refactor: Remove Playwright dependency completely from project
- Replace Playwright base image with python:3.12-slim in Dockerfile - Remove playwright from pyproject.toml dependencies - Remove ensure_playwright_browsers() function from mcp_server_main.py - Delete KİK v1 client files (client.py, models.py) - v2 uses httpx - Delete postinstall.sh Playwright installation script - Delete obsolete setup.py and requirements.txt.bak - Remove saidsurucu-yargi-mcp-f5fa007 snapshot directory - Update client_v2.py docstring to reflect httpx usage - Regenerate uv.lock without playwright KİK v2 now uses pure httpx for all HTTP operations with SSL legacy support.
This commit is contained in:
saidsurucu
+2
-2
@@ -1,5 +1,5 @@
|
||||
# -------- BASE IMAGE (includes Chromium & deps) ----------------------------
|
||||
FROM mcr.microsoft.com/playwright/python:v1.53.0-noble
|
||||
# -------- BASE IMAGE ---------------------------------------------------------
|
||||
FROM python:3.12-slim
|
||||
|
||||
# -------- Runtime setup ----------------------------------------------------
|
||||
WORKDIR /app
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -325,7 +325,7 @@ class KikV2ApiClient:
|
||||
|
||||
This method uses a two-step process:
|
||||
1. Call GetSorgulamaUrl endpoint to get the actual document URL
|
||||
2. Use Playwright to navigate to that URL and extract content
|
||||
2. Use httpx to fetch the document content
|
||||
|
||||
Args:
|
||||
document_id: The gundemMaddesiId from search results
|
||||
|
||||
@@ -1,74 +0,0 @@
|
||||
# kik_mcp_module/models.py
|
||||
from pydantic import BaseModel, Field, HttpUrl, computed_field, ConfigDict
|
||||
from typing import List, Optional
|
||||
from enum import Enum
|
||||
import base64 # Base64 encoding/decoding için
|
||||
|
||||
class KikKararTipi(str, Enum):
|
||||
"""Enum for KIK (Public Procurement Authority) Decision Types."""
|
||||
UYUSMAZLIK = "rbUyusmazlik"
|
||||
DUZENLEYICI = "rbDuzenleyici"
|
||||
MAHKEME = "rbMahkeme"
|
||||
|
||||
class KikSearchRequest(BaseModel):
|
||||
"""Model for KIK Decision search criteria."""
|
||||
karar_tipi: KikKararTipi = Field(KikKararTipi.UYUSMAZLIK, description="Type")
|
||||
karar_no: str = Field("", description="No")
|
||||
karar_tarihi_baslangic: str = Field("", description="Start", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
karar_tarihi_bitis: str = Field("", description="End", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
resmi_gazete_sayisi: str = Field("", description="Gazette")
|
||||
resmi_gazete_tarihi: str = Field("", description="Date", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
basvuru_konusu_ihale: str = Field("", description="Subject")
|
||||
basvuru_sahibi: str = Field("", description="Applicant")
|
||||
ihaleyi_yapan_idare: str = Field("", description="Entity")
|
||||
yil: str = Field("", description="Year")
|
||||
karar_metni: str = Field("", description="Text")
|
||||
page: int = Field(1, ge=1, description="Page")
|
||||
|
||||
class KikDecisionEntry(BaseModel):
|
||||
"""Represents a single decision entry from KIK search results."""
|
||||
preview_event_target: str = Field(..., description="Event target")
|
||||
karar_no_str: str = Field(..., alias="kararNo", description="Decision number")
|
||||
karar_tipi: KikKararTipi = Field(..., description="Decision type")
|
||||
|
||||
karar_tarihi_str: str = Field(..., alias="kararTarihi", description="Date")
|
||||
idare_str: str = Field("", alias="idare", description="Entity")
|
||||
basvuru_sahibi_str: str = Field("", alias="basvuruSahibi", description="Applicant")
|
||||
ihale_konusu_str: str = Field("", alias="ihaleKonusu", description="Subject")
|
||||
|
||||
@computed_field
|
||||
@property
|
||||
def karar_id(self) -> str:
|
||||
"""
|
||||
A Base64 encoded unique ID for the decision, combining decision type and number.
|
||||
Format before encoding: "{karar_tipi.value}|{karar_no_str}"
|
||||
"""
|
||||
combined_key = f"{self.karar_tipi.value}|{self.karar_no_str}"
|
||||
return base64.b64encode(combined_key.encode('utf-8')).decode('utf-8')
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True)
|
||||
|
||||
class KikSearchResult(BaseModel):
|
||||
"""Model for KIK search results."""
|
||||
decisions: List[KikDecisionEntry]
|
||||
total_records: int = 0
|
||||
current_page: int = 1
|
||||
|
||||
class KikDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
KIK decision document, with Markdown content potentially paginated.
|
||||
"""
|
||||
retrieved_with_karar_id: Optional[str] = Field(None, description="Request ID")
|
||||
retrieved_karar_no: Optional[str] = Field(None, description="Decision number")
|
||||
retrieved_karar_tipi: Optional[KikKararTipi] = Field(None, description="Decision type")
|
||||
|
||||
karar_id_param_from_url: Optional[str] = Field(None, alias="kararIdParam", description="Internal ID")
|
||||
markdown_chunk: Optional[str] = Field(None, description="Content")
|
||||
source_url: Optional[str] = Field(None, description="Source URL")
|
||||
error_message: Optional[str] = Field(None, description="Error")
|
||||
current_page: int = Field(1, description="Page")
|
||||
total_pages: int = Field(1, description="Total pages")
|
||||
is_paginated: bool = Field(False, description="Paginated")
|
||||
full_content_char_count: Optional[int] = Field(None, description="Char count")
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True)
|
||||
+2
-35
@@ -2191,47 +2191,14 @@ async def fetch(
|
||||
|
||||
# --- Token Metrics Tool Removed for Optimization ---
|
||||
|
||||
def ensure_playwright_browsers():
|
||||
"""Ensure Playwright browsers are installed for KIK tool functionality."""
|
||||
try:
|
||||
import subprocess
|
||||
import os
|
||||
|
||||
# Check if chromium is already installed
|
||||
chromium_path = os.path.expanduser("~/Library/Caches/ms-playwright/chromium-1179")
|
||||
if os.path.exists(chromium_path):
|
||||
logger.info("Playwright Chromium browser already installed.")
|
||||
return
|
||||
|
||||
logger.info("Installing Playwright Chromium browser for KIK tool...")
|
||||
result = subprocess.run(
|
||||
["python", "-m", "playwright", "install", "chromium"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=300 # 5 minutes timeout
|
||||
)
|
||||
|
||||
if result.returncode == 0:
|
||||
logger.info("Playwright Chromium browser installed successfully.")
|
||||
else:
|
||||
logger.warning(f"Failed to install Playwright browser: {result.stderr}")
|
||||
logger.warning("KIK tool may not work properly without Playwright browsers.")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not auto-install Playwright browsers: {e}")
|
||||
logger.warning("KIK tool may not work properly. Manual installation: 'playwright install chromium'")
|
||||
|
||||
def main():
|
||||
# Initialize the app properly with create_app()
|
||||
global app
|
||||
app = create_app()
|
||||
|
||||
|
||||
logger.info(f"Starting {app.name} server via main() function...")
|
||||
# logger.info(f"Logs will be written to: {LOG_FILE_PATH}") # File logging disabled
|
||||
|
||||
# Ensure Playwright browsers are installed
|
||||
ensure_playwright_browsers()
|
||||
|
||||
|
||||
try:
|
||||
app.run()
|
||||
except KeyboardInterrupt:
|
||||
|
||||
@@ -1,7 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Post-install script for FastMCP Cloud
|
||||
# Installs Chromium browser for Playwright
|
||||
|
||||
echo "Installing Playwright Chromium browser..."
|
||||
playwright install chromium
|
||||
echo "Chromium installation complete."
|
||||
@@ -25,7 +25,6 @@ dependencies = [
|
||||
"markitdown[pdf]>=0.1.1",
|
||||
"pydantic>=2.11.4",
|
||||
"aiohttp>=3.11.18",
|
||||
"playwright>=1.52.0",
|
||||
"fastmcp>=2.10.5",
|
||||
"pypdf>=5.5.0",
|
||||
"fastapi>=0.115.14",
|
||||
|
||||
@@ -1,11 +0,0 @@
|
||||
fastmcp
|
||||
httpx
|
||||
beautifulsoup4
|
||||
markitdown[pdf]
|
||||
pydantic
|
||||
aiohttp
|
||||
playwright
|
||||
pypdf
|
||||
fastapi>=0.115.14
|
||||
uvicorn[standard]>=0.30.0
|
||||
starlette>=0.37.0
|
||||
@@ -1,186 +0,0 @@
|
||||
# flyctl launch added from .gitignore
|
||||
# Byte-compiled / optimized / DLL files
|
||||
**/__pycache__
|
||||
**/*.py[cod]
|
||||
**/*$py.class
|
||||
|
||||
# C extensions
|
||||
**/*.so
|
||||
|
||||
# Distribution / packaging
|
||||
**/.Python
|
||||
**/build
|
||||
**/develop-eggs
|
||||
**/dist
|
||||
**/downloads
|
||||
**/eggs
|
||||
**/.eggs
|
||||
**/lib
|
||||
**/lib64
|
||||
**/parts
|
||||
**/sdist
|
||||
**/var
|
||||
**/wheels
|
||||
**/share/python-wheels
|
||||
**/*.egg-info
|
||||
**/.installed.cfg
|
||||
**/*.egg
|
||||
**/MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
**/*.manifest
|
||||
**/*.spec
|
||||
|
||||
# Installer logs
|
||||
**/pip-log.txt
|
||||
**/pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
**/htmlcov
|
||||
**/.tox
|
||||
**/.nox
|
||||
**/.coverage
|
||||
**/.coverage.*
|
||||
**/.cache
|
||||
**/nosetests.xml
|
||||
**/coverage.xml
|
||||
**/*.cover
|
||||
**/*.py,cover
|
||||
**/.hypothesis
|
||||
**/.pytest_cache
|
||||
**/cover
|
||||
|
||||
# Translations
|
||||
**/*.mo
|
||||
**/*.pot
|
||||
|
||||
# Django stuff:
|
||||
**/*.log
|
||||
**/local_settings.py
|
||||
**/db.sqlite3
|
||||
**/db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
**/instance
|
||||
**/.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
**/.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
**/docs/_build
|
||||
|
||||
# PyBuilder
|
||||
**/.pybuilder
|
||||
**/target
|
||||
|
||||
# Jupyter Notebook
|
||||
**/.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
**/profile_default
|
||||
**/ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/#use-with-ide
|
||||
**/.pdm.toml
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
**/__pypackages__
|
||||
|
||||
# Celery stuff
|
||||
**/celerybeat-schedule
|
||||
**/celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
**/*.sage.py
|
||||
|
||||
# Environments
|
||||
**/.env
|
||||
**/.venv
|
||||
**/env
|
||||
**/venv
|
||||
**/ENV
|
||||
**/env.bak
|
||||
**/venv.bak
|
||||
|
||||
# Spyder project settings
|
||||
**/.spyderproject
|
||||
**/.spyproject
|
||||
|
||||
# Rope project settings
|
||||
**/.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
site
|
||||
|
||||
# mypy
|
||||
**/.mypy_cache
|
||||
**/.dmypy.json
|
||||
**/dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
**/.pyre
|
||||
|
||||
# pytype static type analyzer
|
||||
**/.pytype
|
||||
|
||||
# Cython debug symbols
|
||||
**/cython_debug
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
**/.DS_Store
|
||||
**/hello.py
|
||||
|
||||
**/*.html
|
||||
**/fast-mcp-docs.md
|
||||
|
||||
# Debug and test files
|
||||
**/debug_*
|
||||
**/test_*
|
||||
**/CLAUDE.md
|
||||
|
||||
# ASGI/Deployment files
|
||||
**/ssl
|
||||
**/*.pem
|
||||
**/*.key
|
||||
**/*.crt
|
||||
|
||||
# Docker volumes
|
||||
**/redis-data
|
||||
|
||||
# Production logs
|
||||
**/logs/*.log.*
|
||||
**/Dockerfile
|
||||
**/Dockerfile
|
||||
fly.toml
|
||||
@@ -1,103 +0,0 @@
|
||||
# OAuth Configuration for Clerk + Google
|
||||
# Copy this file to .env and fill in your actual values
|
||||
|
||||
# =============================================================================
|
||||
# AUTHENTICATION SETTINGS
|
||||
# =============================================================================
|
||||
|
||||
# Enable/disable authentication (set to "true" to enable OAuth)
|
||||
ENABLE_AUTH=false
|
||||
|
||||
# =============================================================================
|
||||
# CLERK CONFIGURATION
|
||||
# =============================================================================
|
||||
|
||||
# Clerk API keys (get from https://dashboard.clerk.com/)
|
||||
CLERK_SECRET_KEY=sk_test_your_secret_key_here
|
||||
CLERK_PUBLISHABLE_KEY=pk_test_your_publishable_key_here
|
||||
|
||||
# OAuth Redirect URLs
|
||||
CLERK_OAUTH_REDIRECT_URL=http://localhost:8000/auth/callback
|
||||
CLERK_FRONTEND_URL=http://localhost:3000
|
||||
|
||||
# Clerk domain issuer (usually auto-configured)
|
||||
CLERK_ISSUER=https://your-clerk-domain.clerk.accounts.dev
|
||||
CLERK_DOMAIN=your-clerk-domain
|
||||
|
||||
# =============================================================================
|
||||
# GOOGLE OAUTH SETTINGS
|
||||
# =============================================================================
|
||||
# Note: Google OAuth is configured through Clerk dashboard
|
||||
# You need to:
|
||||
# 1. Go to Clerk Dashboard > Social Connections
|
||||
# 2. Enable Google provider
|
||||
# 3. Add your Google OAuth client ID and secret
|
||||
# 4. Configure redirect URIs in Google Console
|
||||
|
||||
# =============================================================================
|
||||
# STRIPE CONFIGURATION (for payments/subscriptions)
|
||||
# =============================================================================
|
||||
|
||||
STRIPE_SECRET=sk_test_your_stripe_secret_key_here
|
||||
STRIPE_WEBHOOK_SECRET=whsec_your_webhook_secret_here
|
||||
|
||||
# =============================================================================
|
||||
# SERVER CONFIGURATION
|
||||
# =============================================================================
|
||||
|
||||
# CORS origins (comma-separated list)
|
||||
ALLOWED_ORIGINS=http://localhost:3000,http://localhost:8000,https://yourdomain.com
|
||||
|
||||
# Server settings
|
||||
HOST=0.0.0.0
|
||||
PORT=8000
|
||||
LOG_LEVEL=info
|
||||
|
||||
# Base URL for the application (used for OAuth callbacks and API URLs)
|
||||
BASE_URL=http://localhost:8000
|
||||
|
||||
# JWT Secret for MCP token generation
|
||||
JWT_SECRET_KEY=your_jwt_secret_key_here
|
||||
|
||||
# =============================================================================
|
||||
# MCP SERVER SETTINGS
|
||||
# =============================================================================
|
||||
|
||||
# Additional MCP server configuration can go here
|
||||
# For example, rate limiting, feature flags, etc.
|
||||
|
||||
# Example: Rate limiting
|
||||
# MAX_REQUESTS_PER_MINUTE=60
|
||||
# BURST_CAPACITY=20
|
||||
|
||||
# =============================================================================
|
||||
# USAGE INSTRUCTIONS
|
||||
# =============================================================================
|
||||
|
||||
# 1. Copy this file to .env:
|
||||
# cp .env.example .env
|
||||
|
||||
# 2. Get Clerk credentials:
|
||||
# - Sign up at https://clerk.com/
|
||||
# - Create a new application
|
||||
# - Go to API Keys tab
|
||||
# - Copy Secret Key and Publishable Key
|
||||
|
||||
# 3. Configure Google OAuth in Clerk:
|
||||
# - In Clerk Dashboard, go to Social Connections
|
||||
# - Enable Google provider
|
||||
# - Get Google OAuth credentials from Google Console
|
||||
# - Add redirect URI: http://localhost:8000/auth/callback
|
||||
|
||||
# 4. Update OAuth URLs:
|
||||
# - Set CLERK_OAUTH_REDIRECT_URL to your callback URL
|
||||
# - Set CLERK_FRONTEND_URL to your frontend application URL
|
||||
|
||||
# 5. Enable authentication:
|
||||
# - Set ENABLE_AUTH=true
|
||||
|
||||
# 6. Test the OAuth flow:
|
||||
# - Start server: uvicorn asgi_app:app --reload
|
||||
# - Visit: http://localhost:8000/auth/login
|
||||
# - Complete OAuth flow with Google
|
||||
# - Check: http://localhost:8000/auth/user
|
||||
@@ -1,2 +0,0 @@
|
||||
# Auto detect text files and perform LF normalization
|
||||
* text=auto
|
||||
@@ -1,37 +0,0 @@
|
||||
name: Publish to PyPI
|
||||
|
||||
on:
|
||||
release:
|
||||
types: [published]
|
||||
workflow_dispatch: # Manual trigger for testing
|
||||
|
||||
jobs:
|
||||
pypi-publish:
|
||||
name: Upload release to PyPI
|
||||
runs-on: ubuntu-latest
|
||||
environment:
|
||||
name: pypi
|
||||
url: https://pypi.org/p/yargi-mcp
|
||||
permissions:
|
||||
id-token: write # IMPORTANT: this permission is mandatory for trusted publishing
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install build
|
||||
|
||||
- name: Build package
|
||||
run: python -m build
|
||||
|
||||
- name: Publish package to PyPI
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
password: ${{ secrets.PYPI_API_TOKEN }}
|
||||
skip-existing: true
|
||||
@@ -1,215 +0,0 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/#use-with-ide
|
||||
.pdm.toml
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
.DS_Store
|
||||
hello.py
|
||||
|
||||
*.html
|
||||
fast-mcp-docs.md
|
||||
|
||||
# Debug and test files
|
||||
debug_*
|
||||
test_*
|
||||
CLAUDE.md
|
||||
|
||||
# ASGI/Deployment files
|
||||
ssl/
|
||||
*.pem
|
||||
*.key
|
||||
*.crt
|
||||
|
||||
# Docker volumes
|
||||
redis-data/
|
||||
|
||||
# Production logs
|
||||
logs/*.log.*
|
||||
|
||||
# Remove these lines - we need deployment files in git:
|
||||
# Dockerfile - NEEDED for SaaS deployment
|
||||
# fly.toml - NEEDED for Fly.io deployment
|
||||
# .github/workflows/fly-deploy.yml - NEEDED for GitHub Actions
|
||||
|
||||
GEMINI.md
|
||||
fly.toml
|
||||
scripts/deploy-flyio.sh
|
||||
docs/DEPLOYMENT_FLYIO.md
|
||||
setup_jwt_template.py
|
||||
mcp_server_main.py.backup
|
||||
mcp_overhead_content.json
|
||||
ANTHROPIC_TEST_README.md
|
||||
extract_mcp_overhead.py
|
||||
mcp_overhead_content.txt
|
||||
mcp_overhead_summary.txt
|
||||
run_http_server.py
|
||||
run_local_test.py
|
||||
|
||||
# MCP overhead analysis files
|
||||
mcp_overhead_*.json
|
||||
mcp_overhead_*.txt
|
||||
mcp_test_results_*.json
|
||||
mcp_quick_test_*.json
|
||||
|
||||
# General text files (temporary notes, etc)
|
||||
*.txt
|
||||
analyze_playwright_mcp.py
|
||||
measure_mcp_directly.py
|
||||
playwright_mcp_overhead.json
|
||||
simple_test.py
|
||||
analyze_anayasa_html.py
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 73 KiB |
@@ -1,29 +0,0 @@
|
||||
# -------- BASE IMAGE (includes Chromium & deps) ----------------------------
|
||||
FROM mcr.microsoft.com/playwright/python:v1.53.0-noble
|
||||
|
||||
# -------- Runtime setup ----------------------------------------------------
|
||||
WORKDIR /app
|
||||
|
||||
# Copy dependency manifests first for layer-cache
|
||||
COPY pyproject.toml poetry.lock* requirements*.txt* ./
|
||||
|
||||
# Fast, deterministic install with `uv`
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv pip install --system --no-cache-dir .[asgi,saas]
|
||||
|
||||
# Copy application source
|
||||
COPY . .
|
||||
|
||||
# -------- Environment ------------------------------------------------------
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
ENV ENABLE_AUTH=true
|
||||
ENV PORT=8000
|
||||
|
||||
# -------- Health check -----------------------------------------------------
|
||||
HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
|
||||
CMD python -c "import httpx, os, sys; r=httpx.get(f'http://localhost:{os.getenv(\"PORT\",\"8000\")}/health'); sys.exit(0 if r.status_code==200 else 1)"
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
# -------- Entrypoint -------------------------------------------------------
|
||||
CMD ["uvicorn", "asgi_app:app", "--host", "0.0.0.0", "--port", "8000", "--proxy-headers"]
|
||||
@@ -1,21 +0,0 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2025 saidsurucu
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@@ -1 +0,0 @@
|
||||
web: uvicorn asgi_app:app --host 0.0.0.0 --port $PORT
|
||||
@@ -1,272 +0,0 @@
|
||||
# Yargı MCP: Türk Hukuk Kaynakları için MCP Sunucusu
|
||||
|
||||
[](https://www.star-history.com/#saidsurucu/yargi-mcp&Date)
|
||||
|
||||
Bu proje, çeşitli Türk hukuk kaynaklarına (Yargıtay, Danıştay, Emsal Kararlar, Uyuşmazlık Mahkemesi, Anayasa Mahkemesi - Norm Denetimi ile Bireysel Başvuru Kararları, Kamu İhale Kurulu Kararları, Rekabet Kurumu Kararları, Sayıştay Kararları, KVKK Kararları ve BDDK Kararları) erişimi kolaylaştıran bir [FastMCP](https://gofastmcp.com/) sunucusu oluşturur. Bu sayede, bu kaynaklardan veri arama ve belge getirme işlemleri, Model Context Protocol (MCP) destekleyen LLM (Büyük Dil Modeli) uygulamaları (örneğin Claude Desktop veya [5ire](https://5ire.app)) ve diğer istemciler tarafından araç (tool) olarak kullanılabilir hale gelir.
|
||||
|
||||
|
||||
|
||||
🎯 **Temel Özellikler**
|
||||
|
||||
🚀 **YÜKSEK PERFORMANS OPTİMİZASYONU:** Bu MCP sunucusu **%61.8 token azaltma** ile optimize edilmiştir (8,692 token tasarrufu). Claude AI ile daha hızlı yanıt süreleri ve daha verimli etkileşim sağlar.
|
||||
|
||||
* Çeşitli Türk hukuk veritabanlarına programatik erişim için standart bir MCP arayüzü.
|
||||
* **Kapsamlı Mahkeme Daire/Kurul Filtreleme:** 79 farklı daire/kurul filtreleme seçeneği
|
||||
* **Dual/Triple API Desteği:** Her mahkeme için birden fazla API kaynağı ile maksimum kapsama
|
||||
* **Kapsamlı Tarih Filtreleme:** Tüm Bedesten API araçlarında ISO 8601 formatında tarih aralığı filtreleme
|
||||
* **Kesin Cümle Arama:** Tüm Bedesten API araçlarında çift tırnak ile tam cümle arama desteği
|
||||
* Aşağıdaki kurumların kararlarını arama ve getirme yeteneği:
|
||||
* **Yargıtay:** Detaylı kriterlerle karar arama ve karar metinlerini Markdown formatında getirme. **Dual API** (Ana + Bedesten) + **52 Daire/Kurul Filtreleme** + **Tarih & Kesin Cümle Arama** (Hukuk/Ceza Daireleri, Genel Kurullar)
|
||||
* **Danıştay:** Anahtar kelime bazlı ve detaylı kriterlerle karar arama; karar metinlerini Markdown formatında getirme. **Triple API** (Keyword + Detailed + Bedesten) + **27 Daire/Kurul Filtreleme** + **Tarih & Kesin Cümle Arama** (İdari Daireler, Vergi/İdare Kurulları, Askeri Yüksek İdare Mahkemesi)
|
||||
* **Yerel Hukuk Mahkemeleri:** Bedesten API ile yerel hukuk mahkemesi kararlarına erişim + **Tarih & Kesin Cümle Arama**
|
||||
* **İstinaf Hukuk Mahkemeleri:** Bedesten API ile istinaf mahkemesi kararlarına erişim + **Tarih & Kesin Cümle Arama**
|
||||
* **Kanun Yararına Bozma (KYB):** Bedesten API ile olağanüstü kanun yoluna erişim + **Tarih & Kesin Cümle Arama**
|
||||
* **Emsal (UYAP):** Detaylı kriterlerle emsal karar arama ve karar metinlerini Markdown formatında getirme.
|
||||
* **Uyuşmazlık Mahkemesi:** Form tabanlı kriterlerle karar arama ve karar metinlerini (URL ile erişilen) Markdown formatında getirme.
|
||||
* **Anayasa Mahkemesi (Norm Denetimi):** Kapsamlı kriterlerle norm denetimi kararlarını arama; uzun karar metinlerini (5.000 karakterlik) sayfalanmış Markdown formatında getirme.
|
||||
* **Anayasa Mahkemesi (Bireysel Başvuru):** Kapsamlı kriterlerle bireysel başvuru "Karar Arama Raporu" oluşturma ve listedeki kararların metinlerini (5.000 karakterlik) sayfalanmış Markdown formatında getirme.
|
||||
* **KİK (Kamu İhale Kurulu):** Çeşitli kriterlerle Kurul kararlarını arama; uzun karar metinlerini (varsayılan 5.000 karakterlik) sayfalanmış Markdown formatında getirme.
|
||||
* **Rekabet Kurumu:** Çeşitli kriterlerle Kurul kararlarını arama; karar metinlerini Markdown formatında getirme.
|
||||
* **Sayıştay:** 3 karar türü ile kapsamlı denetim kararlarına erişim + **8 Daire Filtreleme** + **Tarih Aralığı & İçerik Arama** (Genel Kurul yorumlayıcı kararları, Temyiz Kurulu itiraz kararları, Daire ilk derece denetim kararları)
|
||||
* **KVKK (Kişisel Verilerin Korunması Kurulu):** Brave Search API ile veri koruma kararlarını arama; uzun karar metinlerini (5.000 karakterlik) sayfalanmış Markdown formatında getirme + **Türkçe Arama** + **Site Hedeflemeli Arama** (kvkk.gov.tr kararları)
|
||||
* **BDDK (Bankacılık Düzenleme ve Denetleme Kurumu):** Bankacılık düzenleme kararlarını arama; karar metinlerini Markdown formatında getirme + **Optimized Search** + **"Karar Sayısı" Targeting** + **Spesifik URL Filtreleme** (bddk.org.tr/Mevzuat/DokumanGetir)
|
||||
|
||||
* Karar metinlerinin daha kolay işlenebilmesi için Markdown formatına çevrilmesi.
|
||||
* Claude Desktop uygulaması ile `fastmcp install` komutu kullanılarak kolay entegrasyon.
|
||||
* Yargı MCP artık [5ire](https://5ire.app) gibi Claude Desktop haricindeki MCP istemcilerini de destekliyor!
|
||||
---
|
||||
<details>
|
||||
<summary>🚀 <strong>Claude Haricindeki Modellerle Kullanmak İçin Çok Kolay Kurulum (Örnek: 5ire için)</strong></summary>
|
||||
|
||||
Bu bölüm, Yargı MCP aracını 5ire gibi Claude Desktop dışındaki MCP istemcileriyle kullanmak isteyenler içindir.
|
||||
|
||||
* **Python Kurulumu:** Sisteminizde Python 3.11 veya üzeri kurulu olmalıdır. Kurulum sırasında "**Add Python to PATH**" (Python'ı PATH'e ekle) seçeneğini işaretlemeyi unutmayın. [Buradan](https://www.python.org/downloads/) indirebilirsiniz.
|
||||
* **Git Kurulumu (Windows):** Bilgisayarınıza [git](https://git-scm.com/downloads/win) yazılımını indirip kurun. "Git for Windows/x64 Setup" seçeneğini indirmelisiniz.
|
||||
* **`uv` Kurulumu:**
|
||||
* **Windows Kullanıcıları (PowerShell):** Bir CMD ekranı açın ve bu kodu çalıştırın: `powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"`
|
||||
* **Mac/Linux Kullanıcıları (Terminal):** Bir Terminal ekranı açın ve bu kodu çalıştırın: `curl -LsSf https://astral.sh/uv/install.sh | sh`
|
||||
* **Microsoft Visual C++ Redistributable (Windows):** Bazı Python paketlerinin doğru çalışması için gereklidir. [Buradan](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170) indirip kurun.
|
||||
* İşletim sisteminize uygun [5ire](https://5ire.app) MCP istemcisini indirip kurun.
|
||||
* 5ire'ı açın. **Workspace -> Providers** menüsünden kullanmak istediğiniz LLM servisinin API anahtarını girin.
|
||||
* **Tools** menüsüne girin. **+Local** veya **New** yazan butona basın.
|
||||
* **Tool Key:** `yargimcp`
|
||||
* **Name:** `Yargı MCP`
|
||||
* **Command:**
|
||||
```
|
||||
uvx yargi-mcp
|
||||
```
|
||||
* **Save** butonuna basarak kaydedin.
|
||||
|
||||
* Şimdi **Tools** altında **Yargı MCP**'yi görüyor olmalısınız. Üstüne geldiğinizde sağda çıkan butona tıklayıp etkinleştirin (yeşil ışık yanmalı).
|
||||
* Artık Yargı MCP ile konuşabilirsiniz.
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
<details>
|
||||
<summary>⚙️ <strong>Claude Desktop Manuel Kurulumu</strong></summary>
|
||||
|
||||
1. **Ön Gereksinimler:** Python, `uv`, (Windows için) Microsoft Visual C++ Redistributable'ın sisteminizde kurulu olduğundan emin olun. Detaylı bilgi için yukarıdaki "5ire için Kurulum" bölümündeki ilgili adımlara bakabilirsiniz.
|
||||
2. Claude Desktop **Settings -> Developer -> Edit Config**.
|
||||
3. Açılan `claude_desktop_config.json` dosyasına `mcpServers` altına ekleyin:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
// ... (varsa diğer sunucularınız) ...
|
||||
"Yargı MCP": {
|
||||
"command": "uvx",
|
||||
"args": [
|
||||
"yargi-mcp"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
4. Claude Desktop'ı kapatıp yeniden başlatın.
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
<details>
|
||||
<summary>🌟 <strong>Gemini CLI ile Kullanım</strong></summary>
|
||||
|
||||
Yargı MCP'yi Gemini CLI ile kullanmak için:
|
||||
|
||||
1. **Ön Gereksinimler:** Python, `uv`, (Windows için) Microsoft Visual C++ Redistributable'ın sisteminizde kurulu olduğundan emin olun. Detaylı bilgi için yukarıdaki "5ire için Kurulum" bölümündeki ilgili adımlara bakabilirsiniz.
|
||||
|
||||
2. **Gemini CLI ayarlarını yapılandırın:**
|
||||
|
||||
Gemini CLI'ın ayar dosyasını düzenleyin:
|
||||
- **macOS/Linux:** `~/.gemini/settings.json`
|
||||
- **Windows:** `%USERPROFILE%\.gemini\settings.json`
|
||||
|
||||
Aşağıdaki `mcpServers` bloğunu ekleyin:
|
||||
```json
|
||||
{
|
||||
"theme": "Default",
|
||||
"selectedAuthType": "###",
|
||||
"mcpServers": {
|
||||
"yargi_mcp": {
|
||||
"command": "uvx",
|
||||
"args": [
|
||||
"yargi-mcp"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Yapılandırma açıklamaları:**
|
||||
- `"yargi_mcp"`: Sunucunuz için yerel bir isim
|
||||
- `"command"`: `uvx` komutu (uv'nin paket çalıştırma aracı)
|
||||
- `"args"`: GitHub'dan doğrudan Yargı MCP'yi çalıştırmak için gerekli argümanlar
|
||||
|
||||
3. **Kullanım:**
|
||||
- Gemini CLI'ı başlatın
|
||||
- Yargı MCP araçları otomatik olarak kullanılabilir olacaktır
|
||||
- Örnek komutlar:
|
||||
- "Yargıtay'ın mülkiyet hakkı ile ilgili son kararlarını ara"
|
||||
- "Danıştay'ın imar planı iptaline ilişkin kararlarını bul"
|
||||
- "Anayasa Mahkemesi'nin ifade özgürlüğü kararlarını getir"
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>🛠️ <strong>Kullanılabilir Araçlar (MCP Tools)</strong></summary>
|
||||
|
||||
Bu FastMCP sunucusu **19 optimize edilmiş MCP aracı** sunar (token verimliliği için optimize edilmiş):
|
||||
|
||||
### **Yargıtay Araçları (Birleşik Bedesten API - Token Optimized)**
|
||||
*Not: Yargıtay araçları token verimliliği için birleşik Bedesten API'ye entegre edilmiştir*
|
||||
|
||||
### **Danıştay Araçları (Birleşik Bedesten API - Token Optimized)**
|
||||
*Not: Danıştay araçları token verimliliği için birleşik Bedesten API'ye entegre edilmiştir*
|
||||
|
||||
### **Birleşik Bedesten API Araçları (5 Mahkeme) - 🚀 TOKEN OPTİMİZE**
|
||||
1. `search_bedesten_unified(phrase, court_types, birimAdi, kararTarihiStart, kararTarihiEnd, ...)`: **5 mahkeme türünü** birleşik arama (Yargıtay, Danıştay, Yerel Hukuk, İstinaf Hukuk, KYB) + **79 daire filtreleme** + **Tarih & Kesin Cümle Arama**
|
||||
2. `get_bedesten_document_markdown(documentId: str)`: Bedesten API'den herhangi bir belgeyi Markdown formatında getirir (HTML/PDF → Markdown)
|
||||
|
||||
### **Emsal Karar Araçları (UYAP)**
|
||||
3. `search_emsal_detailed_decisions(keyword, ...)`: Emsal (UYAP) kararlarını detaylı kriterlerle arar.
|
||||
4. `get_emsal_document_markdown(id: str)`: Belirli bir Emsal kararının metnini Markdown formatında getirir.
|
||||
|
||||
### **Uyuşmazlık Mahkemesi Araçları**
|
||||
5. `search_uyusmazlik_decisions(icerik, ...)`: Uyuşmazlık Mahkemesi kararlarını çeşitli form kriterleriyle arar.
|
||||
6. `get_uyusmazlik_document_markdown_from_url(document_url)`: Bir Uyuşmazlık kararını tam URL'sinden alıp Markdown formatında getirir.
|
||||
|
||||
### **Anayasa Mahkemesi Araçları (Birleşik API) - 🚀 TOKEN OPTİMİZE**
|
||||
7. `search_anayasa_unified(decision_type, keywords_all, ...)`: AYM kararlarını birleşik arama (Norm Denetimi + Bireysel Başvuru) - **4 araç → 2 araç optimizasyonu**
|
||||
8. `get_anayasa_document_unified(document_url, page_number)`: AYM kararlarını birleşik belge getirme - **sayfalanmış Markdown** içeriği
|
||||
|
||||
### **KİK (Kamu İhale Kurulu) Araçları**
|
||||
9. `search_kik_decisions(karar_tipi, ...)`: KİK (Kamu İhale Kurulu) kararlarını arar.
|
||||
10. `get_kik_document_markdown(karar_id, page_number)`: Belirli bir KİK kararını, Base64 ile encode edilmiş `karar_id`'sini kullanarak alır ve **sayfalanmış Markdown** içeriğini getirir.
|
||||
### **Rekabet Kurumu Araçları**
|
||||
* `search_rekabet_kurumu_decisions(KararTuru: Literal[...], ...) -> RekabetSearchResult`: Rekabet Kurumu kararlarını arar. `KararTuru` için kullanıcı dostu isimler kullanılır (örn: "Birleşme ve Devralma").
|
||||
* `get_rekabet_kurumu_document(karar_id: str, page_number: Optional[int] = 1) -> RekabetDocument`: Belirli bir Rekabet Kurumu kararını `karar_id` ile alır. Kararın PDF formatındaki orijinalinden istenen sayfayı ayıklar ve Markdown formatında döndürür.
|
||||
|
||||
|
||||
---
|
||||
|
||||
* **Sayıştay Araçları (3 Karar Türü + 8 Daire Filtreleme):**
|
||||
* `search_sayistay_genel_kurul(karar_no, karar_tarih_baslangic, karar_tamami, ...)`: Sayıştay Genel Kurul (yorumlayıcı) kararlarını arar. **Tarih aralığı** (2006-2024) + **İçerik arama** (400 karakter)
|
||||
* `search_sayistay_temyiz_kurulu(ilam_dairesi, kamu_idaresi_turu, temyiz_karar, ...)`: Temyiz Kurulu (itiraz) kararlarını arar. **8 Daire filtreleme** + **Kurum türü** + **Konu sınıflandırması**
|
||||
* `search_sayistay_daire(yargilama_dairesi, web_karar_metni, hesap_yili, ...)`: Daire (ilk derece denetim) kararlarını arar. **8 Daire filtreleme** + **Hesap yılı** + **İçerik arama**
|
||||
* `get_sayistay_genel_kurul_document_markdown(decision_id: str)`: Genel Kurul kararının tam metnini Markdown formatında getirir
|
||||
* `get_sayistay_temyiz_kurulu_document_markdown(decision_id: str)`: Temyiz Kurulu kararının tam metnini Markdown formatında getirir
|
||||
* `get_sayistay_daire_document_markdown(decision_id: str)`: Daire kararının tam metnini Markdown formatında getirir
|
||||
|
||||
* **KVKK Araçları (Brave Search API + Türkçe Arama):**
|
||||
* `search_kvkk_decisions(keywords, page, pageSize, ...)`: KVKK (Kişisel Verilerin Korunması Kurulu) kararlarını Brave Search API ile arar. **Türkçe arama** + **Site hedeflemeli** (`site:kvkk.gov.tr "karar özeti"`) + **Sayfalama desteği**
|
||||
* `get_kvkk_document_markdown(decision_url: str, page_number: Optional[int] = 1)`: KVKK kararının tam metnini **sayfalanmış Markdown** formatında getirir (5.000 karakterlik sayfa)
|
||||
|
||||
### BDDK Araçları
|
||||
* `search_bddk_decisions(keywords, page)`: BDDK (Bankacılık Düzenleme ve Denetleme Kurumu) kararlarını arar. **"Karar Sayısı" targeting** + **Spesifik URL filtreleme** (`bddk.org.tr/Mevzuat/DokumanGetir`) + **Optimized search**
|
||||
* `get_bddk_document_markdown(document_id: str, page_number: Optional[int] = 1)`: BDDK kararının tam metnini **sayfalanmış Markdown** formatında getirir (5.000 karakterlik sayfa)
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>📊 <strong>Kapsamlı İstatistikler & Optimizasyon Başarıları</strong></summary>
|
||||
|
||||
🚀 **TOKEN OPTİMİZASYON BAŞARISI:**
|
||||
- **%61.8 Token Azaltma:** 14,061 → 5,369 tokens (8,692 token tasarrufu)
|
||||
- **Hedef Aşım:** 10,000 token hedefini 4,631 token aştık
|
||||
- **Daha Hızlı Yanıt:** Claude AI ile optimize edilmiş etkileşim
|
||||
- **Korunan İşlevsellik:** %100 özellik desteği devam ediyor
|
||||
|
||||
**GENEL İSTATİSTİKLER:**
|
||||
- **Toplam Mahkeme/Kurum:** 13 farklı hukuki kurum (KVKK dahil)
|
||||
- **Toplam MCP Tool:** 19 optimize edilmiş arama ve belge getirme aracı
|
||||
- **Daire/Kurul Filtreleme:** 87 farklı seçenek (52 Yargıtay + 27 Danıştay + 8 Sayıştay)
|
||||
- **Tarih Filtreleme:** Birleşik Bedesten API aracında ISO 8601 formatında tam tarih aralığı desteği
|
||||
- **Kesin Cümle Arama:** Birleşik Bedesten API aracında çift tırnak ile tam cümle arama (`"\"mülkiyet kararı\""` formatı)
|
||||
- **Birleşik API:** 10 ayrı Bedesten aracı → 2 birleşik araç (search_bedesten_unified + get_bedesten_document_markdown)
|
||||
- **API Kaynağı:** Dual/Triple API desteği ile maksimum kapsama
|
||||
- **Tam Türk Adalet Sistemi:** Yerel mahkemelerden en yüksek mahkemelere kadar
|
||||
|
||||
**🏛️ Desteklenen Mahkeme Hiyerarşisi:**
|
||||
```
|
||||
Yerel Mahkemeler → İstinaf → Yargıtay/Danıştay → Anayasa Mahkemesi
|
||||
↓ ↓ ↓ ↓
|
||||
Bedesten API Bedesten API Dual/Triple API Norm+Bireysel API
|
||||
+ Tarih + Kesin + Tarih + Kesin + Daire + Tarih + Gelişmiş
|
||||
Cümle Arama Cümle Arama + Kesin Cümle Arama
|
||||
```
|
||||
|
||||
**⚖️ Kapsamlı Filtreleme Özellikleri:**
|
||||
- **Daire Filtreleme:** 79 seçenek (52 Yargıtay + 27 Danıştay)
|
||||
- **Yargıtay:** 52 seçenek (1-23 Hukuk, 1-23 Ceza, Genel Kurullar, Başkanlar Kurulu)
|
||||
- **Danıştay:** 27 seçenek (1-17 Daireler, İdare/Vergi Kurulları, Askeri Mahkemeler)
|
||||
- **Tarih Filtreleme:** 5 Bedesten API aracında ISO 8601 formatı (YYYY-MM-DDTHH:MM:SS.000Z)
|
||||
- Tek tarih, tarih aralığı, tek taraflı filtreleme desteği
|
||||
- Yargıtay, Danıştay, Yerel Hukuk, İstinaf Hukuk, KYB kararları
|
||||
- **Kesin Cümle Arama:** 5 Bedesten API aracında çift tırnak formatı
|
||||
- Normal arama: `"mülkiyet kararı"` (kelimeler ayrı ayrı)
|
||||
- Kesin arama: `"\"mülkiyet kararı\""` (tam cümle olarak)
|
||||
- Daha kesin sonuçlar için hukuki terimler ve kavramlar
|
||||
|
||||
**🔧 OPTİMİZASYON DETAYLARI:**
|
||||
- **Anayasa Mahkemesi:** 4 araç → 2 birleşik araç (search_anayasa_unified + get_anayasa_document_unified)
|
||||
- **Yargıtay & Danıştay:** Ana API araçları birleşik Bedesten API'ye entegre edildi
|
||||
- **Sayıştay:** 6 araç → 2 birleşik araç (search_sayistay_unified + get_sayistay_document_unified)
|
||||
- **Parameter Optimizasyonu:** pageSize parametreleri optimize edildi
|
||||
- **Açıklama Optimizasyonu:** Uzun açıklamalar kısaltıldı (örn: KIK karar_metni)
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>🌐 <strong>Web Service / ASGI Deployment</strong></summary>
|
||||
|
||||
Yargı MCP artık web servisi olarak da çalıştırılabilir! ASGI desteği sayesinde:
|
||||
|
||||
- **Web API olarak erişim**: HTTP endpoint'leri üzerinden MCP araçlarına erişim
|
||||
- **Cloud deployment**: Heroku, Railway, Google Cloud Run, AWS Lambda desteği
|
||||
- **Docker desteği**: Production-ready Docker container
|
||||
- **FastAPI entegrasyonu**: REST API ve interaktif dokümantasyon
|
||||
|
||||
**Hızlı başlangıç:**
|
||||
```bash
|
||||
# ASGI dependencies yükle
|
||||
pip install yargi-mcp[asgi]
|
||||
|
||||
# Web servisi olarak başlat
|
||||
python run_asgi.py
|
||||
# veya
|
||||
uvicorn asgi_app:app --host 0.0.0.0 --port 8000
|
||||
```
|
||||
|
||||
Detaylı deployment rehberi için: [docs/DEPLOYMENT.md](docs/DEPLOYMENT.md)
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
📜 **Lisans**
|
||||
|
||||
Bu proje MIT Lisansı altında lisanslanmıştır. Detaylar için `LICENSE` dosyasına bakınız.
|
||||
@@ -1,7 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Entry point for yargi-mcp package."""
|
||||
|
||||
from mcp_server_main import main
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,355 +0,0 @@
|
||||
# anayasa_mcp_module/bireysel_client.py
|
||||
# This client is for Bireysel Başvuru: https://kararlarbilgibankasi.anayasa.gov.tr
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup, Tag
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from urllib.parse import urlencode, urljoin, quote
|
||||
from markitdown import MarkItDown
|
||||
import math # For math.ceil for pagination
|
||||
|
||||
from .models import (
|
||||
AnayasaBireyselReportSearchRequest,
|
||||
AnayasaBireyselReportDecisionDetail,
|
||||
AnayasaBireyselReportDecisionSummary,
|
||||
AnayasaBireyselReportSearchResult,
|
||||
AnayasaBireyselBasvuruDocumentMarkdown, # Model for Bireysel Başvuru document
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
|
||||
class AnayasaBireyselBasvuruApiClient:
|
||||
BASE_URL = "https://kararlarbilgibankasi.anayasa.gov.tr"
|
||||
SEARCH_PATH = "/Ara"
|
||||
DOCUMENT_MARKDOWN_CHUNK_SIZE = 5000 # Character limit per page
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=True,
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
def _build_query_params_for_bireysel_report(self, params: AnayasaBireyselReportSearchRequest) -> List[Tuple[str, str]]:
|
||||
query_params: List[Tuple[str, str]] = []
|
||||
query_params.append(("KararBulteni", "1")) # Specific to this report type
|
||||
|
||||
if params.keywords:
|
||||
for kw in params.keywords:
|
||||
query_params.append(("KelimeAra[]", kw))
|
||||
|
||||
if params.page_to_fetch and params.page_to_fetch > 1:
|
||||
query_params.append(("page", str(params.page_to_fetch)))
|
||||
|
||||
return query_params
|
||||
|
||||
async def search_bireysel_basvuru_report(
|
||||
self,
|
||||
params: AnayasaBireyselReportSearchRequest
|
||||
) -> AnayasaBireyselReportSearchResult:
|
||||
final_query_params = self._build_query_params_for_bireysel_report(params)
|
||||
request_url = self.SEARCH_PATH
|
||||
|
||||
logger.info(f"AnayasaBireyselBasvuruApiClient: Performing Bireysel Başvuru Report search. Path: {request_url}, Params: {final_query_params}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(request_url, params=final_query_params)
|
||||
response.raise_for_status()
|
||||
html_content = response.text
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"AnayasaBireyselBasvuruApiClient: HTTP request error during Bireysel Başvuru Report search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaBireyselBasvuruApiClient: Error processing Bireysel Başvuru Report search request: {e}")
|
||||
raise
|
||||
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
|
||||
total_records = None
|
||||
bulunan_karar_div = soup.find("div", class_="bulunankararsayisi")
|
||||
if bulunan_karar_div:
|
||||
match_records = re.search(r'(\d+)\s*Karar Bulundu', bulunan_karar_div.get_text(strip=True))
|
||||
if match_records:
|
||||
total_records = int(match_records.group(1))
|
||||
|
||||
processed_decisions: List[AnayasaBireyselReportDecisionSummary] = []
|
||||
|
||||
report_content_area = soup.find("div", class_="HaberBulteni")
|
||||
if not report_content_area:
|
||||
logger.warning("HaberBulteni div not found, attempting to parse decision divs from the whole page.")
|
||||
report_content_area = soup
|
||||
|
||||
decision_divs = report_content_area.find_all("div", class_="KararBulteniBirKarar")
|
||||
if not decision_divs:
|
||||
logger.warning("No KararBulteniBirKarar divs found.")
|
||||
|
||||
|
||||
for decision_div in decision_divs:
|
||||
title_tag = decision_div.find("h4")
|
||||
title_text = title_tag.get_text(strip=True) if title_tag and title_tag.strong else (title_tag.get_text(strip=True) if title_tag else "")
|
||||
|
||||
|
||||
alti_cizili_div = decision_div.find("div", class_="AltiCizili")
|
||||
ref_no, dec_type, body, app_date, dec_date, url_path = "", "", "", "", "", ""
|
||||
if alti_cizili_div:
|
||||
link_tag = alti_cizili_div.find("a", href=True)
|
||||
if link_tag:
|
||||
ref_no = link_tag.get_text(strip=True)
|
||||
url_path = link_tag['href']
|
||||
|
||||
parts_text = alti_cizili_div.get_text(separator="|", strip=True)
|
||||
parts = [part.strip() for part in parts_text.split("|")]
|
||||
|
||||
# Clean ref_no from the first part if it was extracted from link
|
||||
if ref_no and parts and parts[0].strip().startswith(ref_no):
|
||||
parts[0] = parts[0].replace(ref_no, "").strip()
|
||||
if not parts[0]: parts.pop(0) # Remove empty string if ref_no was the only content
|
||||
|
||||
# Assign parts based on typical order, adjusting for missing ref_no at start
|
||||
current_idx = 0
|
||||
if not ref_no and len(parts) > current_idx and re.match(r"\d+/\d+", parts[current_idx]): # Check if first part is ref_no
|
||||
ref_no = parts[current_idx]
|
||||
current_idx += 1
|
||||
|
||||
dec_type = parts[current_idx] if len(parts) > current_idx else ""
|
||||
current_idx += 1
|
||||
body = parts[current_idx] if len(parts) > current_idx else ""
|
||||
current_idx += 1
|
||||
|
||||
app_date_raw = parts[current_idx] if len(parts) > current_idx else ""
|
||||
current_idx += 1
|
||||
dec_date_raw = parts[current_idx] if len(parts) > current_idx else ""
|
||||
|
||||
if app_date_raw and "Başvuru Tarihi :" in app_date_raw:
|
||||
app_date = app_date_raw.replace("Başvuru Tarihi :", "").strip()
|
||||
elif app_date_raw: # If label is missing but format matches
|
||||
app_date_match = re.search(r'(\d{1,2}/\d{1,2}/\d{4})', app_date_raw)
|
||||
if app_date_match: app_date = app_date_match.group(1)
|
||||
|
||||
|
||||
if dec_date_raw and "Karar Tarihi :" in dec_date_raw:
|
||||
dec_date = dec_date_raw.replace("Karar Tarihi :", "").strip()
|
||||
elif dec_date_raw: # If label is missing but format matches
|
||||
dec_date_match = re.search(r'(\d{1,2}/\d{1,2}/\d{4})', dec_date_raw)
|
||||
if dec_date_match: dec_date = dec_date_match.group(1)
|
||||
|
||||
|
||||
subject_div = decision_div.find(lambda tag: tag.name == 'div' and not tag.has_attr('class') and tag.get_text(strip=True).startswith("BAŞVURU KONUSU :"))
|
||||
subject_text = subject_div.get_text(strip=True).replace("BAŞVURU KONUSU :", "").strip() if subject_div else ""
|
||||
|
||||
details_list: List[AnayasaBireyselReportDecisionDetail] = []
|
||||
karar_detaylari_div = decision_div.find_next_sibling("div", id="KararDetaylari") # Corrected: was KararDetaylari
|
||||
if karar_detaylari_div:
|
||||
table = karar_detaylari_div.find("table", class_="table")
|
||||
if table and table.find("tbody"):
|
||||
for row in table.find("tbody").find_all("tr"):
|
||||
cells = row.find_all("td")
|
||||
if len(cells) == 4: # Hak, Müdahale İddiası, Sonuç, Giderim
|
||||
details_list.append(AnayasaBireyselReportDecisionDetail(
|
||||
hak=cells[0].get_text(strip=True) or "",
|
||||
mudahale_iddiasi=cells[1].get_text(strip=True) or "",
|
||||
sonuc=cells[2].get_text(strip=True) or "",
|
||||
giderim=cells[3].get_text(strip=True) or "",
|
||||
))
|
||||
|
||||
full_decision_page_url = urljoin(self.BASE_URL, url_path) if url_path else ""
|
||||
|
||||
processed_decisions.append(AnayasaBireyselReportDecisionSummary(
|
||||
title=title_text,
|
||||
decision_reference_no=ref_no,
|
||||
decision_page_url=full_decision_page_url,
|
||||
decision_type_summary=dec_type,
|
||||
decision_making_body=body,
|
||||
application_date_summary=app_date,
|
||||
decision_date_summary=dec_date,
|
||||
application_subject_summary=subject_text,
|
||||
details=details_list
|
||||
))
|
||||
|
||||
return AnayasaBireyselReportSearchResult(
|
||||
decisions=processed_decisions,
|
||||
total_records_found=total_records,
|
||||
retrieved_page_number=params.page_to_fetch
|
||||
)
|
||||
|
||||
def _convert_html_to_markdown_bireysel(self, full_decision_html_content: str) -> Optional[str]:
|
||||
if not full_decision_html_content:
|
||||
return None
|
||||
|
||||
processed_html = html.unescape(full_decision_html_content)
|
||||
soup = BeautifulSoup(processed_html, "html.parser")
|
||||
html_input_for_markdown = ""
|
||||
|
||||
karar_tab_content = soup.find("div", id="Karar")
|
||||
if karar_tab_content:
|
||||
karar_html_span = karar_tab_content.find("span", class_="kararHtml")
|
||||
if karar_html_span:
|
||||
word_section = karar_html_span.find("div", class_="WordSection1")
|
||||
if word_section:
|
||||
for s in word_section.select('script, style, .item.col-xs-12.col-sm-12, center:has(b)'):
|
||||
s.decompose()
|
||||
html_input_for_markdown = str(word_section)
|
||||
else:
|
||||
logger.warning("AnayasaBireyselBasvuruApiClient: WordSection1 not found in span.kararHtml. Using span.kararHtml content.")
