+htmlcov/
+.tox/
+.nox/
+coverage.xml
+*.cover
+
+# Jupyter and IDE files
+.ipynb_checkpoints
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.cursor/
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# uv cache
+uv-cache/

focus_feed-1.0/.pre-commit-config.yaml

@@ -0,0 +1,22 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.0
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.13.0
+    hooks:
+      - id: mypy
+        files: ^src/
+        additional_dependencies:
+          - pydantic-settings
+          - pydantic
+          - openai
+          - feedgen
+          - watchdog
+          - faster-whisper
+          - pypdf
+          - beautifulsoup4

focus_feed-1.0/AGENTS.md

@@ -0,0 +1,58 @@
+# AGENTS.md - Focus Feed
+
+Purpose: Transform education content (PDF/HTML/MP4) into RSS feeds.
+
+Command: `uv run focus-feed <command>` from the workspace root (directory containing `src/`, `tests/`, and `data/`).
+
+## Core
+- MP4: Requires `transcribe` → `summarize` → feed-eligible.
+- PDF/HTML: Requires `extract` → `summarize` → feed-eligible.
+- Feeds: Generated only where `feed.json` exists. Requires feed-eligible files.
+
+## Key Commands
+- `process` / `watch`: Process files batch/incrementally.
+- `transcribe`, `summarize`, `extract`, `title`, `feeds`, `validate`, `create-feed`, `cleanup`.
+- Flags: `--force`, `--dry-run`.
+
+## Metadata Schema
+Each file gets a `[filename].json` with:
+```json
+{
+  "title": {"filename": "", "extracted": "", "generated": ""},
+  "description": "", "summary": "", "content": "",
+  "filetype": "mp4|pdf|html", "hash": "sha256...",
+  "date": 1710000000.123, "publication_date": 1710000000.0,
+  "duration": 45.5, "creation_time": "ISO-8601",
+  "transcribe": {"status": "complete"},
+  "summarize": {"status": "complete"},
+  "extract": {"status": "complete"},
+  "generate_title": {"status": "complete"},
+  "error": ""
+}
+```
+
+Feed Eligibility: MP4 = transcribe & summarize complete. PDF/HTML = extract & summarize complete.
+
+Title Rules: `generated` > `extracted` > `filename`. Parent folder name prepended.
+
+## Config (Env Vars)
+Required: `BASE_URL`, `LLM_ENDPOINT`, `LLM_API_KEY`, `LLM_MODEL`, `PROMPT_ARTICLE`, `PROMPT_PODCAST`, `PROMPT_TITLE`.
+
+Optional: `PROMPT_ARTICLE_REFLECTION`, `PROMPT_PODCAST_REFLECTION`, `TRANSCRIPTION_ENDPOINT` (remote overrides local), `TRANSCRIPTION_API_KEY`, `TRANSCRIPTION_REMOTE_MODEL`, `TRANSCRIPTION_MODEL`, `TRANSCRIPTION_DEVICE`, `TRANSCRIPTION_COMPUTE_TYPE`.
+
+## Artifacts
+- `artifacts/proposal.md` - Project proposal and scope.
+- `artifacts/specs.md` - Functional/non-functional specs.
+- `artifacts/design.md` - System architecture and data flow.
+- `artifacts/tasks.md` - Implementation task list.
+
+## Development
+```bash
+uv sync
+uv run pytest
+uv run ruff check
+uv run ruff format
+uv run mypy .
+```
+
+Run commands from workspace root.

