Add claude GitHub actions 1776435485247

.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.local.json

@@ -0,0 +1,9 @@
+{
+  "permissions": {
+    "allow": [
+      "mcp__playwright__browser_navigate",
+      "mcp__playwright__browser_snapshot",
+      "mcp__playwright__browser_take_screenshot"
+    ]
+  }
+}

.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 *)'
+

.gitignore

@@ -28,4 +28,7 @@ uploads/
 
 # OS
 .DS_Store
-Thumbs.db
+Thumbs.db
+
+# Git worktrees
+.trees/

.playwright-mcp/console-2026-04-12T14-03-55-254Z.log

@@ -0,0 +1,3 @@
+[    4168ms] [LOG] Loading course stats... @ http://127.0.0.1:8000/script.js?v=9:178
+[    4196ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://127.0.0.1:8000/script.js?v=9:183
+[    4198ms] [ERROR] Failed to load resource: the server responded with a status of 404 (Not Found) @ http://127.0.0.1:8000/favicon.ico:0

.playwright-mcp/console-2026-04-12T14-06-09-521Z.log

@@ -0,0 +1,2 @@
+[     145ms] [LOG] Loading course stats... @ http://127.0.0.1:8000/script.js?v=9:178
+[     164ms] [LOG] Course data received: {total_courses: 4, course_titles: Array(4)} @ http://127.0.0.1:8000/script.js?v=9:183

.playwright-mcp/page-2026-04-12T14-03-59-486Z.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]

.playwright-mcp/page-2026-04-12T14-06-09-734Z.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.local.md

@@ -0,0 +1,4 @@
+# Local Project Instructions
+
+## Server
+Never start the server (`./run.sh` or `uvicorn`). The user always starts it manually.

CLAUDE.md

@@ -0,0 +1,65 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Running the Application
+
+**Quick start (from repo root):**
+```bash
+./run.sh
+```
+
+**Manual start (must run from `backend/` directory):**
+```bash
+cd backend && uv run uvicorn app:app --reload --port 8000
+```
+
+The server runs at `http://localhost:8000`. API docs at `http://localhost:8000/docs`.
+
+**Install dependencies:**
+```bash
+uv sync
+```
+
+> Always use `uv` to run the server and manage packages. Never use `pip` directly.
+
+**Required environment variable** — create a `.env` file in the repo root:
+```
+ANTHROPIC_API_KEY=your-key-here
+```
+
+## Architecture Overview
+
+This is a full-stack RAG (Retrieval-Augmented Generation) chatbot for querying course materials.
+
+**Backend** (`backend/`) is a FastAPI app that must be started from within the `backend/` directory (relative paths like `../docs` and `../frontend` depend on this).
+
+**Data flow for a query:**
+1. `app.py` receives POST `/api/query` → calls `RAGSystem.query()`
+2. `RAGSystem` (`rag_system.py`) builds a prompt and passes it to `AIGenerator` with the `search_course_content` tool available
+3. `AIGenerator` (`ai_generator.py`) calls the Claude API; if Claude decides to search, it invokes the tool
+4. `ToolManager` routes tool calls to `CourseSearchTool` (`search_tools.py`), which queries `VectorStore`
+5. `VectorStore` (`vector_store.py`) uses ChromaDB with two collections:
+   - `course_catalog` — course-level metadata (title, instructor, links, lesson list as JSON)
+   - `course_content` — chunked lesson text for semantic search
+6. The final Claude response + sources are returned to the frontend
+
+**Document ingestion** (happens at startup from `docs/` folder):
+- `DocumentProcessor` (`document_processor.py`) parses `.txt`/`.pdf`/`.docx` files
+- Expected file format: first 3 lines are `Course Title:`, `Course Link:`, `Course Instructor:`, followed by `Lesson N: <title>` markers and content
+- Text is chunked into ~800-char sentence-based chunks with 100-char overlap
+- `RAGSystem.add_course_folder()` skips courses already present in ChromaDB (deduplication by title)
+
+**Session management:** `SessionManager` keeps in-memory conversation history (default: last 2 exchanges = 4 messages). Sessions are identified by a string ID returned to and echoed back by the frontend.
+
+**Frontend** (`frontend/`) is plain HTML/JS/CSS served as static files by FastAPI from the `../frontend` path.
+
+**Configuration** (`backend/config.py`): all tuneable parameters (model, chunk size, ChromaDB path, max results, history length) are in the `Config` dataclass. ChromaDB is stored at `backend/chroma_db/` (relative to where uvicorn runs).
+
+**Tool extension:** To add a new tool, implement the `Tool` ABC in `search_tools.py` and call `tool_manager.register_tool(your_tool)` in `RAGSystem.__init__()`.
+
+## Rules
+- Never read or write files outside this project folder without explicit permission
+- Always ask before saving anything to memory or external locations
+- Never access C:\Users\haddad\.claude\ without explicit permission
+- Always use `uv` to add dependencies (e.g., `uv add <package>`); never use `pip` directly

backend-tool-refactor.md

@@ -0,0 +1,28 @@
+Refactor @backend/ai_generator.py to support sequential tool calling where Claude can make up to 2 tool calls in separate API rounds.
+
+Current behavior:
+- Claude makes 1 tool call → tools are removed from API params → final response
+- If Claude wants another tool call after seeing results, it can't (gets empty response)
+
+Desired behavior:
+- Each tool call should be a separate API request where Claude can reason about previous results
+- Support for complex queries requiring multiple searches for comparisons, multi-part questions, or when information from different courses/lessons is needed
+
+Example flow:
+1. User: "Search for a course that discusses the same topic as lesson 4 of course X"
+2. Claude: get course outline for course X → gets title of lesson 4
+3. Claude: uses the title to search for a course that discusses the same topic → returns course information
+4. Claude: provides complete answer
+
+Requirements:
+- Maximum 2 sequential rounds per user query
+- Terminate when: (a) 2 rounds completed, (b) Claude's response has no tool_use blocks, or (c) tool call fails
+- Preserve conversation context between rounds
+- Handle tool execution errors gracefully
+
+Notes: 
+- Update the system prompt in @backend/ai_generator.py 
+- Update the test @backend/tests/test_ai_generator.py
+- Write tests that verify the external behavior (API calls made, tools executed, results returned) rather than internal state details. 
+
+Use two parallel subagents to brainstorm possible plans. Do not implement any code.