|
||||
for s in karar_html_span.select('script, style, .item.col-xs-12.col-sm-12, center:has(b)'):
|
||||
s.decompose()
|
||||
html_input_for_markdown = str(karar_html_span)
|
||||
else:
|
||||
logger.warning("AnayasaBireyselBasvuruApiClient: span.kararHtml not found in div#Karar. Using div#Karar content.")
|
||||
for s in karar_tab_content.select('script, style, .item.col-xs-12.col-sm-12, center:has(b)'):
|
||||
s.decompose()
|
||||
html_input_for_markdown = str(karar_tab_content)
|
||||
else:
|
||||
logger.warning("AnayasaBireyselBasvuruApiClient: div#Karar (KARAR tab) not found. Trying WordSection1 fallback.")
|
||||
word_section_fallback = soup.find("div", class_="WordSection1")
|
||||
if word_section_fallback:
|
||||
for s in word_section_fallback.select('script, style, .item.col-xs-12.col-sm-12, center:has(b)'):
|
||||
s.decompose()
|
||||
html_input_for_markdown = str(word_section_fallback)
|
||||
else:
|
||||
body_tag = soup.find("body")
|
||||
if body_tag:
|
||||
for s in body_tag.select('script, style, .item.col-xs-12.col-sm-12, center:has(b), .banner, .footer, .yazdirmaalani, .filtreler, .menu, .altmenu, .geri, .arabuton, .temizlebutonu, form#KararGetir, .TabBaslik, #KararDetaylari, .share-button-container'):
|
||||
s.decompose()
|
||||
html_input_for_markdown = str(body_tag)
|
||||
else:
|
||||
html_input_for_markdown = processed_html
|
||||
|
||||
markdown_text = None
|
||||
try:
|
||||
# Ensure the content is wrapped in basic HTML structure if it's not already
|
||||
if not html_input_for_markdown.strip().lower().startswith(("<html", "<!doctype")):
|
||||
html_content = f"<html><head><meta charset=\"UTF-8\"></head><body>{html_input_for_markdown}</body></html>"
|
||||
else:
|
||||
html_content = html_input_for_markdown
|
||||
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_content.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaBireyselBasvuruApiClient: MarkItDown conversion error: {e}")
|
||||
return markdown_text
|
||||
|
||||
async def get_decision_document_as_markdown(
|
||||
self,
|
||||
document_url_path: str, # e.g. /BB/2021/20295
|
||||
page_number: int = 1
|
||||
) -> AnayasaBireyselBasvuruDocumentMarkdown:
|
||||
full_url = urljoin(self.BASE_URL, document_url_path)
|
||||
logger.info(f"AnayasaBireyselBasvuruApiClient: Fetching Bireysel Başvuru document for Markdown (page {page_number}) from URL: {full_url}")
|
||||
|
||||
basvuru_no_from_page = None
|
||||
karar_tarihi_from_page = None
|
||||
basvuru_tarihi_from_page = None
|
||||
karari_veren_birim_from_page = None
|
||||
karar_turu_from_page = None
|
||||
resmi_gazete_info_from_page = None
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(full_url)
|
||||
response.raise_for_status()
|
||||
html_content_from_api = response.text
|
||||
|
||||
if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
|
||||
logger.warning(f"AnayasaBireyselBasvuruApiClient: Received empty HTML from {full_url}.")
|
||||
return AnayasaBireyselBasvuruDocumentMarkdown(
|
||||
source_url=full_url, markdown_chunk=None, current_page=page_number, total_pages=0, is_paginated=False
|
||||
)
|
||||
|
||||
soup = BeautifulSoup(html_content_from_api, 'html.parser')
|
||||
|
||||
meta_desc_tag = soup.find("meta", attrs={"name": "description"})
|
||||
if meta_desc_tag and meta_desc_tag.get("content"):
|
||||
content = meta_desc_tag["content"]
|
||||
bn_match = re.search(r"B\.\s*No:\s*([\d\/]+)", content)
|
||||
if bn_match: basvuru_no_from_page = bn_match.group(1).strip()
|
||||
|
||||
date_match = re.search(r"(\d{1,2}\/\d{1,2}\/\d{4}),\s*§", content)
|
||||
if date_match: karar_tarihi_from_page = date_match.group(1).strip()
|
||||
|
||||
karar_detaylari_tab = soup.find("div", id="KararDetaylari")
|
||||
if karar_detaylari_tab:
|
||||
table = karar_detaylari_tab.find("table", class_="table")
|
||||
if table:
|
||||
rows = table.find_all("tr")
|
||||
for row in rows:
|
||||
cells = row.find_all("td")
|
||||
if len(cells) == 2:
|
||||
key = cells[0].get_text(strip=True)
|
||||
value = cells[1].get_text(strip=True)
|
||||
if "Kararı Veren Birim" in key: karari_veren_birim_from_page = value
|
||||
elif "Karar Türü (Başvuru Sonucu)" in key: karar_turu_from_page = value
|
||||
elif "Başvuru No" in key and not basvuru_no_from_page: basvuru_no_from_page = value
|
||||
elif "Başvuru Tarihi" in key: basvuru_tarihi_from_page = value
|
||||
elif "Karar Tarihi" in key and not karar_tarihi_from_page: karar_tarihi_from_page = value
|
||||
elif "Resmi Gazete Tarih / Sayı" in key: resmi_gazete_info_from_page = value
|
||||
|
||||
full_markdown_content = self._convert_html_to_markdown_bireysel(html_content_from_api)
|
||||
|
||||
if not full_markdown_content:
|
||||
return AnayasaBireyselBasvuruDocumentMarkdown(
|
||||
source_url=full_url,
|
||||
basvuru_no_from_page=basvuru_no_from_page,
|
||||
karar_tarihi_from_page=karar_tarihi_from_page,
|
||||
basvuru_tarihi_from_page=basvuru_tarihi_from_page,
|
||||
karari_veren_birim_from_page=karari_veren_birim_from_page,
|
||||
karar_turu_from_page=karar_turu_from_page,
|
||||
resmi_gazete_info_from_page=resmi_gazete_info_from_page,
|
||||
markdown_chunk=None,
|
||||
current_page=page_number,
|
||||
total_pages=0,
|
||||
is_paginated=False
|
||||
)
|
||||
|
||||
content_length = len(full_markdown_content)
|
||||
total_pages = math.ceil(content_length / self.DOCUMENT_MARKDOWN_CHUNK_SIZE)
|
||||
if total_pages == 0: total_pages = 1
|
||||
|
||||
current_page_clamped = max(1, min(page_number, total_pages))
|
||||
start_index = (current_page_clamped - 1) * self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
end_index = start_index + self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
markdown_chunk = full_markdown_content[start_index:end_index]
|
||||
|
||||
return AnayasaBireyselBasvuruDocumentMarkdown(
|
||||
source_url=full_url,
|
||||
basvuru_no_from_page=basvuru_no_from_page,
|
||||
karar_tarihi_from_page=karar_tarihi_from_page,
|
||||
basvuru_tarihi_from_page=basvuru_tarihi_from_page,
|
||||
karari_veren_birim_from_page=karari_veren_birim_from_page,
|
||||
karar_turu_from_page=karar_turu_from_page,
|
||||
resmi_gazete_info_from_page=resmi_gazete_info_from_page,
|
||||
markdown_chunk=markdown_chunk,
|
||||
current_page=current_page_clamped,
|
||||
total_pages=total_pages,
|
||||
is_paginated=(total_pages > 1)
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"AnayasaBireyselBasvuruApiClient: HTTP error fetching Bireysel Başvuru document from {full_url}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaBireyselBasvuruApiClient: General error processing Bireysel Başvuru document from {full_url}: {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
if hasattr(self, 'http_client') and self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("AnayasaBireyselBasvuruApiClient: HTTP client session closed.")
|
||||
@@ -1,356 +0,0 @@
|
||||
# anayasa_mcp_module/client.py
|
||||
# This client is for Norm Denetimi: https://normkararlarbilgibankasi.anayasa.gov.tr
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from urllib.parse import urlencode, urljoin, quote
|
||||
from markitdown import MarkItDown
|
||||
import math # For math.ceil for pagination
|
||||
|
||||
from .models import (
|
||||
AnayasaNormDenetimiSearchRequest,
|
||||
AnayasaDecisionSummary,
|
||||
AnayasaReviewedNormInfo,
|
||||
AnayasaSearchResult,
|
||||
AnayasaDocumentMarkdown, # Model for Norm Denetimi document
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
class AnayasaMahkemesiApiClient:
|
||||
BASE_URL = "https://normkararlarbilgibankasi.anayasa.gov.tr"
|
||||
SEARCH_PATH_SEGMENT = "Ara"
|
||||
DOCUMENT_MARKDOWN_CHUNK_SIZE = 5000 # Character limit per page
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=True,
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
def _build_search_query_params_for_aym(self, params: AnayasaNormDenetimiSearchRequest) -> List[Tuple[str, str]]:
|
||||
query_params: List[Tuple[str, str]] = []
|
||||
if params.keywords_all:
|
||||
for kw in params.keywords_all: query_params.append(("KelimeAra[]", kw))
|
||||
if params.keywords_any:
|
||||
for kw in params.keywords_any: query_params.append(("HerhangiBirKelimeAra[]", kw))
|
||||
if params.keywords_exclude:
|
||||
for kw in params.keywords_exclude: query_params.append(("BulunmayanKelimeAra[]", kw))
|
||||
if params.period and params.period and params.period != "ALL": query_params.append(("Donemler_id", params.period))
|
||||
if params.case_number_esas: query_params.append(("EsasNo", params.case_number_esas))
|
||||
if params.decision_number_karar: query_params.append(("KararNo", params.decision_number_karar))
|
||||
if params.first_review_date_start: query_params.append(("IlkIncelemeTarihiIlk", params.first_review_date_start))
|
||||
if params.first_review_date_end: query_params.append(("IlkIncelemeTarihiSon", params.first_review_date_end))
|
||||
if params.decision_date_start: query_params.append(("KararTarihiIlk", params.decision_date_start))
|
||||
if params.decision_date_end: query_params.append(("KararTarihiSon", params.decision_date_end))
|
||||
if params.application_type and params.application_type and params.application_type != "ALL": query_params.append(("BasvuruTurler_id", params.application_type))
|
||||
if params.applicant_general_name: query_params.append(("BasvuranGeneller_id", params.applicant_general_name))
|
||||
if params.applicant_specific_name: query_params.append(("BasvuranOzeller_id", params.applicant_specific_name))
|
||||
if params.attending_members_names:
|
||||
for name in params.attending_members_names: query_params.append(("Uyeler_id[]", name))
|
||||
if params.rapporteur_name: query_params.append(("Raportorler_id", params.rapporteur_name))
|
||||
if params.norm_type and params.norm_type and params.norm_type != "ALL": query_params.append(("NormunTurler_id", params.norm_type))
|
||||
if params.norm_id_or_name: query_params.append(("NormunNumarasiAdlar_id", params.norm_id_or_name))
|
||||
if params.norm_article: query_params.append(("NormunMaddeNumarasi", params.norm_article))
|
||||
if params.review_outcomes:
|
||||
for outcome_val in params.review_outcomes:
|
||||
if outcome_val and outcome_val != "ALL": query_params.append(("IncelemeTuruKararSonuclar_id[]", outcome_val))
|
||||
if params.reason_for_final_outcome and params.reason_for_final_outcome and params.reason_for_final_outcome != "ALL":
|
||||
query_params.append(("KararSonucununGerekcesi", params.reason_for_final_outcome))
|
||||
if params.basis_constitution_article_numbers:
|
||||
for article_no in params.basis_constitution_article_numbers: query_params.append(("DayanakHukmu[]", article_no))
|
||||
if params.official_gazette_date_start: query_params.append(("ResmiGazeteTarihiIlk", params.official_gazette_date_start))
|
||||
if params.official_gazette_date_end: query_params.append(("ResmiGazeteTarihiSon", params.official_gazette_date_end))
|
||||
if params.official_gazette_number_start: query_params.append(("ResmiGazeteSayisiIlk", params.official_gazette_number_start))
|
||||
if params.official_gazette_number_end: query_params.append(("ResmiGazeteSayisiSon", params.official_gazette_number_end))
|
||||
if params.has_press_release and params.has_press_release and params.has_press_release != "ALL": query_params.append(("BasinDuyurusu", params.has_press_release))
|
||||
if params.has_dissenting_opinion and params.has_dissenting_opinion and params.has_dissenting_opinion != "ALL": query_params.append(("KarsiOy", params.has_dissenting_opinion))
|
||||
if params.has_different_reasoning and params.has_different_reasoning and params.has_different_reasoning != "ALL": query_params.append(("FarkliGerekce", params.has_different_reasoning))
|
||||
|
||||
# Add pagination and sorting parameters as query params instead of URL path
|
||||
if params.results_per_page and params.results_per_page != 10:
|
||||
query_params.append(("SatirSayisi", str(params.results_per_page)))
|
||||
|
||||
if params.sort_by_criteria and params.sort_by_criteria != "KararTarihi":
|
||||
query_params.append(("Siralama", params.sort_by_criteria))
|
||||
|
||||
if params.page_to_fetch and params.page_to_fetch > 1:
|
||||
query_params.append(("page", str(params.page_to_fetch)))
|
||||
return query_params
|
||||
|
||||
async def search_norm_denetimi_decisions(
|
||||
self,
|
||||
params: AnayasaNormDenetimiSearchRequest
|
||||
) -> AnayasaSearchResult:
|
||||
# Use simple /Ara endpoint - the complex path structure seems to cause 404s
|
||||
request_path = f"/{self.SEARCH_PATH_SEGMENT}"
|
||||
|
||||
final_query_params = self._build_search_query_params_for_aym(params)
|
||||
logger.info(f"AnayasaMahkemesiApiClient: Performing Norm Denetimi search. Path: {request_path}, Params: {final_query_params}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(request_path, params=final_query_params)
|
||||
response.raise_for_status()
|
||||
html_content = response.text
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"AnayasaMahkemesiApiClient: HTTP request error during Norm Denetimi search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaMahkemesiApiClient: Error processing Norm Denetimi search request: {e}")
|
||||
raise
|
||||
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
|
||||
total_records = None
|
||||
bulunan_karar_div = soup.find("div", class_="bulunankararsayisi")
|
||||
if not bulunan_karar_div: # Fallback for mobile view
|
||||
bulunan_karar_div = soup.find("div", class_="bulunankararsayisiMobil")
|
||||
|
||||
if bulunan_karar_div:
|
||||
match_records = re.search(r'(\d+)\s*Karar Bulundu', bulunan_karar_div.get_text(strip=True))
|
||||
if match_records:
|
||||
total_records = int(match_records.group(1))
|
||||
|
||||
processed_decisions: List[AnayasaDecisionSummary] = []
|
||||
decision_divs = soup.find_all("div", class_="birkarar")
|
||||
|
||||
for decision_div in decision_divs:
|
||||
link_tag = decision_div.find("a", href=True)
|
||||
doc_url_path = link_tag['href'] if link_tag else None
|
||||
decision_page_url_str = urljoin(self.BASE_URL, doc_url_path) if doc_url_path else None
|
||||
|
||||
title_div = decision_div.find("div", class_="bkararbaslik")
|
||||
ek_no_text_raw = title_div.get_text(strip=True, separator=" ").replace('\xa0', ' ') if title_div else ""
|
||||
ek_no_match = re.search(r"(E\.\s*\d+/\d+\s*,\s*K\.\s*\d+/\d+)", ek_no_text_raw)
|
||||
ek_no_text = ek_no_match.group(1) if ek_no_match else ek_no_text_raw.split("Sayılı Karar")[0].strip()
|
||||
|
||||
keyword_count_div = title_div.find("div", class_="BulunanKelimeSayisi") if title_div else None
|
||||
keyword_count_text = keyword_count_div.get_text(strip=True).replace("Bulunan Kelime Sayısı", "").strip() if keyword_count_div else None
|
||||
keyword_count = int(keyword_count_text) if keyword_count_text and keyword_count_text.isdigit() else None
|
||||
|
||||
info_div = decision_div.find("div", class_="kararbilgileri")
|
||||
info_parts = [part.strip() for part in info_div.get_text(separator="|").split("|")] if info_div else []
|
||||
|
||||
app_type_summary = info_parts[0] if len(info_parts) > 0 else None
|
||||
applicant_summary = info_parts[1] if len(info_parts) > 1 else None
|
||||
outcome_summary = info_parts[2] if len(info_parts) > 2 else None
|
||||
dec_date_raw = info_parts[3] if len(info_parts) > 3 else None
|
||||
decision_date_summary = dec_date_raw.replace("Karar Tarihi:", "").strip() if dec_date_raw else None
|
||||
|
||||
reviewed_norms_list: List[AnayasaReviewedNormInfo] = []
|
||||
details_table_container = decision_div.find_next_sibling("div", class_=re.compile(r"col-sm-12")) # The details table is in a sibling div
|
||||
if details_table_container:
|
||||
details_table = details_table_container.find("table", class_="table")
|
||||
if details_table and details_table.find("tbody"):
|
||||
for row in details_table.find("tbody").find_all("tr"):
|
||||
cells = row.find_all("td")
|
||||
if len(cells) == 6:
|
||||
reviewed_norms_list.append(AnayasaReviewedNormInfo(
|
||||
norm_name_or_number=cells[0].get_text(strip=True) or None,
|
||||
article_number=cells[1].get_text(strip=True) or None,
|
||||
review_type_and_outcome=cells[2].get_text(strip=True) or None,
|
||||
outcome_reason=cells[3].get_text(strip=True) or None,
|
||||
basis_constitution_articles_cited=[a.strip() for a in cells[4].get_text(strip=True).split(',') if a.strip()] if cells[4].get_text(strip=True) else [],
|
||||
postponement_period=cells[5].get_text(strip=True) or None
|
||||
))
|
||||
|
||||
processed_decisions.append(AnayasaDecisionSummary(
|
||||
decision_reference_no=ek_no_text,
|
||||
decision_page_url=decision_page_url_str,
|
||||
keywords_found_count=keyword_count,
|
||||
application_type_summary=app_type_summary,
|
||||
applicant_summary=applicant_summary,
|
||||
decision_outcome_summary=outcome_summary,
|
||||
decision_date_summary=decision_date_summary,
|
||||
reviewed_norms=reviewed_norms_list
|
||||
))
|
||||
|
||||
return AnayasaSearchResult(
|
||||
decisions=processed_decisions,
|
||||
total_records_found=total_records,
|
||||
retrieved_page_number=params.page_to_fetch
|
||||
)
|
||||
|
||||
def _convert_html_to_markdown_norm_denetimi(self, full_decision_html_content: str) -> Optional[str]:
|
||||
"""Converts direct HTML content from an Anayasa Mahkemesi Norm Denetimi decision page to Markdown."""
|
||||
if not full_decision_html_content:
|
||||
return None
|
||||
|
||||
processed_html = html.unescape(full_decision_html_content)
|
||||
soup = BeautifulSoup(processed_html, "html.parser")
|
||||
html_input_for_markdown = ""
|
||||
|
||||
karar_tab_content = soup.find("div", id="Karar") # "KARAR" tab content
|
||||
if karar_tab_content:
|
||||
karar_metni_div = karar_tab_content.find("div", class_="KararMetni")
|
||||
if karar_metni_div:
|
||||
# Remove scripts and styles
|
||||
for script_tag in karar_metni_div.find_all("script"): script_tag.decompose()
|
||||
for style_tag in karar_metni_div.find_all("style"): style_tag.decompose()
|
||||
# Remove "Künye Kopyala" button and other non-content divs
|
||||
for item_div in karar_metni_div.find_all("div", class_="item col-sm-12"): item_div.decompose()
|
||||
for modal_div in karar_metni_div.find_all("div", class_="modal fade"): modal_div.decompose() # If any modals
|
||||
|
||||
word_section = karar_metni_div.find("div", class_="WordSection1")
|
||||
html_input_for_markdown = str(word_section) if word_section else str(karar_metni_div)
|
||||
else:
|
||||
html_input_for_markdown = str(karar_tab_content)
|
||||
else:
|
||||
# Fallback if specific structure is not found
|
||||
word_section_fallback = soup.find("div", class_="WordSection1")
|
||||
if word_section_fallback:
|
||||
html_input_for_markdown = str(word_section_fallback)
|
||||
else:
|
||||
# Last resort: use the whole body or the raw HTML
|
||||
body_tag = soup.find("body")
|
||||
html_input_for_markdown = str(body_tag) if body_tag else processed_html
|
||||
|
||||
markdown_text = None
|
||||
try:
|
||||
# Ensure the content is wrapped in basic HTML structure if it's not already
|
||||
if not html_input_for_markdown.strip().lower().startswith(("<html", "<!doctype")):
|
||||
html_content = f"<html><head><meta charset=\"UTF-8\"></head><body>{html_input_for_markdown}</body></html>"
|
||||
else:
|
||||
html_content = html_input_for_markdown
|
||||
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_content.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaMahkemesiApiClient: MarkItDown conversion error: {e}")
|
||||
return markdown_text
|
||||
|
||||
async def get_decision_document_as_markdown(
|
||||
self,
|
||||
document_url: str,
|
||||
page_number: int = 1
|
||||
) -> AnayasaDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Anayasa Mahkemesi (Norm Denetimi) decision,
|
||||
converts its content to Markdown, and returns the requested page/chunk.
|
||||
"""
|
||||
full_url = urljoin(self.BASE_URL, document_url) if not document_url.startswith("http") else document_url
|
||||
logger.info(f"AnayasaMahkemesiApiClient: Fetching Norm Denetimi document for Markdown (page {page_number}) from URL: {full_url}")
|
||||
|
||||
decision_ek_no_from_page = None
|
||||
decision_date_from_page = None
|
||||
official_gazette_from_page = None
|
||||
|
||||
try:
|
||||
# Use a new client instance for document fetching if headers/timeout needs to be different,
|
||||
# or reuse self.http_client if settings are compatible. For now, self.http_client.
|
||||
get_response = await self.http_client.get(full_url, headers={"Accept": "text/html"})
|
||||
get_response.raise_for_status()
|
||||
html_content_from_api = get_response.text
|
||||
|
||||
if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
|
||||
logger.warning(f"AnayasaMahkemesiApiClient: Received empty or non-string HTML from URL {full_url}.")
|
||||
return AnayasaDocumentMarkdown(
|
||||
source_url=full_url, markdown_chunk=None, current_page=page_number, total_pages=0, is_paginated=False
|
||||
)
|
||||
|
||||
# Extract metadata from the page content (E.K. No, Date, RG)
|
||||
soup = BeautifulSoup(html_content_from_api, "html.parser")
|
||||
karar_metni_div = soup.find("div", class_="KararMetni") # Usually within div#Karar
|
||||
if not karar_metni_div: # Fallback if not in KararMetni
|
||||
karar_metni_div = soup.find("div", class_="WordSection1")
|
||||
|
||||
# Initialize with empty string defaults
|
||||
decision_ek_no_from_page = ""
|
||||
decision_date_from_page = ""
|
||||
official_gazette_from_page = ""
|
||||
|
||||
if karar_metni_div:
|
||||
# Attempt to find E.K. No (Esas No, Karar No)
|
||||
# Norm Denetimi pages often have this in bold <p> tags directly or in the WordSection1
|
||||
# Look for patterns like "Esas No.: YYYY/NN" and "Karar No.: YYYY/NN"
|
||||
|
||||
esas_no_tag = karar_metni_div.find(lambda tag: tag.name == "p" and tag.find("b") and "Esas No.:" in tag.find("b").get_text())
|
||||
karar_no_tag = karar_metni_div.find(lambda tag: tag.name == "p" and tag.find("b") and "Karar No.:" in tag.find("b").get_text())
|
||||
karar_tarihi_tag = karar_metni_div.find(lambda tag: tag.name == "p" and tag.find("b") and "Karar tarihi:" in tag.find("b").get_text()) # Less common on Norm pages
|
||||
resmi_gazete_tag = karar_metni_div.find(lambda tag: tag.name == "p" and ("Resmî Gazete tarih ve sayısı:" in tag.get_text() or "Resmi Gazete tarih/sayı:" in tag.get_text()))
|
||||
|
||||
|
||||
if esas_no_tag and esas_no_tag.find("b") and karar_no_tag and karar_no_tag.find("b"):
|
||||
esas_str = esas_no_tag.find("b").get_text(strip=True).replace('Esas No.:', '').strip()
|
||||
karar_str = karar_no_tag.find("b").get_text(strip=True).replace('Karar No.:', '').strip()
|
||||
decision_ek_no_from_page = f"E.{esas_str}, K.{karar_str}"
|
||||
|
||||
if karar_tarihi_tag and karar_tarihi_tag.find("b"):
|
||||
decision_date_from_page = karar_tarihi_tag.find("b").get_text(strip=True).replace("Karar tarihi:", "").strip()
|
||||
elif karar_metni_div: # Fallback for Karar Tarihi if not in specific tag
|
||||
date_match = re.search(r"Karar Tarihi\s*:\s*([\d\.]+)", karar_metni_div.get_text()) # Norm pages often use DD.MM.YYYY
|
||||
if date_match: decision_date_from_page = date_match.group(1).strip()
|
||||
|
||||
|
||||
if resmi_gazete_tag:
|
||||
# Try to get the bold part first if it exists
|
||||
bold_rg_tag = resmi_gazete_tag.find("b")
|
||||
rg_text_content = bold_rg_tag.get_text(strip=True) if bold_rg_tag else resmi_gazete_tag.get_text(strip=True)
|
||||
official_gazette_from_page = rg_text_content.replace("Resmî Gazete tarih ve sayısı:", "").replace("Resmi Gazete tarih/sayı:", "").strip()
|
||||
|
||||
|
||||
full_markdown_content = self._convert_html_to_markdown_norm_denetimi(html_content_from_api)
|
||||
|
||||
if not full_markdown_content:
|
||||
return AnayasaDocumentMarkdown(
|
||||
source_url=full_url,
|
||||
decision_reference_no_from_page=decision_ek_no_from_page,
|
||||
decision_date_from_page=decision_date_from_page,
|
||||
official_gazette_info_from_page=official_gazette_from_page,
|
||||
markdown_chunk=None,
|
||||
current_page=page_number,
|
||||
total_pages=0,
|
||||
is_paginated=False
|
||||
)
|
||||
|
||||
content_length = len(full_markdown_content)
|
||||
total_pages = math.ceil(content_length / self.DOCUMENT_MARKDOWN_CHUNK_SIZE)
|
||||
if total_pages == 0: total_pages = 1
|
||||
|
||||
current_page_clamped = max(1, min(page_number, total_pages))
|
||||
start_index = (current_page_clamped - 1) * self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
end_index = start_index + self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
markdown_chunk = full_markdown_content[start_index:end_index]
|
||||
|
||||
return AnayasaDocumentMarkdown(
|
||||
source_url=full_url,
|
||||
decision_reference_no_from_page=decision_ek_no_from_page,
|
||||
decision_date_from_page=decision_date_from_page,
|
||||
official_gazette_info_from_page=official_gazette_from_page,
|
||||
markdown_chunk=markdown_chunk,
|
||||
current_page=current_page_clamped,
|
||||
total_pages=total_pages,
|
||||
is_paginated=(total_pages > 1)
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"AnayasaMahkemesiApiClient: HTTP error fetching Norm Denetimi document from {full_url}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"AnayasaMahkemesiApiClient: General error processing Norm Denetimi document from {full_url}: {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
if hasattr(self, 'http_client') and self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("AnayasaMahkemesiApiClient (Norm Denetimi): HTTP client session closed.")
|
||||
@@ -1,230 +0,0 @@
|
||||
# anayasa_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl
|
||||
from typing import List, Optional, Dict, Any, Literal
|
||||
from enum import Enum
|
||||
|
||||
# --- Enums (AnayasaDonemEnum, etc. - same as before) ---
|
||||
class AnayasaDonemEnum(str, Enum):
|
||||
TUMU = "ALL"
|
||||
DONEM_1961 = "1"
|
||||
DONEM_1982 = "2"
|
||||
|
||||
|
||||
class AnayasaVarYokEnum(str, Enum):
|
||||
TUMU = "ALL"
|
||||
YOK = "0"
|
||||
VAR = "1"
|
||||
|
||||
|
||||
class AnayasaIncelemeSonucuEnum(str, Enum):
|
||||
TUMU = "ALL"
|
||||
ESAS_ACILMAMIS_SAYILMA = "1"
|
||||
ESAS_IPTAL = "2"
|
||||
ESAS_KARAR_YER_OLMADIGI = "3"
|
||||
ESAS_RET = "4"
|
||||
ILK_ACILMAMIS_SAYILMA = "5"
|
||||
ILK_ISIN_GERI_CEVRILMESI = "6"
|
||||
ILK_KARAR_YER_OLMADIGI = "7"
|
||||
ILK_RET = "8"
|
||||
KANUN_6216_M43_4_IPTAL = "12"
|
||||
|
||||
class AnayasaSonucGerekcesiEnum(str, Enum):
|
||||
TUMU = "ALL"
|
||||
ANAYASAYA_AYKIRI_DEGIL = "29"
|
||||
ANAYASAYA_ESAS_YONUNDEN_AYKIRILIK = "1"
|
||||
ANAYASAYA_ESAS_YONUNDEN_UYGUNLUK = "2"
|
||||
ANAYASAYA_SEKIL_ESAS_UYGUNLUK = "30"
|
||||
ANAYASAYA_SEKIL_YONUNDEN_AYKIRILIK = "3"
|
||||
ANAYASAYA_SEKIL_YONUNDEN_UYGUNLUK = "4"
|
||||
AYKIRILIK_ANAYASAYA_ESAS_YONUNDEN_DUPLICATE = "27"
|
||||
BASVURU_KARARI = "5"
|
||||
DENETIM_DISI = "6"
|
||||
DIGER_GEREKCE_1 = "7"
|
||||
DIGER_GEREKCE_2 = "8"
|
||||
EKSIKLIGIN_GIDERILMEMESI = "9"
|
||||
GEREKCE = "10"
|
||||
GOREV = "11"
|
||||
GOREV_YETKI = "12"
|
||||
GOREVLI_MAHKEME = "13"
|
||||
GORULMEKTE_OLAN_DAVA = "14"
|
||||
MAHKEME = "15"
|
||||
NORMDA_DEGISIKLIK_YAPILMASI = "16"
|
||||
NORMUN_YURURLUKTEN_KALDIRILMASI = "17"
|
||||
ON_YIL_YASAGI = "18"
|
||||
SURE = "19"
|
||||
USULE_UYMAMA = "20"
|
||||
UYGULANACAK_NORM = "21"
|
||||
UYGULANAMAZ_HALE_GELME = "22"
|
||||
YETKI = "23"
|
||||
YETKI_SURE = "24"
|
||||
YOK_HUKMUNDE_OLMAMA = "25"
|
||||
YOKLUK = "26"
|
||||
# --- End Enums ---
|
||||
|
||||
class AnayasaNormDenetimiSearchRequest(BaseModel):
|
||||
"""Model for Anayasa Mahkemesi (Norm Denetimi) search request for the MCP tool."""
|
||||
keywords_all: Optional[List[str]] = Field(default_factory=list, description="Keywords for AND logic (KelimeAra[]).")
|
||||
keywords_any: Optional[List[str]] = Field(default_factory=list, description="Keywords for OR logic (HerhangiBirKelimeAra[]).")
|
||||
keywords_exclude: Optional[List[str]] = Field(default_factory=list, description="Keywords to exclude (BulunmayanKelimeAra[]).")
|
||||
period: Optional[Literal["ALL", "1", "2"]] = Field(default="ALL", description="Constitutional period (Donemler_id).")
|
||||
case_number_esas: str = Field("", description="Case registry number (EsasNo), e.g., '2023/123'.")
|
||||
decision_number_karar: str = Field("", description="Decision number (KararNo), e.g., '2023/456'.")
|
||||
first_review_date_start: str = Field("", description="First review start date (IlkIncelemeTarihiIlk), format DD/MM/YYYY.")
|
||||
first_review_date_end: str = Field("", description="First review end date (IlkIncelemeTarihiSon), format DD/MM/YYYY.")
|
||||
decision_date_start: str = Field("", description="Decision start date (KararTarihiIlk), format DD/MM/YYYY.")
|
||||
decision_date_end: str = Field("", description="Decision end date (KararTarihiSon), format DD/MM/YYYY.")
|
||||
application_type: Optional[Literal["ALL", "1", "2", "3"]] = Field(default="ALL", description="Type of application (BasvuruTurler_id).")
|
||||
applicant_general_name: str = Field("", description="General applicant name (BasvuranGeneller_id).")
|
||||
applicant_specific_name: str = Field("", description="Specific applicant name (BasvuranOzeller_id).")
|
||||
official_gazette_date_start: str = Field("", description="Official Gazette start date (ResmiGazeteTarihiIlk), format DD/MM/YYYY.")
|
||||
official_gazette_date_end: str = Field("", description="Official Gazette end date (ResmiGazeteTarihiSon), format DD/MM/YYYY.")
|
||||
official_gazette_number_start: str = Field("", description="Official Gazette starting number (ResmiGazeteSayisiIlk).")
|
||||
official_gazette_number_end: str = Field("", description="Official Gazette ending number (ResmiGazeteSayisiSon).")
|
||||
has_press_release: Optional[Literal["ALL", "0", "1"]] = Field(default="ALL", description="Press release available (BasinDuyurusu).")
|
||||
has_dissenting_opinion: Optional[Literal["ALL", "0", "1"]] = Field(default="ALL", description="Dissenting opinion exists (KarsiOy).")
|
||||
has_different_reasoning: Optional[Literal["ALL", "0", "1"]] = Field(default="ALL", description="Different reasoning exists (FarkliGerekce).")
|
||||
attending_members_names: Optional[List[str]] = Field(default_factory=list, description="List of attending members' exact names (Uyeler_id[]).")
|
||||
rapporteur_name: str = Field("", description="Rapporteur's exact name (Raportorler_id).")
|
||||
norm_type: Optional[Literal["ALL", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "0"]] = Field(default="ALL", description="Type of the reviewed norm (NormunTurler_id).")
|
||||
norm_id_or_name: str = Field("", description="Number or name of the norm (NormunNumarasiAdlar_id).")
|
||||
norm_article: str = Field("", description="Article number of the norm (NormunMaddeNumarasi).")
|
||||
review_outcomes: Optional[List[Literal["1", "2", "3", "4", "5", "6", "7", "8", "12"]]] = Field(default_factory=list, description="List of review types and outcomes (IncelemeTuruKararSonuclar_id[]).")
|
||||
reason_for_final_outcome: Optional[Literal["ALL", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "29", "30"]] = Field(default="ALL", description="Main reason for the decision outcome (KararSonucununGerekcesi).")
|
||||
basis_constitution_article_numbers: Optional[List[str]] = Field(default_factory=list, description="List of supporting Constitution article numbers (DayanakHukmu[]).")
|
||||
results_per_page: int = Field(10, ge=1, le=10, description="Results per page.")
|
||||
page_to_fetch: int = Field(1, ge=1, description="Page number to fetch for results list.")
|
||||
sort_by_criteria: str = Field("KararTarihi", description="Sort criteria. Options: 'KararTarihi', 'YayinTarihi', 'Toplam' (keyword count).")
|
||||
|
||||
class AnayasaReviewedNormInfo(BaseModel):
|
||||
"""Details of a norm reviewed within an AYM decision summary."""
|
||||
norm_name_or_number: str = Field("", description="Norm name or number")
|
||||
article_number: str = Field("", description="Article number")
|
||||
review_type_and_outcome: str = Field("", description="Review type and outcome")
|
||||
outcome_reason: str = Field("", description="Outcome reason")
|
||||
basis_constitution_articles_cited: List[str] = Field(default_factory=list)
|
||||
postponement_period: str = Field("", description="Postponement period")
|
||||
|
||||
class AnayasaDecisionSummary(BaseModel):
|
||||
"""Model for a single Anayasa Mahkemesi (Norm Denetimi) decision summary from search results."""
|
||||
decision_reference_no: str = Field("", description="Decision reference number")
|
||||
decision_page_url: str = Field("", description="Decision page URL")
|
||||
keywords_found_count: Optional[int] = Field(0, description="Keywords found count")
|
||||
application_type_summary: str = Field("", description="Application type summary")
|
||||
applicant_summary: str = Field("", description="Applicant summary")
|
||||
decision_outcome_summary: str = Field("", description="Decision outcome summary")
|
||||
decision_date_summary: str = Field("", description="Decision date summary")
|
||||
reviewed_norms: List[AnayasaReviewedNormInfo] = Field(default_factory=list)
|
||||
|
||||
class AnayasaSearchResult(BaseModel):
|
||||
"""Model for the overall search result for Anayasa Mahkemesi Norm Denetimi decisions."""
|
||||
decisions: List[AnayasaDecisionSummary]
|
||||
total_records_found: int = Field(0, description="Total records found")
|
||||
retrieved_page_number: int = Field(1, description="Retrieved page number")
|
||||
|
||||
class AnayasaDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
Model for an Anayasa Mahkemesi (Norm Denetimi) decision document, containing a chunk of Markdown content
|
||||
and pagination information.
|
||||
"""
|
||||
source_url: HttpUrl
|
||||
decision_reference_no_from_page: str = Field("", description="E.K. No parsed from the document page.")
|
||||
decision_date_from_page: str = Field("", description="Decision date parsed from the document page.")
|
||||
official_gazette_info_from_page: str = Field("", description="Official Gazette info parsed from the document page.")
|
||||
markdown_chunk: str = Field("", description="A 5,000 character chunk of the Markdown content.") # Corrected chunk size
|
||||
current_page: int = Field(description="The current page number of the markdown chunk (1-indexed).")
|
||||
total_pages: int = Field(description="Total number of pages for the full markdown content.")
|
||||
is_paginated: bool = Field(description="True if the full markdown content is split into multiple pages.")
|
||||
|
||||
|
||||
# --- Models for Anayasa Mahkemesi - Bireysel Başvuru Karar Raporu ---
|
||||
|
||||
class AnayasaBireyselReportSearchRequest(BaseModel):
|
||||
"""Model for Anayasa Mahkemesi (Bireysel Başvuru) 'Karar Arama Raporu' search request."""
|
||||
keywords: Optional[List[str]] = Field(default_factory=list, description="Keywords for AND logic (KelimeAra[]).")
|
||||
page_to_fetch: int = Field(1, ge=1, description="Page number to fetch for the report (page). Default is 1.")
|
||||
|
||||
class AnayasaBireyselReportDecisionDetail(BaseModel):
|
||||
"""Details of a specific right/claim within a Bireysel Başvuru decision summary in a report."""
|
||||
hak: str = Field("", description="İhlal edildiği iddia edilen hak (örneğin, Mülkiyet hakkı).")
|
||||
mudahale_iddiasi: str = Field("", description="İhlale neden olan müdahale iddiası.")
|
||||
sonuc: str = Field("", description="İnceleme sonucu (örneğin, İhlal, Düşme).")
|
||||
giderim: str = Field("", description="Kararlaştırılan giderim (örneğin, Yeniden yargılama).")
|
||||
|
||||
class AnayasaBireyselReportDecisionSummary(BaseModel):
|
||||
"""Model for a single Anayasa Mahkemesi (Bireysel Başvuru) decision summary from a 'Karar Arama Raporu'."""
|
||||
title: str = Field("", description="Başvurunun başlığı (e.g., 'HASAN DURMUŞ Başvurusuna İlişkin Karar').")
|
||||
decision_reference_no: str = Field("", description="Başvuru Numarası (e.g., '2019/19126').")
|
||||
decision_page_url: str = Field("", description="URL to the full decision page.")
|
||||
decision_type_summary: str = Field("", description="Karar Türü (Başvuru Sonucu) (e.g., 'Esas (İhlal)').")
|
||||
decision_making_body: str = Field("", description="Kararı Veren Birim (e.g., 'Genel Kurul', 'Birinci Bölüm').")
|
||||
application_date_summary: str = Field("", description="Başvuru Tarihi (DD/MM/YYYY).")
|
||||
decision_date_summary: str = Field("", description="Karar Tarihi (DD/MM/YYYY).")
|
||||
application_subject_summary: str = Field("", description="Başvuru konusunun özeti.")
|
||||
details: List[AnayasaBireyselReportDecisionDetail] = Field(default_factory=list, description="İncelenen haklar ve sonuçlarına ilişkin detaylar.")
|
||||
|
||||
class AnayasaBireyselReportSearchResult(BaseModel):
|
||||
"""Model for the overall search result for Anayasa Mahkemesi 'Karar Arama Raporu'."""
|
||||
decisions: List[AnayasaBireyselReportDecisionSummary]
|
||||
total_records_found: int = Field(0, description="Raporda bulunan toplam karar sayısı.")
|
||||
retrieved_page_number: int = Field(description="Alınan rapor sayfa numarası.")
|
||||
|
||||
|
||||
class AnayasaBireyselBasvuruDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
Model for an Anayasa Mahkemesi (Bireysel Başvuru) decision document, containing a chunk of Markdown content
|
||||
and pagination information. Fetched from /BB/YYYY/NNNN paths.
|
||||
"""
|
||||
source_url: HttpUrl
|
||||
basvuru_no_from_page: Optional[str] = Field(None, description="Başvuru Numarası (B.No) parsed from the document page.")
|
||||
karar_tarihi_from_page: Optional[str] = Field(None, description="Decision date parsed from the document page.")
|
||||
basvuru_tarihi_from_page: Optional[str] = Field(None, description="Application date parsed from the document page.")
|
||||
karari_veren_birim_from_page: Optional[str] = Field(None, description="Deciding body (Bölüm/Genel Kurul) parsed from the document page.")
|
||||
karar_turu_from_page: Optional[str] = Field(None, description="Decision type (Başvuru Sonucu) parsed from the document page.")
|
||||
resmi_gazete_info_from_page: Optional[str] = Field(None, description="Official Gazette info parsed from the document page, if available.")
|
||||
markdown_chunk: Optional[str] = Field(None, description="A 5,000 character chunk of the Markdown content.")
|
||||
current_page: int = Field(description="The current page number of the markdown chunk (1-indexed).")
|
||||
total_pages: int = Field(description="Total number of pages for the full markdown content.")
|
||||
is_paginated: bool = Field(description="True if the full markdown content is split into multiple pages.")
|
||||
|
||||
# --- End Models for Bireysel Başvuru ---
|
||||
|
||||
# --- Unified Models ---
|
||||
class AnayasaUnifiedSearchRequest(BaseModel):
|
||||
"""Unified search request for both Norm Denetimi and Bireysel Başvuru."""
|
||||
decision_type: Literal["norm_denetimi", "bireysel_basvuru"] = Field(..., description="Decision type: norm_denetimi or bireysel_basvuru")
|
||||
|
||||
# Common parameters
|
||||
keywords: List[str] = Field(default_factory=list, description="Keywords to search for")
|
||||
page_to_fetch: int = Field(1, ge=1, le=100, description="Page number to fetch (1-100)")
|
||||
results_per_page: int = Field(10, ge=1, le=100, description="Results per page (1-100)")
|
||||
|
||||
# Norm Denetimi specific parameters (ignored for bireysel_basvuru)
|
||||
keywords_all: List[str] = Field(default_factory=list, description="All keywords must be present (norm_denetimi only)")
|
||||
keywords_any: List[str] = Field(default_factory=list, description="Any of these keywords (norm_denetimi only)")
|
||||
decision_type_norm: Literal["ALL", "1", "2", "3"] = Field("ALL", description="Decision type for norm denetimi")
|
||||
application_date_start: str = Field("", description="Application start date (norm_denetimi only)")
|
||||
application_date_end: str = Field("", description="Application end date (norm_denetimi only)")
|
||||
|
||||
# Bireysel Başvuru specific parameters (ignored for norm_denetimi)
|
||||
decision_start_date: str = Field("", description="Decision start date (bireysel_basvuru only)")
|
||||
decision_end_date: str = Field("", description="Decision end date (bireysel_basvuru only)")
|
||||
norm_type: Literal["ALL", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "0"] = Field("ALL", description="Norm type (bireysel_basvuru only)")
|
||||
subject_category: str = Field("", description="Subject category (bireysel_basvuru only)")
|
||||
|
||||
class AnayasaUnifiedSearchResult(BaseModel):
|
||||
"""Unified search result containing decisions from either system."""
|
||||
decision_type: Literal["norm_denetimi", "bireysel_basvuru"] = Field(..., description="Type of decisions returned")
|
||||
decisions: List[Dict[str, Any]] = Field(default_factory=list, description="Decision list (structure varies by type)")
|
||||
total_records_found: int = Field(0, description="Total number of records found")
|
||||
retrieved_page_number: int = Field(1, description="Page number that was retrieved")
|
||||
|
||||
class AnayasaUnifiedDocumentMarkdown(BaseModel):
|
||||
"""Unified document model for both Norm Denetimi and Bireysel Başvuru."""
|
||||
decision_type: Literal["norm_denetimi", "bireysel_basvuru"] = Field(..., description="Type of document")
|
||||
source_url: HttpUrl = Field(..., description="Source URL of the document")
|
||||
document_data: Dict[str, Any] = Field(default_factory=dict, description="Document content and metadata")
|
||||
markdown_chunk: Optional[str] = Field(None, description="Markdown content chunk")
|
||||
current_page: int = Field(1, description="Current page number")
|
||||
total_pages: int = Field(1, description="Total number of pages")
|
||||
is_paginated: bool = Field(False, description="Whether document is paginated")
|
||||
@@ -1,122 +0,0 @@
|
||||
# anayasa_mcp_module/unified_client.py
|
||||
# Unified client for both Norm Denetimi and Bireysel Başvuru
|
||||
|
||||
import logging
|
||||
from typing import Optional
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from .models import (
|
||||
AnayasaUnifiedSearchRequest,
|
||||
AnayasaUnifiedSearchResult,
|
||||
AnayasaUnifiedDocumentMarkdown,
|
||||
# Removed AnayasaDecisionTypeEnum - now using string literals
|
||||
AnayasaNormDenetimiSearchRequest,
|
||||
AnayasaBireyselReportSearchRequest
|
||||
)
|
||||
from .client import AnayasaMahkemesiApiClient
|
||||
from .bireysel_client import AnayasaBireyselBasvuruApiClient
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class AnayasaUnifiedClient:
|
||||
"""Unified client that handles both Norm Denetimi and Bireysel Başvuru searches."""