focus_feed-1.0/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.5
+Name: focus-feed
+Version: 1.0
+Summary: A local RSS/Atom feed generator for audio, HTML and PDF files
+Requires-Python: >=3.14
+Requires-Dist: av>=11.0
+Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: click>=8.5.0
+Requires-Dist: feedgen>=1.0.0
+Requires-Dist: markdown>=3.5.0
+Requires-Dist: openai>=2.48.0
+Requires-Dist: pydantic-settings>=2.15.0
+Requires-Dist: pydantic>=2.12.0
+Requires-Dist: pypdf>=4.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: watchdog>=3.0.0
+Provides-Extra: local-transcription
+Requires-Dist: faster-whisper>=1.0.0; extra == 'local-transcription'

focus_feed-1.0/README.md

@@ -0,0 +1,286 @@
+# Focus Feed
+
+**Transform your education content into mobile-friendly RSS feeds for podcast and article consumption.**
+
+## Project Summary
+
+Turn disorganized PDF, HTML, and MP4 audio files into RSS feeds for mobile apps.
+
+- Podcast feed - For MP4 audio (Antennapod and other podcast apps)
+- Articles feed - For PDF/HTML documents (any RSS reader)
+- Per-folder feeds - Organize with `feed.json` in subfolders
+- Discovery - Auto-generated `index.html` lists all available feeds
+
+All processing uses your configured endpoints. Optional local transcription available.
+
+**Documentation:**
+- [Proposal](./artifacts/proposal.md) - Problem and scope
+- [Specifications](./artifacts/specs.md) - Detailed requirements
+- [Design Document](./artifacts/design.md) - Architecture
+
+---
+
+## Quick Start
+
+1. **Configure** via environment variables or `.env` file
+
+2. **Process your content** (targeting specific files or directories):
+   ```bash
+   uv run focus-feed process ./videos/lecture.mp4
+   uv run focus-feed process ./documents/ ./videos/
+   ```
+
+3. **Access your feeds** at `{BASE_URL}/index.html`
+
+---
+To process all files, pass your data directory:
+   ```bash
+   uv run focus-feed process ./data
+   ```
+
+---
+
+## Configuration
+
+### Required Environment Variables
+
+- `BASE_URL` - Root URL where data directory is served (e.g., `https://example.com`)
+- `LLM_ENDPOINT` - OpenAI-compatible API endpoint for summarization (can be remote or local)
+- `LLM_API_KEY` - API key for LLM endpoint
+- `LLM_MODEL` - Model identifier for summarization
+- `PROMPT_ARTICLE` - Article summarization prompt (PDF/HTML)
+- `PROMPT_PODCAST` - Podcast summarization prompt (MP4)
+- `PROMPT_TITLE` - Title generation prompt
+
+### Optional Environment Variables
+
+- `PROMPT_ARTICLE_REFLECTION` - Article summarization with reflection questions (default: `PROMPT_ARTICLE`)
+- `PROMPT_PODCAST_REFLECTION` - Podcast summarization with reflection questions (default: `PROMPT_PODCAST`)
+- `TRANSCRIPTION_ENDPOINT` - Remote transcription API endpoint (enables remote mode)
+- `TRANSCRIPTION_API_KEY` - Remote transcription API key
+- `TRANSCRIPTION_REMOTE_MODEL` - Remote transcription model override
+- `TRANSCRIPTION_MODEL` - Local transcription model (default: `large-v3-turbo`)
+- `TRANSCRIPTION_DEVICE` - Transcription device (cuda/cpu) (default: `cuda`)
+- `TRANSCRIPTION_COMPUTE_TYPE` - Compute type for transcription (default: `float16`)
+
+### Example `.env` File
+
+```bash
+# Required
+BASE_URL=https://example.com
+LLM_ENDPOINT=https://llm.example.com/v1
+LLM_API_KEY=your-api-key
+LLM_MODEL=mistralai/Mistral-7B-Instruct
+
+# Prompts
