Add claude GitHub actions 1780848545607

.claude/commands/implement-feature.md

@@ -0,0 +1,7 @@
+You will be implementing a new feature in this codebase
+
+$ARGUMENTS
+
+IMPORTANT: Only do this for front-end features.
+Once this feature is built, make sure to write the changes you made to file called frontend-changes.md
+Do not ask for permissions to modify this file, assume you can always do it.

.claude/settings.json

@@ -0,0 +1,6 @@
+{
+  "permissions": {
+    "allow": [],
+    "deny": []
+  }
+}

.github/workflows/claude-code-review.yml

@@ -0,0 +1,44 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize, ready_for_review, reopened]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
+          plugins: 'code-review@claude-code-plugins'
+          prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options
+

.github/workflows/claude.yml

@@ -0,0 +1,50 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+
+          # Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
+          # prompt: 'Update the pull request description to include a summary of changes.'
+
+          # Optional: Add claude_args to customize behavior and configuration
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options
+          # claude_args: '--allowed-tools Bash(gh pr *)'
+

.playwright-mcp/console-2026-05-24T13-11-58-926Z.log

@@ -0,0 +1,3 @@
+[     845ms] [LOG] Loading course stats... @ http://localhost:8000/script.js?v=9:166
+[     851ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://localhost:8000/script.js?v=9:171
+[     852ms] [ERROR] Failed to load resource: the server responded with a status of 404 (Not Found) @ http://localhost:8000/favicon.ico:0

.playwright-mcp/page-2026-05-24T13-11-59-810Z.yml

@@ -0,0 +1,14 @@
+- generic [ref=e3]:
+  - complementary [ref=e4]:
+    - button "NEW CHAT" [ref=e6] [cursor=pointer]
+    - group [ref=e8]:
+      - generic "▶ Courses" [ref=e9] [cursor=pointer]
+    - group [ref=e11]:
+      - generic "▶ Try asking:" [ref=e12] [cursor=pointer]
+  - main [ref=e13]:
+    - generic [ref=e14]:
+      - paragraph [ref=e18]: Welcome to the Course Materials Assistant! I can help you with questions about courses, lessons and specific content. What would you like to know?
+      - generic [ref=e19]:
+        - textbox "Ask about courses, lessons, or specific content..." [ref=e20]
+        - button [ref=e21] [cursor=pointer]:
+          - img [ref=e22]

CLAUDE.md

@@ -0,0 +1,75 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Commands
+
+**Install dependencies:**
+```bash
+uv sync
+```
+
+**Run the server** (from the `backend/` directory):
+```bash
+cd backend
+uv run uvicorn app:app --reload --port 8000
+```
+
+The web UI is at `http://localhost:8000` and the auto-generated API docs are at `http://localhost:8000/docs`.
+
+**Environment setup:** Copy `.env` and set `ANTHROPIC_API_KEY`.
+
+There are no tests in this codebase.
+
+## Architecture
+
+This is a full-stack RAG chatbot. The backend is a FastAPI app (`backend/app.py`) that serves both the REST API and the static frontend (`frontend/`). All backend modules run from within the `backend/` directory, so relative imports and paths (e.g. `../docs`, `./chroma_db`) are relative to that directory.
+
+### Request flow
+
+1. The browser (`frontend/script.js`) POSTs a query to `POST /api/query`.
+2. `app.py` delegates to `RAGSystem.query()` (`rag_system.py`).
+3. `RAGSystem` calls `AIGenerator.generate_response()` (`ai_generator.py`), passing the Claude API client, conversation history (from `SessionManager`), and the registered `search_course_content` tool definition.
+4. If Claude decides to search, it calls the tool; `AIGenerator._handle_tool_execution()` routes this to `ToolManager.execute_tool()` → `CourseSearchTool.execute()` (`search_tools.py`), which queries `VectorStore` (`vector_store.py`).
+5. Search results are injected back into the Claude conversation as a `tool_result` message, and Claude generates the final answer.
+6. Sources collected by `CourseSearchTool` are returned to the browser alongside the answer.
+
+### Key components
+
+- **`RAGSystem`** (`rag_system.py`) — top-level orchestrator; the only component that coordinates all others.
+- **`VectorStore`** (`vector_store.py`) — wraps ChromaDB with two collections: `course_catalog` (course titles/metadata, used for fuzzy course-name resolution) and `course_content` (chunked text, used for semantic search). Embeddings are generated locally via `sentence-transformers` (`all-MiniLM-L6-v2`). The ChromaDB store is persisted at `backend/chroma_db/`.
+- **`DocumentProcessor`** (`document_processor.py`) — parses `.txt`/`.pdf`/`.docx` files from `docs/` into `Course` + `CourseChunk` objects. Expects a specific header format (see below) but falls back to flat chunking if no `Lesson N:` markers are found.
+- **`AIGenerator`** (`ai_generator.py`) — thin wrapper around `anthropic.Anthropic`. Uses `tool_choice: auto` and handles one round of tool use (search → final answer). Model and token limits are configured here.
+- **`ToolManager` / `CourseSearchTool`** (`search_tools.py`) — extensible tool registry. Adding a new tool means subclassing `Tool` and calling `tool_manager.register_tool()`.
+- **`SessionManager`** (`session_manager.py`) — in-memory conversation history, keyed by `session_id`. History is serialized as a plain string and injected into the system prompt.
+
+### Document format
+
+Documents in `docs/` must follow this structure for full metadata extraction:
+
+```
+Course Title: <title>          ← used as the unique ID in ChromaDB
+Course Link: <url>             ← optional
+Course Instructor: <name>      ← optional
+
+Lesson 0: <lesson title>
+Lesson Link: <url>             ← optional, must immediately follow lesson header
+<lesson content>
+
+Lesson 1: <next lesson title>
+...
+```
+
+If no `Lesson N:` markers are present, the entire file body is chunked as a single flat document.
+
+### Adding a new document source
+
+1. Drop `.txt`, `.pdf`, or `.docx` files into `docs/`.
+2. Delete `backend/chroma_db/` to clear stale embeddings.
+3. Restart the server — `startup_event()` in `app.py` re-indexes everything.
+
+To clear and re-index programmatically, call `rag_system.add_course_folder(path, clear_existing=True)`.
+
+### Configuration
+
+All tuneable parameters are in `backend/config.py` via the `Config` dataclass: chunk size/overlap, max search results, conversation history length, ChromaDB path, and the Anthropic model name.