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.norm_client = AnayasaMahkemesiApiClient(request_timeout)
|
||||
self.bireysel_client = AnayasaBireyselBasvuruApiClient(request_timeout)
|
||||
|
||||
async def search_unified(self, params: AnayasaUnifiedSearchRequest) -> AnayasaUnifiedSearchResult:
|
||||
"""Unified search that routes to appropriate client based on decision_type."""
|
||||
|
||||
if params.decision_type == "norm_denetimi":
|
||||
# Convert to norm denetimi request
|
||||
norm_params = AnayasaNormDenetimiSearchRequest(
|
||||
keywords_all=params.keywords_all or params.keywords,
|
||||
keywords_any=params.keywords_any,
|
||||
application_type=params.decision_type_norm,
|
||||
page_to_fetch=params.page_to_fetch,
|
||||
results_per_page=params.results_per_page
|
||||
)
|
||||
|
||||
result = await self.norm_client.search_norm_denetimi_decisions(norm_params)
|
||||
|
||||
# Convert to unified format
|
||||
decisions_list = [decision.model_dump() for decision in result.decisions]
|
||||
|
||||
return AnayasaUnifiedSearchResult(
|
||||
decision_type="norm_denetimi",
|
||||
decisions=decisions_list,
|
||||
total_records_found=result.total_records_found,
|
||||
retrieved_page_number=result.retrieved_page_number
|
||||
)
|
||||
|
||||
elif params.decision_type == "bireysel_basvuru":
|
||||
# Convert to bireysel başvuru request
|
||||
bireysel_params = AnayasaBireyselReportSearchRequest(
|
||||
keywords=params.keywords,
|
||||
decision_start_date=params.decision_start_date,
|
||||
decision_end_date=params.decision_end_date,
|
||||
norm_type=params.norm_type,
|
||||
subject_category=params.subject_category,
|
||||
page_to_fetch=params.page_to_fetch,
|
||||
results_per_page=params.results_per_page
|
||||
)
|
||||
|
||||
result = await self.bireysel_client.search_bireysel_basvuru_report(bireysel_params)
|
||||
|
||||
# Convert to unified format
|
||||
decisions_list = [decision.model_dump() for decision in result.decisions]
|
||||
|
||||
return AnayasaUnifiedSearchResult(
|
||||
decision_type="bireysel_basvuru",
|
||||
decisions=decisions_list,
|
||||
total_records_found=result.total_records_found,
|
||||
retrieved_page_number=result.retrieved_page_number
|
||||
)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Unsupported decision type: {params.decision_type}")
|
||||
|
||||
async def get_document_unified(self, document_url: str, page_number: int = 1) -> AnayasaUnifiedDocumentMarkdown:
|
||||
"""Unified document retrieval that auto-detects the appropriate client."""
|
||||
|
||||
# Auto-detect decision type based on URL
|
||||
parsed_url = urlparse(document_url)
|
||||
|
||||
if "normkararlarbilgibankasi" in parsed_url.netloc or "/ND/" in document_url:
|
||||
# Norm Denetimi document
|
||||
result = await self.norm_client.get_decision_document_as_markdown(document_url, page_number)
|
||||
|
||||
return AnayasaUnifiedDocumentMarkdown(
|
||||
decision_type="norm_denetimi",
|
||||
source_url=result.source_url,
|
||||
document_data=result.model_dump(),
|
||||
markdown_chunk=result.markdown_chunk,
|
||||
current_page=result.current_page,
|
||||
total_pages=result.total_pages,
|
||||
is_paginated=result.is_paginated
|
||||
)
|
||||
|
||||
elif "kararlarbilgibankasi" in parsed_url.netloc or "/BB/" in document_url:
|
||||
# Bireysel Başvuru document
|
||||
result = await self.bireysel_client.get_decision_document_as_markdown(document_url, page_number)
|
||||
|
||||
return AnayasaUnifiedDocumentMarkdown(
|
||||
decision_type="bireysel_basvuru",
|
||||
source_url=result.source_url,
|
||||
document_data=result.model_dump(),
|
||||
markdown_chunk=result.markdown_chunk,
|
||||
current_page=result.current_page,
|
||||
total_pages=result.total_pages,
|
||||
is_paginated=result.is_paginated
|
||||
)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Cannot determine document type from URL: {document_url}")
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close both client sessions."""
|
||||
if hasattr(self.norm_client, 'close_client_session'):
|
||||
await self.norm_client.close_client_session()
|
||||
if hasattr(self.bireysel_client, 'close_client_session'):
|
||||
await self.bireysel_client.close_client_session()
|
||||
@@ -1,566 +0,0 @@
|
||||
"""
|
||||
ASGI application for Yargı MCP Server
|
||||
|
||||
This module provides ASGI/HTTP access to the Yargı MCP server,
|
||||
allowing it to be deployed as a web service with FastAPI wrapper
|
||||
for Stripe webhook integration.
|
||||
|
||||
Usage:
|
||||
uvicorn asgi_app:app --host 0.0.0.0 --port 8000
|
||||
"""
|
||||
|
||||
import os
|
||||
import time
|
||||
import logging
|
||||
from datetime import datetime, timedelta
|
||||
from fastapi import FastAPI, Request, HTTPException, Query
|
||||
from fastapi.responses import JSONResponse, HTMLResponse
|
||||
from fastapi.exception_handlers import http_exception_handler
|
||||
from starlette.middleware import Middleware
|
||||
from starlette.middleware.cors import CORSMiddleware
|
||||
from starlette.responses import Response
|
||||
from starlette.requests import Request as StarletteRequest
|
||||
|
||||
# Import the MCP app creator function
|
||||
from mcp_server_main import create_app
|
||||
|
||||
# Import Stripe webhook router
|
||||
from stripe_webhook import router as stripe_router
|
||||
|
||||
# Import simplified MCP Auth HTTP adapter
|
||||
from mcp_auth_http_simple import router as mcp_auth_router
|
||||
|
||||
# OAuth configuration from environment variables
|
||||
CLERK_ISSUER = os.getenv("CLERK_ISSUER", "https://accounts.yargimcp.com")
|
||||
BASE_URL = os.getenv("BASE_URL", "https://yargimcp.com")
|
||||
|
||||
# Setup logging
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Configure CORS and Auth middleware
|
||||
cors_origins = os.getenv("ALLOWED_ORIGINS", "*").split(",")
|
||||
|
||||
# Import FastMCP Bearer Auth Provider
|
||||
from fastmcp.server.auth import BearerAuthProvider
|
||||
from fastmcp.server.auth.providers.bearer import RSAKeyPair
|
||||
|
||||
# Clerk JWT configuration for Bearer token validation
|
||||
CLERK_SECRET_KEY = os.getenv("CLERK_SECRET_KEY")
|
||||
CLERK_ISSUER = os.getenv("CLERK_ISSUER", "https://accounts.yargimcp.com")
|
||||
CLERK_PUBLISHABLE_KEY = os.getenv("CLERK_PUBLISHABLE_KEY")
|
||||
|
||||
# Configure Bearer token authentication
|
||||
bearer_auth = None
|
||||
if CLERK_SECRET_KEY and CLERK_ISSUER:
|
||||
# Production: Use Clerk JWKS endpoint for token validation
|
||||
bearer_auth = BearerAuthProvider(
|
||||
jwks_uri=f"{CLERK_ISSUER}/.well-known/jwks.json",
|
||||
issuer=CLERK_ISSUER,
|
||||
algorithm="RS256",
|
||||
audience=None, # Disable audience validation - Clerk uses different audience format
|
||||
required_scopes=[] # Disable scope validation - Clerk JWT has ['read', 'search']
|
||||
)
|
||||
logger.info(f"Bearer auth configured with Clerk JWKS: {CLERK_ISSUER}/.well-known/jwks.json")
|
||||
else:
|
||||
# Development: Generate RSA key pair for testing
|
||||
logger.warning("No Clerk credentials found - using development RSA key pair")
|
||||
dev_key_pair = RSAKeyPair.generate()
|
||||
bearer_auth = BearerAuthProvider(
|
||||
public_key=dev_key_pair.public_key,
|
||||
issuer="https://dev.yargimcp.com",
|
||||
audience="dev-mcp-server",
|
||||
required_scopes=["yargi.read"]
|
||||
)
|
||||
|
||||
# Generate a test token for development
|
||||
dev_token = dev_key_pair.create_token(
|
||||
subject="dev-user",
|
||||
issuer="https://dev.yargimcp.com",
|
||||
audience="dev-mcp-server",
|
||||
scopes=["yargi.read", "yargi.search"],
|
||||
expires_in_seconds=3600 * 24 # 24 hours for development
|
||||
)
|
||||
logger.info(f"Development Bearer token: {dev_token}")
|
||||
|
||||
custom_middleware = [
|
||||
Middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=cors_origins,
|
||||
allow_credentials=True,
|
||||
allow_methods=["GET", "POST", "OPTIONS", "DELETE"],
|
||||
allow_headers=["Content-Type", "Authorization", "X-Request-ID", "X-Session-ID"],
|
||||
),
|
||||
]
|
||||
|
||||
# Create MCP app with Bearer authentication
|
||||
mcp_server = create_app(auth=bearer_auth)
|
||||
|
||||
# Add Starlette middleware to FastAPI (not MCP)
|
||||
# MCP already has Bearer auth, no need for additional middleware on MCP level
|
||||
|
||||
# Create MCP Starlette sub-application with root path - mount will add /mcp prefix
|
||||
mcp_app = mcp_server.http_app(path="/")
|
||||
|
||||
# Configure JSON encoder for proper Turkish character support
|
||||
import json
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
class UTF8JSONResponse(JSONResponse):
|
||||
def __init__(self, content=None, status_code=200, headers=None, **kwargs):
|
||||
if headers is None:
|
||||
headers = {}
|
||||
headers["Content-Type"] = "application/json; charset=utf-8"
|
||||
super().__init__(content, status_code, headers, **kwargs)
|
||||
|
||||
def render(self, content) -> bytes:
|
||||
return json.dumps(
|
||||
content,
|
||||
ensure_ascii=False,
|
||||
allow_nan=False,
|
||||
indent=None,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
# Create FastAPI wrapper application
|
||||
app = FastAPI(
|
||||
title="Yargı MCP Server",
|
||||
description="MCP server for Turkish legal databases with OAuth authentication",
|
||||
version="0.1.0",
|
||||
middleware=custom_middleware,
|
||||
default_response_class=UTF8JSONResponse # Use UTF-8 JSON encoder
|
||||
)
|
||||
|
||||
# Add Stripe webhook router to FastAPI
|
||||
app.include_router(stripe_router, prefix="/api")
|
||||
|
||||
# Add MCP Auth HTTP adapter to FastAPI (handles OAuth endpoints)
|
||||
app.include_router(mcp_auth_router)
|
||||
|
||||
# Custom 401 exception handler for MCP spec compliance
|
||||
@app.exception_handler(401)
|
||||
async def custom_401_handler(request: Request, exc: HTTPException):
|
||||
"""Custom 401 handler that adds WWW-Authenticate header as required by MCP spec"""
|
||||
response = await http_exception_handler(request, exc)
|
||||
|
||||
# Add WWW-Authenticate header pointing to protected resource metadata
|
||||
# as required by RFC 9728 Section 5.1 and MCP Authorization spec
|
||||
response.headers["WWW-Authenticate"] = (
|
||||
'Bearer '
|
||||
'error="invalid_token", '
|
||||
'error_description="The access token is missing or invalid", '
|
||||
f'resource="{BASE_URL}/.well-known/oauth-protected-resource"'
|
||||
)
|
||||
|
||||
return response
|
||||
|
||||
# FastAPI health check endpoint - BEFORE mounting MCP app
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
"""Health check endpoint for monitoring"""
|
||||
return JSONResponse({
|
||||
"status": "healthy",
|
||||
"service": "Yargı MCP Server",
|
||||
"version": "0.1.0",
|
||||
"tools_count": len(mcp_server._tool_manager._tools),
|
||||
"auth_enabled": os.getenv("ENABLE_AUTH", "false").lower() == "true"
|
||||
})
|
||||
|
||||
# Add explicit redirect for /mcp to /mcp/ with method preservation
|
||||
@app.api_route("/mcp", methods=["GET", "POST", "HEAD", "OPTIONS"])
|
||||
async def redirect_to_slash(request: Request):
|
||||
"""Redirect /mcp to /mcp/ preserving HTTP method with 308"""
|
||||
from fastapi.responses import RedirectResponse
|
||||
return RedirectResponse(url="/mcp/", status_code=308)
|
||||
|
||||
# Mount MCP app at /mcp/ with trailing slash
|
||||
app.mount("/mcp/", mcp_app)
|
||||
|
||||
# Set the lifespan context after mounting
|
||||
app.router.lifespan_context = mcp_app.lifespan
|
||||
|
||||
|
||||
# SSE transport deprecated - removed
|
||||
|
||||
# FastAPI root endpoint
|
||||
@app.get("/")
|
||||
async def root():
|
||||
"""Root endpoint with service information"""
|
||||
return JSONResponse({
|
||||
"service": "Yargı MCP Server",
|
||||
"description": "MCP server for Turkish legal databases with OAuth authentication",
|
||||
"endpoints": {
|
||||
"mcp": "/mcp",
|
||||
"health": "/health",
|
||||
"status": "/status",
|
||||
"stripe_webhook": "/api/stripe/webhook",
|
||||
"oauth_login": "/auth/login",
|
||||
"oauth_callback": "/auth/callback",
|
||||
"oauth_google": "/auth/google/login",
|
||||
"user_info": "/auth/user"
|
||||
},
|
||||
"transports": {
|
||||
"http": "/mcp"
|
||||
},
|
||||
"supported_databases": [
|
||||
"Yargıtay (Court of Cassation)",
|
||||
"Danıştay (Council of State)",
|
||||
"Emsal (Precedent)",
|
||||
"Uyuşmazlık Mahkemesi (Court of Jurisdictional Disputes)",
|
||||
"Anayasa Mahkemesi (Constitutional Court)",
|
||||
"Kamu İhale Kurulu (Public Procurement Authority)",
|
||||
"Rekabet Kurumu (Competition Authority)",
|
||||
"Sayıştay (Court of Accounts)",
|
||||
"Bedesten API (Multiple courts)"
|
||||
],
|
||||
"authentication": {
|
||||
"enabled": os.getenv("ENABLE_AUTH", "false").lower() == "true",
|
||||
"type": "OAuth 2.0 via Clerk",
|
||||
"issuer": os.getenv("CLERK_ISSUER", "https://clerk.accounts.dev"),
|
||||
"providers": ["google"],
|
||||
"flow": "authorization_code"
|
||||
}
|
||||
})
|
||||
|
||||
# OAuth 2.0 Authorization Server Metadata proxy (for MCP clients that can't reach Clerk directly)
|
||||
# MCP Auth Toolkit expects this to be under /mcp/.well-known/oauth-authorization-server
|
||||
@app.get("/mcp/.well-known/oauth-authorization-server")
|
||||
async def oauth_authorization_server():
|
||||
"""OAuth 2.0 Authorization Server Metadata proxy to Clerk - MCP Auth Toolkit standard location"""
|
||||
return JSONResponse({
|
||||
"issuer": BASE_URL,
|
||||
"authorization_endpoint": "https://yargimcp.com/mcp-callback",
|
||||
"token_endpoint": f"{BASE_URL}/token",
|
||||
"jwks_uri": f"{CLERK_ISSUER}/.well-known/jwks.json",
|
||||
"response_types_supported": ["code"],
|
||||
"grant_types_supported": ["authorization_code", "refresh_token"],
|
||||
"token_endpoint_auth_methods_supported": ["client_secret_basic", "none"],
|
||||
"scopes_supported": ["read", "search", "openid", "profile", "email"],
|
||||
"subject_types_supported": ["public"],
|
||||
"id_token_signing_alg_values_supported": ["RS256"],
|
||||
"claims_supported": ["sub", "iss", "aud", "exp", "iat", "email", "name"],
|
||||
"code_challenge_methods_supported": ["S256"],
|
||||
"service_documentation": f"{BASE_URL}/mcp",
|
||||
"registration_endpoint": f"{BASE_URL}/register",
|
||||
"resource_documentation": f"{BASE_URL}/mcp"
|
||||
})
|
||||
|
||||
# Claude AI MCP specific endpoint format
|
||||
@app.get("/.well-known/oauth-authorization-server/mcp")
|
||||
async def oauth_authorization_server_mcp_suffix():
|
||||
"""OAuth 2.0 Authorization Server Metadata - Claude AI MCP specific format"""
|
||||
return JSONResponse({
|
||||
"issuer": BASE_URL,
|
||||
"authorization_endpoint": "https://yargimcp.com/mcp-callback",
|
||||
"token_endpoint": f"{BASE_URL}/token",
|
||||
"jwks_uri": f"{CLERK_ISSUER}/.well-known/jwks.json",
|
||||
"response_types_supported": ["code"],
|
||||
"grant_types_supported": ["authorization_code", "refresh_token"],
|
||||
"token_endpoint_auth_methods_supported": ["client_secret_basic", "none"],
|
||||
"scopes_supported": ["read", "search", "openid", "profile", "email"],
|
||||
"subject_types_supported": ["public"],
|
||||
"id_token_signing_alg_values_supported": ["RS256"],
|
||||
"claims_supported": ["sub", "iss", "aud", "exp", "iat", "email", "name"],
|
||||
"code_challenge_methods_supported": ["S256"],
|
||||
"service_documentation": f"{BASE_URL}/mcp",
|
||||
"registration_endpoint": f"{BASE_URL}/register",
|
||||
"resource_documentation": f"{BASE_URL}/mcp"
|
||||
})
|
||||
|
||||
@app.get("/.well-known/oauth-protected-resource/mcp")
|
||||
async def oauth_protected_resource_mcp_suffix():
|
||||
"""OAuth 2.0 Protected Resource Metadata - Claude AI MCP specific format"""
|
||||
return JSONResponse({
|
||||
"resource": BASE_URL,
|
||||
"authorization_servers": [
|
||||
BASE_URL
|
||||
],
|
||||
"scopes_supported": ["read", "search"],
|
||||
"bearer_methods_supported": ["header"],
|
||||
"resource_documentation": f"{BASE_URL}/mcp",
|
||||
"resource_policy_uri": f"{BASE_URL}/privacy"
|
||||
})
|
||||
|
||||
# Keep root level for compatibility with some MCP clients
|
||||
@app.get("/.well-known/oauth-authorization-server")
|
||||
async def oauth_authorization_server_root():
|
||||
"""OAuth 2.0 Authorization Server Metadata proxy to Clerk - root level for compatibility"""
|
||||
return JSONResponse({
|
||||
"issuer": BASE_URL,
|
||||
"authorization_endpoint": "https://yargimcp.com/mcp-callback",
|
||||
"token_endpoint": f"{BASE_URL}/token",
|
||||
"jwks_uri": f"{CLERK_ISSUER}/.well-known/jwks.json",
|
||||
"response_types_supported": ["code"],
|
||||
"grant_types_supported": ["authorization_code", "refresh_token"],
|
||||
"token_endpoint_auth_methods_supported": ["client_secret_basic", "none"],
|
||||
"scopes_supported": ["read", "search", "openid", "profile", "email"],
|
||||
"subject_types_supported": ["public"],
|
||||
"id_token_signing_alg_values_supported": ["RS256"],
|
||||
"claims_supported": ["sub", "iss", "aud", "exp", "iat", "email", "name"],
|
||||
"code_challenge_methods_supported": ["S256"],
|
||||
"service_documentation": f"{BASE_URL}/mcp",
|
||||
"registration_endpoint": f"{BASE_URL}/register",
|
||||
"resource_documentation": f"{BASE_URL}/mcp"
|
||||
})
|
||||
|
||||
# Note: GET /mcp is handled by the mounted MCP app itself
|
||||
# This prevents 405 Method Not Allowed errors on POST requests
|
||||
|
||||
# OAuth 2.0 Protected Resource Metadata (RFC 9728) - MCP Spec Required
|
||||
@app.get("/.well-known/oauth-protected-resource")
|
||||
async def oauth_protected_resource():
|
||||
"""OAuth 2.0 Protected Resource Metadata as required by MCP spec"""
|
||||
return JSONResponse({
|
||||
"resource": BASE_URL,
|
||||
"authorization_servers": [
|
||||
BASE_URL
|
||||
],
|
||||
"scopes_supported": ["read", "search"],
|
||||
"bearer_methods_supported": ["header"],
|
||||
"resource_documentation": f"{BASE_URL}/mcp",
|
||||
"resource_policy_uri": f"{BASE_URL}/privacy"
|
||||
})
|
||||
|
||||
# Standard well-known discovery endpoint
|
||||
@app.get("/.well-known/mcp")
|
||||
async def well_known_mcp():
|
||||
"""Standard MCP discovery endpoint"""
|
||||
return JSONResponse({
|
||||
"mcp_server": {
|
||||
"name": "Yargı MCP Server",
|
||||
"version": "0.1.0",
|
||||
"endpoint": f"{BASE_URL}/mcp",
|
||||
"authentication": {
|
||||
"type": "oauth2",
|
||||
"authorization_url": f"{BASE_URL}/auth/login",
|
||||
"scopes": ["read", "search"]
|
||||
},
|
||||
"capabilities": ["tools", "resources"],
|
||||
"tools_count": len(mcp_server._tool_manager._tools)
|
||||
}
|
||||
})
|
||||
|
||||
# MCP Discovery endpoint for ChatGPT integration
|
||||
@app.get("/mcp/discovery")
|
||||
async def mcp_discovery():
|
||||
"""MCP Discovery endpoint for ChatGPT and other MCP clients"""
|
||||
return JSONResponse({
|
||||
"name": "Yargı MCP Server",
|
||||
"description": "MCP server for Turkish legal databases",
|
||||
"version": "0.1.0",
|
||||
"protocol": "mcp",
|
||||
"transport": "http",
|
||||
"endpoint": "/mcp",
|
||||
"authentication": {
|
||||
"type": "oauth2",
|
||||
"authorization_url": "/auth/login",
|
||||
"token_url": "/auth/callback",
|
||||
"scopes": ["read", "search"],
|
||||
"provider": "clerk"
|
||||
},
|
||||
"capabilities": {
|
||||
"tools": True,
|
||||
"resources": True,
|
||||
"prompts": False
|
||||
},
|
||||
"tools_count": len(mcp_server._tool_manager._tools),
|
||||
"contact": {
|
||||
"url": BASE_URL,
|
||||
"email": "support@yargi-mcp.dev"
|
||||
}
|
||||
})
|
||||
|
||||
# FastAPI status endpoint
|
||||
@app.get("/status")
|
||||
async def status():
|
||||
"""Status endpoint with detailed information"""
|
||||
tools = []
|
||||
for tool in mcp_server._tool_manager._tools.values():
|
||||
tools.append({
|
||||
"name": tool.name,
|
||||
"description": tool.description[:100] + "..." if len(tool.description) > 100 else tool.description
|
||||
})
|
||||
|
||||
return JSONResponse({
|
||||
"status": "operational",
|
||||
"tools": tools,
|
||||
"total_tools": len(tools),
|
||||
"transport": "streamable_http",
|
||||
"architecture": "FastAPI wrapper + MCP Starlette sub-app",
|
||||
"auth_status": "enabled" if os.getenv("ENABLE_AUTH", "false").lower() == "true" else "disabled"
|
||||
})
|
||||
|
||||
# Note: JWT token validation is now handled entirely by Clerk
|
||||
# All authentication flows use Clerk JWT tokens directly
|
||||
|
||||
async def validate_clerk_session(request: Request, clerk_token: str = None) -> str:
|
||||
"""Validate Clerk session from cookies or JWT token and return user_id"""
|
||||
logger.info(f"Validating Clerk session - token provided: {bool(clerk_token)}")
|
||||
|
||||
try:
|
||||
# Try to import Clerk SDK
|
||||
from clerk_backend_api import Clerk
|
||||
clerk = Clerk(bearer_auth=os.getenv("CLERK_SECRET_KEY"))
|
||||
|
||||
# Try JWT token first (from URL parameter)
|
||||
if clerk_token:
|
||||
logger.info("Validating Clerk JWT token from URL parameter")
|
||||
try:
|
||||
# Extract session_id from JWT token and verify with Clerk
|
||||
import jwt
|
||||
decoded_token = jwt.decode(clerk_token, options={"verify_signature": False})
|
||||
session_id = decoded_token.get("sid") # Use standard JWT 'sid' claim
|
||||
|
||||
if session_id:
|
||||
# Verify with Clerk using session_id
|
||||
session = clerk.sessions.verify(session_id=session_id, token=clerk_token)
|
||||
user_id = session.user_id if session else None
|
||||
|
||||
if user_id:
|
||||
logger.info(f"JWT token validation successful - user_id: {user_id}")
|
||||
return user_id
|
||||
else:
|
||||
logger.error("JWT token validation failed - no user_id in session")
|
||||
else:
|
||||
logger.error("No session_id found in JWT token")
|
||||
except Exception as e:
|
||||
logger.error(f"JWT token validation failed: {str(e)}")
|
||||
# Fall through to cookie validation
|
||||
|
||||
# Fallback to cookie validation
|
||||
logger.info("Attempting cookie-based session validation")
|
||||
clerk_session = request.cookies.get("__session")
|
||||
if not clerk_session:
|
||||
logger.error("No Clerk session cookie found")
|
||||
raise HTTPException(status_code=401, detail="No Clerk session found")
|
||||
|
||||
# Validate session with Clerk
|
||||
session = clerk.sessions.verify_session(clerk_session)
|
||||
logger.info(f"Cookie session validation successful - user_id: {session.user_id}")
|
||||
return session.user_id
|
||||
|
||||
except ImportError:
|
||||
# Fallback for development without Clerk SDK
|
||||
logger.warning("Clerk SDK not available - using development fallback")
|
||||
return "dev_user_123"
|
||||
except Exception as e:
|
||||
logger.error(f"Session validation failed: {str(e)}")
|
||||
raise HTTPException(status_code=401, detail=f"Session validation failed: {str(e)}")
|
||||
|
||||
# MCP OAuth Callback Endpoint
|
||||
@app.get("/auth/mcp-callback")
|
||||
async def mcp_oauth_callback(request: Request, clerk_token: str = Query(None)):
|
||||
"""Handle OAuth callback for MCP token generation"""
|
||||
logger.info(f"MCP OAuth callback - clerk_token provided: {bool(clerk_token)}")
|
||||
|
||||
try:
|
||||
# Validate Clerk session with JWT token support
|
||||
user_id = await validate_clerk_session(request, clerk_token)
|
||||
logger.info(f"User authenticated successfully - user_id: {user_id}")
|
||||
|
||||
# Use the Clerk JWT token directly (no need to generate custom token)
|
||||
logger.info("User authenticated successfully via Clerk")
|
||||
|
||||
# Return success response
|
||||
return HTMLResponse(f"""
|
||||
<html>
|
||||
<head>
|
||||
<title>MCP Connection Successful</title>
|
||||
<style>
|
||||
body {{ font-family: Arial, sans-serif; text-align: center; padding: 50px; }}
|
||||
.success {{ color: #28a745; }}
|
||||
.token {{ background: #f8f9fa; padding: 15px; border-radius: 5px; margin: 20px 0; word-break: break-all; }}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<h1 class="success">✅ MCP Connection Successful!</h1>
|
||||
<p>Your Yargı MCP integration is now active.</p>
|
||||
<div class="token">
|
||||
<strong>Authentication:</strong><br>
|
||||
<code>Use your Clerk JWT token directly with Bearer authentication</code>
|
||||
</div>
|
||||
<p>You can now close this window and return to your MCP client.</p>
|
||||
<script>
|
||||
// Try to close the popup if opened as such
|
||||
if (window.opener) {{
|
||||
window.opener.postMessage({{
|
||||
type: 'MCP_AUTH_SUCCESS',
|
||||
token: 'use_clerk_jwt_token'
|
||||
}}, '*');
|
||||
setTimeout(() => window.close(), 3000);
|
||||
}}
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
""")
|
||||
|
||||
except HTTPException as e:
|
||||
logger.error(f"MCP OAuth callback failed: {e.detail}")
|
||||
return HTMLResponse(f"""
|
||||
<html>
|
||||
<head>
|
||||
<title>MCP Connection Failed</title>
|
||||
<style>
|
||||
body {{ font-family: Arial, sans-serif; text-align: center; padding: 50px; }}
|
||||
.error {{ color: #dc3545; }}
|
||||
.debug {{ background: #f8f9fa; padding: 10px; margin: 20px 0; border-radius: 5px; font-family: monospace; }}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<h1 class="error">❌ MCP Connection Failed</h1>
|
||||
<p>{e.detail}</p>
|
||||
<div class="debug">
|
||||
<strong>Debug Info:</strong><br>
|
||||
Clerk Token: {'✅ Provided' if clerk_token else '❌ Missing'}<br>
|
||||
Error: {e.detail}<br>
|
||||
Status: {e.status_code}
|
||||
</div>
|
||||
<p>Please try again or contact support.</p>
|
||||
<a href="https://yargimcp.com/sign-in">Return to Sign In</a>
|
||||
</body>
|
||||
</html>
|
||||
""", status_code=e.status_code)
|
||||
except Exception as e:
|
||||
logger.error(f"Unexpected error in MCP OAuth callback: {str(e)}")
|
||||
return HTMLResponse(f"""
|
||||
<html>
|
||||
<head>
|
||||
<title>MCP Connection Error</title>
|
||||
<style>
|
||||
body {{ font-family: Arial, sans-serif; text-align: center; padding: 50px; }}
|
||||
.error {{ color: #dc3545; }}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<h1 class="error">❌ Unexpected Error</h1>
|
||||
<p>An unexpected error occurred during authentication.</p>
|
||||
<p>Error: {str(e)}</p>
|
||||
<a href="https://yargimcp.com/sign-in">Return to Sign In</a>
|
||||
</body>
|
||||
</html>
|
||||
""", status_code=500)
|
||||
|
||||
# OAuth2 Token Endpoint - Now uses Clerk JWT tokens directly
|
||||
@app.post("/auth/mcp-token")
|
||||
async def mcp_token_endpoint(request: Request):
|
||||
"""OAuth2 token endpoint for MCP clients - returns Clerk JWT token info"""
|
||||
try:
|
||||
# Validate Clerk session
|
||||
user_id = await validate_clerk_session(request)
|
||||
|
||||
return JSONResponse({
|
||||
"message": "Use your Clerk JWT token directly with Bearer authentication",
|
||||
"token_type": "Bearer",
|
||||
"scope": "yargi.read",
|
||||
"user_id": user_id,
|
||||
"instructions": "Include 'Authorization: Bearer YOUR_CLERK_JWT_TOKEN' in your requests"
|
||||
})
|
||||
except HTTPException as e:
|
||||
return JSONResponse(
|
||||
status_code=e.status_code,
|
||||
content={"error": "invalid_request", "error_description": e.detail}
|
||||
)
|
||||
|
||||
# Note: Only HTTP transport supported - SSE transport deprecated
|
||||
|
||||
# Export for uvicorn
|
||||
__all__ = ["app"]
|
||||
@@ -1,17 +0,0 @@
|
||||
# bddk_mcp_module/__init__.py
|
||||
|
||||
from .client import BddkApiClient
|
||||
from .models import (
|
||||
BddkSearchRequest,
|
||||
BddkDecisionSummary,
|
||||
BddkSearchResult,
|
||||
BddkDocumentMarkdown
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"BddkApiClient",
|
||||
"BddkSearchRequest",
|
||||
"BddkDecisionSummary",
|
||||
"BddkSearchResult",
|
||||
"BddkDocumentMarkdown"
|
||||
]
|
||||
@@ -1,247 +0,0 @@
|
||||
# bddk_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from typing import List, Optional, Dict, Any
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import io
|
||||
import math
|
||||
from urllib.parse import urlparse
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
BddkSearchRequest,
|
||||
BddkDecisionSummary,
|
||||
BddkSearchResult,
|
||||
BddkDocumentMarkdown
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
|
||||
class BddkApiClient:
|
||||
"""
|
||||
API client for searching and retrieving BDDK (Banking Regulation Authority) decisions
|
||||
using Tavily Search API for discovery and direct HTTP requests for content retrieval.
|
||||
"""
|
||||
|
||||
TAVILY_API_URL = "https://api.tavily.com/search"
|
||||
BDDK_BASE_URL = "https://www.bddk.org.tr"
|
||||
DOCUMENT_URL_TEMPLATE = "https://www.bddk.org.tr/Mevzuat/DokumanGetir/{document_id}"
|
||||
DOCUMENT_MARKDOWN_CHUNK_SIZE = 5000 # Character limit per page
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
"""Initialize the BDDK API client."""
|
||||
self.tavily_api_key = os.getenv("TAVILY_API_KEY")
|
||||
if not self.tavily_api_key:
|
||||
# Fallback to development token
|
||||
self.tavily_api_key = "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"
|
||||
logger.info("Using fallback Tavily API token (development token)")
|
||||
else:
|
||||
logger.info("Using Tavily API key from environment variable")
|
||||
|
||||
self.http_client = httpx.AsyncClient(
|
||||
headers={
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
|
||||
},
|
||||
timeout=httpx.Timeout(request_timeout)
|
||||
)
|
||||
self.markitdown = MarkItDown()
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close the HTTP client session."""
|
||||
await self.http_client.aclose()
|
||||
logger.info("BddkApiClient: HTTP client session closed.")
|
||||
|
||||
def _extract_document_id(self, url: str) -> Optional[str]:
|
||||
"""Extract document ID from BDDK URL."""
|
||||
# Primary pattern: https://www.bddk.org.tr/Mevzuat/DokumanGetir/310
|
||||
match = re.search(r'/DokumanGetir/(\d+)', url)
|
||||
if match:
|
||||
return match.group(1)
|
||||
|
||||
# Alternative patterns for different BDDK URL formats
|
||||
# Pattern: /Liste/55 -> use as document ID
|
||||
match = re.search(r'/Liste/(\d+)', url)
|
||||
if match:
|
||||
return match.group(1)
|
||||
|
||||
# Pattern: /EkGetir/13?ekId=381 -> use ekId as document ID
|
||||
match = re.search(r'ekId=(\d+)', url)
|
||||
if match:
|
||||
return match.group(1)
|
||||
|
||||
return None
|
||||
|
||||
async def search_decisions(
|
||||
self,
|
||||
request: BddkSearchRequest
|
||||
) -> BddkSearchResult:
|
||||
"""
|
||||
Search for BDDK decisions using Tavily API.
|
||||
|
||||
Args:
|
||||
request: Search request parameters
|
||||
|
||||
Returns:
|
||||
BddkSearchResult with matching decisions
|
||||
"""
|
||||
try:
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {self.tavily_api_key}"
|
||||
}
|
||||
|
||||
# Tavily API request - enhanced for BDDK decision documents
|
||||
query = f"{request.keywords} \"Karar Sayısı\""
|
||||
payload = {
|
||||
"query": query,
|
||||
"country": "turkey",
|
||||
"include_domains": ["https://www.bddk.org.tr/Mevzuat/DokumanGetir"],
|
||||
"max_results": request.pageSize,
|
||||
"search_depth": "advanced"
|
||||
}
|
||||
|
||||
# Calculate offset for pagination
|
||||
if request.page > 1:
|
||||
# Tavily doesn't have direct pagination, so we'll need to handle this
|
||||
# For now, we'll just return empty for pages > 1
|
||||
logger.warning(f"Tavily API doesn't support pagination. Page {request.page} requested.")
|
||||
|
||||
response = await self.http_client.post(
|
||||
self.TAVILY_API_URL,
|
||||
json=payload,
|
||||
headers=headers
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
data = response.json()
|
||||
|
||||
# Log raw Tavily response for debugging
|
||||
logger.info(f"Tavily returned {len(data.get('results', []))} results")
|
||||
|
||||
# Convert Tavily results to our format
|
||||
decisions = []
|
||||
for result in data.get("results", []):
|
||||
# Extract document ID from URL
|
||||
url = result.get("url", "")
|
||||
logger.debug(f"Processing URL: {url}")
|
||||
doc_id = self._extract_document_id(url)
|
||||
if doc_id:
|
||||
decision = BddkDecisionSummary(
|
||||
title=result.get("title", "").replace("[PDF] ", "").strip(),
|
||||
document_id=doc_id,
|
||||
content=result.get("content", "")[:500] # Limit content length
|
||||
)
|
||||
decisions.append(decision)
|
||||
logger.debug(f"Added decision: {decision.title} (ID: {doc_id})")
|
||||
else:
|
||||
logger.warning(f"Could not extract document ID from URL: {url}")
|
||||
|
||||
return BddkSearchResult(
|
||||
decisions=decisions,
|
||||
total_results=len(data.get("results", [])),
|
||||
page=request.page,
|
||||
pageSize=request.pageSize
|
||||
)
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
logger.error(f"HTTP error searching BDDK decisions: {e}")
|
||||
if e.response.status_code == 401:
|
||||
raise Exception("Tavily API authentication failed. Check API key.")
|
||||
raise Exception(f"Failed to search BDDK decisions: {str(e)}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error searching BDDK decisions: {e}")
|
||||
raise Exception(f"Failed to search BDDK decisions: {str(e)}")
|
||||
|
||||
async def get_document_markdown(
|
||||
self,
|
||||
document_id: str,
|
||||
page_number: int = 1
|
||||
) -> BddkDocumentMarkdown:
|
||||
"""
|
||||
Retrieve a BDDK document and convert it to Markdown format.
|
||||
|
||||
Args:
|
||||
document_id: BDDK document ID (e.g., '310')
|
||||
page_number: Page number for paginated content (1-indexed)
|
||||
|
||||
Returns:
|
||||
BddkDocumentMarkdown with paginated content
|
||||
"""
|
||||
try:
|
||||
# Try different URL patterns for BDDK documents
|
||||
potential_urls = [
|
||||
f"https://www.bddk.org.tr/Mevzuat/DokumanGetir/{document_id}",
|
||||
f"https://www.bddk.org.tr/Mevzuat/Liste/{document_id}",
|
||||
f"https://www.bddk.org.tr/KurumHakkinda/EkGetir/13?ekId={document_id}",
|
||||
f"https://www.bddk.org.tr/KurumHakkinda/EkGetir/5?ekId={document_id}"
|
||||
]
|
||||
|
||||
document_url = None
|
||||
response = None
|
||||
|
||||
# Try each URL pattern until one works
|
||||
for url in potential_urls:
|
||||
try:
|
||||
logger.info(f"Trying BDDK document URL: {url}")
|
||||
response = await self.http_client.get(
|
||||
url,
|
||||
follow_redirects=True
|
||||
)
|
||||
response.raise_for_status()
|
||||
document_url = url
|
||||
break
|
||||
except httpx.HTTPStatusError:
|
||||
continue
|
||||
|
||||
if not response or not document_url:
|
||||
raise Exception(f"Could not find document with ID {document_id}")
|
||||
|
||||
logger.info(f"Successfully fetched BDDK document from: {document_url}")
|
||||
|
||||
# Determine content type
|
||||
content_type = response.headers.get("content-type", "").lower()
|
||||
|
||||
# Convert to Markdown based on content type
|
||||
if "pdf" in content_type:
|
||||
# Handle PDF documents
|
||||
pdf_stream = io.BytesIO(response.content)
|
||||
result = self.markitdown.convert_stream(pdf_stream, file_extension=".pdf")
|
||||
markdown_content = result.text_content
|
||||
else:
|
||||
# Handle HTML documents
|
||||
html_stream = io.BytesIO(response.content)
|
||||
result = self.markitdown.convert_stream(html_stream, file_extension=".html")
|
||||
markdown_content = result.text_content
|
||||
|
||||
# Clean up the markdown content
|
||||
markdown_content = markdown_content.strip()
|
||||
|
||||
# Calculate pagination
|
||||
total_length = len(markdown_content)
|
||||
total_pages = math.ceil(total_length / self.DOCUMENT_MARKDOWN_CHUNK_SIZE)
|
||||
|
||||
# Extract the requested page
|
||||
start_idx = (page_number - 1) * self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
end_idx = start_idx + self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
page_content = markdown_content[start_idx:end_idx]
|
||||
|
||||
return BddkDocumentMarkdown(
|
||||
document_id=document_id,
|
||||
markdown_content=page_content,
|
||||
page_number=page_number,
|
||||
total_pages=total_pages
|
||||
)
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
logger.error(f"HTTP error fetching BDDK document {document_id}: {e}")
|
||||
raise Exception(f"Failed to fetch BDDK document: {str(e)}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing BDDK document {document_id}: {e}")
|
||||
raise Exception(f"Failed to process BDDK document: {str(e)}")
|
||||
@@ -1,43 +0,0 @@
|
||||
# bddk_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List, Optional
|
||||
|
||||
class BddkSearchRequest(BaseModel):
|
||||
"""
|
||||
Request model for searching BDDK decisions via Tavily API.
|
||||
|
||||
BDDK (Bankacılık Düzenleme ve Denetleme Kurumu) is Turkey's Banking
|
||||
Regulation and Supervision Agency responsible for banking licenses,
|
||||
electronic money institutions, and financial regulations.
|
||||
"""
|
||||
keywords: str = Field(..., description="Search keywords in Turkish")
|
||||
page: int = Field(1, ge=1, description="Page number (1-indexed)")
|
||||
pageSize: int = Field(10, ge=1, le=50, description="Results per page (1-50)")
|
||||
|
||||
class BddkDecisionSummary(BaseModel):
|
||||
"""Summary of a BDDK decision from search results."""
|
||||
title: str = Field(..., description="Decision title")
|
||||
document_id: str = Field(..., description="BDDK document ID (e.g., '310')")
|
||||
content: str = Field(..., description="Decision summary/excerpt")
|
||||
|
||||
class BddkSearchResult(BaseModel):
|
||||
"""Response model for BDDK decision search results."""
|
||||
decisions: List[BddkDecisionSummary] = Field(
|
||||
default_factory=list,
|
||||
description="List of matching BDDK decisions"
|
||||
)
|
||||
total_results: int = Field(0, description="Total number of results")
|
||||
page: int = Field(1, description="Current page number")
|
||||
pageSize: int = Field(10, description="Results per page")
|
||||
|
||||
class BddkDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
BDDK decision document converted to Markdown format.
|
||||
|
||||
Supports paginated content for long documents (5000 chars per page).
|
||||
"""
|
||||
document_id: str = Field(..., description="BDDK document ID")
|
||||
markdown_content: str = Field("", description="Document content in Markdown")
|
||||
page_number: int = Field(1, description="Current page number")
|
||||
total_pages: int = Field(1, description="Total number of pages")
|
||||
@@ -1 +0,0 @@
|
||||
# bedesten_mcp_module/__init__.py
|
||||
@@ -1,181 +0,0 @@
|
||||
# bedesten_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
import base64
|
||||
from typing import Optional
|
||||
import logging
|
||||
from markitdown import MarkItDown
|
||||
import io
|
||||
|
||||
from .models import (
|
||||
BedestenSearchRequest, BedestenSearchResponse,
|
||||
BedestenDocumentRequest, BedestenDocumentResponse,
|
||||
BedestenDocumentMarkdown, BedestenDocumentRequestData
|
||||
)
|
||||
from .enums import get_full_birim_adi
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class BedestenApiClient:
|
||||
"""
|
||||
API Client for Bedesten (bedesten.adalet.gov.tr) - Alternative legal decision search system.
|
||||
Currently used for Yargıtay decisions, but can be extended for other court types.
|
||||
"""
|
||||
BASE_URL = "https://bedesten.adalet.gov.tr"
|
||||
SEARCH_ENDPOINT = "/emsal-karar/searchDocuments"
|
||||
DOCUMENT_ENDPOINT = "/emsal-karar/getDocumentContent"
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "*/*",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"AdaletApplicationName": "UyapMevzuat",
|
||||
"Content-Type": "application/json; charset=utf-8",
|
||||
"Origin": "https://mevzuat.adalet.gov.tr",
|
||||
"Referer": "https://mevzuat.adalet.gov.tr/",
|
||||
"Sec-Fetch-Dest": "empty",
|
||||
"Sec-Fetch-Mode": "cors",
|
||||
"Sec-Fetch-Site": "same-site",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout
|
||||
)
|
||||
|
||||
async def search_documents(self, search_request: BedestenSearchRequest) -> BedestenSearchResponse:
|
||||
"""
|
||||
Search for documents using Bedesten API.
|
||||
Currently supports: YARGITAYKARARI, DANISTAYKARARI, YERELHUKMAHKARARI, etc.
|
||||
"""
|
||||
logger.info(f"BedestenApiClient: Searching documents with phrase: {search_request.data.phrase}")
|
||||
|
||||
# Map abbreviated birimAdi to full Turkish name before sending to API
|
||||
original_birim_adi = search_request.data.birimAdi
|
||||
mapped_birim_adi = get_full_birim_adi(original_birim_adi)
|
||||
search_request.data.birimAdi = mapped_birim_adi
|
||||
if original_birim_adi != "ALL":
|
||||
logger.info(f"BedestenApiClient: Mapped birimAdi '{original_birim_adi}' to '{mapped_birim_adi}'")
|
||||
|
||||
try:
|
||||
# Create request dict and remove birimAdi if empty
|
||||
request_dict = search_request.model_dump()
|
||||
if not request_dict["data"]["birimAdi"]: # Remove if empty string
|
||||
del request_dict["data"]["birimAdi"]
|
||||
|
||||
response = await self.http_client.post(
|
||||
self.SEARCH_ENDPOINT,
|
||||
json=request_dict
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Parse and return the response
|
||||
return BedestenSearchResponse(**response_json)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"BedestenApiClient: HTTP request error during search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"BedestenApiClient: Error processing search response: {e}")
|
||||
raise
|
||||
|
||||
async def get_document_as_markdown(self, document_id: str) -> BedestenDocumentMarkdown:
|
||||
"""
|
||||
Get document content and convert to markdown.
|
||||
Handles both HTML (text/html) and PDF (application/pdf) content types.
|
||||
"""
|
||||
logger.info(f"BedestenApiClient: Fetching document for markdown conversion (ID: {document_id})")
|
||||
|
||||
try:
|
||||
# Prepare request
|
||||
doc_request = BedestenDocumentRequest(
|
||||
data=BedestenDocumentRequestData(documentId=document_id)
|
||||
)
|
||||
|
||||
# Get document
|
||||
response = await self.http_client.post(
|
||||
self.DOCUMENT_ENDPOINT,
|
||||
json=doc_request.model_dump()
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
doc_response = BedestenDocumentResponse(**response_json)
|
||||
|
||||
# Decode base64 content
|
||||
content_bytes = base64.b64decode(doc_response.data.content)
|
||||
mime_type = doc_response.data.mimeType
|
||||
|
||||
logger.info(f"BedestenApiClient: Document mime type: {mime_type}")
|
||||
|
||||
# Convert to markdown based on mime type
|
||||
if mime_type == "text/html":
|
||||
html_content = content_bytes.decode('utf-8')
|
||||
markdown_content = self._convert_html_to_markdown(html_content)
|
||||
elif mime_type == "application/pdf":
|
||||
markdown_content = self._convert_pdf_to_markdown(content_bytes)
|
||||
else:
|
||||
logger.warning(f"Unsupported mime type: {mime_type}")
|
||||
markdown_content = f"Unsupported content type: {mime_type}. Unable to convert to markdown."
|
||||
|
||||
return BedestenDocumentMarkdown(
|
||||
documentId=document_id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=f"{self.BASE_URL}/document/{document_id}",
|
||||
mime_type=mime_type
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"BedestenApiClient: HTTP error fetching document {document_id}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"BedestenApiClient: Error processing document {document_id}: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown(self, html_content: str) -> Optional[str]:
|
||||
"""Convert HTML to Markdown using MarkItDown"""
|
||||
if not html_content:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_content.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
result = md_converter.convert(html_stream)
|
||||
markdown_content = result.text_content
|
||||
|
||||
logger.info("Successfully converted HTML to Markdown")
|
||||
return markdown_content
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting HTML to Markdown: {e}")
|
||||
return f"Error converting HTML content: {str(e)}"
|
||||
|
||||
def _convert_pdf_to_markdown(self, pdf_bytes: bytes) -> Optional[str]:
|
||||
"""Convert PDF to Markdown using MarkItDown"""
|
||||
if not pdf_bytes:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Create BytesIO stream from PDF bytes
|
||||
pdf_stream = io.BytesIO(pdf_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
result = md_converter.convert(pdf_stream)
|
||||
markdown_content = result.text_content
|
||||
|
||||
logger.info("Successfully converted PDF to Markdown")
|
||||
return markdown_content
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting PDF to Markdown: {e}")
|
||||
return f"Error converting PDF content: {str(e)}. The document may be corrupted or in an unsupported format."