+PROMPT_ARTICLE="Summarize key takeaways from this document concisely in a few paragraphs."
+PROMPT_PODCAST="Summarize key takeaways from this podcast transcript concisely in a few paragraphs."
+PROMPT_TITLE="Generate a concise, descriptive title (5-10 words) for the given content."
+
+# Optional
+PROMPT_ARTICLE_REFLECTION="Summarize with reflection questions: ..."
+PROMPT_PODCAST_REFLECTION="Summarize with reflection questions: ..."
+
+# Transcription (default: local faster-whisper on GPU)
+TRANSCRIPTION_MODEL=large-v3-turbo
+TRANSCRIPTION_DEVICE=cuda
+TRANSCRIPTION_COMPUTE_TYPE=float16
+
+# Remote transcription (optional - overrides local when set)
+# TRANSCRIPTION_ENDPOINT=https://transcription.example.com/v1
+# TRANSCRIPTION_API_KEY=your-transcription-api-key
+```
+
+**Note:** When `TRANSCRIPTION_ENDPOINT` is configured, remote transcription mode is used instead of local faster-whisper.
+
+---
+
+## Processing Modes
+
+### Batch Mode
+
+Process all files at once:
+```bash
+uv run focus-feed process ./data
+```
+
+### Incremental Mode
+
+Watch for new/updated files:
+```bash
+uv run focus-feed watch ./data
+```
+
+---
+
+## Granular Processing
+
+Target specific steps or files by passing files and directories as positional arguments:
+
+- `transcribe` - Transcribe MP4 files to markdown
+- `summarize` - Generate summaries from transcripts or document content
+- `extract` - Extract metadata from PDF/HTML files
+- `title` - Generate titles for files that lack proper titles
+- `feeds` - Generate RSS feeds and index.html
+- `validate` - Validate all metadata files
+- `create-feed` - Create a template `feed.json` in a directory
+- `cleanup` - Remove unknown keys from JSON metadata files
+
+### Common Flags
+
+- `--force` - Force re-processing even if complete
+- `--dry-run` - Preview without making changes (transcribe, summarize, extract)
+- `--config-file <path>` - Use custom `.env` file
+
+### Examples
+
+```bash
+# Process a single file
+uv run focus-feed process ./videos/lecture.mp4
+
+# Force re-transcription of a specific file
+uv run focus-feed transcribe ./videos/lecture.mp4 --force
+
+# Summarize a PDF
+uv run focus-feed summarize ./documents/report.pdf
+
+# Process all files in a directory
+uv run focus-feed process ./documents/
+
+# Process multiple files and directories at once
+uv run focus-feed process ./videos/lecture.mp4 ./documents/report.pdf ./course1/
+
+# See what would be transcribed
+uv run focus-feed transcribe --dry-run
+```
+
+---
+## File Organization
+
+### Directory Structure
+
+```
+data/
+├── index.html                 # Auto-generated: lists all feeds
+├── feed.json                  # REQUIRED for root-level feeds
+├── podcast.xml                # Generated if MP4 files present
+├── articles.xml               # Generated if PDF/HTML files present
+└── Course1/
+    ├── feed.json              # REQUIRED for per-folder feeds
+    ├── podcast.xml            # Course1 audio feed
+    ├── articles.xml           # Course1 articles feed
+    ├── lecture.mp4
+    ├── lecture.mp4.json       # Auto-generated metadata
+    └── reflection.md          # Optional: reflection questions
+```
+
+### feed.json Format
+
+```json
+{
+  "title": "Course 1: Introduction to AI",
+  "description": "All materials for Course 1",
+  "language": "en-us",
+  "author": "Course Author"
+}
+```
+
+**Required:** `title`
+**Optional:** `description`, `language`, `author`, `link`, `image`