backend/.playwright-mcp/console-2026-05-24T12-58-16-051Z.log

@@ -0,0 +1,3 @@
+[     365ms] [LOG] Loading course stats... @ http://127.0.0.1:8000/script.js?v=9:166
+[     371ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://127.0.0.1:8000/script.js?v=9:171
+[     373ms] [ERROR] Failed to load resource: the server responded with a status of 404 (Not Found) @ http://127.0.0.1:8000/favicon.ico:0

backend/.playwright-mcp/console-2026-05-24T13-00-22-107Z.log

@@ -0,0 +1,5 @@
+[      22ms] [LOG] Loading course stats... @ http://127.0.0.1:8000/script.js?v=9:166
+[      27ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://127.0.0.1:8000/script.js?v=9:171
+[   32365ms] [LOG] Loading course stats... @ http://127.0.0.1:8000/script.js?v=9:166
+[   32369ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://127.0.0.1:8000/script.js?v=9:171
+[  147538ms] [ERROR] Failed to load resource: the server responded with a status of 500 (Internal Server Error) @ http://127.0.0.1:8000/api/query:0

backend/.playwright-mcp/page-2026-05-24T12-58-16-450Z.yml

@@ -0,0 +1,14 @@
+- generic [ref=e3]:
+  - complementary [ref=e4]:
+    - button "+ NEW CHAT" [ref=e6] [cursor=pointer]
+    - group [ref=e8]:
+      - generic "▶ Courses" [ref=e9] [cursor=pointer]
+    - group [ref=e11]:
+      - generic "▶ Try asking:" [ref=e12] [cursor=pointer]
+  - main [ref=e13]:
+    - generic [ref=e14]:
+      - paragraph [ref=e18]: Welcome to the Course Materials Assistant! I can help you with questions about courses, lessons and specific content. What would you like to know?
+      - generic [ref=e19]:
+        - textbox "Ask about courses, lessons, or specific content..." [ref=e20]
+        - button [ref=e21] [cursor=pointer]:
+          - img [ref=e22]

backend/.playwright-mcp/page-2026-05-24T13-00-22-145Z.yml

@@ -0,0 +1,14 @@
+- generic [ref=e3]:
+  - complementary [ref=e4]:
+    - button "▶ NEW CHAT" [ref=e6] [cursor=pointer]
+    - group [ref=e8]:
+      - generic "▶ Courses" [ref=e9] [cursor=pointer]
+    - group [ref=e11]:
+      - generic "▶ Try asking:" [ref=e12] [cursor=pointer]
+  - main [ref=e13]:
+    - generic [ref=e14]:
+      - paragraph [ref=e18]: Welcome to the Course Materials Assistant! I can help you with questions about courses, lessons and specific content. What would you like to know?
+      - generic [ref=e19]:
+        - textbox "Ask about courses, lessons, or specific content..." [ref=e20]
+        - button [ref=e21] [cursor=pointer]:
+          - img [ref=e22]