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close HTTP client session"""
|
||||
await self.http_client.aclose()
|
||||
logger.info("BedestenApiClient: HTTP client session closed.")
|
||||
@@ -1,113 +0,0 @@
|
||||
# bedesten_mcp_module/enums.py
|
||||
|
||||
from typing import Literal
|
||||
|
||||
# Unified compressed enum for both Yargıtay and Danıştay chambers
|
||||
BirimAdiEnum = Literal[
|
||||
"ALL", # All chambers
|
||||
|
||||
# Yargıtay (Court of Cassation) - Civil Chambers
|
||||
"H1", "H2", "H3", "H4", "H5", "H6", "H7", "H8", "H9", "H10",
|
||||
"H11", "H12", "H13", "H14", "H15", "H16", "H17", "H18", "H19", "H20",
|
||||
"H21", "H22", "H23",
|
||||
|
||||
# Yargıtay - Criminal Chambers
|
||||
"C1", "C2", "C3", "C4", "C5", "C6", "C7", "C8", "C9", "C10",
|
||||
"C11", "C12", "C13", "C14", "C15", "C16", "C17", "C18", "C19", "C20",
|
||||
"C21", "C22", "C23",
|
||||
|
||||
# Yargıtay - Councils and Assemblies
|
||||
"HGK", # Hukuk Genel Kurulu
|
||||
"CGK", # Ceza Genel Kurulu
|
||||
"BGK", # Büyük Genel Kurulu
|
||||
"HBK", # Hukuk Daireleri Başkanlar Kurulu
|
||||
"CBK", # Ceza Daireleri Başkanlar Kurulu
|
||||
|
||||
# Danıştay (Council of State) - Chambers
|
||||
"D1", "D2", "D3", "D4", "D5", "D6", "D7", "D8", "D9", "D10",
|
||||
"D11", "D12", "D13", "D14", "D15", "D16", "D17",
|
||||
|
||||
# Danıştay - Councils and Boards
|
||||
"DBGK", # Büyük Gen.Kur. (Grand General Assembly)
|
||||
"IDDK", # İdare Dava Daireleri Kurulu
|
||||
"VDDK", # Vergi Dava Daireleri Kurulu
|
||||
"IBK", # İçtihatları Birleştirme Kurulu
|
||||
"IIK", # İdari İşler Kurulu
|
||||
"DBK", # Başkanlar Kurulu
|
||||
|
||||
# Military High Administrative Court
|
||||
"AYIM", # Askeri Yüksek İdare Mahkemesi
|
||||
"AYIMDK", # Askeri Yüksek İdare Mahkemesi Daireler Kurulu
|
||||
"AYIMB", # Askeri Yüksek İdare Mahkemesi Başsavcılığı
|
||||
"AYIM1", # Askeri Yüksek İdare Mahkemesi 1. Daire
|
||||
"AYIM2", # Askeri Yüksek İdare Mahkemesi 2. Daire
|
||||
"AYIM3" # Askeri Yüksek İdare Mahkemesi 3. Daire
|
||||
]
|
||||
|
||||
# Mapping from abbreviated values to full Turkish API values
|
||||
BIRIM_ADI_MAPPING = {
|
||||
"ALL": None, # Will be handled specially in client
|
||||
|
||||
# Yargıtay Civil Chambers (1-23)
|
||||
"H1": "1. Hukuk Dairesi", "H2": "2. Hukuk Dairesi", "H3": "3. Hukuk Dairesi",
|
||||
"H4": "4. Hukuk Dairesi", "H5": "5. Hukuk Dairesi", "H6": "6. Hukuk Dairesi",
|
||||
"H7": "7. Hukuk Dairesi", "H8": "8. Hukuk Dairesi", "H9": "9. Hukuk Dairesi",
|
||||
"H10": "10. Hukuk Dairesi", "H11": "11. Hukuk Dairesi", "H12": "12. Hukuk Dairesi",
|
||||
"H13": "13. Hukuk Dairesi", "H14": "14. Hukuk Dairesi", "H15": "15. Hukuk Dairesi",
|
||||
"H16": "16. Hukuk Dairesi", "H17": "17. Hukuk Dairesi", "H18": "18. Hukuk Dairesi",
|
||||
"H19": "19. Hukuk Dairesi", "H20": "20. Hukuk Dairesi", "H21": "21. Hukuk Dairesi",
|
||||
"H22": "22. Hukuk Dairesi", "H23": "23. Hukuk Dairesi",
|
||||
|
||||
# Yargıtay Criminal Chambers (1-23)
|
||||
"C1": "1. Ceza Dairesi", "C2": "2. Ceza Dairesi", "C3": "3. Ceza Dairesi",
|
||||
"C4": "4. Ceza Dairesi", "C5": "5. Ceza Dairesi", "C6": "6. Ceza Dairesi",
|
||||
"C7": "7. Ceza Dairesi", "C8": "8. Ceza Dairesi", "C9": "9. Ceza Dairesi",
|
||||
"C10": "10. Ceza Dairesi", "C11": "11. Ceza Dairesi", "C12": "12. Ceza Dairesi",
|
||||
"C13": "13. Ceza Dairesi", "C14": "14. Ceza Dairesi", "C15": "15. Ceza Dairesi",
|
||||
"C16": "16. Ceza Dairesi", "C17": "17. Ceza Dairesi", "C18": "18. Ceza Dairesi",
|
||||
"C19": "19. Ceza Dairesi", "C20": "20. Ceza Dairesi", "C21": "21. Ceza Dairesi",
|
||||
"C22": "22. Ceza Dairesi", "C23": "23. Ceza Dairesi",
|
||||
|
||||
# Yargıtay Councils and Assemblies
|
||||
"HGK": "Hukuk Genel Kurulu",
|
||||
"CGK": "Ceza Genel Kurulu",
|
||||
"BGK": "Büyük Genel Kurulu",
|
||||
"HBK": "Hukuk Daireleri Başkanlar Kurulu",
|
||||
"CBK": "Ceza Daireleri Başkanlar Kurulu",
|
||||
|
||||
# Danıştay Chambers (1-17)
|
||||
"D1": "1. Daire", "D2": "2. Daire", "D3": "3. Daire", "D4": "4. Daire",
|
||||
"D5": "5. Daire", "D6": "6. Daire", "D7": "7. Daire", "D8": "8. Daire",
|
||||
"D9": "9. Daire", "D10": "10. Daire", "D11": "11. Daire", "D12": "12. Daire",
|
||||
"D13": "13. Daire", "D14": "14. Daire", "D15": "15. Daire", "D16": "16. Daire",
|
||||
"D17": "17. Daire",
|
||||
|
||||
# Danıştay Councils and Boards
|
||||
"DBGK": "Büyük Gen.Kur.",
|
||||
"IDDK": "İdare Dava Daireleri Kurulu",
|
||||
"VDDK": "Vergi Dava Daireleri Kurulu",
|
||||
"IBK": "İçtihatları Birleştirme Kurulu",
|
||||
"IIK": "İdari İşler Kurulu",
|
||||
"DBK": "Başkanlar Kurulu",
|
||||
|
||||
# Military High Administrative Court
|
||||
"AYIM": "Askeri Yüksek İdare Mahkemesi",
|
||||
"AYIMDK": "Askeri Yüksek İdare Mahkemesi Daireler Kurulu",
|
||||
"AYIMB": "Askeri Yüksek İdare Mahkemesi Başsavcılığı",
|
||||
"AYIM1": "Askeri Yüksek İdare Mahkemesi 1. Daire",
|
||||
"AYIM2": "Askeri Yüksek İdare Mahkemesi 2. Daire",
|
||||
"AYIM3": "Askeri Yüksek İdare Mahkemesi 3. Daire"
|
||||
}
|
||||
|
||||
# Helper function to get full Turkish name from abbreviated value
|
||||
def get_full_birim_adi(abbreviated_value: str) -> str:
|
||||
"""Convert abbreviated birimAdi value to full Turkish name for API calls."""
|
||||
if abbreviated_value == "ALL" or not abbreviated_value:
|
||||
return "" # Empty string for ALL or None
|
||||
|
||||
return BIRIM_ADI_MAPPING.get(abbreviated_value, abbreviated_value)
|
||||
|
||||
# Helper function to validate abbreviated value
|
||||
def is_valid_birim_adi(abbreviated_value: str) -> bool:
|
||||
"""Check if abbreviated birimAdi value is valid."""
|
||||
return abbreviated_value in BIRIM_ADI_MAPPING
|
||||
@@ -1,91 +0,0 @@
|
||||
# bedesten_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List, Optional, Dict, Any, Literal, Union
|
||||
from datetime import datetime
|
||||
|
||||
# Import compressed BirimAdiEnum for chamber filtering
|
||||
from .enums import BirimAdiEnum
|
||||
|
||||
# Court Type Options for Unified Search
|
||||
BedestenCourtTypeEnum = Literal[
|
||||
"YARGITAYKARARI", # Yargıtay (Court of Cassation)
|
||||
"DANISTAYKARAR", # Danıştay (Council of State)
|
||||
"YERELHUKUK", # Local Civil Courts
|
||||
"ISTINAFHUKUK", # Civil Courts of Appeals
|
||||
"KYB" # Extraordinary Appeals (Kanun Yararına Bozma)
|
||||
]
|
||||
|
||||
# Search Request Models
|
||||
class BedestenSearchData(BaseModel):
|
||||
pageSize: int = Field(..., description="Results per page (1-10)")
|
||||
pageNumber: int = Field(..., description="Page number (1-indexed)")
|
||||
itemTypeList: List[str] = Field(..., description="Court type filter (YARGITAYKARARI/DANISTAYKARAR/YERELHUKUK/ISTINAFHUKUK/KYB)")
|
||||
phrase: str = Field(..., description="Search phrase. Supports: 'word', \"exact phrase\", +required, -exclude, AND/OR/NOT operators. No wildcards or regex.")
|
||||
birimAdi: BirimAdiEnum = Field("ALL", description="""
|
||||
Chamber filter (optional). Abbreviated values with Turkish names:
|
||||
• Yargıtay: H1-H23 (1-23. Hukuk Dairesi), C1-C23 (1-23. Ceza Dairesi), HGK (Hukuk Genel Kurulu), CGK (Ceza Genel Kurulu), BGK (Büyük Genel Kurulu), HBK (Hukuk Daireleri Başkanlar Kurulu), CBK (Ceza Daireleri Başkanlar Kurulu)
|
||||
• Danıştay: D1-D17 (1-17. Daire), DBGK (Büyük Gen.Kur.), IDDK (İdare Dava Daireleri Kurulu), VDDK (Vergi Dava Daireleri Kurulu), IBK (İçtihatları Birleştirme Kurulu), IIK (İdari İşler Kurulu), DBK (Başkanlar Kurulu), AYIM (Askeri Yüksek İdare Mahkemesi), AYIM1-3 (Askeri Yüksek İdare Mahkemesi 1-3. Daire)
|
||||
""")
|
||||
kararTarihiStart: Optional[str] = Field(None, description="Start date (ISO 8601 format)")
|
||||
kararTarihiEnd: Optional[str] = Field(None, description="End date (ISO 8601 format)")
|
||||
sortFields: List[str] = Field(default=["KARAR_TARIHI"], description="Sort fields")
|
||||
sortDirection: str = Field(default="desc", description="Sort direction (asc/desc)")
|
||||
|
||||
class BedestenSearchRequest(BaseModel):
|
||||
data: BedestenSearchData
|
||||
applicationName: str = "UyapMevzuat"
|
||||
paging: bool = True
|
||||
|
||||
# Search Response Models
|
||||
class BedestenItemType(BaseModel):
|
||||
name: str
|
||||
description: str
|
||||
|
||||
class BedestenDecisionEntry(BaseModel):
|
||||
documentId: str
|
||||
itemType: BedestenItemType
|
||||
birimId: Optional[str] = None
|
||||
birimAdi: Optional[str]
|
||||
esasNoYil: Optional[int] = None
|
||||
esasNoSira: Optional[int] = None
|
||||
kararNoYil: Optional[int] = None
|
||||
kararNoSira: Optional[int] = None
|
||||
kararTuru: Optional[str] = None
|
||||
kararTarihi: str
|
||||
kararTarihiStr: str
|
||||
kesinlesmeDurumu: Optional[str] = None
|
||||
kararNo: Optional[str] = None
|
||||
esasNo: Optional[str] = None
|
||||
|
||||
class BedestenSearchDataResponse(BaseModel):
|
||||
emsalKararList: List[BedestenDecisionEntry]
|
||||
total: int
|
||||
start: int
|
||||
|
||||
class BedestenSearchResponse(BaseModel):
|
||||
data: Optional[BedestenSearchDataResponse]
|
||||
metadata: Dict[str, Any]
|
||||
|
||||
# Document Request/Response Models
|
||||
class BedestenDocumentRequestData(BaseModel):
|
||||
documentId: str
|
||||
|
||||
class BedestenDocumentRequest(BaseModel):
|
||||
data: BedestenDocumentRequestData
|
||||
applicationName: str = "UyapMevzuat"
|
||||
|
||||
class BedestenDocumentData(BaseModel):
|
||||
content: str # Base64 encoded HTML or PDF
|
||||
mimeType: str
|
||||
version: int
|
||||
|
||||
class BedestenDocumentResponse(BaseModel):
|
||||
data: BedestenDocumentData
|
||||
metadata: Dict[str, Any]
|
||||
|
||||
class BedestenDocumentMarkdown(BaseModel):
|
||||
documentId: str = Field(..., description="The document ID (Belge Kimliği) from Bedesten")
|
||||
markdown_content: Optional[str] = Field(None, description="The decision content (Karar İçeriği) converted to Markdown")
|
||||
source_url: str = Field(..., description="The source URL (Kaynak URL) of the document")
|
||||
mime_type: Optional[str] = Field(None, description="Original content type (İçerik Türü) (text/html or application/pdf)")
|
||||
@@ -1,21 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
from fastmcp import Client
|
||||
from mcp_server_main import app
|
||||
import json
|
||||
import asyncio
|
||||
|
||||
async def check_response_format():
|
||||
client = Client(app)
|
||||
async with client:
|
||||
result = await client.call_tool('search_bedesten_unified', {
|
||||
'phrase': 'mülkiyet',
|
||||
'court_types': ['YARGITAYKARARI'],
|
||||
'birimAdi': 'H1',
|
||||
'pageSize': 3
|
||||
})
|
||||
if result and result.content:
|
||||
data = json.loads(result.content[0].text)
|
||||
print('Response keys:', list(data.keys()))
|
||||
print('Sample response:', json.dumps(data, indent=2, ensure_ascii=False)[:500])
|
||||
|
||||
asyncio.run(check_response_format())
|
||||
@@ -1,192 +0,0 @@
|
||||
# danistay_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import Dict, Any, List, Optional
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
DanistayKeywordSearchRequest,
|
||||
DanistayDetailedSearchRequest,
|
||||
DanistayApiResponse,
|
||||
DanistayDocumentMarkdown,
|
||||
DanistayKeywordSearchRequestData,
|
||||
DanistayDetailedSearchRequestData
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
class DanistayApiClient:
|
||||
BASE_URL = "https://karararama.danistay.gov.tr"
|
||||
KEYWORD_SEARCH_ENDPOINT = "/aramalist"
|
||||
DETAILED_SEARCH_ENDPOINT = "/aramadetaylist"
|
||||
DOCUMENT_ENDPOINT = "/getDokuman"
|
||||
|
||||
def __init__(self, request_timeout: float = 30.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Content-Type": "application/json; charset=UTF-8", # Arama endpoint'leri için
|
||||
"Accept": "application/json, text/plain, */*", # Arama endpoint'leri için
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=False
|
||||
)
|
||||
|
||||
def _prepare_keywords_for_api(self, keywords: List[str]) -> List[str]:
|
||||
return ['"' + k.strip('"') + '"' for k in keywords if k and k.strip()]
|
||||
|
||||
async def search_keyword_decisions(
|
||||
self,
|
||||
params: DanistayKeywordSearchRequest
|
||||
) -> DanistayApiResponse:
|
||||
data_for_payload = DanistayKeywordSearchRequestData(
|
||||
andKelimeler=self._prepare_keywords_for_api(params.andKelimeler),
|
||||
orKelimeler=self._prepare_keywords_for_api(params.orKelimeler),
|
||||
notAndKelimeler=self._prepare_keywords_for_api(params.notAndKelimeler),
|
||||
notOrKelimeler=self._prepare_keywords_for_api(params.notOrKelimeler),
|
||||
pageSize=params.pageSize,
|
||||
pageNumber=params.pageNumber
|
||||
)
|
||||
final_payload = {"data": data_for_payload.model_dump(exclude_none=True)}
|
||||
logger.info(f"DanistayApiClient: Performing KEYWORD search via {self.KEYWORD_SEARCH_ENDPOINT} with payload: {final_payload}")
|
||||
return await self._execute_api_search(self.KEYWORD_SEARCH_ENDPOINT, final_payload)
|
||||
|
||||
async def search_detailed_decisions(
|
||||
self,
|
||||
params: DanistayDetailedSearchRequest
|
||||
) -> DanistayApiResponse:
|
||||
data_for_payload = DanistayDetailedSearchRequestData(
|
||||
daire=params.daire or "",
|
||||
esasYil=params.esasYil or "",
|
||||
esasIlkSiraNo=params.esasIlkSiraNo or "",
|
||||
esasSonSiraNo=params.esasSonSiraNo or "",
|
||||
kararYil=params.kararYil or "",
|
||||
kararIlkSiraNo=params.kararIlkSiraNo or "",
|
||||
kararSonSiraNo=params.kararSonSiraNo or "",
|
||||
baslangicTarihi=params.baslangicTarihi or "",
|
||||
bitisTarihi=params.bitisTarihi or "",
|
||||
mevzuatNumarasi=params.mevzuatNumarasi or "",
|
||||
mevzuatAdi=params.mevzuatAdi or "",
|
||||
madde=params.madde or "",
|
||||
siralama="1",
|
||||
siralamaDirection="desc",
|
||||
pageSize=params.pageSize,
|
||||
pageNumber=params.pageNumber
|
||||
)
|
||||
# Create request dict and remove empty string fields to avoid API issues
|
||||
payload_dict = data_for_payload.model_dump(exclude_defaults=False, exclude_none=False)
|
||||
# Remove empty string fields that might cause API issues
|
||||
cleaned_payload = {k: v for k, v in payload_dict.items() if v != ""}
|
||||
final_payload = {"data": cleaned_payload}
|
||||
logger.info(f"DanistayApiClient: Performing DETAILED search via {self.DETAILED_SEARCH_ENDPOINT} with payload: {final_payload}")
|
||||
return await self._execute_api_search(self.DETAILED_SEARCH_ENDPOINT, final_payload)
|
||||
|
||||
async def _execute_api_search(self, endpoint: str, payload: Dict) -> DanistayApiResponse:
|
||||
try:
|
||||
response = await self.http_client.post(endpoint, json=payload)
|
||||
response.raise_for_status()
|
||||
response_json_data = response.json()
|
||||
logger.debug(f"DanistayApiClient: Raw API response from {endpoint}: {response_json_data}")
|
||||
api_response_parsed = DanistayApiResponse(**response_json_data)
|
||||
if api_response_parsed.data and api_response_parsed.data.data:
|
||||
for decision_item in api_response_parsed.data.data:
|
||||
if decision_item.id:
|
||||
decision_item.document_url = f"{self.BASE_URL}{self.DOCUMENT_ENDPOINT}?id={decision_item.id}"
|
||||
return api_response_parsed
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"DanistayApiClient: HTTP request error during search to {endpoint}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"DanistayApiClient: Error processing or validating search response from {endpoint}: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown_danistay(self, direct_html_content: str) -> Optional[str]:
|
||||
"""
|
||||
Converts direct HTML content (assumed from Danıştay /getDokuman) to Markdown.
|
||||
"""
|
||||
if not direct_html_content:
|
||||
return None
|
||||
|
||||
# Basic HTML unescaping and fixing common escaped characters
|
||||
# This step might be less critical if MarkItDown handles them, but good for pre-cleaning.
|
||||
processed_html = html.unescape(direct_html_content)
|
||||
processed_html = processed_html.replace('\\"', '"') # If any such JS-escaped strings exist
|
||||
# Danistay HTML doesn't seem to have \\r\\n etc. from the example, but keeping for robustness
|
||||
processed_html = processed_html.replace('\\r\\n', '\n').replace('\\n', '\n').replace('\\t', '\t')
|
||||
|
||||
# For simplicity and to leverage MarkItDown's capability to handle full docs,
|
||||
# we pass the pre-processed full HTML.
|
||||
html_input_for_markdown = processed_html
|
||||
|
||||
markdown_text = None
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_input_for_markdown.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
logger.info("DanistayApiClient: HTML to Markdown conversion successful.")
|
||||
except Exception as e:
|
||||
logger.error(f"DanistayApiClient: Error during MarkItDown HTML to Markdown conversion: {e}")
|
||||
|
||||
return markdown_text
|
||||
|
||||
async def get_decision_document_as_markdown(self, id: str) -> DanistayDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Danıştay decision by ID and returns its content as Markdown.
|
||||
The /getDokuman endpoint for Danıştay requires arananKelime parameter.
|
||||
"""
|
||||
# Add required arananKelime parameter - using empty string as minimum requirement
|
||||
document_api_url = f"{self.DOCUMENT_ENDPOINT}?id={id}&arananKelime="
|
||||
source_url = f"{self.BASE_URL}{document_api_url}"
|
||||
logger.info(f"DanistayApiClient: Fetching Danistay document for Markdown (ID: {id}) from {source_url}")
|
||||
|
||||
try:
|
||||
# For direct HTML response, we might want different headers if the API is sensitive,
|
||||
# but httpx usually handles basic GET requests well.
|
||||
response = await self.http_client.get(document_api_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Danıştay /getDokuman directly returns HTML text
|
||||
html_content_from_api = response.text
|
||||
|
||||
if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
|
||||
logger.warning(f"DanistayApiClient: Received empty or non-string HTML content for ID {id}.")
|
||||
# Return with None markdown_content if HTML is effectively empty
|
||||
return DanistayDocumentMarkdown(
|
||||
id=id,
|
||||
markdown_content=None,
|
||||
source_url=source_url
|
||||
)
|
||||
|
||||
markdown_content = self._convert_html_to_markdown_danistay(html_content_from_api)
|
||||
|
||||
return DanistayDocumentMarkdown(
|
||||
id=id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=source_url
|
||||
)
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"DanistayApiClient: HTTP error fetching Danistay document (ID: {id}): {e}")
|
||||
raise
|
||||
# Removed ValueError for JSON as Danistay /getDokuman returns direct HTML
|
||||
except Exception as e: # Catches other errors like MarkItDown issues if they propagate
|
||||
logger.error(f"DanistayApiClient: General error processing Danistay document (ID: {id}): {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Closes the HTTPX client session."""
|
||||
if self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("DanistayApiClient: HTTP client session closed.")
|
||||
@@ -1,112 +0,0 @@
|
||||
# danistay_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl, ConfigDict
|
||||
from typing import List, Optional, Dict, Any
|
||||
|
||||
class DanistayBaseSearchRequest(BaseModel):
|
||||
"""Base model for common search parameters for Danistay."""
|
||||
pageSize: int = Field(default=10, ge=1, le=10)
|
||||
pageNumber: int = Field(default=1, ge=1)
|
||||
# siralama and siralamaDirection are part of detailed search, not necessarily keyword search
|
||||
# as per user's provided payloads.
|
||||
|
||||
class DanistayKeywordSearchRequestData(BaseModel):
|
||||
"""Internal data model for the keyword search payload's 'data' field."""
|
||||
andKelimeler: List[str] = Field(default_factory=list)
|
||||
orKelimeler: List[str] = Field(default_factory=list)
|
||||
notAndKelimeler: List[str] = Field(default_factory=list)
|
||||
notOrKelimeler: List[str] = Field(default_factory=list)
|
||||
pageSize: int
|
||||
pageNumber: int
|
||||
|
||||
class DanistayKeywordSearchRequest(BaseModel): # This is the model the MCP tool will accept
|
||||
"""Model for keyword-based search request for Danistay."""
|
||||
andKelimeler: List[str] = Field(default_factory=list, description="AND keywords")
|
||||
orKelimeler: List[str] = Field(default_factory=list, description="OR keywords")
|
||||
notAndKelimeler: List[str] = Field(default_factory=list, description="NOT AND keywords")
|
||||
notOrKelimeler: List[str] = Field(default_factory=list, description="NOT OR keywords")
|
||||
pageSize: int = Field(default=10, ge=1, le=10)
|
||||
pageNumber: int = Field(default=1, ge=1)
|
||||
|
||||
class DanistayDetailedSearchRequestData(BaseModel): # Internal data model for detailed search payload
|
||||
"""Internal data model for the detailed search payload's 'data' field."""
|
||||
daire: Optional[str] = "" # API expects empty string for None
|
||||
esasYil: Optional[str] = ""
|
||||
esasIlkSiraNo: Optional[str] = ""
|
||||
esasSonSiraNo: Optional[str] = ""
|
||||
kararYil: Optional[str] = ""
|
||||
kararIlkSiraNo: Optional[str] = ""
|
||||
kararSonSiraNo: Optional[str] = ""
|
||||
baslangicTarihi: Optional[str] = ""
|
||||
bitisTarihi: Optional[str] = ""
|
||||
mevzuatNumarasi: Optional[str] = ""
|
||||
mevzuatAdi: Optional[str] = ""
|
||||
madde: Optional[str] = ""
|
||||
siralama: str # Seems mandatory in detailed search payload
|
||||
siralamaDirection: str # Seems mandatory
|
||||
pageSize: int
|
||||
pageNumber: int
|
||||
# Note: 'arananKelime' is not in the detailed search payload example provided by user.
|
||||
# If it can be included, it should be added here.
|
||||
|
||||
class DanistayDetailedSearchRequest(DanistayBaseSearchRequest): # MCP tool will accept this
|
||||
"""Model for detailed search request for Danistay."""
|
||||
daire: str = Field("", description="Chamber")
|
||||
esasYil: str = Field("", description="Case year")
|
||||
esasIlkSiraNo: str = Field("", description="Start case no")
|
||||
esasSonSiraNo: str = Field("", description="End case no")
|
||||
kararYil: str = Field("", description="Decision year")
|
||||
kararIlkSiraNo: str = Field("", description="Start decision no")
|
||||
kararSonSiraNo: str = Field("", description="End decision no")
|
||||
baslangicTarihi: str = Field("", description="Start date")
|
||||
bitisTarihi: str = Field("", description="End date")
|
||||
mevzuatNumarasi: str = Field("", description="Law number")
|
||||
mevzuatAdi: str = Field("", description="Law name")
|
||||
madde: str = Field("", description="Article")
|
||||
# Add a general keyword field if detailed search also supports it
|
||||
# arananKelime: Optional[str] = Field(None, description="General keyword for detailed search.")
|
||||
|
||||
|
||||
class DanistayApiDecisionEntry(BaseModel):
|
||||
"""Model for an individual decision entry from the Danistay API search response.
|
||||
Based on user-provided response samples for both keyword and detailed search.
|
||||
"""
|
||||
id: str
|
||||
# The API response for keyword search uses "daireKurul", detailed search example uses "daire".
|
||||
# We use an alias to handle both and map to a consistent field name "chamber".
|
||||
chamber: str = Field("", alias="daire", description="Chamber")
|
||||
esasNo: str = Field("", description="Case number")
|
||||
kararNo: str = Field("", description="Decision number")
|
||||
kararTarihi: str = Field("", description="Decision date")
|
||||
arananKelime: str = Field("", description="Keyword")
|
||||
# index: Optional[int] = None # Present in response, can be added if needed by MCP tool
|
||||
# siraNo: Optional[int] = None # Present in detailed response, can be added
|
||||
|
||||
document_url: Optional[HttpUrl] = Field(None, description="Document URL")
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True, extra='ignore') # Important for alias to work and ignore extra fields
|
||||
|
||||
class DanistayApiResponseInnerData(BaseModel):
|
||||
"""Model for the inner 'data' object in the Danistay API search response."""
|
||||
data: List[DanistayApiDecisionEntry]
|
||||
recordsTotal: int
|
||||
recordsFiltered: int
|
||||
draw: int = Field(0, description="Draw counter")
|
||||
|
||||
class DanistayApiResponse(BaseModel):
|
||||
"""Model for the complete search response from the Danistay API."""
|
||||
data: Optional[DanistayApiResponseInnerData] = Field(None, description="Response data, can be null when no results found")
|
||||
metadata: Optional[Dict[str, Any]] = Field(None, description="Optional metadata (Meta Veri) from API.")
|
||||
|
||||
class DanistayDocumentMarkdown(BaseModel):
|
||||
"""Model for a Danistay decision document, containing only Markdown content."""
|
||||
id: str
|
||||
markdown_content: str = Field("", description="The decision content (Karar İçeriği) converted to Markdown.")
|
||||
source_url: HttpUrl
|
||||
|
||||
class CompactDanistaySearchResult(BaseModel):
|
||||
"""A compact search result model for the MCP tool to return."""
|
||||
decisions: List[DanistayApiDecisionEntry]
|
||||
total_records: int
|
||||
requested_page: int
|
||||
page_size: int
|
||||
@@ -1,66 +0,0 @@
|
||||
version: '3.8'
|
||||
|
||||
services:
|
||||
yargi-mcp:
|
||||
build: .
|
||||
image: yargi-mcp:latest
|
||||
container_name: yargi-mcp-server
|
||||
ports:
|
||||
- "${PORT:-8000}:8000"
|
||||
environment:
|
||||
- HOST=0.0.0.0
|
||||
- PORT=8000
|
||||
- LOG_LEVEL=${LOG_LEVEL:-info}
|
||||
- ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-*}
|
||||
- API_TOKEN=${API_TOKEN:-}
|
||||
- PYTHONUNBUFFERED=1
|
||||
volumes:
|
||||
# Mount logs directory
|
||||
- ./logs:/app/logs
|
||||
# Mount .env file if it exists
|
||||
- ./.env:/app/.env:ro
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "python", "-c", "import httpx; httpx.get('http://localhost:8000/health').raise_for_status()"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 10s
|
||||
networks:
|
||||
- yargi-network
|
||||
|
||||
# Optional: Nginx reverse proxy
|
||||
nginx:
|
||||
image: nginx:alpine
|
||||
container_name: yargi-nginx
|
||||
ports:
|
||||
- "80:80"
|
||||
- "443:443"
|
||||
volumes:
|
||||
- ./nginx.conf:/etc/nginx/nginx.conf:ro
|
||||
- ./ssl:/etc/nginx/ssl:ro
|
||||
depends_on:
|
||||
- yargi-mcp
|
||||
networks:
|
||||
- yargi-network
|
||||
profiles:
|
||||
- production
|
||||
|
||||
# Optional: Redis for caching (future enhancement)
|
||||
redis:
|
||||
image: redis:alpine
|
||||
container_name: yargi-redis
|
||||
command: redis-server --appendonly yes
|
||||
volumes:
|
||||
- redis-data:/data
|
||||
networks:
|
||||
- yargi-network
|
||||
profiles:
|
||||
- with-cache
|
||||
|
||||
networks:
|
||||
yargi-network:
|
||||
driver: bridge
|
||||
|
||||
volumes:
|
||||
redis-data:
|
||||
@@ -1,428 +0,0 @@
|
||||
# Yargı MCP Server Dağıtım Rehberi
|
||||
|
||||
Bu rehber, Yargı MCP Server'ın ASGI web servisi olarak çeşitli dağıtım seçeneklerini kapsar.
|
||||
|
||||
## İçindekiler
|
||||
|
||||
- [Hızlı Başlangıç](#hızlı-başlangıç)
|
||||
- [Yerel Geliştirme](#yerel-geliştirme)
|
||||
- [Production Dağıtımı](#production-dağıtımı)
|
||||
- [Cloud Dağıtımı](#cloud-dağıtımı)
|
||||
- [Docker Dağıtımı](#docker-dağıtımı)
|
||||
- [Güvenlik Hususları](#güvenlik-hususları)
|
||||
- [İzleme](#izleme)
|
||||
|
||||
## Hızlı Başlangıç
|
||||
|
||||
### 1. Bağımlılıkları Yükleyin
|
||||
|
||||
```bash
|
||||
# ASGI sunucusu için uvicorn yükleyin
|
||||
pip install uvicorn
|
||||
|
||||
# Veya tüm bağımlılıklarla birlikte yükleyin
|
||||
pip install -e .
|
||||
pip install uvicorn
|
||||
```
|
||||
|
||||
### 2. Sunucuyu Çalıştırın
|
||||
|
||||
```bash
|
||||
# Temel başlatma
|
||||
python run_asgi.py
|
||||
|
||||
# Veya doğrudan uvicorn ile
|
||||
uvicorn asgi_app:app --host 0.0.0.0 --port 8000
|
||||
```
|
||||
|
||||
Sunucu şu adreslerde kullanılabilir olacak:
|
||||
- MCP Endpoint: `http://localhost:8000/mcp/`
|
||||
- Sağlık Kontrolü: `http://localhost:8000/health`
|
||||
- API Durumu: `http://localhost:8000/status`
|
||||
|
||||
## Yerel Geliştirme
|
||||
|
||||
### Otomatik Yeniden Yükleme ile Geliştirme Sunucusu
|
||||
|
||||
```bash
|
||||
python run_asgi.py --reload --log-level debug
|
||||
```
|
||||
|
||||
### FastAPI Entegrasyonunu Kullanma
|
||||
|
||||
Ek REST API endpoint'leri için:
|
||||
|
||||
```bash
|
||||
uvicorn fastapi_app:app --reload
|
||||
```
|
||||
|
||||
Bu şunları sağlar:
|
||||
- `/docs` adresinde interaktif API dokümantasyonu
|
||||
- `/api/tools` adresinde araç listesi
|
||||
- `/api/databases` adresinde veritabanı bilgileri
|
||||
|
||||
### Ortam Değişkenleri
|
||||
|
||||
`.env.example` dosyasını temel alarak bir `.env` dosyası oluşturun:
|
||||
|
||||
```bash
|
||||
cp .env.example .env
|
||||
```
|
||||
|
||||
Temel değişkenler:
|
||||
- `HOST`: Sunucu host adresi (varsayılan: 127.0.0.1)
|
||||
- `PORT`: Sunucu portu (varsayılan: 8000)
|
||||
- `ALLOWED_ORIGINS`: CORS kökenleri (virgülle ayrılmış)
|
||||
- `LOG_LEVEL`: Log seviyesi (debug, info, warning, error)
|
||||
|
||||
## Production Dağıtımı
|
||||
|
||||
### 1. Uvicorn ile Çoklu Worker Kullanımı
|
||||
|
||||
```bash
|
||||
python run_asgi.py --host 0.0.0.0 --port 8000 --workers 4
|
||||
```
|
||||
|
||||
### 2. Gunicorn Kullanımı
|
||||
|
||||
```bash
|
||||
pip install gunicorn
|
||||
gunicorn asgi_app:app -w 4 -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:8000
|
||||
```
|
||||
|
||||
### 3. Nginx Reverse Proxy ile
|
||||
|
||||
1. Nginx'i yükleyin
|
||||
2. Sağlanan `nginx.conf` dosyasını kullanın:
|
||||
|
||||
```bash
|
||||
sudo cp nginx.conf /etc/nginx/sites-available/yargi-mcp
|
||||
sudo ln -s /etc/nginx/sites-available/yargi-mcp /etc/nginx/sites-enabled/
|
||||
sudo nginx -t
|
||||
sudo systemctl reload nginx
|
||||
```
|
||||
|
||||
### 4. Systemd Servisi
|
||||
|
||||
`/etc/systemd/system/yargi-mcp.service` dosyasını oluşturun:
|
||||
|
||||
```ini
|
||||
[Unit]
|
||||
Description=Yargı MCP Server
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=exec
|
||||
User=www-data
|
||||
WorkingDirectory=/opt/yargi-mcp
|
||||
Environment="PATH=/opt/yargi-mcp/venv/bin"
|
||||
ExecStart=/opt/yargi-mcp/venv/bin/uvicorn asgi_app:app --host 0.0.0.0 --port 8000 --workers 4
|
||||
Restart=on-failure
|
||||
RestartSec=5
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
```
|
||||
|
||||
Etkinleştirin ve başlatın:
|
||||
|
||||
```bash
|
||||
sudo systemctl enable yargi-mcp
|
||||
sudo systemctl start yargi-mcp
|
||||
```
|
||||
|
||||
## Cloud Dağıtımı
|
||||
|
||||
### Heroku
|
||||
|
||||
1. `Procfile` oluşturun:
|
||||
```
|
||||
web: uvicorn asgi_app:app --host 0.0.0.0 --port $PORT
|
||||
```
|
||||
|
||||
2. Dağıtın:
|
||||
```bash
|
||||
heroku create uygulama-isminiz
|
||||
git push heroku main
|
||||
```
|
||||
|
||||
### Railway
|
||||
|
||||
1. `railway.json` ekleyin:
|
||||
```json
|
||||
{
|
||||
"build": {
|
||||
"builder": "NIXPACKS"
|
||||
},
|
||||
"deploy": {
|
||||
"startCommand": "uvicorn asgi_app:app --host 0.0.0.0 --port $PORT"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
2. Railway CLI veya GitHub entegrasyonu ile dağıtın
|
||||
|
||||
### Google Cloud Run
|
||||
|
||||
1. Container oluşturun:
|
||||
```bash
|
||||
docker build -t yargi-mcp .
|
||||
docker tag yargi-mcp gcr.io/PROJE_ADINIZ/yargi-mcp
|
||||
docker push gcr.io/PROJE_ADINIZ/yargi-mcp
|
||||
```
|
||||
|
||||
2. Dağıtın:
|
||||
```bash
|
||||
gcloud run deploy yargi-mcp \
|
||||
--image gcr.io/PROJE_ADINIZ/yargi-mcp \
|
||||
--platform managed \
|
||||
--region us-central1 \
|
||||
--allow-unauthenticated
|
||||
```
|
||||
|
||||
### AWS Lambda (Mangum kullanarak)
|
||||
|
||||
1. Mangum'u yükleyin:
|
||||
```bash
|
||||
pip install mangum
|
||||
```
|
||||
|
||||
2. `lambda_handler.py` oluşturun:
|
||||
```python
|
||||
from mangum import Mangum
|
||||
from asgi_app import app
|
||||
|
||||
handler = Mangum(app, lifespan="off")
|
||||
```
|
||||
|
||||
3. AWS SAM veya Serverless Framework kullanarak dağıtın
|
||||
|
||||
## Docker Dağıtımı
|
||||
|
||||
### Tek Container
|
||||
|
||||
```bash
|
||||
# Oluşturun
|
||||
docker build -t yargi-mcp .
|
||||
|
||||
# Çalıştırın
|
||||
docker run -p 8000:8000 --env-file .env yargi-mcp
|
||||
```
|
||||
|
||||
### Docker Compose
|
||||
|
||||
```bash
|
||||
# Geliştirme
|
||||
docker-compose up
|
||||
|
||||
# Nginx ile Production
|
||||
docker-compose --profile production up
|
||||
|
||||
# Redis önbellekleme ile
|
||||
docker-compose --profile with-cache up
|
||||
```
|
||||
|
||||
### Kubernetes
|
||||
|
||||
Deployment YAML oluşturun:
|
||||
|
||||
```yaml
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: yargi-mcp
|
||||
spec:
|
||||
replicas: 3
|
||||
selector:
|
||||
matchLabels:
|
||||
app: yargi-mcp
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: yargi-mcp
|
||||
spec:
|
||||
containers:
|
||||
- name: yargi-mcp
|
||||
image: yargi-mcp:latest
|
||||
ports:
|
||||
- containerPort: 8000
|
||||
env:
|
||||
- name: HOST
|
||||
value: "0.0.0.0"
|
||||
- name: PORT
|
||||
value: "8000"
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: 8000
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 30
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: yargi-mcp-service
|
||||
spec:
|
||||
selector:
|
||||
app: yargi-mcp
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 8000
|
||||
type: LoadBalancer
|
||||
```
|
||||
|
||||
## Güvenlik Hususları
|
||||
|
||||
### 1. Kimlik Doğrulama
|
||||
|
||||
`API_TOKEN` ortam değişkenini ayarlayarak token kimlik doğrulamasını etkinleştirin:
|
||||
|
||||
```bash
|
||||
export API_TOKEN=gizli-token-degeri
|
||||
```
|
||||
|
||||
Ardından isteklere ekleyin:
|
||||
```bash
|
||||
curl -H "Authorization: Bearer gizli-token-degeri" http://localhost:8000/api/tools
|
||||
```
|
||||
|
||||
### 2. HTTPS/SSL
|
||||
|
||||
Production için her zaman HTTPS kullanın:
|
||||
|
||||
1. SSL sertifikası edinin (Let's Encrypt vb.)
|
||||
2. Nginx veya cloud sağlayıcıda yapılandırın
|
||||
3. `ALLOWED_ORIGINS` değerini https:// kullanacak şekilde güncelleyin
|
||||
|
||||
### 3. Rate Limiting (Hız Sınırlama)
|
||||
|
||||
Sağlanan Nginx yapılandırması rate limiting içerir:
|
||||
- API endpoint'leri: 10 istek/saniye
|
||||
- MCP endpoint: 100 istek/saniye
|
||||
|
||||
### 4. CORS Yapılandırması
|
||||
|
||||
Production için belirli kaynaklara izin verin:
|
||||
|
||||
```bash
|
||||
ALLOWED_ORIGINS=https://app.sizindomain.com,https://www.sizindomain.com
|
||||
```
|
||||
|
||||
## İzleme
|
||||
|
||||
### Sağlık Kontrolleri
|
||||
|
||||
`/health` endpoint'ini izleyin:
|
||||
|
||||
```bash
|
||||
curl http://localhost:8000/health
|
||||
```
|
||||
|
||||
Yanıt:
|
||||
```json
|
||||
{
|
||||
"status": "healthy",
|
||||
"timestamp": "2024-12-26T10:00:00",
|
||||
"uptime_seconds": 3600,
|
||||
"tools_operational": true
|
||||
}
|
||||
```
|
||||
|
||||
### Loglama
|
||||
|
||||
Ortam değişkeni ile log seviyesini yapılandırın:
|
||||
|
||||
```bash
|
||||
LOG_LEVEL=info # veya debug, warning, error
|
||||
```
|
||||
|
||||
Loglar şuraya yazılır:
|
||||
- Konsol (stdout)
|
||||
- `logs/mcp_server.log` dosyası
|
||||
|
||||
### Metrikler (Opsiyonel)
|
||||
|
||||
OpenTelemetry desteği için:
|
||||
|
||||
```bash
|
||||
pip install opentelemetry-instrumentation-fastapi
|
||||
```
|
||||
|
||||
Ortam değişkenlerini ayarlayın:
|
||||
```bash
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
|
||||
OTEL_SERVICE_NAME=yargi-mcp-server
|
||||
```
|
||||
|
||||
## Sorun Giderme
|
||||
|
||||
### Port Zaten Kullanımda
|
||||
|
||||
```bash
|
||||
# 8000 portunu kullanan işlemi bulun
|
||||
lsof -i :8000
|
||||
|
||||
# İşlemi sonlandırın
|
||||
kill -9 <PID>
|
||||
```
|
||||
|
||||
### İzin Hataları
|
||||
|
||||
Dosya izinlerinin doğru olduğundan emin olun:
|
||||
|
||||
```bash
|
||||
chmod +x run_asgi.py
|
||||
chown -R www-data:www-data /opt/yargi-mcp
|
||||
```
|
||||
|
||||
### Bellek Sorunları
|
||||
|
||||
Büyük belge işleme için worker belleğini artırın:
|
||||
|
||||
```bash
|
||||
# systemd servisinde
|
||||
Environment="PYTHONMALLOC=malloc"
|
||||
LimitNOFILE=65536
|
||||
```
|
||||
|
||||
### Zaman Aşımı Sorunları
|
||||
|
||||
Zaman aşımlarını ayarlayın:
|
||||
1. Uvicorn: `--timeout-keep-alive 75`
|
||||
2. Nginx: `proxy_read_timeout 300s;`
|
||||
3. Cloud sağlayıcılar: Platform özel zaman aşımı ayarlarını kontrol edin
|
||||
|
||||
## Performans Ayarlama
|
||||
|
||||
### 1. Worker İşlemleri
|
||||
|
||||
- Geliştirme: 1 worker
|
||||
- Production: CPU çekirdeği başına 2-4 worker
|
||||
|
||||
### 2. Bağlantı Havuzlama
|
||||
|
||||
Sunucu varsayılan olarak httpx ile bağlantı havuzlama kullanır.
|
||||
|
||||
### 3. Önbellekleme (Gelecek Geliştirme)
|
||||
|
||||
Redis önbellekleme docker-compose ile etkinleştirilebilir:
|
||||
|
||||
```bash
|
||||
docker-compose --profile with-cache up
|
||||
```
|
||||
|
||||
### 4. Veritabanı Zaman Aşımları
|
||||
|
||||
`.env` dosyasında veritabanı başına zaman aşımlarını ayarlayın:
|
||||
|
||||
```bash
|
||||
YARGITAY_TIMEOUT=60
|
||||
DANISTAY_TIMEOUT=60
|
||||
ANAYASA_TIMEOUT=90
|
||||
```
|
||||
|
||||
## Destek
|
||||
|
||||
Sorunlar ve sorular için:
|
||||
- GitHub Issues: https://github.com/saidsurucu/yargi-mcp/issues
|
||||
- Dokümantasyon: README.md dosyasına bakın
|
||||
@@ -1,177 +0,0 @@
|
||||
# emsal_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
# from bs4 import BeautifulSoup # Uncomment if needed for advanced HTML pre-processing
|
||||
from typing import Dict, Any, List, Optional
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
EmsalSearchRequest,
|
||||
EmsalDetailedSearchRequestData,
|
||||
EmsalApiResponse,
|
||||
EmsalDocumentMarkdown
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
class EmsalApiClient:
|
||||
"""API Client for Emsal (UYAP Precedent Decision) search system."""
|
||||
BASE_URL = "https://emsal.uyap.gov.tr"
|
||||
DETAILED_SEARCH_ENDPOINT = "/aramadetaylist"
|
||||
DOCUMENT_ENDPOINT = "/getDokuman"
|
||||
|
||||
def __init__(self, request_timeout: float = 30.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Content-Type": "application/json; charset=UTF-8",
|
||||
"Accept": "application/json, text/plain, */*",
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=False # As per user's original FastAPI code
|
||||
)
|
||||
|
||||
async def search_detailed_decisions(
|
||||
self,
|
||||
params: EmsalSearchRequest
|
||||
) -> EmsalApiResponse:
|
||||
"""Performs a detailed search for Emsal decisions."""
|
||||
|
||||
data_for_api_payload = EmsalDetailedSearchRequestData(
|
||||
arananKelime=params.keyword or "",
|
||||
Bam_Hukuk_Mahkemeleri=params.selected_bam_civil_court, # Uses alias "Bam Hukuk Mahkemeleri"
|
||||
Hukuk_Mahkemeleri=params.selected_civil_court, # Uses alias "Hukuk Mahkemeleri"
|
||||
birimHukukMah="+".join(params.selected_regional_civil_chambers) if params.selected_regional_civil_chambers else "",
|
||||
esasYil=params.case_year_esas or "",
|
||||
esasIlkSiraNo=params.case_start_seq_esas or "",
|
||||
esasSonSiraNo=params.case_end_seq_esas or "",
|
||||
kararYil=params.decision_year_karar or "",
|
||||
kararIlkSiraNo=params.decision_start_seq_karar or "",
|
||||
kararSonSiraNo=params.decision_end_seq_karar or "",
|
||||
baslangicTarihi=params.start_date or "",
|
||||
bitisTarihi=params.end_date or "",
|
||||
siralama=params.sort_criteria,
|
||||
siralamaDirection=params.sort_direction,
|
||||
pageSize=params.page_size,
|
||||
pageNumber=params.page_number
|
||||
)
|
||||
|
||||
# Create request dict and remove empty string fields to avoid API issues
|
||||
payload_dict = data_for_api_payload.model_dump(by_alias=True, exclude_none=True)
|
||||
# Remove empty string fields that might cause API issues
|
||||
cleaned_payload = {k: v for k, v in payload_dict.items() if v != ""}
|
||||
final_payload = {"data": cleaned_payload}
|
||||
|
||||
logger.info(f"EmsalApiClient: Performing DETAILED search with payload: {final_payload}")
|
||||
return await self._execute_api_search(self.DETAILED_SEARCH_ENDPOINT, final_payload)
|
||||
|
||||
async def _execute_api_search(self, endpoint: str, payload: Dict) -> EmsalApiResponse:
|
||||
"""Helper method to execute search POST request and process response for Emsal."""
|
||||
try:
|
||||
response = await self.http_client.post(endpoint, json=payload)
|
||||
response.raise_for_status()
|
||||
response_json_data = response.json()
|
||||
logger.debug(f"EmsalApiClient: Raw API response from {endpoint}: {response_json_data}")
|
||||
|
||||
api_response_parsed = EmsalApiResponse(**response_json_data)
|
||||
|
||||
if api_response_parsed.data and api_response_parsed.data.data:
|
||||
for decision_item in api_response_parsed.data.data:
|
||||
if decision_item.id:
|
||||
decision_item.document_url = f"{self.BASE_URL}{self.DOCUMENT_ENDPOINT}?id={decision_item.id}"
|
||||
|
||||
return api_response_parsed
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"EmsalApiClient: HTTP request error during Emsal search to {endpoint}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"EmsalApiClient: Error processing or validating Emsal search response from {endpoint}: {e}")
|
||||
raise
|
||||
|
||||
def _clean_html_and_convert_to_markdown_emsal(self, html_content_from_api_data_field: str) -> Optional[str]:
|
||||
"""
|
||||
Cleans HTML (from Emsal API 'data' field containing HTML string)
|
||||
and converts it to Markdown using MarkItDown.
|
||||
This assumes Emsal /getDokuman response is JSON with HTML in "data" field,
|
||||
similar to Yargitay and the last Emsal /getDokuman example.
|
||||
"""
|
||||
if not html_content_from_api_data_field:
|
||||
return None
|
||||
|
||||
# Basic HTML unescaping and fixing common escaped characters
|
||||
# Based on user's original fix_html_content in app/routers/emsal.py
|
||||
content = html.unescape(html_content_from_api_data_field)
|
||||
content = content.replace('\\"', '"')
|
||||
content = content.replace('\\r\\n', '\n')
|
||||
content = content.replace('\\n', '\n')
|
||||
content = content.replace('\\t', '\t')
|
||||
|
||||
# The HTML string from "data" field starts with "<html><head>..."
|
||||
html_input_for_markdown = content
|
||||
|
||||
markdown_text = None
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_input_for_markdown.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
logger.info("EmsalApiClient: HTML to Markdown conversion successful.")
|
||||
except Exception as e:
|
||||
logger.error(f"EmsalApiClient: Error during MarkItDown HTML to Markdown conversion for Emsal: {e}")
|
||||
|
||||
return markdown_text
|
||||
|
||||
async def get_decision_document_as_markdown(self, id: str) -> EmsalDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Emsal decision by ID and returns its content as Markdown.
|
||||
Assumes Emsal /getDokuman endpoint returns JSON with HTML content in the 'data' field.
|
||||
"""
|
||||
document_api_url = f"{self.DOCUMENT_ENDPOINT}?id={id}"
|
||||
source_url = f"{self.BASE_URL}{document_api_url}"
|
||||
logger.info(f"EmsalApiClient: Fetching Emsal document for Markdown (ID: {id}) from {source_url}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(document_api_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Emsal /getDokuman returns JSON with HTML in 'data' field (confirmed by user example)
|
||||
response_json = response.json()
|
||||
html_content_from_api = response_json.get("data")
|
||||
|
||||
if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
|
||||
logger.warning(f"EmsalApiClient: Received empty or non-string HTML in 'data' field for Emsal ID {id}.")
|
||||
return EmsalDocumentMarkdown(id=id, markdown_content=None, source_url=source_url)
|
||||
|
||||
markdown_content = self._clean_html_and_convert_to_markdown_emsal(html_content_from_api)
|
||||
|
||||
return EmsalDocumentMarkdown(
|
||||
id=id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=source_url
|
||||
)
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"EmsalApiClient: HTTP error fetching Emsal document (ID: {id}): {e}")
|
||||
raise
|
||||
except ValueError as e:
|
||||
logger.error(f"EmsalApiClient: ValueError processing Emsal document response (ID: {id}): {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"EmsalApiClient: General error processing Emsal document (ID: {id}): {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Closes the HTTPX client session."""
|
||||
if self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("EmsalApiClient: HTTP client session closed.")
|
||||
@@ -1,101 +0,0 @@
|
||||
# emsal_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl, ConfigDict
|
||||
from typing import List, Optional, Dict, Any
|
||||
|
||||
class EmsalDetailedSearchRequestData(BaseModel):
|
||||
"""
|
||||
Internal model for the 'data' object in the Emsal detailed search payload.
|
||||
Field names use aliases to match the exact keys in the API payload
|
||||
(e.g., "Bam Hukuk Mahkemeleri" with spaces).
|
||||
The API expects empty strings for None/omitted optional fields.
|
||||
"""
|
||||
arananKelime: Optional[str] = ""
|
||||
|
||||
Bam_Hukuk_Mahkemeleri: str = Field("", alias="Bam Hukuk Mahkemeleri")
|
||||
Hukuk_Mahkemeleri: str = Field("", alias="Hukuk Mahkemeleri")
|
||||
# Add other specific court type fields from the form if they are separate keys in payload
|
||||
# E.g., "Ceza Mahkemeleri", "İdari Mahkemeler" etc.
|
||||
|
||||
birimHukukMah: Optional[str] = Field("", description="Regional chambers (+ separated)")
|
||||
|
||||
esasYil: Optional[str] = ""
|
||||
esasIlkSiraNo: Optional[str] = ""
|
||||
esasSonSiraNo: Optional[str] = ""
|
||||
kararYil: Optional[str] = ""
|
||||
kararIlkSiraNo: Optional[str] = ""
|
||||
kararSonSiraNo: Optional[str] = ""
|
||||
baslangicTarihi: Optional[str] = ""
|
||||
bitisTarihi: Optional[str] = ""
|
||||
siralama: str # Mandatory in payload example
|
||||
siralamaDirection: str # Mandatory in payload example
|
||||
pageSize: int
|
||||
pageNumber: int
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True) # Enables use of alias in serialization (when dumping to dict for payload)
|
||||
|
||||
class EmsalSearchRequest(BaseModel): # This is the model the MCP tool will accept
|
||||
"""Model for Emsal detailed search request, with user-friendly field names."""
|
||||
keyword: str = Field("", description="Keyword")
|
||||
|
||||
selected_bam_civil_court: str = Field("", description="BAM Civil Court")
|
||||
selected_civil_court: str = Field("", description="Civil Court")
|
||||
selected_regional_civil_chambers: List[str] = Field(default_factory=list, description="Regional chambers")
|
||||
|
||||
case_year_esas: str = Field("", description="Case year")
|
||||
case_start_seq_esas: str = Field("", description="Start case no")
|
||||
case_end_seq_esas: str = Field("", description="End case no")
|
||||
|
||||
decision_year_karar: str = Field("", description="Decision year")
|
||||
decision_start_seq_karar: str = Field("", description="Start decision no")
|
||||
decision_end_seq_karar: str = Field("", description="End decision no")
|
||||
|
||||
start_date: str = Field("", description="Start date (DD.MM.YYYY)")
|
||||
end_date: str = Field("", description="End date (DD.MM.YYYY)")
|
||||
|
||||
sort_criteria: str = Field("1", description="Sort by")
|
||||
sort_direction: str = Field("desc", description="Direction")
|
||||
|
||||
page_number: int = Field(default=1, ge=1)
|
||||
page_size: int = Field(default=10, ge=1, le=10)
|
||||
|
||||
|
||||
class EmsalApiDecisionEntry(BaseModel):
|
||||
"""Model for an individual decision entry from the Emsal API search response."""
|
||||
id: str
|
||||
daire: str = Field("", description="Chamber")
|
||||
esasNo: str = Field("", description="Case number")
|
||||
kararNo: str = Field("", description="Decision number")
|
||||
kararTarihi: str = Field("", description="Decision date")
|
||||
arananKelime: str = Field("", description="Keyword")
|
||||
durum: str = Field("", description="Status")
|
||||
# index: Optional[int] = None # Present in Emsal response, can be added if tool needs it
|
||||
|
||||
document_url: Optional[HttpUrl] = Field(None, description="Document URL")
|
||||
|
||||
model_config = ConfigDict(extra='ignore')
|
||||
|
||||
class EmsalApiResponseInnerData(BaseModel):
|
||||
"""Model for the inner 'data' object in the Emsal API search response."""
|
||||
data: List[EmsalApiDecisionEntry]
|
||||
recordsTotal: int
|
||||
recordsFiltered: int
|
||||
draw: int = Field(0, description="Draw counter (Çizim Sayıcısı) from API, usually for DataTables.")
|
||||
|
||||
class EmsalApiResponse(BaseModel):
|
||||
"""Model for the complete search response from the Emsal API."""
|
||||
data: EmsalApiResponseInnerData
|
||||
metadata: Optional[Dict[str, Any]] = Field(None, description="Optional metadata (Meta Veri) from API, if any.")
|
||||
|
||||
class EmsalDocumentMarkdown(BaseModel):
|
||||
"""Model for an Emsal decision document, containing only Markdown content."""
|
||||
id: str
|
||||
markdown_content: str = Field("", description="The decision content (Karar İçeriği) converted to Markdown.")
|
||||
source_url: HttpUrl
|
||||
|
||||
class CompactEmsalSearchResult(BaseModel):
|
||||
"""A compact search result model for the MCP tool to return."""
|
||||
decisions: List[EmsalApiDecisionEntry]
|
||||
total_records: int
|
||||
requested_page: int
|
||||
page_size: int
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,74 +0,0 @@
|
||||
# kik_mcp_module/models.py
|
||||
from pydantic import BaseModel, Field, HttpUrl, computed_field, ConfigDict
|
||||
from typing import List, Optional
|
||||
from enum import Enum
|
||||
import base64 # Base64 encoding/decoding için
|
||||
|
||||
class KikKararTipi(str, Enum):
|
||||
"""Enum for KIK (Public Procurement Authority) Decision Types."""
|
||||
UYUSMAZLIK = "rbUyusmazlik"
|
||||
DUZENLEYICI = "rbDuzenleyici"
|
||||
MAHKEME = "rbMahkeme"
|
||||
|
||||
class KikSearchRequest(BaseModel):
|
||||
"""Model for KIK Decision search criteria."""
|
||||
karar_tipi: KikKararTipi = Field(KikKararTipi.UYUSMAZLIK, description="Type")
|
||||
karar_no: str = Field("", description="No")
|
||||
karar_tarihi_baslangic: str = Field("", description="Start", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
karar_tarihi_bitis: str = Field("", description="End", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
resmi_gazete_sayisi: str = Field("", description="Gazette")
|
||||
resmi_gazete_tarihi: str = Field("", description="Date", pattern=r"^\d{2}\.\d{2}\.\d{4}$|^$")
|
||||
basvuru_konusu_ihale: str = Field("", description="Subject")
|
||||
basvuru_sahibi: str = Field("", description="Applicant")
|
||||
ihaleyi_yapan_idare: str = Field("", description="Entity")
|
||||
yil: str = Field("", description="Year")
|
||||
karar_metni: str = Field("", description="Text")
|
||||
page: int = Field(1, ge=1, description="Page")
|
||||
|
||||
class KikDecisionEntry(BaseModel):
|
||||
"""Represents a single decision entry from KIK search results."""