+
+### reflection.md (Optional)
+
+Place a `reflection.md` file in any folder to focus summarization on specific questions:
+
+```markdown
+# Reflection Questions
+
+1. What are the key frameworks or mental models presented?
+2. What analytical tools can help develop critical thinking?
+3. How does this content relate to systems thinking?
+```
+
+**Note:** Works with both MP4 and PDF/HTML files. Completely optional.
+
+---
+
+## Feed Generation Rules
+
+- **Podcast feed** (`podcast.xml`): Generated only if `feed.json` exists AND at least one MP4 file is processed
+- **Articles feed** (`articles.xml`): Generated only if `feed.json` exists AND at least one PDF/HTML file is processed
+- **Root-level feeds**: Require `feed.json` in the data directory root
+- **Per-folder feeds**: Require `feed.json` in the subfolder
+- **Index page** (`index.html`): Auto-generated at root, lists all feeds from all folders
+
+---
+## Supported File Types
+
+- **MP4 (audio)** - Transcribed + summarized, Podcast feed, `description=""`, `summary`=key takeaways, `content`=transcript
+- **PDF** - Metadata + content extracted, Articles feed, `description`=metadata, `content`=text, `summary`=null (unless summarized)
+- **HTML** - Metadata + content extracted, Articles feed, `description`=metadata, `content`=text, `summary`=null (unless summarized)
+
+---
+
+## Requirements
+
+### Software
+- Python 3.14+
+- uv - For dependency management
+- LLM Endpoint - OpenAI-compatible API for summarization (can be remote or local)
+- Optional: `ffprobe` - For audio metadata extraction (falls back to file metadata)
+
+### Optional: Local Transcription
+- Nvidia GPU with CUDA - Required for efficient local transcription
+- CUDA Toolkit - Must be installed
+- Models: faster-whisper models (downloaded automatically, ~2-6 GB)
+
+### Models
+- Summarization: Any OpenAI-compatible model with 128K+ context window recommended
+
+---
+
+## Optional Dependencies
+
+### Local Transcription (GPU-accelerated)
+
+```bash
+uv sync --extra local-transcription
+```
+
+Installs `faster-whisper` and `av` for local GPU-accelerated transcription.
+
+---
+
+## Troubleshooting
+
+### Transcription Issues
+
+- **Large files take time**: No time constraints; acceptable for personal use
+- **CUDA out of memory**: Use smaller model (`medium`, `small`, `base`) or `int8` compute type
+- **Model not found**: Verify model name or installation
+
+### Remote Transcription Issues
+
+- **Audio exceeds maximum duration**: Configure vLLM server with `VLLM_MAX_AUDIO_DECODE_DURATION_S=3600` (or higher)
+- **Connection errors**: Verify `TRANSCRIPTION_ENDPOINT` and `TRANSCRIPTION_API_KEY`
+
+### Feed Issues
+
+- **Missing feeds**: Ensure `feed.json` exists and files are processed (check `.json` metadata)
+- **No root feeds**: Root-level `feed.json` is required
+- **Invalid characters**: Control characters in PDF/HTML are automatically removed
+
+### File Processing Issues
+
+- **Special characters**: Warnings are generated; filenames are preserved
+- **Orphaned JSON**: Delete `.json` file to re-process
+- **Force re-processing**: Use `--force` flag
+
+---
+
+## Project Artifacts
+
+- [Proposal](./artifacts/proposal.md) - Problem and scope
+- [Specifications](./artifacts/specs.md) - Detailed requirements
+- [Design Document](./artifacts/design.md) - Architecture
+- [Tasks](./artifacts/tasks.md) - Implementation plan