|
||||
preview_event_target: str = Field(..., description="Event target")
|
||||
karar_no_str: str = Field(..., alias="kararNo", description="Decision number")
|
||||
karar_tipi: KikKararTipi = Field(..., description="Decision type")
|
||||
|
||||
karar_tarihi_str: str = Field(..., alias="kararTarihi", description="Date")
|
||||
idare_str: str = Field("", alias="idare", description="Entity")
|
||||
basvuru_sahibi_str: str = Field("", alias="basvuruSahibi", description="Applicant")
|
||||
ihale_konusu_str: str = Field("", alias="ihaleKonusu", description="Subject")
|
||||
|
||||
@computed_field
|
||||
@property
|
||||
def karar_id(self) -> str:
|
||||
"""
|
||||
A Base64 encoded unique ID for the decision, combining decision type and number.
|
||||
Format before encoding: "{karar_tipi.value}|{karar_no_str}"
|
||||
"""
|
||||
combined_key = f"{self.karar_tipi.value}|{self.karar_no_str}"
|
||||
return base64.b64encode(combined_key.encode('utf-8')).decode('utf-8')
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True)
|
||||
|
||||
class KikSearchResult(BaseModel):
|
||||
"""Model for KIK search results."""
|
||||
decisions: List[KikDecisionEntry]
|
||||
total_records: int = 0
|
||||
current_page: int = 1
|
||||
|
||||
class KikDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
KIK decision document, with Markdown content potentially paginated.
|
||||
"""
|
||||
retrieved_with_karar_id: Optional[str] = Field(None, description="Request ID")
|
||||
retrieved_karar_no: Optional[str] = Field(None, description="Decision number")
|
||||
retrieved_karar_tipi: Optional[KikKararTipi] = Field(None, description="Decision type")
|
||||
|
||||
karar_id_param_from_url: Optional[str] = Field(None, alias="kararIdParam", description="Internal ID")
|
||||
markdown_chunk: Optional[str] = Field(None, description="Content")
|
||||
source_url: Optional[str] = Field(None, description="Source URL")
|
||||
error_message: Optional[str] = Field(None, description="Error")
|
||||
current_page: int = Field(1, description="Page")
|
||||
total_pages: int = Field(1, description="Total pages")
|
||||
is_paginated: bool = Field(False, description="Paginated")
|
||||
full_content_char_count: Optional[int] = Field(None, description="Char count")
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True)
|
||||
@@ -1 +0,0 @@
|
||||
# kvkk_mcp_module/__init__.py
|
||||
@@ -1,372 +0,0 @@
|
||||
# kvkk_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import List, Optional, Dict, Any
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import io
|
||||
import math
|
||||
from urllib.parse import urljoin, urlparse, parse_qs
|
||||
from markitdown import MarkItDown
|
||||
from pydantic import HttpUrl
|
||||
|
||||
from .models import (
|
||||
KvkkSearchRequest,
|
||||
KvkkDecisionSummary,
|
||||
KvkkSearchResult,
|
||||
KvkkDocumentMarkdown
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
|
||||
class KvkkApiClient:
|
||||
"""
|
||||
API client for searching and retrieving KVKK (Personal Data Protection Authority) decisions
|
||||
using Brave Search API for discovery and direct HTTP requests for content retrieval.
|
||||
"""
|
||||
|
||||
BRAVE_API_URL = "https://api.search.brave.com/res/v1/web/search"
|
||||
KVKK_BASE_URL = "https://www.kvkk.gov.tr"
|
||||
DOCUMENT_MARKDOWN_CHUNK_SIZE = 5000 # Character limit per page
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
"""Initialize the KVKK API client."""
|
||||
self.brave_api_token = os.getenv("BRAVE_API_TOKEN")
|
||||
if not self.brave_api_token:
|
||||
# Fallback to provided free token
|
||||
self.brave_api_token = "BSAuaRKB-dvSDSQxIN0ft1p2k6N82Kq"
|
||||
logger.info("Using fallback Brave API token (limited free token)")
|
||||
else:
|
||||
logger.info("Using Brave API token from environment variable")
|
||||
|
||||
self.http_client = httpx.AsyncClient(
|
||||
headers={
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=True,
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
def _construct_search_query(self, keywords: str) -> str:
|
||||
"""Construct the search query for Brave API."""
|
||||
base_query = 'site:kvkk.gov.tr "karar özeti"'
|
||||
if keywords.strip():
|
||||
return f"{base_query} {keywords.strip()}"
|
||||
return base_query
|
||||
|
||||
def _extract_decision_id_from_url(self, url: str) -> Optional[str]:
|
||||
"""Extract decision ID from KVKK decision URL."""
|
||||
try:
|
||||
# Example URL: https://www.kvkk.gov.tr/Icerik/7288/2021-1303
|
||||
parsed_url = urlparse(url)
|
||||
path_parts = parsed_url.path.strip('/').split('/')
|
||||
|
||||
if len(path_parts) >= 3 and path_parts[0] == 'Icerik':
|
||||
# Extract the decision ID from the path
|
||||
decision_id = '/'.join(path_parts[1:]) # e.g., "7288/2021-1303"
|
||||
return decision_id
|
||||
|
||||
except Exception as e:
|
||||
logger.debug(f"Could not extract decision ID from URL {url}: {e}")
|
||||
|
||||
return None
|
||||
|
||||
def _extract_decision_metadata_from_title(self, title: str) -> Dict[str, Optional[str]]:
|
||||
"""Extract decision metadata from title string."""
|
||||
metadata = {
|
||||
"decision_date": None,
|
||||
"decision_number": None
|
||||
}
|
||||
|
||||
if not title:
|
||||
return metadata
|
||||
|
||||
# Extract decision date (DD/MM/YYYY format)
|
||||
date_match = re.search(r'(\d{1,2}/\d{1,2}/\d{4})', title)
|
||||
if date_match:
|
||||
metadata["decision_date"] = date_match.group(1)
|
||||
|
||||
# Extract decision number (YYYY/XXXX format)
|
||||
number_match = re.search(r'(\d{4}/\d+)', title)
|
||||
if number_match:
|
||||
metadata["decision_number"] = number_match.group(1)
|
||||
|
||||
return metadata
|
||||
|
||||
async def search_decisions(self, params: KvkkSearchRequest) -> KvkkSearchResult:
|
||||
"""Search for KVKK decisions using Brave API."""
|
||||
|
||||
search_query = self._construct_search_query(params.keywords)
|
||||
logger.info(f"KvkkApiClient: Searching with query: {search_query}")
|
||||
|
||||
try:
|
||||
# Calculate offset for pagination
|
||||
offset = (params.page - 1) * params.pageSize
|
||||
|
||||
response = await self.http_client.get(
|
||||
self.BRAVE_API_URL,
|
||||
headers={
|
||||
"Accept": "application/json",
|
||||
"Accept-Encoding": "gzip",
|
||||
"x-subscription-token": self.brave_api_token
|
||||
},
|
||||
params={
|
||||
"q": search_query,
|
||||
"country": "TR",
|
||||
"search_lang": "tr",
|
||||
"ui_lang": "tr-TR",
|
||||
"offset": offset,
|
||||
"count": params.pageSize
|
||||
}
|
||||
)
|
||||
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
|
||||
# Extract search results
|
||||
decisions = []
|
||||
web_results = data.get("web", {}).get("results", [])
|
||||
|
||||
for result in web_results:
|
||||
title = result.get("title", "")
|
||||
url = result.get("url", "")
|
||||
description = result.get("description", "")
|
||||
|
||||
# Extract metadata from title
|
||||
metadata = self._extract_decision_metadata_from_title(title)
|
||||
|
||||
# Extract decision ID from URL
|
||||
decision_id = self._extract_decision_id_from_url(url)
|
||||
|
||||
decision = KvkkDecisionSummary(
|
||||
title=title,
|
||||
url=HttpUrl(url) if url else None,
|
||||
description=description,
|
||||
decision_id=decision_id,
|
||||
publication_date=metadata.get("decision_date"),
|
||||
decision_number=metadata.get("decision_number")
|
||||
)
|
||||
decisions.append(decision)
|
||||
|
||||
# Get total results if available
|
||||
total_results = None
|
||||
query_info = data.get("query", {})
|
||||
if "total_results" in query_info:
|
||||
total_results = query_info["total_results"]
|
||||
|
||||
return KvkkSearchResult(
|
||||
decisions=decisions,
|
||||
total_results=total_results,
|
||||
page=params.page,
|
||||
pageSize=params.pageSize,
|
||||
query=search_query
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"KvkkApiClient: HTTP request error during search: {e}")
|
||||
return KvkkSearchResult(
|
||||
decisions=[],
|
||||
total_results=0,
|
||||
page=params.page,
|
||||
pageSize=params.pageSize,
|
||||
query=search_query
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"KvkkApiClient: Unexpected error during search: {e}")
|
||||
return KvkkSearchResult(
|
||||
decisions=[],
|
||||
total_results=0,
|
||||
page=params.page,
|
||||
pageSize=params.pageSize,
|
||||
query=search_query
|
||||
)
|
||||
|
||||
def _extract_decision_content_from_html(self, html: str, url: str) -> Dict[str, Any]:
|
||||
"""Extract decision content from KVKK decision page HTML."""
|
||||
try:
|
||||
soup = BeautifulSoup(html, 'html.parser')
|
||||
|
||||
# Extract title
|
||||
title = None
|
||||
title_element = soup.find('h3', class_='blog-post-title')
|
||||
if title_element:
|
||||
title = title_element.get_text(strip=True)
|
||||
elif soup.title:
|
||||
title = soup.title.get_text(strip=True)
|
||||
|
||||
# Extract decision content from the main content div
|
||||
content_div = soup.find('div', class_='blog-post-inner')
|
||||
if not content_div:
|
||||
# Fallback to other possible content containers
|
||||
content_div = soup.find('div', style='text-align:justify;')
|
||||
if not content_div:
|
||||
logger.warning(f"Could not find decision content div in {url}")
|
||||
return {
|
||||
"title": title,
|
||||
"decision_date": None,
|
||||
"decision_number": None,
|
||||
"subject_summary": None,
|
||||
"html_content": None
|
||||
}
|
||||
|
||||
# Extract decision metadata from table
|
||||
decision_date = None
|
||||
decision_number = None
|
||||
subject_summary = None
|
||||
|
||||
table = content_div.find('table')
|
||||
if table:
|
||||
rows = table.find_all('tr')
|
||||
for row in rows:
|
||||
cells = row.find_all('td')
|
||||
if len(cells) >= 3:
|
||||
field_name = cells[0].get_text(strip=True)
|
||||
field_value = cells[2].get_text(strip=True)
|
||||
|
||||
if 'Karar Tarihi' in field_name:
|
||||
decision_date = field_value
|
||||
elif 'Karar No' in field_name:
|
||||
decision_number = field_value
|
||||
elif 'Konu Özeti' in field_name:
|
||||
subject_summary = field_value
|
||||
|
||||
return {
|
||||
"title": title,
|
||||
"decision_date": decision_date,
|
||||
"decision_number": decision_number,
|
||||
"subject_summary": subject_summary,
|
||||
"html_content": str(content_div)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error extracting content from HTML for {url}: {e}")
|
||||
return {
|
||||
"title": None,
|
||||
"decision_date": None,
|
||||
"decision_number": None,
|
||||
"subject_summary": None,
|
||||
"html_content": None
|
||||
}
|
||||
|
||||
def _convert_html_to_markdown(self, html_content: str) -> Optional[str]:
|
||||
"""Convert HTML content to Markdown using MarkItDown with BytesIO to avoid filename length issues."""
|
||||
if not html_content:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_content.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown(enable_plugins=False)
|
||||
result = md_converter.convert(html_stream)
|
||||
return result.text_content
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting HTML to Markdown: {e}")
|
||||
return None
|
||||
|
||||
async def get_decision_document(self, decision_url: str, page_number: int = 1) -> KvkkDocumentMarkdown:
|
||||
"""Retrieve and convert a KVKK decision document to paginated Markdown."""
|
||||
logger.info(f"KvkkApiClient: Getting decision document from: {decision_url}, page: {page_number}")
|
||||
|
||||
try:
|
||||
# Fetch the decision page
|
||||
response = await self.http_client.get(decision_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Extract content from HTML
|
||||
extracted_data = self._extract_decision_content_from_html(response.text, decision_url)
|
||||
|
||||
# Convert HTML content to Markdown
|
||||
full_markdown_content = None
|
||||
if extracted_data["html_content"]:
|
||||
full_markdown_content = self._convert_html_to_markdown(extracted_data["html_content"])
|
||||
|
||||
if not full_markdown_content:
|
||||
return KvkkDocumentMarkdown(
|
||||
source_url=HttpUrl(decision_url),
|
||||
title=extracted_data["title"],
|
||||
decision_date=extracted_data["decision_date"],
|
||||
decision_number=extracted_data["decision_number"],
|
||||
subject_summary=extracted_data["subject_summary"],
|
||||
markdown_chunk=None,
|
||||
current_page=page_number,
|
||||
total_pages=0,
|
||||
is_paginated=False,
|
||||
error_message="Could not convert document content to Markdown"
|
||||
)
|
||||
|
||||
# Calculate pagination
|
||||
content_length = len(full_markdown_content)
|
||||
total_pages = math.ceil(content_length / self.DOCUMENT_MARKDOWN_CHUNK_SIZE)
|
||||
if total_pages == 0:
|
||||
total_pages = 1
|
||||
|
||||
# Clamp page number to valid range
|
||||
current_page_clamped = max(1, min(page_number, total_pages))
|
||||
|
||||
# Extract the requested chunk
|
||||
start_index = (current_page_clamped - 1) * self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
end_index = start_index + self.DOCUMENT_MARKDOWN_CHUNK_SIZE
|
||||
markdown_chunk = full_markdown_content[start_index:end_index]
|
||||
|
||||
return KvkkDocumentMarkdown(
|
||||
source_url=HttpUrl(decision_url),
|
||||
title=extracted_data["title"],
|
||||
decision_date=extracted_data["decision_date"],
|
||||
decision_number=extracted_data["decision_number"],
|
||||
subject_summary=extracted_data["subject_summary"],
|
||||
markdown_chunk=markdown_chunk,
|
||||
current_page=current_page_clamped,
|
||||
total_pages=total_pages,
|
||||
is_paginated=(total_pages > 1),
|
||||
error_message=None
|
||||
)
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
error_msg = f"HTTP error {e.response.status_code} when fetching decision document"
|
||||
logger.error(f"KvkkApiClient: {error_msg}")
|
||||
return KvkkDocumentMarkdown(
|
||||
source_url=HttpUrl(decision_url),
|
||||
title=None,
|
||||
decision_date=None,
|
||||
decision_number=None,
|
||||
subject_summary=None,
|
||||
markdown_chunk=None,
|
||||
current_page=page_number,
|
||||
total_pages=0,
|
||||
is_paginated=False,
|
||||
error_message=error_msg
|
||||
)
|
||||
except Exception as e:
|
||||
error_msg = f"Unexpected error when fetching decision document: {str(e)}"
|
||||
logger.error(f"KvkkApiClient: {error_msg}")
|
||||
return KvkkDocumentMarkdown(
|
||||
source_url=HttpUrl(decision_url),
|
||||
title=None,
|
||||
decision_date=None,
|
||||
decision_number=None,
|
||||
subject_summary=None,
|
||||
markdown_chunk=None,
|
||||
current_page=page_number,
|
||||
total_pages=0,
|
||||
is_paginated=False,
|
||||
error_message=error_msg
|
||||
)
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close the HTTP client session."""
|
||||
if hasattr(self, 'http_client') and self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("KvkkApiClient: HTTP client session closed.")
|
||||
@@ -1,49 +0,0 @@
|
||||
# kvkk_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl
|
||||
from typing import List, Optional, Any
|
||||
|
||||
class KvkkSearchRequest(BaseModel):
|
||||
"""Model for KVKK (Personal Data Protection Authority) search request via Brave API."""
|
||||
keywords: str = Field(..., description="""
|
||||
Keywords to search for in KVKK decisions.
|
||||
The search will automatically include 'site:kvkk.gov.tr "karar özeti"' to target KVKK decision summaries.
|
||||
Examples: "açık rıza", "veri güvenliği", "kişisel veri işleme"
|
||||
""")
|
||||
page: int = Field(1, ge=1, le=50, description="Page number for search results (1-50).")
|
||||
pageSize: int = Field(10, ge=1, le=10, description="Number of results per page (1-10).")
|
||||
|
||||
class KvkkDecisionSummary(BaseModel):
|
||||
"""Model for a single KVKK decision summary from Brave search results."""
|
||||
title: Optional[str] = Field(None, description="Decision title from search results.")
|
||||
url: Optional[HttpUrl] = Field(None, description="URL to the KVKK decision page.")
|
||||
description: Optional[str] = Field(None, description="Brief description or snippet from search results.")
|
||||
decision_id: Optional[str] = Field(None, description="Value")
|
||||
publication_date: Optional[str] = Field(None, description="Value")
|
||||
decision_number: Optional[str] = Field(None, description="Value")
|
||||
|
||||
class KvkkSearchResult(BaseModel):
|
||||
"""Model for the overall search result for KVKK decisions."""
|
||||
decisions: List[KvkkDecisionSummary] = Field(default_factory=list, description="List of KVKK decisions found.")
|
||||
total_results: Optional[int] = Field(None, description="Value")
|
||||
page: int = Field(1, description="Current page number of results.")
|
||||
pageSize: int = Field(10, description="Number of results per page.")
|
||||
query: Optional[str] = Field(None, description="The actual search query sent to Brave API.")
|
||||
|
||||
class KvkkDocumentMarkdown(BaseModel):
|
||||
"""Model for KVKK decision document content converted to paginated Markdown."""
|
||||
source_url: HttpUrl = Field(description="URL of the original KVKK decision page.")
|
||||
title: Optional[str] = Field(None, description="Title of the KVKK decision.")
|
||||
decision_date: Optional[str] = Field(None, description="Decision date (Karar Tarihi).")
|
||||
decision_number: Optional[str] = Field(None, description="Decision number (Karar No).")
|
||||
subject_summary: Optional[str] = Field(None, description="Subject summary (Konu Özeti).")
|
||||
markdown_chunk: Optional[str] = Field(None, description="A 5,000 character chunk of the Markdown content.")
|
||||
current_page: int = Field(description="The current page number of the markdown chunk (1-indexed).")
|
||||
total_pages: int = Field(description="Total number of pages for the full markdown content.")
|
||||
is_paginated: bool = Field(description="True if the full markdown content is split into multiple pages.")
|
||||
error_message: Optional[str] = Field(None, description="Value")
|
||||
|
||||
class Config:
|
||||
json_encoders = {
|
||||
HttpUrl: str
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
"""
|
||||
MCP Auth Toolkit - OAuth 2.1 + Authorization for Model Context Protocol Servers
|
||||
Integrated with Clerk Authentication
|
||||
"""
|
||||
|
||||
from .middleware import (
|
||||
AuthContext,
|
||||
FastMCPAuthWrapper,
|
||||
MCPAuthMiddleware,
|
||||
auth_required,
|
||||
)
|
||||
from .oauth import OAuthConfig, OAuthProvider
|
||||
from .policy import PolicyEngine, ToolPolicy, create_default_policies
|
||||
from .storage import PersistentStorage
|
||||
|
||||
__version__ = "0.1.0"
|
||||
__all__ = [
|
||||
"OAuthProvider",
|
||||
"OAuthConfig",
|
||||
"AuthContext",
|
||||
"auth_required",
|
||||
"create_default_policies",
|
||||
"MCPAuthMiddleware",
|
||||
"FastMCPAuthWrapper",
|
||||
"PolicyEngine",
|
||||
"ToolPolicy",
|
||||
"PersistentStorage",
|
||||
]
|
||||
@@ -1,73 +0,0 @@
|
||||
"""
|
||||
Clerk OAuth configuration for MCP Auth Toolkit
|
||||
"""
|
||||
|
||||
import os
|
||||
import logging
|
||||
from .oauth import OAuthConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def create_clerk_oauth_config() -> OAuthConfig:
|
||||
"""Create OAuth configuration for Clerk integration using SDK"""
|
||||
|
||||
# Get Clerk configuration from environment
|
||||
clerk_domain = os.getenv("CLERK_DOMAIN", "accounts.yargimcp.com")
|
||||
clerk_publishable_key = os.getenv("CLERK_PUBLISHABLE_KEY")
|
||||
clerk_secret_key = os.getenv("CLERK_SECRET_KEY")
|
||||
|
||||
if not clerk_publishable_key or not clerk_secret_key:
|
||||
raise ValueError("CLERK_PUBLISHABLE_KEY and CLERK_SECRET_KEY are required")
|
||||
|
||||
# For Clerk with custom domains, we use our adapter endpoints
|
||||
# This allows us to handle the custom domain flow properly
|
||||
base_url = os.getenv("BASE_URL", "https://yargimcp.com")
|
||||
|
||||
config = OAuthConfig(
|
||||
client_id=clerk_publishable_key,
|
||||
client_secret=clerk_secret_key,
|
||||
# Use our adapter endpoints instead of Clerk's direct endpoints
|
||||
authorization_endpoint=f"{base_url}/authorize",
|
||||
token_endpoint=f"{base_url}/token",
|
||||
# Keep Clerk's JWKS for token validation
|
||||
jwks_uri=f"https://{clerk_domain}/.well-known/jwks.json",
|
||||
issuer=base_url, # We're the issuer for MCP tokens
|
||||
scopes=["mcp:tools:read", "mcp:tools:write", "openid", "profile", "email"]
|
||||
)
|
||||
|
||||
logger.info(f"Created Clerk OAuth config with adapter endpoints")
|
||||
logger.info(f"Clerk domain: {clerk_domain}")
|
||||
logger.debug(f"Authorization endpoint: {config.authorization_endpoint}")
|
||||
logger.debug(f"Token endpoint: {config.token_endpoint}")
|
||||
|
||||
return config
|
||||
|
||||
|
||||
def get_jwt_secret() -> str:
|
||||
"""Get JWT secret for token signing"""
|
||||
jwt_secret = os.getenv("JWT_SECRET_KEY")
|
||||
|
||||
if not jwt_secret:
|
||||
raise ValueError("JWT_SECRET_KEY environment variable is required")
|
||||
|
||||
return jwt_secret
|
||||
|
||||
|
||||
def create_mcp_server_config():
|
||||
"""Create complete MCP server configuration for Clerk integration"""
|
||||
|
||||
try:
|
||||
oauth_config = create_clerk_oauth_config()
|
||||
jwt_secret = get_jwt_secret()
|
||||
|
||||
return {
|
||||
"oauth_config": oauth_config,
|
||||
"jwt_secret": jwt_secret,
|
||||
"base_url": os.getenv("BASE_URL", "https://yargi-mcp.fly.dev"),
|
||||
"auth_enabled": os.getenv("ENABLE_AUTH", "true").lower() == "true"
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create MCP server config: {e}")
|
||||
raise
|
||||
@@ -1,315 +0,0 @@
|
||||
"""
|
||||
MCP server middleware for OAuth authentication and authorization
|
||||
"""
|
||||
|
||||
import functools
|
||||
import logging
|
||||
from collections.abc import Callable
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
try:
|
||||
from fastmcp import FastMCP
|
||||
FASTMCP_AVAILABLE = True
|
||||
except ImportError:
|
||||
FASTMCP_AVAILABLE = False
|
||||
FastMCP = None
|
||||
logger.warning("FastMCP not available, some features will be disabled")
|
||||
|
||||
from .oauth import OAuthProvider
|
||||
from .policy import PolicyEngine
|
||||
|
||||
|
||||
@dataclass
|
||||
class AuthContext:
|
||||
"""Authentication context passed to MCP tools"""
|
||||
|
||||
user_id: str
|
||||
scopes: list[str]
|
||||
claims: dict[str, Any]
|
||||
token: str
|
||||
|
||||
|
||||
class MCPAuthMiddleware:
|
||||
"""Authentication middleware for MCP servers"""
|
||||
|
||||
def __init__(self, oauth_provider: OAuthProvider, policy_engine: PolicyEngine):
|
||||
self.oauth_provider = oauth_provider
|
||||
self.policy_engine = policy_engine
|
||||
|
||||
def authenticate_request(self, authorization_header: str) -> AuthContext | None:
|
||||
"""Extract and validate auth token from request"""
|
||||
|
||||
if not authorization_header:
|
||||
logger.debug("No authorization header provided")
|
||||
return None
|
||||
|
||||
if not authorization_header.startswith("Bearer "):
|
||||
logger.debug("Authorization header does not start with 'Bearer '")
|
||||
return None
|
||||
|
||||
token = authorization_header[7:] # Remove 'Bearer ' prefix
|
||||
|
||||
token_info = self.oauth_provider.introspect_token(token)
|
||||
|
||||
if not token_info.get("active"):
|
||||
logger.warning("Token is not active")
|
||||
return None
|
||||
|
||||
logger.debug(f"Authenticated user: {token_info.get('sub', 'unknown')}")
|
||||
|
||||
return AuthContext(
|
||||
user_id=token_info.get("sub", "unknown"),
|
||||
scopes=token_info.get("mcp_tool_scopes", []),
|
||||
claims=token_info,
|
||||
token=token,
|
||||
)
|
||||
|
||||
def authorize_tool_call(
|
||||
self, tool_name: str, auth_context: AuthContext
|
||||
) -> tuple[bool, str | None]:
|
||||
"""Check if user can call the specified tool"""
|
||||
|
||||
return self.policy_engine.authorize_tool_call(
|
||||
tool_name=tool_name,
|
||||
user_scopes=auth_context.scopes,
|
||||
user_claims=auth_context.claims,
|
||||
)
|
||||
|
||||
|
||||
def auth_required(
|
||||
oauth_provider: OAuthProvider,
|
||||
policy_engine: PolicyEngine,
|
||||
tool_name: str | None = None,
|
||||
):
|
||||
"""
|
||||
Decorator to require authentication for MCP tool functions
|
||||
|
||||
Usage:
|
||||
@auth_required(oauth_provider, policy_engine, "search_yargitay")
|
||||
def my_tool_function(context: AuthContext, ...):
|
||||
pass
|
||||
"""
|
||||
|
||||
def decorator(func: Callable) -> Callable:
|
||||
middleware = MCPAuthMiddleware(oauth_provider, policy_engine)
|
||||
|
||||
@functools.wraps(func)
|
||||
async def wrapper(*args, **kwargs):
|
||||
# Extract authorization header from kwargs
|
||||
auth_header = kwargs.pop("authorization", None)
|
||||
|
||||
# Also check in args if it's a Request object
|
||||
if not auth_header and args:
|
||||
for arg in args:
|
||||
if hasattr(arg, 'headers'):
|
||||
auth_header = arg.headers.get("Authorization")
|
||||
break
|
||||
|
||||
if not auth_header:
|
||||
logger.warning(f"No authorization header for tool '{tool_name or func.__name__}'")
|
||||
raise PermissionError("Authorization header required")
|
||||
|
||||
auth_context = middleware.authenticate_request(auth_header)
|
||||
|
||||
if not auth_context:
|
||||
logger.warning(f"Authentication failed for tool '{tool_name or func.__name__}'")
|
||||
raise PermissionError("Invalid or expired token")
|
||||
|
||||
actual_tool_name = tool_name or func.__name__
|
||||
|
||||
authorized, reason = middleware.authorize_tool_call(
|
||||
actual_tool_name, auth_context
|
||||
)
|
||||
|
||||
if not authorized:
|
||||
logger.warning(f"Authorization failed for tool '{actual_tool_name}': {reason}")
|
||||
raise PermissionError(f"Access denied: {reason}")
|
||||
|
||||
# Add auth context to function call
|
||||
return await func(auth_context, *args, **kwargs)
|
||||
|
||||
return wrapper
|
||||
|
||||
return decorator
|
||||
|
||||
|
||||
class FastMCPAuthWrapper:
|
||||
"""Wrapper for FastMCP servers to add authentication"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
mcp_server: "FastMCP",
|
||||
oauth_provider: OAuthProvider,
|
||||
policy_engine: PolicyEngine,
|
||||
):
|
||||
if not FASTMCP_AVAILABLE:
|
||||
raise ImportError("FastMCP is required for FastMCPAuthWrapper")
|
||||
|
||||
self.mcp_server = mcp_server
|
||||
self.middleware = MCPAuthMiddleware(oauth_provider, policy_engine)
|
||||
self.oauth_provider = oauth_provider
|
||||
logger.info("Initializing FastMCP authentication wrapper")
|
||||
self._wrap_tools()
|
||||
|
||||
def _wrap_tools(self):
|
||||
"""Wrap all existing tools with auth middleware"""
|
||||
|
||||
# Try different FastMCP tool storage locations
|
||||
tool_registry = None
|
||||
|
||||
if hasattr(self.mcp_server, '_tools'):
|
||||
tool_registry = self.mcp_server._tools
|
||||
elif hasattr(self.mcp_server, 'tools'):
|
||||
tool_registry = self.mcp_server.tools
|
||||
elif hasattr(self.mcp_server, '_tool_registry'):
|
||||
tool_registry = self.mcp_server._tool_registry
|
||||
elif hasattr(self.mcp_server, '_handlers') and hasattr(self.mcp_server._handlers, 'tools'):
|
||||
tool_registry = self.mcp_server._handlers.tools
|
||||
|
||||
if not tool_registry:
|
||||
logger.warning("FastMCP server tool registry not found, tools will not be automatically wrapped")
|
||||
logger.debug(f"Available server attributes: {dir(self.mcp_server)}")
|
||||
return
|
||||
|
||||
logger.debug(f"Found tool registry with {len(tool_registry)} tools")
|
||||
original_tools = dict(tool_registry)
|
||||
wrapped_count = 0
|
||||
|
||||
for tool_name, tool_func in original_tools.items():
|
||||
try:
|
||||
wrapped_func = self._create_auth_wrapper(tool_name, tool_func)
|
||||
tool_registry[tool_name] = wrapped_func
|
||||
wrapped_count += 1
|
||||
logger.debug(f"Wrapped tool: {tool_name}")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to wrap tool {tool_name}: {e}")
|
||||
|
||||
logger.info(f"Successfully wrapped {wrapped_count} tools with authentication")
|
||||
|
||||
def _create_auth_wrapper(self, tool_name: str, original_func: Callable) -> Callable:
|
||||
"""Create auth wrapper for a specific tool"""
|
||||
|
||||
@functools.wraps(original_func)
|
||||
async def auth_wrapper(*args, **kwargs):
|
||||
# Extract authorization from various sources
|
||||
auth_header = None
|
||||
|
||||
# Check kwargs first
|
||||
auth_header = kwargs.pop("authorization", None)
|
||||
|
||||
# Check if first argument is a Request object
|
||||
if not auth_header and args:
|
||||
first_arg = args[0]
|
||||
if hasattr(first_arg, 'headers'):
|
||||
auth_header = first_arg.headers.get("Authorization")
|
||||
|
||||
if not auth_header:
|
||||
logger.warning(f"No authorization header for tool '{tool_name}'")
|
||||
raise PermissionError("Authorization required")
|
||||
|
||||
auth_context = self.middleware.authenticate_request(auth_header)
|
||||
|
||||
if not auth_context:
|
||||
logger.warning(f"Authentication failed for tool '{tool_name}'")
|
||||
raise PermissionError("Invalid token")
|
||||
|
||||
authorized, reason = self.middleware.authorize_tool_call(
|
||||
tool_name, auth_context
|
||||
)
|
||||
|
||||
if not authorized:
|
||||
logger.warning(f"Authorization failed for tool '{tool_name}': {reason}")
|
||||
raise PermissionError(f"Access denied: {reason}")
|
||||
|
||||
# Add auth context to kwargs
|
||||
kwargs["auth_context"] = auth_context
|
||||
logger.debug(f"Calling tool '{tool_name}' for user {auth_context.user_id}")
|
||||
|
||||
return await original_func(*args, **kwargs)
|
||||
|
||||
return auth_wrapper
|
||||
|
||||
def add_oauth_endpoints(self):
|
||||
"""Add OAuth endpoints to the MCP server"""
|
||||
|
||||
@self.mcp_server.tool(
|
||||
description="Initiate OAuth 2.1 authorization flow with PKCE",
|
||||
annotations={"readOnlyHint": True, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_authorize(redirect_uri: str, scopes: Optional[str] = None):
|
||||
"""OAuth authorization endpoint"""
|
||||
scope_list = scopes.split(" ") if scopes else None
|
||||
auth_url, pkce = self.oauth_provider.generate_authorization_url(
|
||||
redirect_uri=redirect_uri, scopes=scope_list
|
||||
)
|
||||
logger.info(f"Generated authorization URL for redirect_uri: {redirect_uri}")
|
||||
return {
|
||||
"authorization_url": auth_url,
|
||||
"code_verifier": pkce.verifier, # For PKCE flow
|
||||
"code_challenge": pkce.challenge,
|
||||
"instructions": "Use the authorization_url to complete OAuth flow, then exchange the returned code using oauth_token tool"
|
||||
}
|
||||
|
||||
@self.mcp_server.tool(
|
||||
description="Exchange OAuth authorization code for access token",
|
||||
annotations={"readOnlyHint": False, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_token(
|
||||
code: str,
|
||||
state: str,
|
||||
redirect_uri: str
|
||||
):
|
||||
"""OAuth token exchange endpoint"""
|
||||
try:
|
||||
result = await self.oauth_provider.exchange_code_for_token(
|
||||
code=code, state=state, redirect_uri=redirect_uri
|
||||
)
|
||||
logger.info("Successfully exchanged authorization code for token")
|
||||
return result
|
||||
except Exception as e:
|
||||
logger.error(f"Token exchange failed: {e}")
|
||||
raise
|
||||
|
||||
@self.mcp_server.tool(
|
||||
description="Validate and introspect OAuth access token",
|
||||
annotations={"readOnlyHint": True, "idempotentHint": True}
|
||||
)
|
||||
async def oauth_introspect(token: str):
|
||||
"""Token introspection endpoint"""
|
||||
result = self.oauth_provider.introspect_token(token)
|
||||
logger.debug(f"Token introspection: active={result.get('active', False)}")
|
||||
return result
|
||||
|
||||
@self.mcp_server.tool(
|
||||
description="Revoke OAuth access token",
|
||||
annotations={"readOnlyHint": False, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_revoke(token: str):
|
||||
"""Token revocation endpoint"""
|
||||
success = self.oauth_provider.revoke_token(token)
|
||||
logger.info(f"Token revocation: success={success}")
|
||||
return {"revoked": success}
|
||||
|
||||
@self.mcp_server.tool(
|
||||
description="Get list of tools available to authenticated user",
|
||||
annotations={"readOnlyHint": True, "idempotentHint": True}
|
||||
)
|
||||
async def oauth_user_tools(authorization: str):
|
||||
"""Get user's allowed tools based on scopes"""
|
||||
auth_context = self.middleware.authenticate_request(authorization)
|
||||
if not auth_context:
|
||||
raise PermissionError("Invalid token")
|
||||
|
||||
allowed_patterns = self.middleware.policy_engine.get_allowed_tools(auth_context.scopes)
|
||||
|
||||
return {
|
||||
"user_id": auth_context.user_id,
|
||||
"scopes": auth_context.scopes,
|
||||
"allowed_tool_patterns": allowed_patterns,
|
||||
"message": "Use these patterns to determine which tools you can access"
|
||||
}
|
||||
|
||||
logger.info("Added OAuth endpoints: oauth_authorize, oauth_token, oauth_introspect, oauth_revoke, oauth_user_tools")
|
||||
@@ -1,304 +0,0 @@
|
||||
"""
|
||||
OAuth 2.1 + PKCE implementation for MCP servers with Clerk integration
|
||||
"""
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import secrets
|
||||
import time
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Any, Optional
|
||||
from urllib.parse import urlencode
|
||||
|
||||
import httpx
|
||||
import jwt
|
||||
from jwt.exceptions import PyJWTError, InvalidTokenError
|
||||
|
||||
from .storage import PersistentStorage
|
||||
|
||||
# Try to import Clerk SDK
|
||||
try:
|
||||
from clerk_backend_api import Clerk
|
||||
CLERK_AVAILABLE = True
|
||||
except ImportError:
|
||||
CLERK_AVAILABLE = False
|
||||
Clerk = None
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class OAuthConfig:
|
||||
"""OAuth provider configuration for Clerk"""
|
||||
|
||||
client_id: str
|
||||
client_secret: str
|
||||
authorization_endpoint: str
|
||||
token_endpoint: str
|
||||
jwks_uri: str | None = None
|
||||
issuer: str = "mcp-auth"
|
||||
scopes: list[str] = None
|
||||
|
||||
def __post_init__(self):
|
||||
if self.scopes is None:
|
||||
self.scopes = ["mcp:tools:read", "mcp:tools:write"]
|
||||
|
||||
|
||||
class PKCEChallenge:
|
||||
"""PKCE challenge/verifier pair for OAuth 2.1"""
|
||||
|
||||
def __init__(self):
|
||||
self.verifier = (
|
||||
base64.urlsafe_b64encode(secrets.token_bytes(32))
|
||||
.decode("utf-8")
|
||||
.rstrip("=")
|
||||
)
|
||||
|
||||
challenge_bytes = hashlib.sha256(self.verifier.encode("utf-8")).digest()
|
||||
self.challenge = (
|
||||
base64.urlsafe_b64encode(challenge_bytes).decode("utf-8").rstrip("=")
|
||||
)
|
||||
|
||||
|
||||
class OAuthProvider:
|
||||
"""OAuth 2.1 provider with PKCE support and Clerk integration"""
|
||||
|
||||
def __init__(self, config: OAuthConfig, jwt_secret: str):
|
||||
self.config = config
|
||||
self.jwt_secret = jwt_secret
|
||||
# Use persistent storage instead of memory
|
||||
self.storage = PersistentStorage()
|
||||
|
||||
# Initialize Clerk SDK if available
|
||||
self.clerk = None
|
||||
if CLERK_AVAILABLE and config.client_secret:
|
||||
try:
|
||||
self.clerk = Clerk(bearer_auth=config.client_secret)
|
||||
logger.info("Clerk SDK initialized successfully")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to initialize Clerk SDK: {e}")
|
||||
|
||||
logger.info("OAuth provider initialized with persistent storage")
|
||||
|
||||
def generate_authorization_url(
|
||||
self,
|
||||
redirect_uri: str,
|
||||
state: str | None = None,
|
||||
scopes: list[str] | None = None,
|
||||
) -> tuple[str, PKCEChallenge]:
|
||||
"""Generate OAuth authorization URL with PKCE for Clerk"""
|
||||
|
||||
pkce = PKCEChallenge()
|
||||
session_id = secrets.token_urlsafe(32)
|
||||
|
||||
if state is None:
|
||||
state = secrets.token_urlsafe(16)
|
||||
|
||||
if scopes is None:
|
||||
scopes = self.config.scopes
|
||||
|
||||
# Store session data with expiration
|
||||
session_data = {
|
||||
"pkce_verifier": pkce.verifier,
|
||||
"state": state,
|
||||
"redirect_uri": redirect_uri,
|
||||
"scopes": scopes,
|
||||
"created_at": time.time(),
|
||||
"expires_at": (datetime.utcnow() + timedelta(minutes=10)).timestamp(),
|
||||
}
|
||||
self.storage.set_session(session_id, session_data)
|
||||
|
||||
# Build Clerk OAuth URL
|
||||
# Check if this is a custom domain (sign-in endpoint)
|
||||
if self.config.authorization_endpoint.endswith('/sign-in'):
|
||||
# For custom domains, Clerk expects redirect_url parameter
|
||||
params = {
|
||||
"redirect_url": redirect_uri,
|
||||
"state": f"{state}:{session_id}",
|
||||
}
|
||||
auth_url = f"{self.config.authorization_endpoint}?{urlencode(params)}"
|
||||
else:
|
||||
# Standard OAuth flow with PKCE
|
||||
params = {
|
||||
"response_type": "code",
|
||||
"client_id": self.config.client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"scope": " ".join(scopes),
|
||||
"state": f"{state}:{session_id}", # Combine state with session ID
|
||||
"code_challenge": pkce.challenge,
|
||||
"code_challenge_method": "S256",
|
||||
}
|
||||
auth_url = f"{self.config.authorization_endpoint}?{urlencode(params)}"
|
||||
|
||||
logger.info(f"Generated OAuth URL with session {session_id[:8]}...")
|
||||
logger.debug(f"Auth URL: {auth_url}")
|
||||
return auth_url, pkce
|
||||
|
||||
async def exchange_code_for_token(
|
||||
self, code: str, state: str, redirect_uri: str
|
||||
) -> dict[str, Any]:
|
||||
"""Exchange authorization code for access token with Clerk"""
|
||||
|
||||
try:
|
||||
original_state, session_id = state.split(":", 1)
|
||||
except ValueError as e:
|
||||
logger.error(f"Invalid state format: {state}")
|
||||
raise ValueError("Invalid state format") from e
|
||||
|
||||
session = self.storage.get_session(session_id)
|
||||
if not session:
|
||||
logger.error(f"Session {session_id} not found")
|
||||
raise ValueError("Invalid session")
|
||||
|
||||
# Check session expiration
|
||||
if datetime.utcnow().timestamp() > session.get("expires_at", 0):
|
||||
self.storage.delete_session(session_id)
|
||||
logger.error(f"Session {session_id} expired")
|
||||
raise ValueError("Session expired")
|
||||
|
||||
if session["state"] != original_state:
|
||||
logger.error(f"State mismatch: expected {session['state']}, got {original_state}")
|
||||
raise ValueError("State mismatch")
|
||||
|
||||
if session["redirect_uri"] != redirect_uri:
|
||||
logger.error(f"Redirect URI mismatch: expected {session['redirect_uri']}, got {redirect_uri}")
|
||||
raise ValueError("Redirect URI mismatch")
|
||||
|
||||
# Prepare token exchange request for Clerk
|
||||
token_data = {
|
||||
"grant_type": "authorization_code",
|
||||
"client_id": self.config.client_id,
|
||||
"client_secret": self.config.client_secret,
|
||||
"code": code,
|
||||
"redirect_uri": redirect_uri,
|
||||
"code_verifier": session["pkce_verifier"],
|
||||
}
|
||||
|
||||
logger.info(f"Exchanging code with Clerk for session {session_id[:8]}...")
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.post(
|
||||
self.config.token_endpoint,
|
||||
data=token_data,
|
||||
headers={"Content-Type": "application/x-www-form-urlencoded"},
|
||||
timeout=30.0,
|
||||
)
|
||||
|
||||
if response.status_code != 200:
|
||||
logger.error(f"Clerk token exchange failed: {response.status_code} - {response.text}")
|
||||
raise ValueError(f"Token exchange failed: {response.text}")
|
||||
|
||||
token_response = response.json()
|
||||
logger.info("Successfully exchanged code for Clerk token")
|
||||
|
||||
# Create MCP-scoped JWT token
|
||||
access_token = self._create_mcp_token(
|
||||
session["scopes"], token_response.get("access_token"), session_id
|
||||
)
|
||||
|
||||
# Store token for introspection
|
||||
token_id = secrets.token_urlsafe(16)
|
||||
token_data = {
|
||||
"access_token": access_token,
|
||||
"scopes": session["scopes"],
|
||||
"created_at": time.time(),
|
||||
"expires_at": (datetime.utcnow() + timedelta(hours=1)).timestamp(),
|
||||
"session_id": session_id,
|
||||
"clerk_token": token_response.get("access_token"),
|
||||
}
|
||||
self.storage.set_token(token_id, token_data)
|
||||
|
||||
# Clean up session
|
||||
self.storage.delete_session(session_id)
|
||||
|
||||
return {
|
||||
"access_token": access_token,
|
||||
"token_type": "bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": " ".join(session["scopes"]),
|
||||
}
|
||||
|
||||
def validate_pkce(self, code_verifier: str, code_challenge: str) -> bool:
|
||||
"""Validate PKCE code challenge (RFC 7636)"""
|
||||
# S256 method
|
||||
verifier_hash = hashlib.sha256(code_verifier.encode()).digest()
|
||||
expected_challenge = base64.urlsafe_b64encode(verifier_hash).decode().rstrip('=')
|
||||
return expected_challenge == code_challenge
|
||||
|
||||
def _create_mcp_token(
|
||||
self, scopes: list[str], upstream_token: str, session_id: str
|
||||
) -> str:
|
||||
"""Create MCP-scoped JWT token with Clerk token embedded"""
|
||||
|
||||
now = int(time.time())
|
||||
payload = {
|
||||
"iss": self.config.issuer,
|
||||
"sub": session_id,
|
||||
"aud": "mcp-server",
|
||||
"iat": now,
|
||||
"exp": now + 3600, # 1 hour expiration
|
||||
"mcp_tool_scopes": scopes,
|
||||
"upstream_token": upstream_token,
|
||||
"clerk_integration": True,
|
||||
}
|
||||
|
||||
return jwt.encode(payload, self.jwt_secret, algorithm="HS256")
|
||||
|
||||
def introspect_token(self, token: str) -> dict[str, Any]:
|
||||
"""Introspect and validate MCP token"""
|
||||
|
||||
try:
|
||||
payload = jwt.decode(token, self.jwt_secret, algorithms=["HS256"])
|
||||
|
||||
# Check if token is expired
|
||||
if payload.get("exp", 0) < time.time():
|
||||
return {"active": False, "error": "token_expired"}
|
||||
|
||||
return {
|
||||
"active": True,
|
||||
"sub": payload.get("sub"),
|
||||
"aud": payload.get("aud"),
|
||||
"iss": payload.get("iss"),
|
||||
"exp": payload.get("exp"),
|
||||
"iat": payload.get("iat"),
|
||||
"mcp_tool_scopes": payload.get("mcp_tool_scopes", []),
|
||||
"upstream_token": payload.get("upstream_token"),
|
||||
"clerk_integration": payload.get("clerk_integration", False),
|
||||
}
|
||||
|
||||
except PyJWTError as e:
|
||||
logger.warning(f"Token validation failed: {e}")
|
||||
return {"active": False, "error": "invalid_token"}
|
||||
|
||||
def revoke_token(self, token: str) -> bool:
|
||||
"""Revoke a token"""
|
||||
|
||||
try:
|
||||
payload = jwt.decode(token, self.jwt_secret, algorithms=["HS256"])
|
||||
session_id = payload.get("sub")
|
||||
|
||||
# Remove all tokens associated with this session
|
||||
all_tokens = self.storage.get_tokens()
|
||||
tokens_to_remove = [
|
||||
token_id
|
||||
for token_id, token_data in all_tokens.items()
|
||||
if token_data.get("session_id") == session_id
|
||||
]
|
||||
|
||||
for token_id in tokens_to_remove:
|
||||
self.storage.delete_token(token_id)
|
||||
|
||||
logger.info(f"Revoked {len(tokens_to_remove)} tokens for session {session_id}")
|
||||
return True
|
||||
|
||||
except InvalidTokenError as e:
|
||||
logger.warning(f"Token revocation failed: {e}")
|
||||
return False
|
||||
|
||||
def cleanup_expired_sessions(self):
|
||||
"""Clean up expired sessions and tokens"""
|
||||
# This is now handled automatically by persistent storage
|
||||
self.storage.cleanup_expired_sessions()
|
||||
logger.debug("Cleanup completed via persistent storage")
|
||||
@@ -1,201 +0,0 @@
|
||||
"""
|
||||
Authorization policy engine for MCP tools
|
||||
"""
|
||||
|
||||
import re
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class PolicyAction(Enum):
|
||||
ALLOW = "allow"
|
||||
DENY = "deny"
|
||||
|
||||
|
||||
@dataclass
|
||||
class ToolPolicy:
|
||||
"""Policy rule for MCP tool access"""
|
||||
|
||||
tool_pattern: str # regex pattern for tool names
|
||||
required_scopes: list[str]
|
||||
action: PolicyAction = PolicyAction.ALLOW
|
||||
conditions: dict[str, Any] | None = None
|
||||
|
||||
def matches_tool(self, tool_name: str) -> bool:
|
||||
"""Check if the policy applies to given tool"""
|
||||
return bool(re.match(self.tool_pattern, tool_name))
|
||||
|
||||
def evaluate_scopes(self, user_scopes: list[str]) -> bool:
|
||||
"""Check if user has required scopes"""
|
||||
return all(scope in user_scopes for scope in self.required_scopes)
|
||||
|
||||
|
||||
class PolicyEngine:
|
||||
"""Authorization policy engine for Turkish legal database tools"""
|
||||
|
||||
def __init__(self):
|
||||
self.policies: list[ToolPolicy] = []
|
||||
self.default_action = PolicyAction.DENY
|
||||
|
||||
def add_policy(self, policy: ToolPolicy):
|
||||
"""Add a policy rule"""
|
||||
self.policies.append(policy)
|
||||
logger.debug(f"Added policy: {policy.tool_pattern} -> {policy.required_scopes}")
|
||||
|
||||
def add_tool_scope_policy(
|
||||
self,
|
||||
tool_pattern: str,
|
||||
required_scopes: str | list[str],
|
||||
action: PolicyAction = PolicyAction.ALLOW,
|
||||
):
|
||||
"""Convenience method to add tool-scope policy"""
|
||||
if isinstance(required_scopes, str):
|
||||
required_scopes = [required_scopes]
|
||||
|
||||
policy = ToolPolicy(
|
||||
tool_pattern=tool_pattern, required_scopes=required_scopes, action=action
|
||||
)
|
||||
self.add_policy(policy)
|
||||
|
||||
def authorize_tool_call(
|
||||
self,
|
||||
tool_name: str,
|
||||
user_scopes: list[str],
|
||||
user_claims: dict[str, Any] | None = None,
|
||||
) -> tuple[bool, str | None]:
|
||||
"""
|
||||
Authorize a tool call
|
||||
|
||||
Returns:
|
||||
(authorized: bool, reason: Optional[str])
|
||||
"""
|
||||
|
||||
logger.debug(f"Authorizing tool '{tool_name}' for user with scopes: {user_scopes}")
|
||||
|
||||
matching_policies = [
|
||||
policy for policy in self.policies if policy.matches_tool(tool_name)
|
||||
]
|
||||
|
||||
if not matching_policies:
|
||||
if self.default_action == PolicyAction.ALLOW:
|
||||
logger.debug(f"No policies found for '{tool_name}', allowing by default")
|
||||
return True, None
|
||||
else:
|
||||
logger.warning(f"No policies found for '{tool_name}', denying by default")
|
||||
return False, f"No policy found for tool '{tool_name}', default deny"
|
||||
|
||||
# Check for explicit deny policies first
|
||||
for policy in matching_policies:
|
||||
if policy.action == PolicyAction.DENY:
|
||||
if policy.evaluate_scopes(user_scopes):
|
||||
logger.warning(f"Explicit deny policy matched for '{tool_name}'")
|
||||
return False, f"Explicit deny policy for tool '{tool_name}'"
|
||||
|
||||
# Check allow policies
|
||||
allow_policies = [
|
||||
p for p in matching_policies if p.action == PolicyAction.ALLOW
|
||||
]
|
||||
|
||||
if not allow_policies:
|
||||
logger.warning(f"No allow policies found for '{tool_name}'")
|
||||
return False, f"No allow policies found for tool '{tool_name}'"
|
||||
|
||||
for policy in allow_policies:
|
||||
if policy.evaluate_scopes(user_scopes):
|
||||
if self._evaluate_conditions(policy.conditions, user_claims):
|
||||
logger.debug(f"Authorization granted for '{tool_name}'")
|
||||
return True, None
|
||||
|
||||
logger.warning(f"Insufficient scopes for '{tool_name}'. Required: {[p.required_scopes for p in allow_policies]}, User has: {user_scopes}")
|
||||
return False, f"Insufficient scopes for tool '{tool_name}'"
|
||||
|
||||
def _evaluate_conditions(
|
||||
self,
|
||||
conditions: dict[str, Any] | None,
|
||||
user_claims: dict[str, Any] | None,
|
||||
) -> bool:
|
||||
"""Evaluate additional policy conditions"""
|
||||
|
||||
if not conditions:
|
||||
return True
|
||||
|
||||
if not user_claims:
|
||||
logger.debug("No user claims provided, conditions evaluation failed")
|
||||
return False
|
||||
|
||||
for key, expected_value in conditions.items():
|
||||
user_value = user_claims.get(key)
|
||||
|
||||
if isinstance(expected_value, list):
|
||||
if user_value not in expected_value:
|
||||
logger.debug(f"Condition failed: {key} = {user_value} not in {expected_value}")
|
||||
return False
|
||||
elif user_value != expected_value:
|
||||
logger.debug(f"Condition failed: {key} = {user_value} != {expected_value}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def get_allowed_tools(self, user_scopes: list[str]) -> list[str]:
|
||||
"""Get list of tool patterns user is allowed to call"""
|
||||
|
||||
allowed_tools = []
|
||||
|
||||
for policy in self.policies:
|
||||
if policy.action == PolicyAction.ALLOW and policy.evaluate_scopes(
|
||||
user_scopes
|
||||
):
|
||||
allowed_tools.append(policy.tool_pattern)
|
||||
|
||||
return allowed_tools
|
||||
|
||||
|
||||
def create_turkish_legal_policies() -> PolicyEngine:
|
||||
"""Create policy set for Turkish legal database MCP server"""
|
||||
|
||||
engine = PolicyEngine()
|
||||
|
||||
# Administrative tools (full access)
|
||||
engine.add_tool_scope_policy(".*", ["mcp:tools:admin"])
|
||||
|
||||
# Search tools - require read access
|
||||
engine.add_tool_scope_policy("search.*", ["mcp:tools:read"])
|
||||
|
||||
# Fetch/get document tools - require read access
|
||||
engine.add_tool_scope_policy("get_.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("fetch.*", ["mcp:tools:read"])
|
||||
|
||||
# Specific Turkish legal database tools
|
||||
engine.add_tool_scope_policy("search_yargitay.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_danistay.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_anayasa.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_rekabet.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_kik.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_emsal.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_uyusmazlik.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_sayistay.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_.*_bedesten", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_yerel_hukuk.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_istinaf_hukuk.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("search_kyb.*", ["mcp:tools:read"])
|
||||
|
||||
# Document retrieval tools
|
||||
engine.add_tool_scope_policy("get_.*_document.*", ["mcp:tools:read"])
|
||||
engine.add_tool_scope_policy("get_.*_markdown", ["mcp:tools:read"])
|
||||
|
||||
# Write operations (if any future tools need them)
|
||||
engine.add_tool_scope_policy("create_.*", ["mcp:tools:write"])
|
||||
engine.add_tool_scope_policy("update_.*", ["mcp:tools:write"])
|
||||
engine.add_tool_scope_policy("delete_.*", ["mcp:tools:write"])
|
||||
|
||||
logger.info("Created Turkish legal database policy engine")
|
||||
return engine
|
||||
|
||||
|
||||
def create_default_policies() -> PolicyEngine:
|
||||
"""Create a default policy set for MCP servers (backwards compatibility)"""
|
||||
return create_turkish_legal_policies()
|
||||
@@ -1,112 +0,0 @@
|
||||
"""
|
||||
Persistent storage for OAuth sessions and tokens
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import tempfile
|
||||
import logging
|
||||
from datetime import datetime
|
||||
from typing import Dict, Any, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class PersistentStorage:
|
||||
"""File-based persistent storage for OAuth data"""
|
||||
|
||||
def __init__(self, storage_dir: str = None):
|
||||
if storage_dir is None:
|
||||
# Use system temp directory or environment variable
|
||||
storage_dir = os.environ.get('TEMP', tempfile.gettempdir())
|
||||
|
||||
self.storage_dir = os.path.join(storage_dir, 'mcp_oauth_storage')
|
||||
os.makedirs(self.storage_dir, exist_ok=True)
|
||||
|
||||
self.sessions_file = os.path.join(self.storage_dir, 'oauth_sessions.json')
|
||||
self.tokens_file = os.path.join(self.storage_dir, 'oauth_tokens.json')
|
||||
|
||||
logger.info(f"Persistent OAuth storage initialized at: {self.storage_dir}")
|
||||
|
||||
def _load_json(self, filepath: str) -> Dict:
|
||||
"""Load JSON data from file"""
|
||||
try:
|
||||
if os.path.exists(filepath):
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading {filepath}: {e}")
|
||||
return {}
|
||||
|
||||
def _save_json(self, filepath: str, data: Dict):
|
||||
"""Save JSON data to file"""
|
||||
try:
|
||||
with open(filepath, 'w', encoding='utf-8') as f:
|
||||
json.dump(data, f, indent=2, default=str)
|
||||
except Exception as e:
|
||||
logger.error(f"Error saving {filepath}: {e}")
|
||||
|
||||
def get_sessions(self) -> Dict[str, Dict[str, Any]]:
|
||||
"""Get all OAuth sessions"""
|
||||
data = self._load_json(self.sessions_file)
|
||||
# Clean expired sessions
|
||||
now = datetime.utcnow().timestamp()
|
||||
valid_sessions = {k: v for k, v in data.items()
|
||||
if v.get('expires_at', 0) > now}
|
||||
if len(valid_sessions) != len(data):
|
||||
self._save_json(self.sessions_file, valid_sessions)
|
||||
return valid_sessions
|
||||
|
||||
def set_session(self, session_id: str, data: Dict[str, Any]):
|
||||
"""Set OAuth session data"""
|
||||
sessions = self.get_sessions()
|
||||
sessions[session_id] = data
|
||||
self._save_json(self.sessions_file, sessions)
|
||||
|
||||
def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get specific OAuth session data"""
|
||||
sessions = self.get_sessions()
|
||||
return sessions.get(session_id)
|
||||
|
||||
def delete_session(self, session_id: str):
|
||||
"""Delete OAuth session"""
|
||||
sessions = self.get_sessions()
|
||||
if session_id in sessions:
|
||||
del sessions[session_id]
|
||||
self._save_json(self.sessions_file, sessions)
|
||||
|
||||
def get_tokens(self) -> Dict[str, Dict[str, Any]]:
|
||||
"""Get all OAuth tokens"""
|
||||
data = self._load_json(self.tokens_file)
|
||||
# Clean expired tokens
|
||||
now = datetime.utcnow().timestamp()
|
||||
valid_tokens = {k: v for k, v in data.items()
|
||||
if v.get('expires_at', 0) > now}
|
||||
if len(valid_tokens) != len(data):
|
||||
self._save_json(self.tokens_file, valid_tokens)
|
||||
return valid_tokens
|
||||
|
||||
def set_token(self, token_id: str, token_data: Dict[str, Any]):
|
||||
"""Set OAuth token data"""
|
||||
tokens = self.get_tokens()
|
||||
tokens[token_id] = token_data
|
||||
self._save_json(self.tokens_file, tokens)
|
||||
|
||||
def get_token(self, token_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get specific OAuth token data"""
|
||||
tokens = self.get_tokens()
|
||||
return tokens.get(token_id)
|
||||
|
||||
def delete_token(self, token_id: str):
|
||||
"""Delete OAuth token"""
|
||||
tokens = self.get_tokens()
|
||||
if token_id in tokens:
|
||||
del tokens[token_id]
|
||||
self._save_json(self.tokens_file, tokens)
|
||||
|
||||
def cleanup_expired_sessions(self):
|
||||
"""Clean up expired sessions and tokens"""
|
||||
# This is handled automatically in get_sessions() and get_tokens()
|
||||
sessions = self.get_sessions()
|
||||
tokens = self.get_tokens()
|
||||
logger.debug(f"Cleanup: {len(sessions)} active sessions, {len(tokens)} active tokens")
|
||||
@@ -1,193 +0,0 @@
|
||||
"""
|
||||
Factory for creating FastMCP app with MCP Auth Toolkit integration
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
try:
|
||||
from fastmcp import FastMCP
|
||||
FASTMCP_AVAILABLE = True
|
||||
except ImportError:
|
||||
FASTMCP_AVAILABLE = False
|
||||
FastMCP = None
|
||||
|
||||
from mcp_auth import (
|
||||
OAuthProvider,
|
||||
PolicyEngine,
|
||||
FastMCPAuthWrapper,
|
||||
create_default_policies
|
||||
)
|
||||
from mcp_auth.clerk_config import create_mcp_server_config
|
||||
|
||||
|
||||
def create_auth_enabled_app(app_name: str = "Yargı MCP Server") -> FastMCP:
|
||||
"""Create FastMCP app with authentication enabled"""
|
||||
|
||||
if not FASTMCP_AVAILABLE:
|
||||
raise ImportError("FastMCP is required for authenticated MCP server")
|
||||
|
||||
logger.info("Creating FastMCP app with MCP Auth Toolkit integration")
|
||||
|
||||
# Create base FastMCP app
|
||||
app = FastMCP(app_name)
|
||||
|
||||
# Check if authentication is enabled
|
||||
auth_enabled = os.getenv("ENABLE_AUTH", "true").lower() == "true"
|
||||
|
||||
if not auth_enabled:
|
||||
logger.info("Authentication disabled, returning basic FastMCP app")
|
||||
return app
|
||||
|
||||
try:
|
||||
# Get configuration
|
||||
logger.info("Getting MCP server configuration...")
|
||||
config = create_mcp_server_config()
|
||||
logger.info("Configuration loaded successfully")
|
||||
|
||||
# Create OAuth provider with Clerk config
|
||||
logger.info("Creating OAuth provider...")
|
||||
oauth_provider = OAuthProvider(
|
||||
config=config["oauth_config"],
|
||||
jwt_secret=config["jwt_secret"]
|
||||
)
|
||||
logger.info("OAuth provider created successfully")
|
||||
|
||||
# Create policy engine for Turkish legal database
|
||||
policy_engine = create_default_policies()
|
||||
|
||||
# Store auth components for later wrapping (after tools are defined)
|
||||
app._oauth_provider = oauth_provider
|
||||
app._policy_engine = policy_engine
|
||||
app._auth_config = config
|
||||
|
||||
# Add OAuth endpoints immediately
|
||||
@app.tool(
|
||||
description="Initiate OAuth 2.1 authorization flow with PKCE",
|
||||
annotations={"readOnlyHint": True, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_authorize(redirect_uri: str, scopes: str = None):
|
||||
"""OAuth authorization endpoint"""
|
||||
scope_list = scopes.split(" ") if scopes else ["mcp:tools:read", "mcp:tools:write"]
|
||||
auth_url, pkce = oauth_provider.generate_authorization_url(
|
||||
redirect_uri=redirect_uri, scopes=scope_list
|
||||
)
|
||||
logger.info(f"Generated authorization URL for redirect_uri: {redirect_uri}")
|
||||
return {
|
||||
"authorization_url": auth_url,
|
||||
"code_verifier": pkce.verifier,
|
||||
"code_challenge": pkce.challenge,
|
||||
"instructions": "Use the authorization_url to complete OAuth flow, then exchange the returned code using oauth_token tool"
|
||||
}
|
||||
|
||||
@app.tool(
|
||||
description="Exchange OAuth authorization code for access token",
|
||||
annotations={"readOnlyHint": False, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_token(code: str, state: str, redirect_uri: str):
|
||||
"""OAuth token exchange endpoint"""
|
||||
try:
|
||||
result = await oauth_provider.exchange_code_for_token(
|
||||
code=code, state=state, redirect_uri=redirect_uri
|
||||
)
|
||||
logger.info("Successfully exchanged authorization code for token")
|
||||
return result
|
||||
except Exception as e:
|
||||
logger.error(f"Token exchange failed: {e}")
|
||||
raise
|
||||
|
||||
@app.tool(
|
||||
description="Validate and introspect OAuth access token",
|
||||
annotations={"readOnlyHint": True, "idempotentHint": True}
|
||||
)
|
||||
async def oauth_introspect(token: str):
|
||||
"""Token introspection endpoint"""
|
||||
result = oauth_provider.introspect_token(token)
|
||||
logger.debug(f"Token introspection: active={result.get('active', False)}")
|
||||
return result
|
||||
|
||||
@app.tool(
|
||||
description="Revoke OAuth access token",
|
||||
annotations={"readOnlyHint": False, "idempotentHint": False}
|
||||
)
|
||||
async def oauth_revoke(token: str):
|
||||
"""Token revocation endpoint"""
|
||||
success = oauth_provider.revoke_token(token)
|
||||
logger.info(f"Token revocation: success={success}")
|
||||
return {"revoked": success}
|
||||
|
||||
logger.info("Successfully created authenticated FastMCP app")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create authenticated app: {e}")
|
||||
logger.info("Falling back to non-authenticated FastMCP app")
|
||||
# Return basic app if auth setup fails
|
||||
return app
|
||||
|
||||
return app
|
||||
|
||||
|
||||
def create_app() -> FastMCP:
|
||||
"""Create FastMCP app (backwards compatible with mcp_factory.py)"""
|
||||
return create_auth_enabled_app()
|
||||
|
||||
|
||||
def get_auth_wrapper(app: FastMCP) -> Optional[FastMCPAuthWrapper]:
|
||||
"""Get auth wrapper from app if available"""
|
||||
return getattr(app, '_auth_wrapper', None)
|
||||
|
||||
|
||||
def get_oauth_provider(app: FastMCP) -> Optional[OAuthProvider]:
|
||||
"""Get OAuth provider from app if available"""
|
||||
return getattr(app, '_oauth_provider', None)
|
||||
|
||||
|
||||
def get_policy_engine(app: FastMCP) -> Optional[PolicyEngine]:
|
||||
"""Get policy engine from app if available"""
|
||||
return getattr(app, '_policy_engine', None)
|
||||
|
||||
|
||||
def is_auth_enabled(app: FastMCP) -> bool:
|
||||
"""Check if authentication is enabled for the app"""
|
||||
return hasattr(app, '_oauth_provider') or hasattr(app, '_auth_wrapper')
|
||||
|
||||
|
||||
def enable_tool_authentication(app: FastMCP):
|
||||
"""Enable authentication on all existing tools (call after tools are defined)"""
|
||||
if not is_auth_enabled(app):
|
||||
logger.debug("Authentication not enabled, skipping tool authentication")
|
||||
return
|
||||
|
||||
oauth_provider = get_oauth_provider(app)
|
||||
policy_engine = get_policy_engine(app)
|
||||
|
||||
if not oauth_provider or not policy_engine:
|
||||
logger.warning("OAuth provider or policy engine not available")
|
||||
return
|
||||
|
||||
try:
|
||||
# Create auth wrapper and wrap tools
|
||||
auth_wrapper = FastMCPAuthWrapper(
|
||||
mcp_server=app,
|
||||
oauth_provider=oauth_provider,
|
||||
policy_engine=policy_engine
|
||||
)
|
||||
|
||||
# Store wrapper for reference
|
||||
app._auth_wrapper = auth_wrapper
|
||||
|
||||
logger.info("Tool authentication enabled successfully")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to enable tool authentication: {e}")
|
||||
|
||||
|
||||
def cleanup_auth_sessions(app: FastMCP):
|
||||
"""Clean up expired auth sessions and tokens"""
|
||||
oauth_provider = get_oauth_provider(app)
|
||||
if oauth_provider:
|
||||
oauth_provider.cleanup_expired_sessions()
|
||||
logger.debug("Cleaned up expired OAuth sessions")
|
||||
@@ -1,383 +0,0 @@
|
||||
"""
|
||||
HTTP adapter for MCP Auth Toolkit OAuth endpoints
|
||||
Exposes MCP OAuth tools as HTTP endpoints for Claude.ai integration
|
||||
"""
|
||||
|
||||
import os
|
||||
import logging
|
||||
import secrets
|
||||
import time
|
||||
from typing import Optional
|
||||
from urllib.parse import urlencode, quote
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
from fastapi import APIRouter, Request, Query, HTTPException
|
||||
from fastapi.responses import RedirectResponse, JSONResponse
|
||||
|
||||
# Try to import Clerk SDK
|
||||
try:
|
||||
from clerk_backend_api import Clerk
|
||||
CLERK_AVAILABLE = True
|
||||
except ImportError as e:
|
||||
CLERK_AVAILABLE = False
|
||||
Clerk = None
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# OAuth configuration
|
||||
BASE_URL = os.getenv("BASE_URL", "https://yargimcp.com")
|
||||
|
||||
|
||||
@router.get("/.well-known/oauth-authorization-server")
|
||||
async def get_oauth_metadata():
|
||||
"""OAuth 2.0 Authorization Server Metadata (RFC 8414)"""
|
||||
return JSONResponse({
|
||||
"issuer": BASE_URL,
|
||||
"authorization_endpoint": f"{BASE_URL}/authorize",
|
||||
"token_endpoint": f"{BASE_URL}/token",
|
||||
"registration_endpoint": f"{BASE_URL}/register",
|
||||
"response_types_supported": ["code"],
|
||||
"grant_types_supported": ["authorization_code", "refresh_token"],
|
||||
"code_challenge_methods_supported": ["S256"],
|
||||
"token_endpoint_auth_methods_supported": ["none"],
|
||||
"scopes_supported": ["mcp:tools:read", "mcp:tools:write", "openid", "profile", "email"],
|
||||
"service_documentation": f"{BASE_URL}/mcp/"
|
||||
})
|
||||
|
||||
|
||||
@router.get("/.well-known/oauth-protected-resource")
|
||||
async def get_protected_resource_metadata():
|
||||
"""OAuth Protected Resource Metadata (RFC 9728)"""
|
||||
return JSONResponse({
|
||||
"resource": BASE_URL,
|
||||
"authorization_servers": [BASE_URL],
|
||||
"bearer_methods_supported": ["header"],
|
||||
"scopes_supported": ["mcp:tools:read", "mcp:tools:write"],
|
||||
"resource_documentation": f"{BASE_URL}/docs"
|
||||
})
|
||||
|
||||
|
||||
@router.get("/authorize")
|
||||
async def authorize_endpoint(
|
||||
response_type: str = Query(...),
|
||||
client_id: str = Query(...),
|
||||
redirect_uri: str = Query(...),
|
||||
code_challenge: str = Query(...),
|
||||
code_challenge_method: str = Query("S256"),
|
||||
state: Optional[str] = Query(None),
|
||||
scope: Optional[str] = Query(None)
|
||||
):
|
||||
"""OAuth 2.1 Authorization Endpoint - Uses Clerk SDK for custom domains"""
|
||||
|
||||
logger.info(f"OAuth authorize request - client_id: {client_id}, redirect_uri: {redirect_uri}")
|
||||
|
||||
if not CLERK_AVAILABLE:
|
||||
logger.error("Clerk SDK not available")
|
||||
raise HTTPException(status_code=500, detail="Clerk SDK not available")
|
||||
|
||||
# Store OAuth session for later validation
|
||||
try:
|
||||
from mcp_server_main import app as mcp_app
|
||||
from mcp_auth_factory import get_oauth_provider
|
||||
|
||||
oauth_provider = get_oauth_provider(mcp_app)
|
||||
if not oauth_provider:
|
||||
raise HTTPException(status_code=500, detail="OAuth provider not configured")
|
||||
|
||||
# Generate session and store PKCE
|
||||
session_id = secrets.token_urlsafe(32)
|
||||
if state is None:
|
||||
state = secrets.token_urlsafe(16)
|
||||
|
||||
# Create PKCE challenge
|
||||
from mcp_auth.oauth import PKCEChallenge
|
||||
pkce = PKCEChallenge()
|
||||
|
||||
# Store session data
|
||||
session_data = {
|
||||
"pkce_verifier": pkce.verifier,
|
||||
"pkce_challenge": code_challenge, # Store the client's challenge
|
||||
"state": state,
|
||||
"redirect_uri": redirect_uri,
|
||||
"client_id": client_id,
|
||||
"scopes": scope.split(" ") if scope else ["mcp:tools:read", "mcp:tools:write"],
|
||||
"created_at": time.time(),
|
||||
"expires_at": (datetime.utcnow() + timedelta(minutes=10)).timestamp(),
|
||||
}
|
||||
oauth_provider.storage.set_session(session_id, session_data)
|
||||
|
||||
# For Clerk with custom domains, we need to use their hosted sign-in page
|
||||
# We'll pass our callback URL and session info in the state
|
||||
callback_url = f"{BASE_URL}/auth/callback"
|
||||
|
||||
# Encode session info in state for retrieval after Clerk auth
|
||||
combined_state = f"{state}:{session_id}"
|
||||
|
||||
# Use Clerk's sign-in URL with proper parameters
|
||||
clerk_domain = os.getenv("CLERK_DOMAIN", "accounts.yargimcp.com")
|
||||
sign_in_params = {
|
||||
"redirect_url": f"{callback_url}?state={quote(combined_state)}",
|
||||
}
|
||||
|
||||
sign_in_url = f"https://{clerk_domain}/sign-in?{urlencode(sign_in_params)}"
|
||||
|
||||
logger.info(f"Redirecting to Clerk sign-in: {sign_in_url}")
|
||||
|
||||
return RedirectResponse(url=sign_in_url)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Authorization failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/auth/callback")
|
||||
async def oauth_callback(
|
||||
request: Request,
|
||||
state: Optional[str] = Query(None),
|
||||
clerk_token: Optional[str] = Query(None)
|
||||
):
|
||||
"""Handle OAuth callback from Clerk - supports both JWT token and cookie auth"""
|
||||
|
||||
logger.info(f"OAuth callback received - state: {state}")
|
||||
logger.info(f"Query params: {dict(request.query_params)}")
|
||||
logger.info(f"Cookies: {dict(request.cookies)}")
|
||||
logger.info(f"Clerk JWT token provided: {bool(clerk_token)}")
|
||||
|
||||
# Support both JWT token (for cross-domain) and cookie auth (for subdomain)
|
||||
|
||||
try:
|
||||
if not state:
|
||||
logger.error("No state parameter provided")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "Missing state parameter"}
|
||||
)
|
||||
|
||||
# Parse state to get original state and session ID
|
||||
try:
|
||||
if ":" in state:
|
||||
original_state, session_id = state.rsplit(":", 1)
|
||||
else:
|
||||
original_state = state
|
||||
session_id = state # Fallback
|
||||
except ValueError:
|
||||
logger.error(f"Invalid state format: {state}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "Invalid state format"}
|
||||
)
|
||||
|
||||
# Get OAuth provider
|
||||
from mcp_server_main import app as mcp_app
|
||||
from mcp_auth_factory import get_oauth_provider
|
||||
|
||||
oauth_provider = get_oauth_provider(mcp_app)
|
||||
if not oauth_provider:
|
||||
raise HTTPException(status_code=500, detail="OAuth provider not configured")
|
||||
|
||||
# Get stored session
|
||||
oauth_session = oauth_provider.storage.get_session(session_id)
|
||||
|
||||
if not oauth_session:
|
||||
logger.error(f"OAuth session not found for ID: {session_id}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "OAuth session expired or not found"}
|
||||
)
|
||||
|
||||
# Check if we have a JWT token (for cross-domain auth)
|
||||
user_authenticated = False
|
||||
auth_method = "none"
|
||||
|
||||
if clerk_token:
|
||||
logger.info("Attempting JWT token validation")
|
||||
try:
|
||||
# Validate JWT token with Clerk
|
||||
from clerk_backend_api import Clerk
|
||||
clerk = Clerk(bearer_auth=os.getenv("CLERK_SECRET_KEY"))
|
||||
|
||||
# Extract session_id from JWT token and verify with Clerk
|
||||
import jwt
|
||||
decoded_token = jwt.decode(clerk_token, options={"verify_signature": False})
|
||||
session_id = decoded_token.get("sid") or decoded_token.get("session_id")
|
||||
|
||||
if session_id:
|
||||
# Verify with Clerk using session_id
|
||||
session = clerk.sessions.verify(session_id=session_id, token=clerk_token)
|
||||
user_id = session.user_id if session else None
|
||||
else:
|
||||
user_id = None
|
||||
|
||||
if user_id:
|
||||
logger.info(f"JWT token validation successful - user_id: {user_id}")
|
||||
user_authenticated = True
|
||||
auth_method = "jwt_token"
|
||||
# Store user info in session for token exchange
|
||||
oauth_session["user_id"] = user_id
|
||||
oauth_session["auth_method"] = "jwt_token"
|
||||
else:
|
||||
logger.error("JWT token validation failed - no user_id in claims")
|
||||
except Exception as e:
|
||||
logger.error(f"JWT token validation failed: {str(e)}")
|
||||
# Fall through to cookie validation
|
||||
|
||||
# If no JWT token or validation failed, check cookies
|
||||
if not user_authenticated:
|
||||
logger.info("Checking for Clerk session cookies")
|
||||
# Check for Clerk session cookies (for subdomain auth)
|
||||
clerk_session_cookie = request.cookies.get("__session")
|
||||
if clerk_session_cookie:
|
||||
logger.info("Found Clerk session cookie, assuming authenticated")
|
||||
user_authenticated = True
|
||||
auth_method = "cookie"
|
||||
oauth_session["auth_method"] = "cookie"
|
||||
else:
|
||||
logger.info("No Clerk session cookie found")
|
||||
|
||||
# For custom domains, we'll also trust that Clerk redirected here
|
||||
if not user_authenticated:
|
||||
logger.info("Trusting Clerk redirect for custom domain flow")
|
||||
user_authenticated = True
|
||||
auth_method = "trusted_redirect"
|
||||
oauth_session["auth_method"] = "trusted_redirect"
|
||||
|
||||
logger.info(f"User authenticated: {user_authenticated}, method: {auth_method}")
|
||||
|
||||
# Generate simple authorization code for custom domain flow
|
||||
auth_code = f"clerk_custom_{session_id}_{int(time.time())}"
|
||||
|
||||
# Store the code mapping for token exchange
|
||||
code_data = {
|
||||
"session_id": session_id,
|
||||
"clerk_authenticated": user_authenticated,
|
||||
"auth_method": auth_method,
|
||||
"custom_domain_flow": True,
|
||||
"created_at": time.time(),
|
||||
"expires_at": (datetime.utcnow() + timedelta(minutes=5)).timestamp(),
|
||||
}
|
||||
if "user_id" in oauth_session:
|
||||
code_data["user_id"] = oauth_session["user_id"]
|
||||
|
||||
oauth_provider.storage.set_session(f"code_{auth_code}", code_data)
|
||||
|
||||
# Build redirect URL back to Claude
|
||||
redirect_params = {
|
||||
"code": auth_code,
|
||||
"state": original_state
|
||||
}
|
||||
|
||||
redirect_url = f"{oauth_session['redirect_uri']}?{urlencode(redirect_params)}"
|
||||
logger.info(f"Redirecting back to Claude: {redirect_url}")
|
||||
|
||||
return RedirectResponse(url=redirect_url)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Callback processing failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=500,
|
||||
content={"error": "server_error", "error_description": str(e)}
|
||||
)
|
||||
|
||||
|
||||
@router.post("/register")
|
||||
async def register_client(request: Request):
|
||||
"""Dynamic Client Registration (RFC 7591)"""
|
||||
|
||||
data = await request.json()
|
||||
logger.info(f"Client registration request: {data}")
|
||||
|
||||
# Simple dynamic registration - accept any client
|
||||
client_id = f"mcp-client-{os.urandom(8).hex()}"
|
||||
|
||||
return JSONResponse({
|
||||
"client_id": client_id,
|
||||
"client_secret": None, # Public client
|
||||
"redirect_uris": data.get("redirect_uris", []),
|
||||
"grant_types": ["authorization_code", "refresh_token"],
|
||||
"response_types": ["code"],
|
||||
"client_name": data.get("client_name", "MCP Client"),
|
||||
"token_endpoint_auth_method": "none",
|
||||
"client_id_issued_at": int(datetime.now().timestamp())
|
||||
})
|
||||
|
||||
|
||||
@router.post("/token")
|
||||
async def token_endpoint(request: Request):
|
||||
"""OAuth 2.1 Token Endpoint"""
|
||||
|
||||
# Parse form data
|
||||
form_data = await request.form()
|
||||
grant_type = form_data.get("grant_type")
|
||||
code = form_data.get("code")
|
||||
redirect_uri = form_data.get("redirect_uri")
|
||||
client_id = form_data.get("client_id")
|
||||
code_verifier = form_data.get("code_verifier")
|
||||
|
||||
logger.info(f"Token exchange - grant_type: {grant_type}, code: {code[:20] if code else 'None'}...")
|
||||
|
||||
if grant_type != "authorization_code":
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "unsupported_grant_type"}
|
||||
)
|
||||
|
||||
try:
|
||||
# OAuth token exchange - validate code and return Clerk JWT
|
||||
# This supports proper OAuth flow while using Clerk JWT tokens
|
||||
|
||||
if not code or not redirect_uri:
|
||||
logger.error("Missing required parameters: code or redirect_uri")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "Missing code or redirect_uri"}
|
||||
)
|
||||
|
||||
# Validate OAuth code with Clerk
|
||||
if CLERK_AVAILABLE:
|
||||
try:
|
||||
clerk = Clerk(bearer_auth=os.getenv("CLERK_SECRET_KEY"))
|
||||
|
||||
# In a real implementation, you'd validate the code with Clerk
|
||||
# For now, we'll assume the code is valid if it looks like a Clerk code
|
||||
if len(code) > 10: # Basic validation
|
||||
# Create a mock session with the code
|
||||
# In practice, this would be validated with Clerk's OAuth flow
|
||||
|
||||
# Return Clerk JWT token format
|
||||
# This should be the actual Clerk JWT token from the OAuth flow
|
||||
return JSONResponse({
|
||||
"access_token": f"mock_clerk_jwt_{code}",
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "yargi.read yargi.search"
|
||||
})
|
||||
else:
|
||||
logger.error(f"Invalid code format: {code}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Invalid authorization code"}
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Clerk validation failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Authorization code validation failed"}
|
||||
)
|
||||
else:
|
||||
logger.warning("Clerk SDK not available, using mock response")
|
||||
return JSONResponse({
|
||||
"access_token": "mock_jwt_token_for_development",
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "yargi.read yargi.search"
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Token exchange failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=500,
|
||||
content={"error": "server_error", "error_description": str(e)}
|
||||
)
|
||||
@@ -1,522 +0,0 @@
|
||||
"""
|
||||
Simplified MCP OAuth HTTP adapter - only Clerk JWT based authentication
|
||||
Uses Redis for authorization code storage to support multi-machine deployment
|
||||
"""
|
||||
|
||||
import os
|
||||
import logging
|
||||
from typing import Optional
|
||||
from urllib.parse import urlencode, quote
|
||||
|
||||
from fastapi import APIRouter, Request, Query, HTTPException
|
||||
from fastapi.responses import RedirectResponse, JSONResponse
|
||||
|
||||
# Import Redis session store
|
||||
from redis_session_store import get_redis_store
|
||||
|
||||
# Try to import Clerk SDK
|
||||
try:
|
||||
from clerk_backend_api import Clerk
|
||||
CLERK_AVAILABLE = True
|
||||
except ImportError:
|
||||
CLERK_AVAILABLE = False
|
||||
Clerk = None
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# OAuth configuration
|
||||
BASE_URL = os.getenv("BASE_URL", "https://api.yargimcp.com")
|
||||
CLERK_DOMAIN = os.getenv("CLERK_DOMAIN", "accounts.yargimcp.com")
|
||||
|
||||
# Initialize Redis store
|
||||
redis_store = None
|
||||
|
||||
def get_redis_session_store():
|
||||
"""Get Redis store instance with lazy initialization."""
|
||||
global redis_store
|
||||
if redis_store is None:
|
||||
try:
|
||||
import concurrent.futures
|
||||
import functools
|
||||
|
||||
# Use thread pool with timeout to prevent hanging
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as executor:
|
||||
future = executor.submit(get_redis_store)
|
||||
try:
|
||||
# 5 second timeout for Redis initialization
|
||||
redis_store = future.result(timeout=5.0)
|
||||
if redis_store:
|
||||
logger.info("Redis session store initialized for OAuth handler")
|
||||
else:
|
||||
logger.warning("Redis store initialization returned None")
|
||||
except concurrent.futures.TimeoutError:
|
||||
logger.error("Redis initialization timed out after 5 seconds")
|
||||
redis_store = None
|
||||
future.cancel() # Try to cancel the hanging operation
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize Redis store: {e}")
|
||||
redis_store = None
|
||||
|
||||
if redis_store is None:
|
||||
# Fall back to in-memory storage with warning
|
||||
logger.warning("Falling back to in-memory storage - multi-machine deployment will not work")
|
||||
|
||||
return redis_store
|
||||
|
||||
@router.get("/.well-known/oauth-authorization-server")
|
||||
async def get_oauth_metadata():
|
||||
"""OAuth 2.0 Authorization Server Metadata (RFC 8414)"""
|
||||
return JSONResponse({
|
||||
"issuer": BASE_URL,
|
||||
"authorization_endpoint": "https://yargimcp.com/mcp-callback",
|
||||
"token_endpoint": f"{BASE_URL}/token",
|
||||
"registration_endpoint": f"{BASE_URL}/register",
|
||||
"response_types_supported": ["code"],
|
||||
"grant_types_supported": ["authorization_code"],
|
||||
"code_challenge_methods_supported": ["S256"],
|
||||
"token_endpoint_auth_methods_supported": ["none"],
|
||||
"scopes_supported": ["read", "search", "openid", "profile", "email"],
|
||||
"service_documentation": f"{BASE_URL}/mcp/"
|
||||
})
|
||||
|
||||
@router.get("/auth/login")
|
||||
async def oauth_authorize(
|
||||
request: Request,
|
||||
client_id: str = Query(...),
|
||||
redirect_uri: str = Query(...),
|
||||
response_type: str = Query("code"),
|
||||
scope: Optional[str] = Query("read search"),
|
||||
state: Optional[str] = Query(None),
|
||||
code_challenge: Optional[str] = Query(None),
|
||||
code_challenge_method: Optional[str] = Query(None)
|
||||
):
|
||||
"""OAuth 2.1 Authorization Endpoint - redirects to Clerk"""
|
||||
|
||||
logger.info(f"OAuth authorize request - client_id: {client_id}")
|
||||
logger.info(f"Redirect URI: {redirect_uri}")
|
||||
logger.info(f"State: {state}")
|
||||
logger.info(f"PKCE Challenge: {bool(code_challenge)}")
|
||||
|
||||
try:
|
||||
# Build callback URL with all necessary parameters
|
||||
callback_url = f"{BASE_URL}/auth/callback"
|
||||
callback_params = {
|
||||
"client_id": client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"state": state or "",
|
||||
"scope": scope or "read search"
|
||||
}
|
||||
|
||||
# Add PKCE parameters if present
|
||||
if code_challenge:
|
||||
callback_params["code_challenge"] = code_challenge
|
||||
callback_params["code_challenge_method"] = code_challenge_method or "S256"
|
||||
|
||||
# Encode callback URL as redirect_url for Clerk
|
||||
callback_with_params = f"{callback_url}?{urlencode(callback_params)}"
|
||||
|
||||
# Build Clerk sign-in URL - use yargimcp.com frontend for JWT token generation
|
||||
clerk_params = {
|
||||
"redirect_url": callback_with_params
|
||||
}
|
||||
|
||||
# Use frontend sign-in page that handles JWT token generation
|
||||
clerk_signin_url = f"https://yargimcp.com/sign-in?{urlencode(clerk_params)}"
|
||||
|
||||
logger.info(f"Redirecting to Clerk: {clerk_signin_url}")
|
||||
|
||||
return RedirectResponse(url=clerk_signin_url)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Authorization failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@router.get("/auth/callback")
|
||||
async def oauth_callback(
|
||||
request: Request,
|
||||
client_id: str = Query(...),
|
||||
redirect_uri: str = Query(...),
|
||||
state: Optional[str] = Query(None),
|
||||
scope: Optional[str] = Query("read search"),
|
||||
code_challenge: Optional[str] = Query(None),
|
||||
code_challenge_method: Optional[str] = Query(None),
|
||||
clerk_token: Optional[str] = Query(None)
|
||||
):
|
||||
"""OAuth callback from Clerk - generates authorization code"""
|
||||
|
||||
logger.info(f"OAuth callback - client_id: {client_id}")
|
||||
logger.info(f"Clerk token provided: {bool(clerk_token)}")
|
||||
|
||||
try:
|
||||
# Validate user with Clerk and generate real JWT token
|
||||
user_authenticated = False
|
||||
user_id = None
|
||||
session_id = None
|
||||
real_jwt_token = None
|
||||
|
||||
if clerk_token and CLERK_AVAILABLE:
|
||||
try:
|
||||
# Extract user info from JWT token (no Clerk session verification needed)
|
||||
import jwt
|
||||
decoded_token = jwt.decode(clerk_token, options={"verify_signature": False})
|
||||
user_id = decoded_token.get("user_id") or decoded_token.get("sub")
|
||||
user_email = decoded_token.get("email")
|
||||
token_scopes = decoded_token.get("scopes", ["read", "search"])
|
||||
|
||||
logger.info(f"JWT token claims - user_id: {user_id}, email: {user_email}, scopes: {token_scopes}")
|
||||
|
||||
if user_id and user_email:
|
||||
# JWT token is already signed by Clerk and contains valid user info
|
||||
user_authenticated = True
|
||||
logger.info(f"User authenticated via JWT token - user_id: {user_id}")
|
||||
|
||||
# Use the JWT token directly as the real token (it's already from Clerk template)
|
||||
real_jwt_token = clerk_token
|
||||
logger.info("Using Clerk JWT token directly (already real token)")
|
||||
|
||||
else:
|
||||
logger.error(f"Missing required fields in JWT token - user_id: {bool(user_id)}, email: {bool(user_email)}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"JWT validation failed: {e}")
|
||||
|
||||
# Fallback to cookie validation
|
||||
if not user_authenticated:
|
||||
clerk_session = request.cookies.get("__session")
|
||||
if clerk_session:
|
||||
user_authenticated = True
|
||||
logger.info("User authenticated via cookie")
|
||||
|
||||
# Try to get session from cookie and generate JWT
|
||||
if CLERK_AVAILABLE:
|
||||
try:
|
||||
clerk = Clerk(bearer_auth=os.getenv("CLERK_SECRET_KEY"))
|
||||
# Note: sessions.verify_session is deprecated, but we'll try
|
||||
# In practice, you'd need to extract session_id from cookie
|
||||
logger.info("Cookie authentication - JWT generation not implemented yet")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to generate JWT from cookie: {e}")
|
||||
|
||||
# Only generate authorization code if we have a real JWT token
|
||||
if user_authenticated and real_jwt_token:
|
||||
# Generate authorization code
|
||||
auth_code = f"clerk_auth_{os.urandom(16).hex()}"
|
||||
|
||||
# Prepare code data
|
||||
import time
|
||||
code_data = {
|
||||
"user_id": user_id,
|
||||
"session_id": session_id,
|
||||
"real_jwt_token": real_jwt_token,
|
||||
"user_authenticated": user_authenticated,
|
||||
"client_id": client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"scope": scope or "read search"
|
||||
}
|
||||
|
||||
# Try to store in Redis, fall back to in-memory if Redis unavailable
|
||||
store = get_redis_session_store()
|
||||
if store:
|
||||
# Store in Redis with automatic expiration
|
||||
success = store.set_oauth_code(auth_code, code_data)
|
||||
if success:
|
||||
logger.info(f"Stored authorization code {auth_code[:10]}... in Redis with real JWT token")
|
||||
else:
|
||||
logger.error(f"Failed to store authorization code in Redis, falling back to in-memory")
|
||||
# Fall back to in-memory storage
|
||||
if not hasattr(oauth_callback, '_code_storage'):
|
||||
oauth_callback._code_storage = {}
|
||||
oauth_callback._code_storage[auth_code] = code_data
|
||||
else:
|
||||
# Fall back to in-memory storage
|
||||
logger.warning("Redis not available, using in-memory storage")
|
||||
if not hasattr(oauth_callback, '_code_storage'):
|
||||
oauth_callback._code_storage = {}
|
||||
oauth_callback._code_storage[auth_code] = code_data
|
||||
logger.info(f"Stored authorization code in memory (fallback)")
|
||||
|
||||
# Redirect back to client with authorization code
|
||||
redirect_params = {
|
||||
"code": auth_code,
|
||||
"state": state or ""
|
||||
}
|
||||
|
||||
final_redirect_url = f"{redirect_uri}?{urlencode(redirect_params)}"
|
||||
logger.info(f"Redirecting back to client: {final_redirect_url}")
|
||||
|
||||
return RedirectResponse(url=final_redirect_url)
|
||||
else:
|
||||
# No JWT token yet - redirect back to sign-in page to wait for authentication
|
||||
logger.info("No JWT token provided - redirecting back to sign-in to complete authentication")
|
||||
|
||||
# Keep the same redirect URL so the flow continues
|
||||
sign_in_params = {
|
||||
"redirect_url": f"{request.url._url}" # Current callback URL with all params
|
||||
}
|
||||
|
||||
sign_in_url = f"https://yargimcp.com/sign-in?{urlencode(sign_in_params)}"
|
||||
logger.info(f"Redirecting back to sign-in: {sign_in_url}")
|
||||
|
||||
return RedirectResponse(url=sign_in_url)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Callback processing failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=500,
|
||||
content={"error": "server_error", "error_description": str(e)}
|
||||
)
|
||||
|
||||
@router.post("/auth/register")
|
||||
async def register_client(request: Request):
|
||||
"""Dynamic Client Registration (RFC 7591)"""
|
||||
|
||||
data = await request.json()
|
||||
logger.info(f"Client registration request: {data}")
|
||||
|
||||
# Simple dynamic registration - accept any client
|
||||
client_id = f"mcp-client-{os.urandom(8).hex()}"
|
||||
|
||||
return JSONResponse({
|
||||
"client_id": client_id,
|
||||
"client_secret": None, # Public client
|
||||
"redirect_uris": data.get("redirect_uris", []),
|
||||
"grant_types": ["authorization_code"],
|
||||
"response_types": ["code"],
|
||||
"client_name": data.get("client_name", "MCP Client"),
|
||||
"token_endpoint_auth_method": "none"
|
||||
})
|
||||
|
||||
@router.post("/auth/callback")
|
||||
async def oauth_callback_post(request: Request):
|
||||
"""OAuth callback POST endpoint for token exchange"""
|
||||
|
||||
# Parse form data (standard OAuth token exchange format)
|
||||
form_data = await request.form()
|
||||
grant_type = form_data.get("grant_type")
|
||||
code = form_data.get("code")
|
||||
redirect_uri = form_data.get("redirect_uri")
|
||||
client_id = form_data.get("client_id")
|
||||
code_verifier = form_data.get("code_verifier")
|
||||
|
||||
logger.info(f"OAuth callback POST - grant_type: {grant_type}")
|
||||
logger.info(f"Code: {code[:20] if code else 'None'}...")
|
||||
logger.info(f"Client ID: {client_id}")
|
||||
logger.info(f"PKCE verifier: {bool(code_verifier)}")
|
||||
|
||||
if grant_type != "authorization_code":
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "unsupported_grant_type"}
|
||||
)
|
||||
|
||||
if not code or not redirect_uri:
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "Missing code or redirect_uri"}
|
||||
)
|
||||
|
||||
try:
|
||||
# Validate authorization code
|
||||
if not code.startswith("clerk_auth_"):
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Invalid authorization code"}
|
||||
)
|
||||
|
||||
# Retrieve stored JWT token using authorization code from Redis or in-memory fallback
|
||||
stored_code_data = None
|
||||
|
||||
# Try to get from Redis first, then fall back to in-memory
|
||||
store = get_redis_session_store()
|
||||
if store:
|
||||
stored_code_data = store.get_oauth_code(code, delete_after_use=True)
|
||||
if stored_code_data:
|
||||
logger.info(f"Retrieved authorization code {code[:10]}... from Redis")
|
||||
else:
|
||||
logger.warning(f"Authorization code {code[:10]}... not found in Redis")
|
||||
|
||||
# Fall back to in-memory storage if Redis unavailable or code not found
|
||||
if not stored_code_data and hasattr(oauth_callback, '_code_storage'):
|
||||
stored_code_data = oauth_callback._code_storage.get(code)
|
||||
if stored_code_data:
|
||||
# Clean up in-memory storage
|
||||
oauth_callback._code_storage.pop(code, None)
|
||||
logger.info(f"Retrieved authorization code {code[:10]}... from in-memory storage")
|
||||
|
||||
if not stored_code_data:
|
||||
logger.error(f"No stored data found for authorization code: {code}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Authorization code not found or expired"}
|
||||
)
|
||||
|
||||
# Note: Redis TTL handles expiration automatically, but check for manual expiration for in-memory fallback
|
||||
import time
|
||||
expires_at = stored_code_data.get("expires_at", 0)
|
||||
if expires_at and time.time() > expires_at:
|
||||
logger.error(f"Authorization code expired: {code}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Authorization code expired"}
|
||||
)
|
||||
|
||||
# Get the real JWT token
|
||||
real_jwt_token = stored_code_data.get("real_jwt_token")
|
||||
|
||||
if real_jwt_token:
|
||||
logger.info("Returning real Clerk JWT token")
|
||||
# Note: Code already deleted from Redis, clean up in-memory fallback if used
|
||||
if hasattr(oauth_callback, '_code_storage'):
|
||||
oauth_callback._code_storage.pop(code, None)
|
||||
|
||||
return JSONResponse({
|
||||
"access_token": real_jwt_token,
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "read search"
|
||||
})
|
||||
else:
|
||||
logger.warning("No real JWT token found, generating mock token")
|
||||
# Fallback to mock token for testing
|
||||
mock_token = f"mock_clerk_jwt_{code}"
|
||||
return JSONResponse({
|
||||
"access_token": mock_token,
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "read search"
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"OAuth callback POST failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=500,
|
||||
content={"error": "server_error", "error_description": str(e)}
|
||||
)
|
||||
|
||||
@router.post("/register")
|
||||
async def register_client(request: Request):
|
||||
"""Dynamic Client Registration (RFC 7591)"""
|
||||
|
||||
data = await request.json()
|
||||
logger.info(f"Client registration request: {data}")
|
||||
|
||||
# Simple dynamic registration - accept any client
|
||||
client_id = f"mcp-client-{os.urandom(8).hex()}"
|
||||
|
||||
return JSONResponse({
|
||||
"client_id": client_id,
|
||||
"client_secret": None, # Public client
|
||||
"redirect_uris": data.get("redirect_uris", []),
|
||||
"grant_types": ["authorization_code"],
|
||||
"response_types": ["code"],
|
||||
"client_name": data.get("client_name", "MCP Client"),
|
||||
"token_endpoint_auth_method": "none"
|
||||
})
|
||||
|
||||
@router.post("/token")
|
||||
async def token_endpoint(request: Request):
|
||||
"""OAuth 2.1 Token Endpoint - exchanges code for Clerk JWT"""
|
||||
|
||||
# Parse form data
|
||||
form_data = await request.form()
|
||||
grant_type = form_data.get("grant_type")
|
||||
code = form_data.get("code")
|
||||
redirect_uri = form_data.get("redirect_uri")
|
||||
client_id = form_data.get("client_id")
|
||||
code_verifier = form_data.get("code_verifier")
|
||||
|
||||
logger.info(f"Token exchange - grant_type: {grant_type}")
|
||||
logger.info(f"Code: {code[:20] if code else 'None'}...")