focus_feed-1.0/artifacts/design.md

@@ -0,0 +1,109 @@
+# Focus Feed - Design
+
+**Runner:** All commands run via `uv run focus-feed <command>` from project root.
+
+## 1. Overview
+Standalone app that processes MP4, PDF, HTML files and generates private RSS feeds for personal consumption. Local-first by default; remote transcription optional.
+
+**Goals**
+- Privacy-first, local processing
+- Idempotent, skips completed files
+- Mobile-ready RSS feeds
+- Per-folder feeds via `feed.json`
+- Auto root `index.html` discovery
+
+## 2. Architecture
+
+**Components**
+- **Scanner & Watcher (`watchdog`):** Recursively discovers files, debounced change detection, periodic rescan fallback for unreliable events
+- **Producer Pipeline:** Queue manager that decides skip/process/resume based on JSON step maps
+  - Transcription Service: MP4 → markdown via faster-whisper local CUDA or remote OpenAI-compatible API
+  - Summarization Service: LLM key takeaways from transcript/extracted text, with reflection.md injection
+  - Extraction Service: PDF/HTML metadata+plaintext via `pypdf`/`beautifulsoup4`; audio metadata via optional `ffprobe` (falls back to file metadata)
+- **Feed Generator (`feedgen`):** Aggregates eligible metadata per feed.json, builds RSS items with enclosure links, pubDate logic, and GUIDs; writes podcast.xml / articles.xml
+- **Index Generator:** Builds root index.html with links/titles/descriptions from all feed.json configs
+- **CLI (`click`) + Config (`pydantic-settings` + `.env`)**
+
+**Data Flow**
+1. Scanner discovers file recursively
+2. If JSON exists, check step statuses. Skip if all applicable steps complete; otherwise resume incomplete steps
+3. Dispatch by type:
+   - MP4: load reflection.md if present → transcribe to markdown → store in content → summarize with reflection prompt → extract audio metadata via optional ffprobe → generate_title via LLM → build title dict → apply parent folder prefix
+   - PDF/HTML: extract metadata & plaintext → sanitize control chars → store description/content → generate_title via LLM → build title dict → apply folder prefix
+4. Write/update JSON with step maps, hash, timestamps
+5. Feed Generator scans for feed.json, collects feed-eligible items from subtree, sorts by folder/filename, converts markdown→HTML with XSS protection, writes podcast.xml / articles.xml
+6. Index Generator updates root index.html with all feeds
+
+## 3. Interfaces & Contracts
+
+**CLI**
+`uv run focus-feed <process|watch|feeds|validate|transcribe|summarize|extract|title|create-feed|cleanup>`
+Flags: `--config-file`, `--force`, `--dry-run`
+
+**Environment**
+Required: BASE_URL, LLM_ENDPOINT, LLM_API_KEY, LLM_MODEL, PROMPT_ARTICLE, PROMPT_PODCAST, PROMPT_TITLE
+Optional: PROMPT_ARTICLE_REFLECTION, PROMPT_PODCAST_REFLECTION, TRANSCRIPTION_ENDPOINT, TRANSCRIPTION_API_KEY, TRANSCRIPTION_MODEL, TRANSCRIPTION_DEVICE, TRANSCRIPTION_COMPUTE_TYPE, TRANSCRIPTION_REMOTE_MODEL
+
+**JSON Metadata**
+Per file `<name>.json` with title dict `{filename,extracted,generated}`, description, summary, content, filetype, dates ms, size, hash, step maps `transcribe/summarize/extract/generate_title` with status/timing, error.
+Title precedence: generated > extracted > filename. Parent folder name auto-prepended.
+
+**Feed Eligibility**
+MP4: transcribe.complete AND summarize.complete
+PDF/HTML: extract.complete AND summarize.complete
+
+Note: Nested feeds include all content from their entire subtree; inner feeds are subsets of outer feeds.
+
+**feed.json**
+Required for feeds. Fields: title required, description, language, author, link, image optional. Aggregates subtree.
+
+**reflection.md**
+Optional per folder. Questions prepended to LLM summarization prompt. Uses reflection prompts if set.
+
+## 4. Technology Stack
+
+**Core deps**
+feedgen, watchdog, openai, pydantic-settings, pydantic, click, pypdf, beautifulsoup4, av, markdown>=3.5.0, python-dotenv
+
+**Transcription**
+- Local default: faster-whisper with CUDA GPU, model large-v3-turbo float16
+- Remote optional: OpenAI-compatible API via TRANSCRIPTION_ENDPOINT. Nvidia GPU not required for remote mode.
+
+**Summarization**
+OpenAI-compatible endpoint. Prompts per filetype. Context 128K+ recommended.
+
+**Extraction**
+PDF: pypdf; HTML: beautifulsoup4; Audio metadata: optional ffprobe with file-metadata fallback. Control characters removed for XML safety.
+
+## 5. Key Decisions
+- Title as dict with provenance for fallback and display
+- LLM title generation for MP4s with sparse metadata
+- Auto folder name prefix for context in readers
+- Regenerate feeds/index after each processing
+- Persistent error state in JSON, manual fix or --force
+- Full plaintext extraction for richer feeds
+- Markdown→HTML with XSS protection
+- Per-folder feeds via feed.json only
+- Optional reflection.md for focused summarization
+- Millisecond precision timestamps
+- Conditional generation: feed.json + eligible files required
+
+## 6. Risks & Mitigations
+Transcription quality → use established models
+LLM inconsistency → tested prompts, configurable
+Watcher misses events → periodic rescan
+Special chars → escape output, warn
+Large audio → acceptable for personal use
+GPU memory → float16, smaller models
+API unavailable → clear errors, retry
+Control chars → auto remove
+Missing feeds → document feed.json requirement
+
+## 7. Assumptions & Dependencies
+- `data/` directory exists and is writable at the workspace root, alongside `src/` and `tests/`
+- Existing web server serves data directory
+- Python 3.14+ and uv for dependency management
+- LLM endpoint available (can be remote or local)
+- Nvidia GPU optional for local transcription; required for best performance in local mode, not needed for remote transcription
+- No ffprobe required by default; audio metadata uses optional ffprobe and falls back to file metadata when unavailable
+- Remote transcription: vLLM server requires `VLLM_MAX_AUDIO_DECODE_DURATION_S` configuration for longer audio files