|
||||
|
||||
if grant_type != "authorization_code":
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "unsupported_grant_type"}
|
||||
)
|
||||
|
||||
if not code or not redirect_uri:
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_request", "error_description": "Missing code or redirect_uri"}
|
||||
)
|
||||
|
||||
try:
|
||||
# Validate authorization code
|
||||
if not code.startswith("clerk_auth_"):
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Invalid authorization code"}
|
||||
)
|
||||
|
||||
# Retrieve stored JWT token using authorization code from Redis or in-memory fallback
|
||||
stored_code_data = None
|
||||
|
||||
# Try to get from Redis first, then fall back to in-memory
|
||||
store = get_redis_session_store()
|
||||
if store:
|
||||
stored_code_data = store.get_oauth_code(code, delete_after_use=True)
|
||||
if stored_code_data:
|
||||
logger.info(f"Retrieved authorization code {code[:10]}... from Redis (/token endpoint)")
|
||||
else:
|
||||
logger.warning(f"Authorization code {code[:10]}... not found in Redis (/token endpoint)")
|
||||
|
||||
# Fall back to in-memory storage if Redis unavailable or code not found
|
||||
if not stored_code_data and hasattr(oauth_callback, '_code_storage'):
|
||||
stored_code_data = oauth_callback._code_storage.get(code)
|
||||
if stored_code_data:
|
||||
# Clean up in-memory storage
|
||||
oauth_callback._code_storage.pop(code, None)
|
||||
logger.info(f"Retrieved authorization code {code[:10]}... from in-memory storage (/token endpoint)")
|
||||
|
||||
if not stored_code_data:
|
||||
logger.error(f"No stored data found for authorization code: {code}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Authorization code not found or expired"}
|
||||
)
|
||||
|
||||
# Note: Redis TTL handles expiration automatically, but check for manual expiration for in-memory fallback
|
||||
import time
|
||||
expires_at = stored_code_data.get("expires_at", 0)
|
||||
if expires_at and time.time() > expires_at:
|
||||
logger.error(f"Authorization code expired: {code}")
|
||||
return JSONResponse(
|
||||
status_code=400,
|
||||
content={"error": "invalid_grant", "error_description": "Authorization code expired"}
|
||||
)
|
||||
|
||||
# Get the real JWT token
|
||||
real_jwt_token = stored_code_data.get("real_jwt_token")
|
||||
|
||||
if real_jwt_token:
|
||||
logger.info("Returning real Clerk JWT token from /token endpoint")
|
||||
# Note: Code already deleted from Redis, clean up in-memory fallback if used
|
||||
if hasattr(oauth_callback, '_code_storage'):
|
||||
oauth_callback._code_storage.pop(code, None)
|
||||
|
||||
return JSONResponse({
|
||||
"access_token": real_jwt_token,
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "read search"
|
||||
})
|
||||
else:
|
||||
logger.warning("No real JWT token found in /token endpoint, generating mock token")
|
||||
# Fallback to mock token for testing
|
||||
mock_token = f"mock_clerk_jwt_{code}"
|
||||
return JSONResponse({
|
||||
"access_token": mock_token,
|
||||
"token_type": "Bearer",
|
||||
"expires_in": 3600,
|
||||
"scope": "read search"
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Token exchange failed: {e}")
|
||||
return JSONResponse(
|
||||
status_code=500,
|
||||
content={"error": "server_error", "error_description": str(e)}
|
||||
)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,94 +0,0 @@
|
||||
events {
|
||||
worker_connections 1024;
|
||||
}
|
||||
|
||||
http {
|
||||
upstream yargi_mcp {
|
||||
server yargi-mcp:8000;
|
||||
}
|
||||
|
||||
# Rate limiting
|
||||
limit_req_zone $binary_remote_addr zone=api_limit:10m rate=10r/s;
|
||||
limit_req_zone $binary_remote_addr zone=mcp_limit:10m rate=100r/s;
|
||||
|
||||
server {
|
||||
listen 80;
|
||||
server_name localhost;
|
||||
|
||||
# Redirect HTTP to HTTPS in production
|
||||
# return 301 https://$server_name$request_uri;
|
||||
|
||||
# Security headers
|
||||
add_header X-Content-Type-Options nosniff;
|
||||
add_header X-Frame-Options DENY;
|
||||
add_header X-XSS-Protection "1; mode=block";
|
||||
add_header Referrer-Policy "strict-origin-when-cross-origin";
|
||||
|
||||
# API endpoints
|
||||
location /api/ {
|
||||
limit_req zone=api_limit burst=20 nodelay;
|
||||
|
||||
proxy_pass http://yargi_mcp;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 60s;
|
||||
proxy_send_timeout 60s;
|
||||
proxy_read_timeout 60s;
|
||||
}
|
||||
|
||||
# MCP endpoint (higher rate limit)
|
||||
location /mcp-server/mcp/ {
|
||||
limit_req zone=mcp_limit burst=50 nodelay;
|
||||
|
||||
proxy_pass http://yargi_mcp;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Longer timeouts for MCP operations
|
||||
proxy_connect_timeout 300s;
|
||||
proxy_send_timeout 300s;
|
||||
proxy_read_timeout 300s;
|
||||
}
|
||||
|
||||
# Health check (no rate limit)
|
||||
location /health {
|
||||
proxy_pass http://yargi_mcp;
|
||||
proxy_set_header Host $host;
|
||||
}
|
||||
|
||||
# Root and other paths
|
||||
location / {
|
||||
limit_req zone=api_limit burst=10 nodelay;
|
||||
|
||||
proxy_pass http://yargi_mcp;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
}
|
||||
}
|
||||
|
||||
# SSL configuration (uncomment for production)
|
||||
# server {
|
||||
# listen 443 ssl http2;
|
||||
# server_name your-domain.com;
|
||||
#
|
||||
# ssl_certificate /etc/nginx/ssl/cert.pem;
|
||||
# ssl_certificate_key /etc/nginx/ssl/key.pem;
|
||||
# ssl_protocols TLSv1.2 TLSv1.3;
|
||||
# ssl_ciphers HIGH:!aNULL:!MD5;
|
||||
#
|
||||
# # Include all location blocks from above
|
||||
# }
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 533 KiB |
@@ -1,66 +0,0 @@
|
||||
[project]
|
||||
name = "yargi-mcp"
|
||||
version = "0.1.6"
|
||||
description = "MCP Server For Turkish Legal Databases"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.11"
|
||||
license = {text = "MIT"}
|
||||
authors = [{name = "Said Surucu", email = "saidsrc@gmail.com"}]
|
||||
keywords = ["mcp", "turkish-law", "legal", "yargitay", "danistay", "bddk", "kvkk", "turkish", "law", "court", "decisions"]
|
||||
classifiers = [
|
||||
"Development Status :: 4 - Beta",
|
||||
"Intended Audience :: Legal Industry",
|
||||
"Intended Audience :: Developers",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"Topic :: Software Development :: Libraries :: Python Modules",
|
||||
"Topic :: Text Processing :: Markup :: Markdown",
|
||||
"Operating System :: OS Independent",
|
||||
]
|
||||
urls = {Homepage = "https://github.com/saidsurucu/yargi-mcp", Issues = "https://github.com/saidsurucu/yargi-mcp/issues"}
|
||||
dependencies = [
|
||||
"beautifulsoup4>=4.13.4",
|
||||
"httpx>=0.28.1",
|
||||
"markitdown[pdf]>=0.1.1",
|
||||
"pydantic>=2.11.4",
|
||||
"aiohttp>=3.11.18",
|
||||
"playwright>=1.52.0",
|
||||
"fastmcp>=2.10.5",
|
||||
"pypdf>=5.5.0",
|
||||
"fastapi>=0.115.14",
|
||||
"PyJWT>=2.8.0",
|
||||
"tiktoken>=0.5.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
asgi = [
|
||||
"uvicorn[standard]>=0.30.0",
|
||||
"starlette>=0.37.0",
|
||||
]
|
||||
api = [
|
||||
"fastapi>=0.115.0",
|
||||
"uvicorn[standard]>=0.30.0",
|
||||
]
|
||||
production = [
|
||||
"gunicorn>=22.0.0",
|
||||
"uvicorn[standard]>=0.30.0",
|
||||
]
|
||||
saas = [
|
||||
"clerk-backend-api>=3.0.0",
|
||||
"stripe>=9.1.0",
|
||||
"upstash-redis>=1.1.0",
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
yargi-mcp = "mcp_server_main:main"
|
||||
|
||||
[tool.setuptools]
|
||||
py-modules = ["mcp_server_main", "mcp_auth_factory", "mcp_auth_http_adapter", "asgi_app", "fastapi_app", "starlette_app", "run_asgi", "stripe_webhook"]
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
include = ["*_mcp_module", "mcp_auth"]
|
||||
|
||||
[build-system]
|
||||
requires = ["setuptools>=65.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
@@ -1,18 +0,0 @@
|
||||
{
|
||||
"$schema": "https://railway.app/railway.schema.json",
|
||||
"build": {
|
||||
"builder": "NIXPACKS",
|
||||
"buildCommand": "pip install -e .[asgi]"
|
||||
},
|
||||
"deploy": {
|
||||
"startCommand": "uvicorn asgi_app:app --host 0.0.0.0 --port $PORT",
|
||||
"healthcheckPath": "/health",
|
||||
"healthcheckTimeout": 30,
|
||||
"restartPolicyType": "ON_FAILURE",
|
||||
"restartPolicyMaxRetries": 3
|
||||
},
|
||||
"variables": {
|
||||
"ALLOWED_ORIGINS": "*",
|
||||
"LOG_LEVEL": "info"
|
||||
}
|
||||
}
|
||||
@@ -1,464 +0,0 @@
|
||||
"""
|
||||
Redis Session Store for OAuth Authorization Codes and User Sessions
|
||||
|
||||
This module provides Redis-based storage for OAuth authorization codes and user sessions,
|
||||
enabling multi-machine deployment support by replacing in-memory storage.
|
||||
|
||||
Uses Upstash Redis via REST API for serverless-friendly operation.
|
||||
"""
|
||||
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
import logging
|
||||
from typing import Optional, Dict, Any, Union
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
try:
|
||||
from upstash_redis import Redis
|
||||
UPSTASH_AVAILABLE = True
|
||||
except ImportError:
|
||||
UPSTASH_AVAILABLE = False
|
||||
Redis = None
|
||||
|
||||
# Use standard Python exceptions for Redis connection errors
|
||||
import socket
|
||||
from requests.exceptions import ConnectionError as RequestsConnectionError, Timeout as RequestsTimeout
|
||||
|
||||
class RedisSessionStore:
|
||||
"""
|
||||
Redis-based session store for OAuth flows and user sessions.
|
||||
|
||||
Uses Upstash Redis REST API for connection-free operation suitable for
|
||||
multi-instance deployments on platforms like Fly.io.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize Redis connection using environment variables."""
|
||||
if not UPSTASH_AVAILABLE:
|
||||
raise ImportError("upstash-redis package is required. Install with: pip install upstash-redis")
|
||||
|
||||
# Initialize Upstash Redis client from environment with optimized connection settings
|
||||
try:
|
||||
# Get Upstash Redis configuration
|
||||
redis_url = os.getenv("UPSTASH_REDIS_REST_URL")
|
||||
redis_token = os.getenv("UPSTASH_REDIS_REST_TOKEN")
|
||||
|
||||
if not redis_url or not redis_token:
|
||||
raise ValueError("UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN must be set")
|
||||
|
||||
logger.info(f"Connecting to Upstash Redis at {redis_url[:30]}...")
|
||||
|
||||
# Initialize with explicit configuration for better SSL handling
|
||||
self.redis = Redis(
|
||||
url=redis_url,
|
||||
token=redis_token
|
||||
)
|
||||
|
||||
logger.info("Upstash Redis client created")
|
||||
|
||||
# Skip connection test during initialization to prevent server hang
|
||||
# Connection will be tested during first actual operation
|
||||
logger.info("Redis client initialized - connection will be tested on first use")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize Upstash Redis: {e}")
|
||||
raise
|
||||
|
||||
# TTL values (in seconds)
|
||||
self.oauth_code_ttl = int(os.getenv("OAUTH_CODE_TTL", "600")) # 10 minutes
|
||||
self.session_ttl = int(os.getenv("SESSION_TTL", "3600")) # 1 hour
|
||||
|
||||
def _serialize_data(self, data: Dict[str, Any]) -> Dict[str, str]:
|
||||
"""Convert data to Redis-compatible string format."""
|
||||
serialized = {}
|
||||
for key, value in data.items():
|
||||
if isinstance(value, (dict, list)):
|
||||
serialized[key] = json.dumps(value)
|
||||
elif isinstance(value, (int, float)):
|
||||
serialized[key] = str(value)
|
||||
elif isinstance(value, bool):
|
||||
serialized[key] = "true" if value else "false"
|
||||
else:
|
||||
serialized[key] = str(value)
|
||||
return serialized
|
||||
|
||||
def _deserialize_data(self, data: Dict[str, str]) -> Dict[str, Any]:
|
||||
"""Convert Redis string data back to original types."""
|
||||
if not data:
|
||||
return {}
|
||||
|
||||
deserialized = {}
|
||||
for key, value in data.items():
|
||||
if not isinstance(value, str):
|
||||
deserialized[key] = value
|
||||
continue
|
||||
|
||||
# Try to deserialize JSON
|
||||
if value.startswith(('[', '{')):
|
||||
try:
|
||||
deserialized[key] = json.loads(value)
|
||||
continue
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
# Try to convert numbers
|
||||
if value.isdigit():
|
||||
deserialized[key] = int(value)
|
||||
continue
|
||||
|
||||
if value.replace('.', '').isdigit():
|
||||
try:
|
||||
deserialized[key] = float(value)
|
||||
continue
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
# Handle booleans
|
||||
if value in ("true", "false"):
|
||||
deserialized[key] = value == "true"
|
||||
continue
|
||||
|
||||
# Keep as string
|
||||
deserialized[key] = value
|
||||
|
||||
return deserialized
|
||||
|
||||
# OAuth Authorization Code Methods
|
||||
|
||||
def set_oauth_code(self, code: str, data: Dict[str, Any]) -> bool:
|
||||
"""
|
||||
Store OAuth authorization code with automatic expiration.
|
||||
|
||||
Args:
|
||||
code: Authorization code string
|
||||
data: Code data including user_id, client_id, etc.
|
||||
|
||||
Returns:
|
||||
True if stored successfully, False otherwise
|
||||
"""
|
||||
try:
|
||||
key = f"oauth:code:{code}"
|
||||
|
||||
# Add timestamp for debugging
|
||||
data_with_timestamp = data.copy()
|
||||
data_with_timestamp.update({
|
||||
"created_at": time.time(),
|
||||
"expires_at": time.time() + self.oauth_code_ttl
|
||||
})
|
||||
|
||||
# Serialize and store - Upstash Redis doesn't support mapping parameter
|
||||
serialized_data = self._serialize_data(data_with_timestamp)
|
||||
|
||||
# Use individual hset calls for each field with retry logic
|
||||
max_retries = 3
|
||||
for attempt in range(max_retries):
|
||||
try:
|
||||
# Clear any existing data first
|
||||
self.redis.delete(key)
|
||||
|
||||
# Set all fields in a pipeline-like manner
|
||||
for field, value in serialized_data.items():
|
||||
self.redis.hset(key, field, value)
|
||||
|
||||
# Set expiration
|
||||
self.redis.expire(key, self.oauth_code_ttl)
|
||||
|
||||
logger.info(f"Stored OAuth code {code[:10]}... with TTL {self.oauth_code_ttl}s (attempt {attempt + 1})")
|
||||
return True
|
||||
|
||||
except (RequestsConnectionError, RequestsTimeout, OSError, socket.error) as e:
|
||||
logger.warning(f"Redis connection error on attempt {attempt + 1}: {e}")
|
||||
if attempt == max_retries - 1:
|
||||
raise # Re-raise on final attempt
|
||||
time.sleep(0.5 * (attempt + 1)) # Exponential backoff
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to store OAuth code {code[:10]}... after {max_retries} attempts: {e}")
|
||||
return False
|
||||
|
||||
def get_oauth_code(self, code: str, delete_after_use: bool = True) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Retrieve OAuth authorization code data.
|
||||
|
||||
Args:
|
||||
code: Authorization code string
|
||||
delete_after_use: If True, delete the code after retrieval (one-time use)
|
||||
|
||||
Returns:
|
||||
Code data dictionary or None if not found/expired
|
||||
"""
|
||||
max_retries = 3
|
||||
for attempt in range(max_retries):
|
||||
try:
|
||||
key = f"oauth:code:{code}"
|
||||
|
||||
# Get all hash fields with retry
|
||||
data = self.redis.hgetall(key)
|
||||
|
||||
if not data:
|
||||
logger.warning(f"OAuth code {code[:10]}... not found or expired (attempt {attempt + 1})")
|
||||
return None
|
||||
|
||||
# Deserialize data
|
||||
deserialized_data = self._deserialize_data(data)
|
||||
|
||||
# Check manual expiration (in case Redis TTL failed)
|
||||
expires_at = deserialized_data.get("expires_at", 0)
|
||||
if expires_at and time.time() > expires_at:
|
||||
logger.warning(f"OAuth code {code[:10]}... manually expired")
|
||||
try:
|
||||
self.redis.delete(key)
|
||||
except Exception as del_error:
|
||||
logger.warning(f"Failed to delete expired code: {del_error}")
|
||||
return None
|
||||
|
||||
# Delete after use for security (one-time use)
|
||||
if delete_after_use:
|
||||
try:
|
||||
self.redis.delete(key)
|
||||
logger.info(f"Retrieved and deleted OAuth code {code[:10]}... (attempt {attempt + 1})")
|
||||
except Exception as del_error:
|
||||
logger.warning(f"Failed to delete code after use: {del_error}")
|
||||
# Continue anyway since we got the data
|
||||
else:
|
||||
logger.info(f"Retrieved OAuth code {code[:10]}... (not deleted, attempt {attempt + 1})")
|
||||
|
||||
return deserialized_data
|
||||
|
||||
except (RequestsConnectionError, RequestsTimeout, OSError, socket.error) as e:
|
||||
logger.warning(f"Redis connection error on retrieval attempt {attempt + 1}: {e}")
|
||||
if attempt == max_retries - 1:
|
||||
logger.error(f"Failed to retrieve OAuth code {code[:10]}... after {max_retries} attempts: {e}")
|
||||
return None
|
||||
time.sleep(0.5 * (attempt + 1)) # Exponential backoff
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to retrieve OAuth code {code[:10]}... on attempt {attempt + 1}: {e}")
|
||||
if attempt == max_retries - 1:
|
||||
return None
|
||||
time.sleep(0.5 * (attempt + 1))
|
||||
|
||||
return None
|
||||
|
||||
# User Session Methods
|
||||
|
||||
def set_session(self, session_id: str, user_data: Dict[str, Any]) -> bool:
|
||||
"""
|
||||
Store user session data with sliding expiration.
|
||||
|
||||
Args:
|
||||
session_id: Unique session identifier
|
||||
user_data: User session data (user_id, email, scopes, etc.)
|
||||
|
||||
Returns:
|
||||
True if stored successfully, False otherwise
|
||||
"""
|
||||
try:
|
||||
key = f"session:{session_id}"
|
||||
|
||||
# Add session metadata
|
||||
session_data = user_data.copy()
|
||||
session_data.update({
|
||||
"session_id": session_id,
|
||||
"created_at": time.time(),
|
||||
"last_accessed": time.time()
|
||||
})
|
||||
|
||||
# Serialize and store - Upstash Redis doesn't support mapping parameter
|
||||
serialized_data = self._serialize_data(session_data)
|
||||
|
||||
# Use individual hset calls for each field (Upstash compatibility)
|
||||
for field, value in serialized_data.items():
|
||||
self.redis.hset(key, field, value)
|
||||
self.redis.expire(key, self.session_ttl)
|
||||
|
||||
logger.info(f"Stored session {session_id[:10]}... with TTL {self.session_ttl}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to store session {session_id[:10]}...: {e}")
|
||||
return False
|
||||
|
||||
def get_session(self, session_id: str, refresh_ttl: bool = True) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Retrieve user session data.
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
refresh_ttl: If True, extend session TTL on access
|
||||
|
||||
Returns:
|
||||
Session data dictionary or None if not found/expired
|
||||
"""
|
||||
try:
|
||||
key = f"session:{session_id}"
|
||||
|
||||
# Get session data
|
||||
data = self.redis.hgetall(key)
|
||||
|
||||
if not data:
|
||||
logger.warning(f"Session {session_id[:10]}... not found or expired")
|
||||
return None
|
||||
|
||||
# Deserialize data
|
||||
session_data = self._deserialize_data(data)
|
||||
|
||||
# Update last accessed time and refresh TTL
|
||||
if refresh_ttl:
|
||||
session_data["last_accessed"] = time.time()
|
||||
self.redis.hset(key, "last_accessed", str(time.time()))
|
||||
self.redis.expire(key, self.session_ttl)
|
||||
logger.debug(f"Refreshed session {session_id[:10]}... TTL")
|
||||
|
||||
return session_data
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to retrieve session {session_id[:10]}...: {e}")
|
||||
return None
|
||||
|
||||
def delete_session(self, session_id: str) -> bool:
|
||||
"""
|
||||
Delete user session (logout).
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
|
||||
Returns:
|
||||
True if deleted successfully, False otherwise
|
||||
"""
|
||||
try:
|
||||
key = f"session:{session_id}"
|
||||
result = self.redis.delete(key)
|
||||
|
||||
if result:
|
||||
logger.info(f"Deleted session {session_id[:10]}...")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"Session {session_id[:10]}... not found for deletion")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to delete session {session_id[:10]}...: {e}")
|
||||
return False
|
||||
|
||||
# Health Check Methods
|
||||
|
||||
def health_check(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Perform Redis health check.
|
||||
|
||||
Returns:
|
||||
Health status dictionary
|
||||
"""
|
||||
try:
|
||||
# Test basic operations
|
||||
test_key = f"health:check:{int(time.time())}"
|
||||
test_value = {"timestamp": time.time(), "test": True}
|
||||
|
||||
# Test set - Use individual hset calls for Upstash compatibility
|
||||
serialized_test = self._serialize_data(test_value)
|
||||
for field, value in serialized_test.items():
|
||||
self.redis.hset(test_key, field, value)
|
||||
|
||||
# Test get
|
||||
retrieved = self.redis.hgetall(test_key)
|
||||
|
||||
# Test delete
|
||||
self.redis.delete(test_key)
|
||||
|
||||
return {
|
||||
"status": "healthy",
|
||||
"redis_connected": True,
|
||||
"operations_working": bool(retrieved),
|
||||
"timestamp": datetime.utcnow().isoformat()
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Redis health check failed: {e}")
|
||||
return {
|
||||
"status": "unhealthy",
|
||||
"redis_connected": False,
|
||||
"error": str(e),
|
||||
"timestamp": datetime.utcnow().isoformat()
|
||||
}
|
||||
|
||||
def get_stats(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get Redis usage statistics.
|
||||
|
||||
Returns:
|
||||
Statistics dictionary
|
||||
"""
|
||||
try:
|
||||
# Get basic info (not all Upstash plans support INFO command)
|
||||
stats = {
|
||||
"oauth_codes_pattern": "oauth:code:*",
|
||||
"sessions_pattern": "session:*",
|
||||
"timestamp": datetime.utcnow().isoformat()
|
||||
}
|
||||
|
||||
try:
|
||||
# Try to get counts (may fail on some Upstash plans)
|
||||
oauth_keys = self.redis.keys("oauth:code:*")
|
||||
session_keys = self.redis.keys("session:*")
|
||||
|
||||
stats.update({
|
||||
"active_oauth_codes": len(oauth_keys) if oauth_keys else 0,
|
||||
"active_sessions": len(session_keys) if session_keys else 0
|
||||
})
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not get detailed stats: {e}")
|
||||
stats["warning"] = "Detailed stats not available on this Redis plan"
|
||||
|
||||
return stats
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get Redis stats: {e}")
|
||||
return {"error": str(e), "timestamp": datetime.utcnow().isoformat()}
|
||||
|
||||
# Global instance for easy importing
|
||||
redis_store = None
|
||||
|
||||
def get_redis_store() -> Optional[RedisSessionStore]:
|
||||
"""
|
||||
Get global Redis store instance (singleton pattern).
|
||||
|
||||
Returns:
|
||||
RedisSessionStore instance or None if initialization fails
|
||||
"""
|
||||
global redis_store
|
||||
|
||||
if redis_store is None:
|
||||
try:
|
||||
logger.info("Initializing Redis store...")
|
||||
redis_store = RedisSessionStore()
|
||||
logger.info("Redis store initialized successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize Redis store: {e}")
|
||||
redis_store = None
|
||||
|
||||
return redis_store
|
||||
|
||||
def init_redis_store() -> RedisSessionStore:
|
||||
"""
|
||||
Initialize Redis store and perform health check.
|
||||
|
||||
Returns:
|
||||
RedisSessionStore instance
|
||||
|
||||
Raises:
|
||||
Exception if Redis is not available or unhealthy
|
||||
"""
|
||||
store = get_redis_store()
|
||||
|
||||
# Perform health check
|
||||
health = store.health_check()
|
||||
|
||||
if health["status"] != "healthy":
|
||||
raise Exception(f"Redis health check failed: {health}")
|
||||
|
||||
logger.info("Redis session store initialized and healthy")
|
||||
return store
|
||||
@@ -1,407 +0,0 @@
|
||||
# rekabet_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import List, Optional, Tuple, Dict, Any
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io # For io.BytesIO
|
||||
from urllib.parse import urlencode, urljoin, quote, parse_qs, urlparse
|
||||
from markitdown import MarkItDown
|
||||
import math
|
||||
|
||||
# pypdf for PDF processing (lighter alternative to PyMuPDF)
|
||||
from pypdf import PdfReader, PdfWriter # PyPDF2'nin devamı niteliğindeki pypdf
|
||||
|
||||
from .models import (
|
||||
RekabetKurumuSearchRequest,
|
||||
RekabetDecisionSummary,
|
||||
RekabetSearchResult,
|
||||
RekabetDocument,
|
||||
RekabetKararTuruGuidEnum
|
||||
)
|
||||
from pydantic import HttpUrl # Ensure HttpUrl is imported from pydantic
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers(): # Pragma: no cover
|
||||
logging.basicConfig(
|
||||
level=logging.INFO, # Varsayılan log seviyesi
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
# Debug betiğinde daha detaylı loglama için seviye ayrıca ayarlanabilir.
|
||||
|
||||
class RekabetKurumuApiClient:
|
||||
BASE_URL = "https://www.rekabet.gov.tr"
|
||||
SEARCH_PATH = "/tr/Kararlar"
|
||||
DECISION_LANDING_PATH_TEMPLATE = "/Karar"
|
||||
# PDF sayfa bazlı Markdown döndürüldüğü için bu sabit artık doğrudan kullanılmıyor.
|
||||
# DOCUMENT_MARKDOWN_CHUNK_SIZE = 5000
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=True,
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
def _build_search_query_params(self, params: RekabetKurumuSearchRequest) -> List[Tuple[str, str]]:
|
||||
query_params: List[Tuple[str, str]] = []
|
||||
query_params.append(("sayfaAdi", params.sayfaAdi if params.sayfaAdi is not None else ""))
|
||||
query_params.append(("YayinlanmaTarihi", params.YayinlanmaTarihi if params.YayinlanmaTarihi is not None else ""))
|
||||
query_params.append(("PdfText", params.PdfText if params.PdfText is not None else ""))
|
||||
|
||||
karar_turu_id_value = ""
|
||||
if params.KararTuruID is not None:
|
||||
karar_turu_id_value = params.KararTuruID.value if params.KararTuruID.value != "ALL" else ""
|
||||
query_params.append(("KararTuruID", karar_turu_id_value))
|
||||
|
||||
query_params.append(("KararSayisi", params.KararSayisi if params.KararSayisi is not None else ""))
|
||||
query_params.append(("KararTarihi", params.KararTarihi if params.KararTarihi is not None else ""))
|
||||
|
||||
if params.page and params.page > 1:
|
||||
query_params.append(("page", str(params.page)))
|
||||
|
||||
return query_params
|
||||
|
||||
async def search_decisions(self, params: RekabetKurumuSearchRequest) -> RekabetSearchResult:
|
||||
request_path = self.SEARCH_PATH
|
||||
final_query_params = self._build_search_query_params(params)
|
||||
logger.info(f"RekabetKurumuApiClient: Performing search. Path: {request_path}, Parameters: {final_query_params}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(request_path, params=final_query_params)
|
||||
response.raise_for_status()
|
||||
html_content = response.text
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"RekabetKurumuApiClient: HTTP request error during search: {e}")
|
||||
raise
|
||||
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
processed_decisions: List[RekabetDecisionSummary] = []
|
||||
total_records: Optional[int] = None
|
||||
total_pages: Optional[int] = None
|
||||
|
||||
pagination_div = soup.find("div", class_="yazi01")
|
||||
if pagination_div:
|
||||
text_content = pagination_div.get_text(separator=" ", strip=True)
|
||||
total_match = re.search(r"Toplam\s*:\s*(\d+)", text_content)
|
||||
if total_match:
|
||||
try:
|
||||
total_records = int(total_match.group(1))
|
||||
logger.debug(f"Total records found from pagination: {total_records}")
|
||||
except ValueError:
|
||||
logger.warning(f"Could not convert 'Toplam' value to int: {total_match.group(1)}")
|
||||
else:
|
||||
logger.warning("'Toplam :' string not found in pagination section.")
|
||||
|
||||
results_per_page_assumed = 10
|
||||
if total_records is not None:
|
||||
calculated_total_pages = math.ceil(total_records / results_per_page_assumed)
|
||||
total_pages = calculated_total_pages if calculated_total_pages > 0 else (1 if total_records > 0 else 0)
|
||||
logger.debug(f"Calculated total pages: {total_pages}")
|
||||
|
||||
if total_pages is None: # Fallback if total_records couldn't be parsed
|
||||
last_page_link = pagination_div.select_one("li.PagedList-skipToLast a")
|
||||
if last_page_link and last_page_link.has_attr('href'):
|
||||
qs = parse_qs(urlparse(last_page_link['href']).query)
|
||||
if 'page' in qs and qs['page']:
|
||||
try:
|
||||
total_pages = int(qs['page'][0])
|
||||
logger.debug(f"Total pages found from 'Last >>' link: {total_pages}")
|
||||
except ValueError:
|
||||
logger.warning(f"Could not convert page value from 'Last >>' link to int: {qs['page'][0]}")
|
||||
elif total_records == 0 : total_pages = 0 # If no records, 0 pages
|
||||
elif total_records is not None and total_records > 0 : total_pages = 1 # If records exist but no last page link (e.g. single page)
|
||||
else: logger.warning("'Last >>' link not found in pagination section.")
|
||||
|
||||
decision_tables_container = soup.find("div", id="kararList")
|
||||
if not decision_tables_container:
|
||||
logger.warning("`div#kararList` (decision list container) not found. HTML structure might have changed or no decisions on this page.")
|
||||
else:
|
||||
decision_tables = decision_tables_container.find_all("table", class_="equalDivide")
|
||||
logger.info(f"Found {len(decision_tables)} 'table' elements with class='equalDivide' for parsing.")
|
||||
|
||||
if not decision_tables and total_records is not None and total_records > 0 :
|
||||
logger.warning(f"Page indicates {total_records} records but no decision tables found with class='equalDivide'.")
|
||||
|
||||
for idx, table in enumerate(decision_tables):
|
||||
logger.debug(f"Processing table {idx + 1}...")
|
||||
try:
|
||||
rows = table.find_all("tr")
|
||||
if len(rows) != 3:
|
||||
logger.warning(f"Table {idx + 1} has an unexpected number of rows ({len(rows)} instead of 3). Skipping. HTML snippet:\n{table.prettify()[:500]}")
|
||||
continue
|
||||
|
||||
# Row 1: Publication Date, Decision Number, Related Cases Link
|
||||
td_elements_r1 = rows[0].find_all("td")
|
||||
pub_date = td_elements_r1[0].get_text(strip=True) if len(td_elements_r1) > 0 else None
|
||||
dec_num = td_elements_r1[1].get_text(strip=True) if len(td_elements_r1) > 1 else None
|
||||
|
||||
related_cases_link_tag = td_elements_r1[2].find("a", href=True) if len(td_elements_r1) > 2 else None
|
||||
related_cases_url_str: Optional[str] = None
|
||||
karar_id_from_related: Optional[str] = None
|
||||
if related_cases_link_tag and related_cases_link_tag.has_attr('href'):
|
||||
related_cases_url_str = urljoin(self.BASE_URL, related_cases_link_tag['href'])
|
||||
qs_related = parse_qs(urlparse(related_cases_link_tag['href']).query)
|
||||
if 'kararId' in qs_related and qs_related['kararId']:
|
||||
karar_id_from_related = qs_related['kararId'][0]
|
||||
|
||||
# Row 2: Decision Date, Decision Type
|
||||
td_elements_r2 = rows[1].find_all("td")
|
||||
dec_date = td_elements_r2[0].get_text(strip=True) if len(td_elements_r2) > 0 else None
|
||||
dec_type_text = td_elements_r2[1].get_text(strip=True) if len(td_elements_r2) > 1 else None
|
||||
|
||||
# Row 3: Title and Main Decision Link
|
||||
title_cell = rows[2].find("td", colspan="5")
|
||||
decision_link_tag = title_cell.find("a", href=True) if title_cell else None
|
||||
|
||||
title_text: Optional[str] = None
|
||||
decision_landing_url_str: Optional[str] = None
|
||||
karar_id_from_main_link: Optional[str] = None
|
||||
|
||||
if decision_link_tag and decision_link_tag.has_attr('href'):
|
||||
title_text = decision_link_tag.get_text(strip=True)
|
||||
href_val = decision_link_tag['href']
|
||||
if href_val.startswith(self.DECISION_LANDING_PATH_TEMPLATE + "?kararId="): # Ensure it's a decision link
|
||||
decision_landing_url_str = urljoin(self.BASE_URL, href_val)
|
||||
qs_main = parse_qs(urlparse(href_val).query)
|
||||
if 'kararId' in qs_main and qs_main['kararId']:
|
||||
karar_id_from_main_link = qs_main['kararId'][0]
|
||||
else:
|
||||
logger.warning(f"Table {idx+1} decision link has unexpected format: {href_val}")
|
||||
else:
|
||||
logger.warning(f"Table {idx+1} could not find title/decision link tag.")
|
||||
|
||||
current_karar_id = karar_id_from_main_link or karar_id_from_related
|
||||
|
||||
if not current_karar_id:
|
||||
logger.warning(f"Table {idx+1} Karar ID not found. Skipping. Title (if any): {title_text}")
|
||||
continue
|
||||
|
||||
# Convert string URLs to HttpUrl for the model
|
||||
final_decision_url = HttpUrl(decision_landing_url_str) if decision_landing_url_str else None
|
||||
final_related_cases_url = HttpUrl(related_cases_url_str) if related_cases_url_str else None
|
||||
|
||||
processed_decisions.append(RekabetDecisionSummary(
|
||||
publication_date=pub_date, decision_number=dec_num, decision_date=dec_date,
|
||||
decision_type_text=dec_type_text, title=title_text,
|
||||
decision_url=final_decision_url,
|
||||
karar_id=current_karar_id,
|
||||
related_cases_url=final_related_cases_url
|
||||
))
|
||||
logger.debug(f"Table {idx+1} parsed successfully: Karar ID '{current_karar_id}', Title '{title_text[:50] if title_text else 'N/A'}...'")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"RekabetKurumuApiClient: Error parsing decision summary {idx+1}: {e}. Problematic Table HTML:\n{table.prettify()}", exc_info=True)
|
||||
continue
|
||||
|
||||
return RekabetSearchResult(
|
||||
decisions=processed_decisions, total_records_found=total_records,
|
||||
retrieved_page_number=params.page, total_pages=total_pages if total_pages is not None else 0
|
||||
)
|
||||
|
||||
async def _extract_pdf_url_and_landing_page_metadata(self, karar_id: str, landing_page_html: str, landing_page_url: str) -> Dict[str, Any]:
|
||||
soup = BeautifulSoup(landing_page_html, 'html.parser')
|
||||
data: Dict[str, Any] = {
|
||||
"pdf_url": None,
|
||||
"title_on_landing_page": soup.title.string.strip() if soup.title and soup.title.string else f"Rekabet Kurumu Kararı {karar_id}",
|
||||
}
|
||||
# This part needs to be robust and specific to Rekabet Kurumu's landing page structure.
|
||||
# Look for common patterns: direct links, download buttons, embedded viewers.
|
||||
pdf_anchor = soup.find("a", href=re.compile(r"\.pdf(\?|$)", re.IGNORECASE)) # Basic PDF link
|
||||
if not pdf_anchor: # Try other common patterns if the basic one fails
|
||||
# Example: Look for links with specific text or class
|
||||
pdf_anchor = soup.find("a", string=re.compile(r"karar metni|pdf indir", re.IGNORECASE))
|
||||
|
||||
if pdf_anchor and pdf_anchor.has_attr('href'):
|
||||
pdf_path = pdf_anchor['href']
|
||||
data["pdf_url"] = urljoin(landing_page_url, pdf_path)
|
||||
logger.info(f"PDF link found on landing page (<a>): {data['pdf_url']}")
|
||||
else:
|
||||
iframe_pdf = soup.find("iframe", src=re.compile(r"\.pdf(\?|$)", re.IGNORECASE))
|
||||
if iframe_pdf and iframe_pdf.has_attr('src'):
|
||||
pdf_path = iframe_pdf['src']
|
||||
data["pdf_url"] = urljoin(landing_page_url, pdf_path)
|
||||
logger.info(f"PDF link found on landing page (<iframe>): {data['pdf_url']}")
|
||||
else:
|
||||
embed_pdf = soup.find("embed", src=re.compile(r"\.pdf(\?|$)", re.IGNORECASE), type="application/pdf")
|
||||
if embed_pdf and embed_pdf.has_attr('src'):
|
||||
pdf_path = embed_pdf['src']
|
||||
data["pdf_url"] = urljoin(landing_page_url, pdf_path)
|
||||
logger.info(f"PDF link found on landing page (<embed>): {data['pdf_url']}")
|
||||
else:
|
||||
logger.warning(f"No PDF link found on landing page {landing_page_url} for kararId {karar_id} using common selectors.")
|
||||
return data
|
||||
|
||||
async def _download_pdf_bytes(self, pdf_url: str) -> Optional[bytes]:
|
||||
try:
|
||||
url_to_fetch = pdf_url if pdf_url.startswith(('http://', 'https://')) else urljoin(self.BASE_URL, pdf_url)
|
||||
logger.info(f"Downloading PDF from: {url_to_fetch}")
|
||||
response = await self.http_client.get(url_to_fetch)
|
||||
response.raise_for_status()
|
||||
pdf_bytes = await response.aread()
|
||||
logger.info(f"PDF content downloaded ({len(pdf_bytes)} bytes) from: {url_to_fetch}")
|
||||
return pdf_bytes
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"HTTP error downloading PDF from {pdf_url}: {e}")
|
||||
except Exception as e:
|
||||
logger.error(f"General error downloading PDF from {pdf_url}: {e}")
|
||||
return None
|
||||
|
||||
def _extract_single_pdf_page_as_pdf_bytes(self, original_pdf_bytes: bytes, page_number_to_extract: int) -> Tuple[Optional[bytes], int]:
|
||||
total_pages_in_original_pdf = 0
|
||||
single_page_pdf_bytes: Optional[bytes] = None
|
||||
|
||||
if not original_pdf_bytes:
|
||||
logger.warning("No original PDF bytes provided for page extraction.")
|
||||
return None, 0
|
||||
|
||||
try:
|
||||
pdf_stream = io.BytesIO(original_pdf_bytes)
|
||||
reader = PdfReader(pdf_stream)
|
||||
total_pages_in_original_pdf = len(reader.pages)
|
||||
|
||||
if not (0 < page_number_to_extract <= total_pages_in_original_pdf):
|
||||
logger.warning(f"Requested page number ({page_number_to_extract}) is out of PDF page range (1-{total_pages_in_original_pdf}).")
|
||||
return None, total_pages_in_original_pdf
|
||||
|
||||
writer = PdfWriter()
|
||||
writer.add_page(reader.pages[page_number_to_extract - 1]) # pypdf is 0-indexed
|
||||
|
||||
output_pdf_stream = io.BytesIO()
|
||||
writer.write(output_pdf_stream)
|
||||
single_page_pdf_bytes = output_pdf_stream.getvalue()
|
||||
|
||||
logger.debug(f"Page {page_number_to_extract} of original PDF (total {total_pages_in_original_pdf} pages) extracted as new PDF using pypdf.")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error extracting PDF page using pypdf: {e}", exc_info=True)
|
||||
return None, total_pages_in_original_pdf
|
||||
return single_page_pdf_bytes, total_pages_in_original_pdf
|
||||
|
||||
def _convert_pdf_bytes_to_markdown(self, pdf_bytes: bytes, source_url_for_logging: str) -> Optional[str]:
|
||||
if not pdf_bytes:
|
||||
logger.warning(f"No PDF bytes provided for Markdown conversion (source: {source_url_for_logging}).")
|
||||
return None
|
||||
|
||||
pdf_stream = io.BytesIO(pdf_bytes)
|
||||
try:
|
||||
md_converter = MarkItDown(enable_plugins=False)
|
||||
conversion_result = md_converter.convert(pdf_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
|
||||
if not markdown_text:
|
||||
logger.warning(f"MarkItDown returned empty content from PDF byte stream (source: {source_url_for_logging}). PDF page might be image-based or MarkItDown could not process the PDF stream.")
|
||||
return markdown_text
|
||||
except Exception as e:
|
||||
logger.error(f"MarkItDown conversion error for PDF byte stream (source: {source_url_for_logging}): {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
async def get_decision_document(self, karar_id: str, page_number: int = 1) -> RekabetDocument:
|
||||
if not karar_id:
|
||||
return RekabetDocument(
|
||||
source_landing_page_url=HttpUrl(f"{self.BASE_URL}"),
|
||||
karar_id=karar_id or "UNKNOWN_KARAR_ID",
|
||||
error_message="karar_id is required.",
|
||||
current_page=1, total_pages=0, is_paginated=False )
|
||||
|
||||
decision_url_path = f"{self.DECISION_LANDING_PATH_TEMPLATE}?kararId={karar_id}"
|
||||
full_landing_page_url = urljoin(self.BASE_URL, decision_url_path)
|
||||
|
||||
logger.info(f"RekabetKurumuApiClient: Getting decision document: {full_landing_page_url}, Requested PDF Page: {page_number}")
|
||||
|
||||
pdf_url_to_report: Optional[HttpUrl] = None
|
||||
title_to_report: Optional[str] = f"Rekabet Kurumu Kararı {karar_id}" # Default
|
||||
error_message: Optional[str] = None
|
||||
markdown_for_requested_page: Optional[str] = None
|
||||
total_pdf_pages: int = 0
|
||||
|
||||
try:
|
||||
async with self.http_client.stream("GET", full_landing_page_url) as response:
|
||||
response.raise_for_status()
|
||||
content_type = response.headers.get("content-type", "").lower()
|
||||
final_url_of_response = HttpUrl(str(response.url))
|
||||
original_pdf_bytes: Optional[bytes] = None
|
||||
|
||||
if "application/pdf" in content_type:
|
||||
logger.info(f"URL {final_url_of_response} is a direct PDF. Processing content.")
|
||||
pdf_url_to_report = final_url_of_response
|
||||
original_pdf_bytes = await response.aread()
|
||||
elif "text/html" in content_type:
|
||||
logger.info(f"URL {final_url_of_response} is an HTML landing page. Looking for PDF link.")
|
||||
landing_page_html_bytes = await response.aread()
|
||||
detected_charset = response.charset_encoding or 'utf-8'
|
||||
try: landing_page_html = landing_page_html_bytes.decode(detected_charset)
|
||||
except UnicodeDecodeError: landing_page_html = landing_page_html_bytes.decode('utf-8', errors='replace')
|
||||
|
||||
if landing_page_html.strip():
|
||||
landing_page_data = self._extract_pdf_url_and_landing_page_metadata(karar_id, landing_page_html, str(final_url_of_response))
|
||||
pdf_url_str_from_html = landing_page_data.get("pdf_url")
|
||||
if landing_page_data.get("title_on_landing_page"): title_to_report = landing_page_data.get("title_on_landing_page")
|
||||
if pdf_url_str_from_html:
|
||||
pdf_url_to_report = HttpUrl(pdf_url_str_from_html)
|
||||
original_pdf_bytes = await self._download_pdf_bytes(str(pdf_url_to_report))
|
||||
else: error_message = (error_message or "") + " PDF URL not found on HTML landing page."
|
||||
else: error_message = "Decision landing page content is empty."
|
||||
else: error_message = f"Unexpected content type ({content_type}) for URL: {final_url_of_response}"
|
||||
|
||||
if original_pdf_bytes:
|
||||
single_page_pdf_bytes, total_pdf_pages_from_extraction = self._extract_single_pdf_page_as_pdf_bytes(original_pdf_bytes, page_number)
|
||||
total_pdf_pages = total_pdf_pages_from_extraction
|
||||
|
||||
if single_page_pdf_bytes:
|
||||
markdown_for_requested_page = self._convert_pdf_bytes_to_markdown(single_page_pdf_bytes, str(pdf_url_to_report or full_landing_page_url))
|
||||
if not markdown_for_requested_page:
|
||||
error_message = (error_message or "") + f"; Could not convert page {page_number} of PDF to Markdown."
|
||||
elif total_pdf_pages > 0 :
|
||||
error_message = (error_message or "") + f"; Could not extract page {page_number} from PDF (page may be out of range or extraction failed)."
|
||||
else:
|
||||
error_message = (error_message or "") + "; PDF could not be processed or page count was zero (original PDF might be invalid)."
|
||||
elif not error_message:
|
||||
error_message = "PDF content could not be downloaded or identified."
|
||||
|
||||
is_paginated = total_pdf_pages > 1
|
||||
current_page_final = page_number
|
||||
if total_pdf_pages > 0:
|
||||
current_page_final = max(1, min(page_number, total_pdf_pages))
|
||||
elif markdown_for_requested_page is None:
|
||||
current_page_final = 1
|
||||
|
||||
# If markdown is None but there was no specific error for markdown conversion (e.g. PDF not found first)
|
||||
# make sure error_message reflects that.
|
||||
if markdown_for_requested_page is None and pdf_url_to_report and not error_message:
|
||||
error_message = (error_message or "") + "; Failed to produce Markdown from PDF page."
|
||||
|
||||
|
||||
return RekabetDocument(
|
||||
source_landing_page_url=full_landing_page_url, karar_id=karar_id,
|
||||
title_on_landing_page=title_to_report, pdf_url=pdf_url_to_report,
|
||||
markdown_chunk=markdown_for_requested_page, current_page=current_page_final,
|
||||
total_pages=total_pdf_pages, is_paginated=is_paginated,
|
||||
error_message=error_message.strip("; ") if error_message else None )
|
||||
|
||||
except httpx.HTTPStatusError as e: error_msg_detail = f"HTTP Status error {e.response.status_code} while processing decision page."
|
||||
except httpx.RequestError as e: error_msg_detail = f"HTTP Request error while processing decision page: {str(e)}"
|
||||
except Exception as e: error_msg_detail = f"General error while processing decision: {str(e)}"
|
||||
|
||||
exc_info_flag = not isinstance(e, (httpx.HTTPStatusError, httpx.RequestError)) if 'e' in locals() else True
|
||||
logger.error(f"RekabetKurumuApiClient: Error processing decision {karar_id} from {full_landing_page_url}: {error_msg_detail}", exc_info=exc_info_flag)
|
||||
error_message = (error_message + "; " if error_message else "") + error_msg_detail
|
||||
|
||||
return RekabetDocument(
|
||||
source_landing_page_url=full_landing_page_url, karar_id=karar_id,
|
||||
title_on_landing_page=title_to_report, pdf_url=pdf_url_to_report,
|
||||
markdown_chunk=None, current_page=page_number, total_pages=0, is_paginated=False,
|
||||
error_message=error_message.strip("; ") if error_message else "An unexpected error occurred." )
|
||||
|
||||
async def close_client_session(self): # Pragma: no cover
|
||||
if hasattr(self, 'http_client') and self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("RekabetKurumuApiClient: HTTP client session closed.")
|
||||
@@ -1,71 +0,0 @@
|
||||
# rekabet_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl
|
||||
from typing import List, Optional, Any
|
||||
from enum import Enum
|
||||
|
||||
# Enum for decision type GUIDs (used by the client and expected by the website)
|
||||
class RekabetKararTuruGuidEnum(str, Enum):
|
||||
TUMU = "ALL" # Represents "All" or "Select Decision Type"
|
||||
BIRLESME_DEVRALMA = "2fff0979-9f9d-42d7-8c2e-a30705889542" # Merger and Acquisition
|
||||
DIGER = "dda8feaf-c919-405c-9da1-823f22b45ad9" # Other
|
||||
MENFI_TESPIT_MUAFIYET = "95ccd210-5304-49c5-b9e0-8ee53c50d4e8" # Negative Clearance and Exemption
|
||||
OZELLESTIRME = "e1f14505-842b-4af5-95d1-312d6de1a541" # Privatization
|
||||
REKABET_IHLALI = "720614bf-efd1-4dca-9785-b98eb65f2677" # Competition Infringement
|
||||
|
||||
# Enum for user-friendly decision type names (for server tool parameters)
|
||||
# These correspond to the display names on the website's select dropdown.
|
||||
class RekabetKararTuruAdiEnum(str, Enum):
|
||||
TUMU = "Tümü" # Corresponds to the empty value "" for GUID, meaning "All"
|
||||
BIRLESME_VE_DEVRALMA = "Birleşme ve Devralma"
|
||||
DIGER = "Diğer"
|
||||
MENFI_TESPIT_VE_MUAFIYET = "Menfi Tespit ve Muafiyet"
|
||||
OZELLESTIRME = "Özelleştirme"
|
||||
REKABET_IHLALI = "Rekabet İhlali"
|
||||
|
||||
class RekabetKurumuSearchRequest(BaseModel):
|
||||
"""Model for Rekabet Kurumu (Turkish Competition Authority) search request."""
|
||||
sayfaAdi: str = Field("", description="Title")
|
||||
YayinlanmaTarihi: str = Field("", description="Date")
|
||||
PdfText: str = Field("", description="Text")
|
||||
KararTuruID: RekabetKararTuruGuidEnum = Field(RekabetKararTuruGuidEnum.TUMU, description="Type")
|
||||
KararSayisi: str = Field("", description="No")
|
||||
KararTarihi: str = Field("", description="Date")
|
||||
page: int = Field(1, ge=1, description="Page")
|
||||
|
||||
class RekabetDecisionSummary(BaseModel):
|
||||
"""Model for a single Rekabet Kurumu decision summary from search results."""
|
||||
publication_date: str = Field("", description="Pub date")
|
||||
decision_number: str = Field("", description="Number")
|
||||
decision_date: str = Field("", description="Date")
|
||||
decision_type_text: str = Field("", description="Type")
|
||||
title: str = Field("", description="Title")
|
||||
decision_url: str = Field("", description="URL")
|
||||
karar_id: str = Field("", description="ID")
|
||||
related_cases_url: str = Field("", description="Cases URL")
|
||||
|
||||
class RekabetSearchResult(BaseModel):
|
||||
"""Model for the overall search result for Rekabet Kurumu decisions."""
|
||||
decisions: List[RekabetDecisionSummary]
|
||||
total_records_found: int = Field(0, description="Total")
|
||||
retrieved_page_number: int = Field(description="Page")
|
||||
total_pages: int = Field(0, description="Pages")
|
||||
|
||||
class RekabetDocument(BaseModel):
|
||||
"""
|
||||
Model for a Rekabet Kurumu decision document.
|
||||
Contains metadata from the landing page, a link to the PDF,
|
||||
and the PDF's content converted to paginated Markdown.
|
||||
"""
|
||||
source_landing_page_url: HttpUrl = Field(description="Source URL")
|
||||
karar_id: str = Field(description="ID")
|
||||
|
||||
title_on_landing_page: Optional[str] = Field(None, description="Title")
|
||||
pdf_url: Optional[HttpUrl] = Field(None, description="PDF URL")
|
||||
|
||||
markdown_chunk: Optional[str] = Field(None, description="Content")
|
||||
current_page: int = Field(1, description="Page")
|
||||
total_pages: int = Field(1, description="Total pages")
|
||||
is_paginated: bool = Field(False, description="Paginated")
|
||||
|
||||
error_message: Optional[str] = Field(None, description="Error")
|
||||
@@ -1,119 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Standalone ASGI server runner for Yargı MCP
|
||||
|
||||
This script provides a simple way to run the Yargı MCP server
|
||||
as a web service using uvicorn.
|
||||
|
||||
Usage:
|
||||
python run_asgi.py
|
||||
python run_asgi.py --host 0.0.0.0 --port 8080
|
||||
python run_asgi.py --reload # For development
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
# Add project root to Python path
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
|
||||
try:
|
||||
import uvicorn
|
||||
except ImportError:
|
||||
print("Error: uvicorn is not installed.")
|
||||
print("Please install it with: pip install uvicorn")
|
||||
sys.exit(1)
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Run Yargı MCP server as an ASGI web service"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--host",
|
||||
type=str,
|
||||
default=os.getenv("HOST", "127.0.0.1"),
|
||||
help="Host to bind to (default: 127.0.0.1)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--port",
|
||||
type=int,
|
||||
default=int(os.getenv("PORT", "8000")),
|
||||
help="Port to bind to (default: 8000)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--reload",
|
||||
action="store_true",
|
||||
help="Enable auto-reload for development"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--transport",
|
||||
choices=["http", "sse"],
|
||||
default="http",
|
||||
help="Transport type (default: http)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--log-level",
|
||||
choices=["debug", "info", "warning", "error"],
|
||||
default=os.getenv("LOG_LEVEL", "info").lower(),
|
||||
help="Log level (default: info)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--workers",
|
||||
type=int,
|
||||
default=1,
|
||||
help="Number of worker processes (default: 1)"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# Select app based on transport
|
||||
app_name = "asgi_app:app" if args.transport == "http" else "asgi_app:sse_app"
|
||||
|
||||
# Configure uvicorn
|
||||
config = {
|
||||
"app": app_name,
|
||||
"host": args.host,
|
||||
"port": args.port,
|
||||
"log_level": args.log_level,
|
||||
"reload": args.reload,
|
||||
"access_log": True,
|
||||
}
|
||||
|
||||
# Add workers only if not in reload mode
|
||||
if not args.reload and args.workers > 1:
|
||||
config["workers"] = args.workers
|
||||
|
||||
# Print startup information
|
||||
print(f"Starting Yargı MCP server...")
|
||||
print(f"Host: {args.host}")
|
||||
print(f"Port: {args.port}")
|
||||
print(f"Transport: {args.transport}")
|
||||
print(f"Log level: {args.log_level}")
|
||||
if args.reload:
|
||||
print("Auto-reload: enabled")
|
||||
else:
|
||||
print(f"Workers: {args.workers}")
|
||||
print(f"\nServer will be available at: http://{args.host}:{args.port}")
|
||||
print(f"MCP endpoint: http://{args.host}:{args.port}/mcp/")
|
||||
print(f"Health check: http://{args.host}:{args.port}/health")
|
||||
print(f"API status: http://{args.host}:{args.port}/status")
|
||||
print("\nPress CTRL+C to stop the server\n")
|
||||
|
||||
# Run uvicorn
|
||||
try:
|
||||
uvicorn.run(**config)
|
||||
except KeyboardInterrupt:
|
||||
print("\nShutting down server...")