focus_feed-1.0/artifacts/proposal.md

@@ -0,0 +1,37 @@
+# Education Content Feed System - Proposal
+
+## Problem
+Education files (PDF, HTML, MP4) in `data/` are disconnected. Users cannot consume them efficiently across devices via standard apps.
+
+## User Intent
+Make content accessible via private RSS feeds hosted on an existing internal web server:
+- Podcast feed for Antennapod and podcast apps
+- Articles feed for RSS readers
+Per-folder feeds via `feed.json`, with auto-generated root `index.html` for discovery.
+
+## Scope
+
+### In Scope
+- **Input:** PDF, HTML, MP4 in `data/` directory (at workspace root) and its subfolders
+- **Processing:** Batch and incremental watch mode
+  - MP4: transcribe to markdown, LLM key takeaway summary
+  - PDF/HTML: extract metadata + content; summarization required for feed eligibility
+  - Track steps: `transcribe`, `summarize`, `extract`, `generate_title`
+- **Metadata:** `<filename>.json` per file with title dict `{filename,extracted,generated}`, description, summary, content, dates (ms), hash, size, duration/creation_time, step maps `transcribe/summarize/extract/generate_title`
+  - MP4: description blank, summary = takeaways, content = transcript
+  - PDF/HTML: description = extracted metadata, content = plaintext, summary null unless summarized
+- **Feeds:** `podcast.xml` for MP4, `articles.xml` for PDF/HTML, per-folder only when `feed.json` exists
+- **Features:** `reflection.md` injection, auto folder-name title prefix, markdown→HTML conversion, control character sanitization
+
+### Out of Scope
+- AI agents for metadata gap filling
+- Cloud services by default; remote transcription optional
+- Web server deployment / public distribution
+
+## Success Criteria
+- Content consumable via standard RSS/podcast apps
+- Automatic transcription + summarization for MP4, extraction for PDF/HTML
+- Local-first processing, incremental skips completed files
+- Warnings for orphaned JSONs and special characters
+- Millisecond-precision timestamps, feed eligibility from step statuses
+- Root `index.html` lists all feeds