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,56 +0,0 @@
|
||||
# sayistay_mcp_module/__init__.py
|
||||
|
||||
"""
|
||||
Sayıştay (Turkish Court of Accounts) MCP Module
|
||||
|
||||
This module provides access to three types of Sayıştay decisions:
|
||||
- Genel Kurul (General Assembly) decisions
|
||||
- Temyiz Kurulu (Appeals Board) decisions
|
||||
- Daire (Chamber) decisions
|
||||
|
||||
The module handles ASP.NET WebForms authentication with CSRF tokens
|
||||
and DataTables-based pagination for comprehensive decision search.
|
||||
"""
|
||||
|
||||
from .client import SayistayApiClient
|
||||
from .models import (
|
||||
# Genel Kurul models
|
||||
GenelKurulSearchRequest,
|
||||
GenelKurulSearchResponse,
|
||||
GenelKurulDecision,
|
||||
|
||||
# Temyiz Kurulu models
|
||||
TemyizKuruluSearchRequest,
|
||||
TemyizKuruluSearchResponse,
|
||||
TemyizKuruluDecision,
|
||||
|
||||
# Daire models
|
||||
DaireSearchRequest,
|
||||
DaireSearchResponse,
|
||||
DaireDecision,
|
||||
|
||||
# Document models
|
||||
SayistayDocumentMarkdown
|
||||
)
|
||||
from .enums import (
|
||||
DaireEnum,
|
||||
KamuIdaresiTuruEnum,
|
||||
WebKararKonusuEnum
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"SayistayApiClient",
|
||||
"GenelKurulSearchRequest",
|
||||
"GenelKurulSearchResponse",
|
||||
"GenelKurulDecision",
|
||||
"TemyizKuruluSearchRequest",
|
||||
"TemyizKuruluSearchResponse",
|
||||
"TemyizKuruluDecision",
|
||||
"DaireSearchRequest",
|
||||
"DaireSearchResponse",
|
||||
"DaireDecision",
|
||||
"SayistayDocumentMarkdown",
|
||||
"DaireEnum",
|
||||
"KamuIdaresiTuruEnum",
|
||||
"WebKararKonusuEnum"
|
||||
]
|
||||
@@ -1,689 +0,0 @@
|
||||
# sayistay_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
import re
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
import logging
|
||||
import html
|
||||
import io
|
||||
from urllib.parse import urlencode, urljoin
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
GenelKurulSearchRequest, GenelKurulSearchResponse, GenelKurulDecision,
|
||||
TemyizKuruluSearchRequest, TemyizKuruluSearchResponse, TemyizKuruluDecision,
|
||||
DaireSearchRequest, DaireSearchResponse, DaireDecision,
|
||||
SayistayDocumentMarkdown
|
||||
)
|
||||
from .enums import DaireEnum, KamuIdaresiTuruEnum, WebKararKonusuEnum, WEB_KARAR_KONUSU_MAPPING
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
|
||||
class SayistayApiClient:
|
||||
"""
|
||||
API Client for Sayıştay (Turkish Court of Accounts) decision search system.
|
||||
|
||||
Handles three types of decisions:
|
||||
- Genel Kurul (General Assembly): Precedent-setting interpretive decisions
|
||||
- Temyiz Kurulu (Appeals Board): Appeals against chamber decisions
|
||||
- Daire (Chamber): First-instance audit findings and sanctions
|
||||
|
||||
Features:
|
||||
- ASP.NET WebForms session management with CSRF tokens
|
||||
- DataTables-based pagination and filtering
|
||||
- Automatic session refresh on expiration
|
||||
- Document retrieval with Markdown conversion
|
||||
"""
|
||||
|
||||
BASE_URL = "https://www.sayistay.gov.tr"
|
||||
|
||||
# Search endpoints for each decision type
|
||||
GENEL_KURUL_ENDPOINT = "/KararlarGenelKurul/DataTablesList"
|
||||
TEMYIZ_KURULU_ENDPOINT = "/KararlarTemyiz/DataTablesList"
|
||||
DAIRE_ENDPOINT = "/KararlarDaire/DataTablesList"
|
||||
|
||||
# Page endpoints for session initialization and document access
|
||||
GENEL_KURUL_PAGE = "/KararlarGenelKurul"
|
||||
TEMYIZ_KURULU_PAGE = "/KararlarTemyiz"
|
||||
DAIRE_PAGE = "/KararlarDaire"
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.request_timeout = request_timeout
|
||||
self.session_cookies: Dict[str, str] = {}
|
||||
self.csrf_tokens: Dict[str, str] = {} # Store tokens for each endpoint
|
||||
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "application/json, text/javascript, */*; q=0.01",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36",
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
"Sec-Fetch-Dest": "empty",
|
||||
"Sec-Fetch-Mode": "cors",
|
||||
"Sec-Fetch-Site": "same-origin"
|
||||
},
|
||||
timeout=request_timeout,
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
async def _initialize_session_for_endpoint(self, endpoint_type: str) -> bool:
|
||||
"""
|
||||
Initialize session and obtain CSRF token for specific endpoint.
|
||||
|
||||
Args:
|
||||
endpoint_type: One of 'genel_kurul', 'temyiz_kurulu', 'daire'
|
||||
|
||||
Returns:
|
||||
True if session initialized successfully, False otherwise
|
||||
"""
|
||||
page_mapping = {
|
||||
'genel_kurul': self.GENEL_KURUL_PAGE,
|
||||
'temyiz_kurulu': self.TEMYIZ_KURULU_PAGE,
|
||||
'daire': self.DAIRE_PAGE
|
||||
}
|
||||
|
||||
if endpoint_type not in page_mapping:
|
||||
logger.error(f"Invalid endpoint type: {endpoint_type}")
|
||||
return False
|
||||
|
||||
page_url = page_mapping[endpoint_type]
|
||||
logger.info(f"Initializing session for {endpoint_type} endpoint: {page_url}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(page_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Extract session cookies
|
||||
for cookie_name, cookie_value in response.cookies.items():
|
||||
self.session_cookies[cookie_name] = cookie_value
|
||||
logger.debug(f"Stored session cookie: {cookie_name}")
|
||||
|
||||
# Extract CSRF token from form
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
csrf_input = soup.find('input', {'name': '__RequestVerificationToken'})
|
||||
|
||||
if csrf_input and csrf_input.get('value'):
|
||||
self.csrf_tokens[endpoint_type] = csrf_input['value']
|
||||
logger.info(f"Extracted CSRF token for {endpoint_type}")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"CSRF token not found in {endpoint_type} page")
|
||||
return False
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"HTTP error during session initialization for {endpoint_type}: {e}")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing session for {endpoint_type}: {e}")
|
||||
return False
|
||||
|
||||
def _enum_to_form_value(self, enum_value: str, enum_type: str) -> str:
|
||||
"""Convert enum values to form values expected by the API."""
|
||||
if enum_value == "ALL":
|
||||
if enum_type == "daire":
|
||||
return "Tüm Daireler"
|
||||
elif enum_type == "kamu_idaresi":
|
||||
return "Tüm Kurumlar"
|
||||
elif enum_type == "web_karar_konusu":
|
||||
return "Tüm Konular"
|
||||
|
||||
# Apply web_karar_konusu mapping
|
||||
if enum_type == "web_karar_konusu":
|
||||
return WEB_KARAR_KONUSU_MAPPING.get(enum_value, enum_value)
|
||||
|
||||
return enum_value
|
||||
|
||||
def _build_datatables_params(self, start: int, length: int, draw: int = 1) -> List[Tuple[str, str]]:
|
||||
"""Build standard DataTables parameters for all endpoints."""
|
||||
params = [
|
||||
("draw", str(draw)),
|
||||
("start", str(start)),
|
||||
("length", str(length)),
|
||||
("search[value]", ""),
|
||||
("search[regex]", "false")
|
||||
]
|
||||
return params
|
||||
|
||||
def _build_genel_kurul_form_data(self, params: GenelKurulSearchRequest, draw: int = 1) -> List[Tuple[str, str]]:
|
||||
"""Build form data for Genel Kurul search request."""
|
||||
form_data = self._build_datatables_params(params.start, params.length, draw)
|
||||
|
||||
# Add DataTables column definitions (from actual request)
|
||||
column_defs = [
|
||||
("columns[0][data]", "KARARNO"),
|
||||
("columns[0][name]", ""),
|
||||
("columns[0][searchable]", "true"),
|
||||
("columns[0][orderable]", "false"),
|
||||
("columns[0][search][value]", ""),
|
||||
("columns[0][search][regex]", "false"),
|
||||
|
||||
("columns[1][data]", "KARARNO"),
|
||||
("columns[1][name]", ""),
|
||||
("columns[1][searchable]", "true"),
|
||||
("columns[1][orderable]", "true"),
|
||||
("columns[1][search][value]", ""),
|
||||
("columns[1][search][regex]", "false"),
|
||||
|
||||
("columns[2][data]", "KARARTARIH"),
|
||||
("columns[2][name]", ""),
|
||||
("columns[2][searchable]", "true"),
|
||||
("columns[2][orderable]", "true"),
|
||||
("columns[2][search][value]", ""),
|
||||
("columns[2][search][regex]", "false"),
|
||||
|
||||
("columns[3][data]", "KARAROZETI"),
|
||||
("columns[3][name]", ""),
|
||||
("columns[3][searchable]", "true"),
|
||||
("columns[3][orderable]", "false"),
|
||||
("columns[3][search][value]", ""),
|
||||
("columns[3][search][regex]", "false"),
|
||||
|
||||
("columns[4][data]", ""),
|
||||
("columns[4][name]", ""),
|
||||
("columns[4][searchable]", "true"),
|
||||
("columns[4][orderable]", "false"),
|
||||
("columns[4][search][value]", ""),
|
||||
("columns[4][search][regex]", "false"),
|
||||
|
||||
("order[0][column]", "2"),
|
||||
("order[0][dir]", "desc")
|
||||
]
|
||||
form_data.extend(column_defs)
|
||||
|
||||
# Add search parameters
|
||||
form_data.extend([
|
||||
("KararlarGenelKurulAra.KARARNO", params.karar_no or ""),
|
||||
("__Invariant[]", "KararlarGenelKurulAra.KARARNO"),
|
||||
("__Invariant[]", "KararlarGenelKurulAra.KARAREK"),
|
||||
("KararlarGenelKurulAra.KARAREK", params.karar_ek or ""),
|
||||
("KararlarGenelKurulAra.KARARTARIHBaslangic", params.karar_tarih_baslangic or "Başlangıç Tarihi"),
|
||||
("KararlarGenelKurulAra.KARARTARIHBitis", params.karar_tarih_bitis or "Bitiş Tarihi"),
|
||||
("KararlarGenelKurulAra.KARARTAMAMI", params.karar_tamami or ""),
|
||||
("__RequestVerificationToken", self.csrf_tokens.get('genel_kurul', ''))
|
||||
])
|
||||
|
||||
return form_data
|
||||
|
||||
def _build_temyiz_kurulu_form_data(self, params: TemyizKuruluSearchRequest, draw: int = 1) -> List[Tuple[str, str]]:
|
||||
"""Build form data for Temyiz Kurulu search request."""
|
||||
form_data = self._build_datatables_params(params.start, params.length, draw)
|
||||
|
||||
# Add DataTables column definitions (from actual request)
|
||||
column_defs = [
|
||||
("columns[0][data]", "TEMYIZTUTANAKTARIHI"),
|
||||
("columns[0][name]", ""),
|
||||
("columns[0][searchable]", "true"),
|
||||
("columns[0][orderable]", "false"),
|
||||
("columns[0][search][value]", ""),
|
||||
("columns[0][search][regex]", "false"),
|
||||
|
||||
("columns[1][data]", "TEMYIZTUTANAKTARIHI"),
|
||||
("columns[1][name]", ""),
|
||||
("columns[1][searchable]", "true"),
|
||||
("columns[1][orderable]", "true"),
|
||||
("columns[1][search][value]", ""),
|
||||
("columns[1][search][regex]", "false"),
|
||||
|
||||
("columns[2][data]", "ILAMDAIRESI"),
|
||||
("columns[2][name]", ""),
|
||||
("columns[2][searchable]", "true"),
|
||||
("columns[2][orderable]", "true"),
|
||||
("columns[2][search][value]", ""),
|
||||
("columns[2][search][regex]", "false"),
|
||||
|
||||
("columns[3][data]", "TEMYIZKARAR"),
|
||||
("columns[3][name]", ""),
|
||||
("columns[3][searchable]", "true"),
|
||||
("columns[3][orderable]", "false"),
|
||||
("columns[3][search][value]", ""),
|
||||
("columns[3][search][regex]", "false"),
|
||||
|
||||
("columns[4][data]", ""),
|
||||
("columns[4][name]", ""),
|
||||
("columns[4][searchable]", "true"),
|
||||
("columns[4][orderable]", "false"),
|
||||
("columns[4][search][value]", ""),
|
||||
("columns[4][search][regex]", "false"),
|
||||
|
||||
("order[0][column]", "1"),
|
||||
("order[0][dir]", "desc")
|
||||
]
|
||||
form_data.extend(column_defs)
|
||||
|
||||
# Add search parameters
|
||||
daire_value = self._enum_to_form_value(params.ilam_dairesi, "daire")
|
||||
kamu_idaresi_value = self._enum_to_form_value(params.kamu_idaresi_turu, "kamu_idaresi")
|
||||
web_karar_konusu_value = self._enum_to_form_value(params.web_karar_konusu, "web_karar_konusu")
|
||||
|
||||
form_data.extend([
|
||||
("KararlarTemyizAra.ILAMDAIRESI", daire_value),
|
||||
("KararlarTemyizAra.YILI", params.yili or ""),
|
||||
("KararlarTemyizAra.KARARTRHBaslangic", params.karar_tarih_baslangic or ""),
|
||||
("KararlarTemyizAra.KARARTRHBitis", params.karar_tarih_bitis or ""),
|
||||
("KararlarTemyizAra.KAMUIDARESITURU", kamu_idaresi_value if kamu_idaresi_value != "Tüm Kurumlar" else ""),
|
||||
("KararlarTemyizAra.ILAMNO", params.ilam_no or ""),
|
||||
("KararlarTemyizAra.DOSYANO", params.dosya_no or ""),
|
||||
("KararlarTemyizAra.TEMYIZTUTANAKNO", params.temyiz_tutanak_no or ""),
|
||||
("__Invariant", "KararlarTemyizAra.TEMYIZTUTANAKNO"),
|
||||
("KararlarTemyizAra.TEMYIZKARAR", params.temyiz_karar or ""),
|
||||
("KararlarTemyizAra.WEBKARARKONUSU", web_karar_konusu_value if web_karar_konusu_value != "Tüm Konular" else ""),
|
||||
("__RequestVerificationToken", self.csrf_tokens.get('temyiz_kurulu', ''))
|
||||
])
|
||||
|
||||
return form_data
|
||||
|
||||
def _build_daire_form_data(self, params: DaireSearchRequest, draw: int = 1) -> List[Tuple[str, str]]:
|
||||
"""Build form data for Daire search request."""
|
||||
form_data = self._build_datatables_params(params.start, params.length, draw)
|
||||
|
||||
# Add DataTables column definitions (from actual request)
|
||||
column_defs = [
|
||||
("columns[0][data]", "YARGILAMADAIRESI"),
|
||||
("columns[0][name]", ""),
|
||||
("columns[0][searchable]", "true"),
|
||||
("columns[0][orderable]", "false"),
|
||||
("columns[0][search][value]", ""),
|
||||
("columns[0][search][regex]", "false"),
|
||||
|
||||
("columns[1][data]", "KARARTRH"),
|
||||
("columns[1][name]", ""),
|
||||
("columns[1][searchable]", "true"),
|
||||
("columns[1][orderable]", "true"),
|
||||
("columns[1][search][value]", ""),
|
||||
("columns[1][search][regex]", "false"),
|
||||
|
||||
("columns[2][data]", "KARARNO"),
|
||||
("columns[2][name]", ""),
|
||||
("columns[2][searchable]", "true"),
|
||||
("columns[2][orderable]", "true"),
|
||||
("columns[2][search][value]", ""),
|
||||
("columns[2][search][regex]", "false"),
|
||||
|
||||
("columns[3][data]", "YARGILAMADAIRESI"),
|
||||
("columns[3][name]", ""),
|
||||
("columns[3][searchable]", "true"),
|
||||
("columns[3][orderable]", "true"),
|
||||
("columns[3][search][value]", ""),
|
||||
("columns[3][search][regex]", "false"),
|
||||
|
||||
("columns[4][data]", "WEBKARARMETNI"),
|
||||
("columns[4][name]", ""),
|
||||
("columns[4][searchable]", "true"),
|
||||
("columns[4][orderable]", "false"),
|
||||
("columns[4][search][value]", ""),
|
||||
("columns[4][search][regex]", "false"),
|
||||
|
||||
("columns[5][data]", ""),
|
||||
("columns[5][name]", ""),
|
||||
("columns[5][searchable]", "true"),
|
||||
("columns[5][orderable]", "false"),
|
||||
("columns[5][search][value]", ""),
|
||||
("columns[5][search][regex]", "false"),
|
||||
|
||||
("order[0][column]", "2"),
|
||||
("order[0][dir]", "desc")
|
||||
]
|
||||
form_data.extend(column_defs)
|
||||
|
||||
# Add search parameters
|
||||
daire_value = self._enum_to_form_value(params.yargilama_dairesi, "daire")
|
||||
kamu_idaresi_value = self._enum_to_form_value(params.kamu_idaresi_turu, "kamu_idaresi")
|
||||
web_karar_konusu_value = self._enum_to_form_value(params.web_karar_konusu, "web_karar_konusu")
|
||||
|
||||
form_data.extend([
|
||||
("KararlarDaireAra.YARGILAMADAIRESI", daire_value),
|
||||
("KararlarDaireAra.KARARTRHBaslangic", params.karar_tarih_baslangic or ""),
|
||||
("KararlarDaireAra.KARARTRHBitis", params.karar_tarih_bitis or ""),
|
||||
("KararlarDaireAra.ILAMNO", params.ilam_no or ""),
|
||||
("KararlarDaireAra.KAMUIDARESITURU", kamu_idaresi_value if kamu_idaresi_value != "Tüm Kurumlar" else ""),
|
||||
("KararlarDaireAra.HESAPYILI", params.hesap_yili or ""),
|
||||
("KararlarDaireAra.WEBKARARKONUSU", web_karar_konusu_value if web_karar_konusu_value != "Tüm Konular" else ""),
|
||||
("KararlarDaireAra.WEBKARARMETNI", params.web_karar_metni or ""),
|
||||
("__RequestVerificationToken", self.csrf_tokens.get('daire', ''))
|
||||
])
|
||||
|
||||
return form_data
|
||||
|
||||
async def search_genel_kurul_decisions(self, params: GenelKurulSearchRequest) -> GenelKurulSearchResponse:
|
||||
"""
|
||||
Search Sayıştay Genel Kurul (General Assembly) decisions.
|
||||
|
||||
Args:
|
||||
params: Search parameters for Genel Kurul decisions
|
||||
|
||||
Returns:
|
||||
GenelKurulSearchResponse with matching decisions
|
||||
"""
|
||||
# Initialize session if needed
|
||||
if 'genel_kurul' not in self.csrf_tokens:
|
||||
if not await self._initialize_session_for_endpoint('genel_kurul'):
|
||||
raise Exception("Failed to initialize session for Genel Kurul endpoint")
|
||||
|
||||
form_data = self._build_genel_kurul_form_data(params)
|
||||
encoded_data = urlencode(form_data, encoding='utf-8')
|
||||
|
||||
logger.info(f"Searching Genel Kurul decisions with parameters: {params.model_dump(exclude_none=True)}")
|
||||
|
||||
try:
|
||||
# Update headers with cookies
|
||||
headers = self.http_client.headers.copy()
|
||||
if self.session_cookies:
|
||||
cookie_header = "; ".join([f"{k}={v}" for k, v in self.session_cookies.items()])
|
||||
headers["Cookie"] = cookie_header
|
||||
|
||||
response = await self.http_client.post(
|
||||
self.GENEL_KURUL_ENDPOINT,
|
||||
data=encoded_data,
|
||||
headers=headers
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Parse response
|
||||
decisions = []
|
||||
for item in response_json.get('data', []):
|
||||
decisions.append(GenelKurulDecision(
|
||||
id=item['Id'],
|
||||
karar_no=item['KARARNO'],
|
||||
karar_tarih=item['KARARTARIH'],
|
||||
karar_ozeti=item['KARAROZETI']
|
||||
))
|
||||
|
||||
return GenelKurulSearchResponse(
|
||||
decisions=decisions,
|
||||
total_records=response_json.get('recordsTotal', 0),
|
||||
total_filtered=response_json.get('recordsFiltered', 0),
|
||||
draw=response_json.get('draw', 1)
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"HTTP error during Genel Kurul search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing Genel Kurul search: {e}")
|
||||
raise
|
||||
|
||||
async def search_temyiz_kurulu_decisions(self, params: TemyizKuruluSearchRequest) -> TemyizKuruluSearchResponse:
|
||||
"""
|
||||
Search Sayıştay Temyiz Kurulu (Appeals Board) decisions.
|
||||
|
||||
Args:
|
||||
params: Search parameters for Temyiz Kurulu decisions
|
||||
|
||||
Returns:
|
||||
TemyizKuruluSearchResponse with matching decisions
|
||||
"""
|
||||
# Initialize session if needed
|
||||
if 'temyiz_kurulu' not in self.csrf_tokens:
|
||||
if not await self._initialize_session_for_endpoint('temyiz_kurulu'):
|
||||
raise Exception("Failed to initialize session for Temyiz Kurulu endpoint")
|
||||
|
||||
form_data = self._build_temyiz_kurulu_form_data(params)
|
||||
encoded_data = urlencode(form_data, encoding='utf-8')
|
||||
|
||||
logger.info(f"Searching Temyiz Kurulu decisions with parameters: {params.model_dump(exclude_none=True)}")
|
||||
|
||||
try:
|
||||
# Update headers with cookies
|
||||
headers = self.http_client.headers.copy()
|
||||
if self.session_cookies:
|
||||
cookie_header = "; ".join([f"{k}={v}" for k, v in self.session_cookies.items()])
|
||||
headers["Cookie"] = cookie_header
|
||||
|
||||
response = await self.http_client.post(
|
||||
self.TEMYIZ_KURULU_ENDPOINT,
|
||||
data=encoded_data,
|
||||
headers=headers
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Parse response
|
||||
decisions = []
|
||||
for item in response_json.get('data', []):
|
||||
decisions.append(TemyizKuruluDecision(
|
||||
id=item['Id'],
|
||||
temyiz_tutanak_tarihi=item['TEMYIZTUTANAKTARIHI'],
|
||||
ilam_dairesi=item['ILAMDAIRESI'],
|
||||
temyiz_karar=item['TEMYIZKARAR']
|
||||
))
|
||||
|
||||
return TemyizKuruluSearchResponse(
|
||||
decisions=decisions,
|
||||
total_records=response_json.get('recordsTotal', 0),
|
||||
total_filtered=response_json.get('recordsFiltered', 0),
|
||||
draw=response_json.get('draw', 1)
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"HTTP error during Temyiz Kurulu search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing Temyiz Kurulu search: {e}")
|
||||
raise
|
||||
|
||||
async def search_daire_decisions(self, params: DaireSearchRequest) -> DaireSearchResponse:
|
||||
"""
|
||||
Search Sayıştay Daire (Chamber) decisions.
|
||||
|
||||
Args:
|
||||
params: Search parameters for Daire decisions
|
||||
|
||||
Returns:
|
||||
DaireSearchResponse with matching decisions
|
||||
"""
|
||||
# Initialize session if needed
|
||||
if 'daire' not in self.csrf_tokens:
|
||||
if not await self._initialize_session_for_endpoint('daire'):
|
||||
raise Exception("Failed to initialize session for Daire endpoint")
|
||||
|
||||
form_data = self._build_daire_form_data(params)
|
||||
encoded_data = urlencode(form_data, encoding='utf-8')
|
||||
|
||||
logger.info(f"Searching Daire decisions with parameters: {params.model_dump(exclude_none=True)}")
|
||||
|
||||
try:
|
||||
# Update headers with cookies
|
||||
headers = self.http_client.headers.copy()
|
||||
if self.session_cookies:
|
||||
cookie_header = "; ".join([f"{k}={v}" for k, v in self.session_cookies.items()])
|
||||
headers["Cookie"] = cookie_header
|
||||
|
||||
response = await self.http_client.post(
|
||||
self.DAIRE_ENDPOINT,
|
||||
data=encoded_data,
|
||||
headers=headers
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Parse response
|
||||
decisions = []
|
||||
for item in response_json.get('data', []):
|
||||
decisions.append(DaireDecision(
|
||||
id=item['Id'],
|
||||
yargilama_dairesi=item['YARGILAMADAIRESI'],
|
||||
karar_tarih=item['KARARTRH'],
|
||||
karar_no=item['KARARNO'],
|
||||
ilam_no=item.get('ILAMNO'), # Use get() to handle None values
|
||||
madde_no=item['MADDENO'],
|
||||
kamu_idaresi_turu=item['KAMUIDARESITURU'],
|
||||
hesap_yili=item['HESAPYILI'],
|
||||
web_karar_konusu=item['WEBKARARKONUSU'],
|
||||
web_karar_metni=item['WEBKARARMETNI']
|
||||
))
|
||||
|
||||
return DaireSearchResponse(
|
||||
decisions=decisions,
|
||||
total_records=response_json.get('recordsTotal', 0),
|
||||
total_filtered=response_json.get('recordsFiltered', 0),
|
||||
draw=response_json.get('draw', 1)
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"HTTP error during Daire search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing Daire search: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown(self, html_content: str) -> Optional[str]:
|
||||
"""Convert HTML content to Markdown using MarkItDown with BytesIO to avoid filename length issues."""
|
||||
if not html_content:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_content.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
result = md_converter.convert(html_stream)
|
||||
markdown_content = result.text_content
|
||||
|
||||
logger.info("Successfully converted HTML to Markdown")
|
||||
return markdown_content
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting HTML to Markdown: {e}")
|
||||
return f"Error converting HTML content: {str(e)}"
|
||||
|
||||
async def get_document_as_markdown(self, decision_id: str, decision_type: str) -> SayistayDocumentMarkdown:
|
||||
"""
|
||||
Retrieve full text of a Sayıştay decision and convert to Markdown.
|
||||
|
||||
Args:
|
||||
decision_id: Unique decision identifier
|
||||
decision_type: Type of decision ('genel_kurul', 'temyiz_kurulu', 'daire')
|
||||
|
||||
Returns:
|
||||
SayistayDocumentMarkdown with converted content
|
||||
"""
|
||||
logger.info(f"Retrieving document for {decision_type} decision ID: {decision_id}")
|
||||
|
||||
# Validate decision_id
|
||||
if not decision_id or not decision_id.strip():
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url="",
|
||||
markdown_content=None,
|
||||
error_message="Decision ID cannot be empty"
|
||||
)
|
||||
|
||||
# Map decision type to URL path
|
||||
url_path_mapping = {
|
||||
'genel_kurul': 'KararlarGenelKurul',
|
||||
'temyiz_kurulu': 'KararlarTemyiz',
|
||||
'daire': 'KararlarDaire'
|
||||
}
|
||||
|
||||
if decision_type not in url_path_mapping:
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url="",
|
||||
markdown_content=None,
|
||||
error_message=f"Invalid decision type: {decision_type}. Must be one of: {list(url_path_mapping.keys())}"
|
||||
)
|
||||
|
||||
# Build document URL
|
||||
url_path = url_path_mapping[decision_type]
|
||||
document_url = f"{self.BASE_URL}/{url_path}/Detay/{decision_id}/"
|
||||
|
||||
try:
|
||||
# Make HTTP GET request to document URL
|
||||
headers = {
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36",
|
||||
"Sec-Fetch-Dest": "document",
|
||||
"Sec-Fetch-Mode": "navigate",
|
||||
"Sec-Fetch-Site": "same-origin"
|
||||
}
|
||||
|
||||
# Include session cookies if available
|
||||
if self.session_cookies:
|
||||
cookie_header = "; ".join([f"{k}={v}" for k, v in self.session_cookies.items()])
|
||||
headers["Cookie"] = cookie_header
|
||||
|
||||
response = await self.http_client.get(document_url, headers=headers)
|
||||
response.raise_for_status()
|
||||
html_content = response.text
|
||||
|
||||
if not html_content or not html_content.strip():
|
||||
logger.warning(f"Received empty HTML content from {document_url}")
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=None,
|
||||
error_message="Document content is empty"
|
||||
)
|
||||
|
||||
# Convert HTML to Markdown using existing method
|
||||
markdown_content = self._convert_html_to_markdown(html_content)
|
||||
|
||||
if markdown_content and "Error converting HTML content" not in markdown_content:
|
||||
logger.info(f"Successfully retrieved and converted document {decision_id} to Markdown")
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=markdown_content,
|
||||
retrieval_date=None # Could add datetime.now().isoformat() if needed
|
||||
)
|
||||
else:
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=None,
|
||||
error_message=f"Failed to convert HTML to Markdown: {markdown_content}"
|
||||
)
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
error_msg = f"HTTP error {e.response.status_code} when fetching document: {e}"
|
||||
logger.error(f"HTTP error fetching document {decision_id}: {error_msg}")
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=None,
|
||||
error_message=error_msg
|
||||
)
|
||||
except httpx.RequestError as e:
|
||||
error_msg = f"Network error when fetching document: {e}"
|
||||
logger.error(f"Network error fetching document {decision_id}: {error_msg}")
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=None,
|
||||
error_message=error_msg
|
||||
)
|
||||
except Exception as e:
|
||||
error_msg = f"Unexpected error when fetching document: {e}"
|
||||
logger.error(f"Unexpected error fetching document {decision_id}: {error_msg}")
|
||||
return SayistayDocumentMarkdown(
|
||||
decision_id=decision_id,
|
||||
decision_type=decision_type,
|
||||
source_url=document_url,
|
||||
markdown_content=None,
|
||||
error_message=error_msg
|
||||
)
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close HTTP client session."""
|
||||
if hasattr(self, 'http_client') and self.http_client and not self.http_client.is_closed:
|
||||
await self.http_client.aclose()
|
||||
logger.info("SayistayApiClient: HTTP client session closed.")
|
||||
@@ -1,61 +0,0 @@
|
||||
# sayistay_mcp_module/enums.py
|
||||
|
||||
from typing import Literal
|
||||
|
||||
# Chamber/Daire options for Temyiz Kurulu and Daire endpoints (1-8 + All)
|
||||
DaireEnum = Literal[
|
||||
"ALL", # All chambers/departments
|
||||
"1", # 1. Daire
|
||||
"2", # 2. Daire
|
||||
"3", # 3. Daire
|
||||
"4", # 4. Daire
|
||||
"5", # 5. Daire
|
||||
"6", # 6. Daire
|
||||
"7", # 7. Daire
|
||||
"8" # 8. Daire
|
||||
]
|
||||
|
||||
# Public Administration Types (Kamu İdaresi Türü)
|
||||
KamuIdaresiTuruEnum = Literal[
|
||||
"ALL", # All institutions
|
||||
"Genel Bütçe Kapsamındaki İdareler", # General Budget Administrations
|
||||
"Yüksek Öğretim Kurumları", # Higher Education Institutions
|
||||
"Diğer Özel Bütçeli İdareler", # Other Special Budget Administrations
|
||||
"Düzenleyici ve Denetleyici Kurumlar", # Regulatory and Supervisory Institutions
|
||||
"Sosyal Güvenlik Kurumları", # Social Security Institutions
|
||||
"Özel İdareler", # Special Administrations
|
||||
"Belediyeler ve Bağlı İdareler", # Municipalities and Affiliated Administrations
|
||||
"Diğer" # Other
|
||||
]
|
||||
|
||||
# Decision Subject Categories (Web Karar Konusu) - Shortened for token efficiency
|
||||
WebKararKonusuEnum = Literal[
|
||||
"ALL", # All subjects
|
||||
"Harcırah Mevzuatı", # Travel Allowance Legislation
|
||||
"İhale Mevzuatı", # Procurement Legislation
|
||||
"İş Mevzuatı", # Labor Legislation
|
||||
"Personel Mevzuatı", # Personnel Legislation
|
||||
"Sorumluluk ve Yargılama Usulleri", # Liability and Trial Procedures
|
||||
"Vergi Resmi Harç ve Diğer Gelirler", # Tax, Official Fee and Other Revenue
|
||||
"Çeşitli Konular" # Various Topics
|
||||
]
|
||||
|
||||
# Mapping from shortened enum values to full API values
|
||||
WEB_KARAR_KONUSU_MAPPING = {
|
||||
"ALL": "ALL",
|
||||
"Harcırah Mevzuatı": "Harcırah Mevzuatı ile İlgili Kararlar",
|
||||
"İhale Mevzuatı": "İhale Mevzuatı ile İlgili Kararlar",
|
||||
"İş Mevzuatı": "İş Mevzuatı ile İlgili Kararlar",
|
||||
"Personel Mevzuatı": "Personel Mevzuatı ile İlgili Kararlar",
|
||||
"Sorumluluk ve Yargılama Usulleri": "Sorumluluk ve Yargılama Usulleri ile İlgili Kararlar",
|
||||
"Vergi Resmi Harç ve Diğer Gelirler": "Vergi Resmi Harç ve Diğer Gelirlerle İlgili Kararlar",
|
||||
"Çeşitli Konular": "Çeşitli Konuları İlgilendiren Kararlar"
|
||||
}
|
||||
|
||||
# Year ranges for different endpoints
|
||||
GENEL_KURUL_YEARS = [str(year) for year in range(2006, 2025)] # 2006-2024
|
||||
TEMYIZ_KURULU_YEARS = [str(year) for year in range(1993, 2023)] # 1993-2022
|
||||
DAIRE_YEARS = [str(year) for year in range(2012, 2026)] # 2012-2025
|
||||
|
||||
# Account years for Temyiz Kurulu and Daire endpoints
|
||||
HESAP_YILLARI = [str(year) for year in range(1993, 2024)] # 1993-2023
|
||||
@@ -1,220 +0,0 @@
|
||||
# sayistay_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import Optional, List, Union, Dict, Any, Literal
|
||||
from enum import Enum
|
||||
from .enums import DaireEnum, KamuIdaresiTuruEnum, WebKararKonusuEnum
|
||||
|
||||
# --- Unified Enums ---
|
||||
class SayistayDecisionTypeEnum(str, Enum):
|
||||
GENEL_KURUL = "genel_kurul"
|
||||
TEMYIZ_KURULU = "temyiz_kurulu"
|
||||
DAIRE = "daire"
|
||||
|
||||
# ============================================================================
|
||||
# Genel Kurul (General Assembly) Models
|
||||
# ============================================================================
|
||||
|
||||
class GenelKurulSearchRequest(BaseModel):
|
||||
"""
|
||||
Search request for Sayıştay Genel Kurul (General Assembly) decisions.
|
||||
|
||||
Genel Kurul decisions are precedent-setting rulings made by the full assembly
|
||||
of the Turkish Court of Accounts, typically addressing interpretation of
|
||||
audit and accountability regulations.
|
||||
"""
|
||||
karar_no: str = Field("", description="Decision no")
|
||||
karar_ek: str = Field("", description="Appendix no")
|
||||
|
||||
karar_tarih_baslangic: str = Field("", description="Start year (YYYY)")
|
||||
|
||||
karar_tarih_bitis: str = Field("", description="End year")
|
||||
|
||||
karar_tamami: str = Field("", description="Value")
|
||||
|
||||
# DataTables pagination
|
||||
start: int = Field(0, description="Starting record for pagination (0-based)")
|
||||
length: int = Field(10, description="Number of records per page (1-10)")
|
||||
|
||||
class GenelKurulDecision(BaseModel):
|
||||
"""Single Genel Kurul decision entry from search results."""
|
||||
id: int = Field(..., description="Unique decision ID")
|
||||
karar_no: str = Field(..., description="Decision number (e.g., '5415/1')")
|
||||
karar_tarih: str = Field(..., description="Decision date in DD.MM.YYYY format")
|
||||
karar_ozeti: str = Field(..., description="Decision summary/abstract")
|
||||
|
||||
class GenelKurulSearchResponse(BaseModel):
|
||||
"""Response from Genel Kurul search endpoint."""
|
||||
decisions: List[GenelKurulDecision] = Field(default_factory=list, description="List of matching decisions")
|
||||
total_records: int = Field(0, description="Total number of matching records")
|
||||
total_filtered: int = Field(0, description="Number of records after filtering")
|
||||
draw: int = Field(1, description="DataTables draw counter")
|
||||
|
||||
# ============================================================================
|
||||
# Temyiz Kurulu (Appeals Board) Models
|
||||
# ============================================================================
|
||||
|
||||
class TemyizKuruluSearchRequest(BaseModel):
|
||||
"""
|
||||
Search request for Sayıştay Temyiz Kurulu (Appeals Board) decisions.
|
||||
|
||||
Temyiz Kurulu reviews appeals against audit chamber decisions,
|
||||
providing higher-level review of audit findings and sanctions.
|
||||
"""
|
||||
ilam_dairesi: DaireEnum = Field("ALL", description="Value")
|
||||
|
||||
yili: str = Field("", description="Value")
|
||||
|
||||
karar_tarih_baslangic: str = Field("", description="Value")
|
||||
|
||||
karar_tarih_bitis: str = Field("", description="End year")
|
||||
|
||||
kamu_idaresi_turu: KamuIdaresiTuruEnum = Field("ALL", description="Value")
|
||||
|
||||
ilam_no: str = Field("", description="Audit report number (İlam No, max 50 chars)")
|
||||
dosya_no: str = Field("", description="File number for the case")
|
||||
temyiz_tutanak_no: str = Field("", description="Appeals board meeting minutes number")
|
||||
|
||||
temyiz_karar: str = Field("", description="Value")
|
||||
|
||||
web_karar_konusu: WebKararKonusuEnum = Field("ALL", description="Value")
|
||||
|
||||
# DataTables pagination
|
||||
start: int = Field(0, description="Starting record for pagination (0-based)")
|
||||
length: int = Field(10, description="Number of records per page (1-10)")
|
||||
|
||||
class TemyizKuruluDecision(BaseModel):
|
||||
"""Single Temyiz Kurulu decision entry from search results."""
|
||||
id: int = Field(..., description="Unique decision ID")
|
||||
temyiz_tutanak_tarihi: str = Field(..., description="Appeals board meeting date in DD.MM.YYYY format")
|
||||
ilam_dairesi: int = Field(..., description="Chamber number (1-8)")
|
||||
temyiz_karar: str = Field(..., description="Appeals decision summary and reasoning")
|
||||
|
||||
class TemyizKuruluSearchResponse(BaseModel):
|
||||
"""Response from Temyiz Kurulu search endpoint."""
|
||||
decisions: List[TemyizKuruluDecision] = Field(default_factory=list, description="List of matching appeals decisions")
|
||||
total_records: int = Field(0, description="Total number of matching records")
|
||||
total_filtered: int = Field(0, description="Number of records after filtering")
|
||||
draw: int = Field(1, description="DataTables draw counter")
|
||||
|
||||
# ============================================================================
|
||||
# Daire (Chamber) Models
|
||||
# ============================================================================
|
||||
|
||||
class DaireSearchRequest(BaseModel):
|
||||
"""
|
||||
Search request for Sayıştay Daire (Chamber) decisions.
|
||||
|
||||
Daire decisions are first-instance audit findings and sanctions
|
||||
issued by individual audit chambers before potential appeals.
|
||||
"""
|
||||
yargilama_dairesi: DaireEnum = Field("ALL", description="Value")
|
||||
|
||||
karar_tarih_baslangic: str = Field("", description="Value")
|
||||
|
||||
karar_tarih_bitis: str = Field("", description="End year")
|
||||
|
||||
ilam_no: str = Field("", description="Audit report number (İlam No, max 50 chars)")
|
||||
|
||||
kamu_idaresi_turu: KamuIdaresiTuruEnum = Field("ALL", description="Value")
|
||||
|
||||
hesap_yili: str = Field("", description="Value")
|
||||
|
||||
web_karar_konusu: WebKararKonusuEnum = Field("ALL", description="Value")
|
||||
|
||||
web_karar_metni: str = Field("", description="Value")
|
||||
|
||||
# DataTables pagination
|
||||
start: int = Field(0, description="Starting record for pagination (0-based)")
|
||||
length: int = Field(10, description="Number of records per page (1-10)")
|
||||
|
||||
class DaireDecision(BaseModel):
|
||||
"""Single Daire decision entry from search results."""
|
||||
id: int = Field(..., description="Unique decision ID")
|
||||
yargilama_dairesi: int = Field(..., description="Chamber number (1-8)")
|
||||
karar_tarih: str = Field(..., description="Decision date in DD.MM.YYYY format")
|
||||
karar_no: str = Field(..., description="Decision number")
|
||||
ilam_no: str = Field("", description="Audit report number (may be null)")
|
||||
madde_no: int = Field(..., description="Article/item number within the decision")
|
||||
kamu_idaresi_turu: str = Field(..., description="Public administration type")
|
||||
hesap_yili: int = Field(..., description="Account year being audited")
|
||||
web_karar_konusu: str = Field(..., description="Decision subject category")
|
||||
web_karar_metni: str = Field(..., description="Decision text/summary")
|
||||
|
||||
class DaireSearchResponse(BaseModel):
|
||||
"""Response from Daire search endpoint."""
|
||||
decisions: List[DaireDecision] = Field(default_factory=list, description="List of matching chamber decisions")
|
||||
total_records: int = Field(0, description="Total number of matching records")
|
||||
total_filtered: int = Field(0, description="Number of records after filtering")
|
||||
draw: int = Field(1, description="DataTables draw counter")
|
||||
|
||||
# ============================================================================
|
||||
# Document Models
|
||||
# ============================================================================
|
||||
|
||||
class SayistayDocumentMarkdown(BaseModel):
|
||||
"""
|
||||
Sayıştay decision document converted to Markdown format.
|
||||
|
||||
Used for retrieving full text of decisions from any of the three
|
||||
decision types (Genel Kurul, Temyiz Kurulu, Daire).
|
||||
"""
|
||||
decision_id: str = Field(..., description="Unique decision identifier")
|
||||
decision_type: str = Field(..., description="Value")
|
||||
source_url: str = Field(..., description="Original URL where the document was retrieved")
|
||||
markdown_content: Optional[str] = Field(None, description="Full decision text converted to Markdown format")
|
||||
retrieval_date: Optional[str] = Field(None, description="Date when document was retrieved (ISO format)")
|
||||
error_message: Optional[str] = Field(None, description="Error message if document retrieval failed")
|
||||
|
||||
# ============================================================================
|
||||
# Unified Models
|
||||
# ============================================================================
|
||||
|
||||
class SayistayUnifiedSearchRequest(BaseModel):
|
||||
"""Unified search request for all Sayıştay decision types."""
|
||||
decision_type: Literal["genel_kurul", "temyiz_kurulu", "daire"] = Field(..., description="Decision type: genel_kurul, temyiz_kurulu, or daire")
|
||||
|
||||
# Common pagination parameters
|
||||
start: int = Field(0, ge=0, description="Starting record for pagination (0-based)")
|
||||
length: int = Field(10, ge=1, le=100, description="Number of records per page (1-100)")
|
||||
|
||||
# Common search parameters
|
||||
karar_tarih_baslangic: str = Field("", description="Start date (DD.MM.YYYY format)")
|
||||
karar_tarih_bitis: str = Field("", description="End date (DD.MM.YYYY format)")
|
||||
kamu_idaresi_turu: KamuIdaresiTuruEnum = Field("ALL", description="Public administration type filter")
|
||||
ilam_no: str = Field("", description="Audit report number (İlam No, max 50 chars)")
|
||||
web_karar_konusu: WebKararKonusuEnum = Field("ALL", description="Decision subject category filter")
|
||||
|
||||
# Genel Kurul specific parameters (ignored for other types)
|
||||
karar_no: str = Field("", description="Decision number (genel_kurul only)")
|
||||
karar_ek: str = Field("", description="Decision appendix number (genel_kurul only)")
|
||||
karar_tamami: str = Field("", description="Full text search (genel_kurul only)")
|
||||
|
||||
# Temyiz Kurulu specific parameters (ignored for other types)
|
||||
ilam_dairesi: DaireEnum = Field("ALL", description="Audit chamber selection (temyiz_kurulu only)")
|
||||
yili: str = Field("", description="Year (YYYY format, temyiz_kurulu only)")
|
||||
dosya_no: str = Field("", description="File number (temyiz_kurulu only)")
|
||||
temyiz_tutanak_no: str = Field("", description="Appeals board meeting minutes number (temyiz_kurulu only)")
|
||||
temyiz_karar: str = Field("", description="Appeals decision text search (temyiz_kurulu only)")
|
||||
|
||||
# Daire specific parameters (ignored for other types)
|
||||
yargilama_dairesi: DaireEnum = Field("ALL", description="Chamber selection (daire only)")
|
||||
hesap_yili: str = Field("", description="Account year (daire only)")
|
||||
web_karar_metni: str = Field("", description="Decision text search (daire only)")
|
||||
|
||||
class SayistayUnifiedSearchResult(BaseModel):
|
||||
"""Unified search result containing decisions from any Sayıştay decision type."""
|
||||
decision_type: Literal["genel_kurul", "temyiz_kurulu", "daire"] = Field(..., description="Type of decisions returned")
|
||||
decisions: List[Dict[str, Any]] = Field(default_factory=list, description="Decision list (structure varies by type)")
|
||||
total_records: int = Field(0, description="Total number of records found")
|
||||
total_filtered: int = Field(0, description="Number of records after filtering")
|
||||
draw: int = Field(1, description="DataTables draw counter")
|
||||
|
||||
class SayistayUnifiedDocumentMarkdown(BaseModel):
|
||||
"""Unified document model for all Sayıştay decision types."""
|
||||
decision_type: Literal["genel_kurul", "temyiz_kurulu", "daire"] = Field(..., description="Type of document")
|
||||
decision_id: str = Field(..., description="Decision ID")
|
||||
source_url: str = Field(..., description="Source URL of the document")
|
||||
document_data: Dict[str, Any] = Field(default_factory=dict, description="Document content and metadata")
|
||||
markdown_content: Optional[str] = Field(None, description="Markdown content")
|
||||
error_message: Optional[str] = Field(None, description="Error message if retrieval failed")
|
||||
@@ -1,133 +0,0 @@
|
||||
# sayistay_mcp_module/unified_client.py
|
||||
# Unified client for all three Sayıştay decision types
|
||||
|
||||
import logging
|
||||
from typing import Optional, Dict, Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from .models import (
|
||||
SayistayUnifiedSearchRequest,
|
||||
SayistayUnifiedSearchResult,
|
||||
SayistayUnifiedDocumentMarkdown,
|
||||
GenelKurulSearchRequest,
|
||||
TemyizKuruluSearchRequest,
|
||||
DaireSearchRequest
|
||||
)
|
||||
from .client import SayistayApiClient
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class SayistayUnifiedClient:
|
||||
"""Unified client that handles all three Sayıştay decision types."""
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.client = SayistayApiClient(request_timeout)
|
||||
|
||||
async def search_unified(self, params: SayistayUnifiedSearchRequest) -> SayistayUnifiedSearchResult:
|
||||
"""Unified search that routes to appropriate search method based on decision_type."""
|
||||
|
||||
if params.decision_type == "genel_kurul":
|
||||
# Convert to genel kurul request
|
||||
genel_kurul_params = GenelKurulSearchRequest(
|
||||
karar_no=params.karar_no,
|
||||
karar_ek=params.karar_ek,
|
||||
karar_tarih_baslangic=params.karar_tarih_baslangic,
|
||||
karar_tarih_bitis=params.karar_tarih_bitis,
|
||||
karar_tamami=params.karar_tamami,
|
||||
start=params.start,
|
||||
length=params.length
|
||||
)
|
||||
|
||||
result = await self.client.search_genel_kurul_decisions(genel_kurul_params)
|
||||
|
||||
# Convert to unified format
|
||||
decisions_list = [decision.model_dump() for decision in result.decisions]
|
||||
|
||||
return SayistayUnifiedSearchResult(
|
||||
decision_type="genel_kurul",
|
||||
decisions=decisions_list,
|
||||
total_records=result.total_records,
|
||||
total_filtered=result.total_filtered,
|
||||
draw=result.draw
|
||||
)
|
||||
|
||||
elif params.decision_type == "temyiz_kurulu":
|
||||
# Convert to temyiz kurulu request
|
||||
temyiz_params = TemyizKuruluSearchRequest(
|
||||
ilam_dairesi=params.ilam_dairesi,
|
||||
yili=params.yili,
|
||||
karar_tarih_baslangic=params.karar_tarih_baslangic,
|
||||
karar_tarih_bitis=params.karar_tarih_bitis,
|
||||
kamu_idaresi_turu=params.kamu_idaresi_turu,
|
||||
ilam_no=params.ilam_no,
|
||||
dosya_no=params.dosya_no,
|
||||
temyiz_tutanak_no=params.temyiz_tutanak_no,
|
||||
temyiz_karar=params.temyiz_karar,
|
||||
web_karar_konusu=params.web_karar_konusu,
|
||||
start=params.start,
|
||||
length=params.length
|
||||
)
|
||||
|
||||
result = await self.client.search_temyiz_kurulu_decisions(temyiz_params)
|
||||
|
||||
# Convert to unified format
|
||||
decisions_list = [decision.model_dump() for decision in result.decisions]
|
||||
|
||||
return SayistayUnifiedSearchResult(
|
||||
decision_type="temyiz_kurulu",
|
||||
decisions=decisions_list,
|
||||
total_records=result.total_records,
|
||||
total_filtered=result.total_filtered,
|
||||
draw=result.draw
|
||||
)
|
||||
|
||||
elif params.decision_type == "daire":
|
||||
# Convert to daire request
|
||||
daire_params = DaireSearchRequest(
|
||||
yargilama_dairesi=params.yargilama_dairesi,
|
||||
karar_tarih_baslangic=params.karar_tarih_baslangic,
|
||||
karar_tarih_bitis=params.karar_tarih_bitis,
|
||||
ilam_no=params.ilam_no,
|
||||
kamu_idaresi_turu=params.kamu_idaresi_turu,
|
||||
hesap_yili=params.hesap_yili,
|
||||
web_karar_konusu=params.web_karar_konusu,
|
||||
web_karar_metni=params.web_karar_metni,
|
||||
start=params.start,
|
||||
length=params.length
|
||||
)
|
||||
|
||||
result = await self.client.search_daire_decisions(daire_params)
|
||||
|
||||
# Convert to unified format
|
||||
decisions_list = [decision.model_dump() for decision in result.decisions]
|
||||
|
||||
return SayistayUnifiedSearchResult(
|
||||
decision_type="daire",
|
||||
decisions=decisions_list,
|
||||
total_records=result.total_records,
|
||||
total_filtered=result.total_filtered,
|
||||
draw=result.draw
|
||||
)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Unsupported decision type: {params.decision_type}")
|
||||
|
||||
async def get_document_unified(self, decision_id: str, decision_type: str) -> SayistayUnifiedDocumentMarkdown:
|
||||
"""Unified document retrieval for all Sayıştay decision types."""
|
||||
|
||||
# Use existing client method (decision_type is already a string)
|
||||
result = await self.client.get_document_as_markdown(decision_id, decision_type)
|
||||
|
||||
return SayistayUnifiedDocumentMarkdown(
|
||||
decision_type=decision_type,
|
||||
decision_id=result.decision_id,
|
||||
source_url=result.source_url,
|
||||
document_data=result.model_dump(),
|
||||
markdown_content=result.markdown_content,
|
||||
error_message=result.error_message
|
||||
)
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close the underlying client session."""
|
||||
if hasattr(self.client, 'close_client_session'):
|
||||
await self.client.close_client_session()
|
||||
@@ -1,159 +0,0 @@
|
||||
"""
|
||||
Starlette integration example for Yargı MCP Server
|
||||
|
||||
This module demonstrates how to integrate the Yargı MCP server
|
||||
with a Starlette application, including authentication middleware
|
||||
and custom routing.
|
||||
|
||||
Usage:
|
||||
uvicorn starlette_app:app --host 0.0.0.0 --port 8000
|
||||
"""
|
||||
|
||||
import os
|
||||
from starlette.applications import Starlette
|
||||
from starlette.routing import Mount, Route
|
||||
from starlette.requests import Request
|
||||
from starlette.responses import JSONResponse, PlainTextResponse, RedirectResponse
|
||||
from starlette.middleware import Middleware
|
||||
from starlette.middleware.cors import CORSMiddleware
|
||||
from starlette.middleware.authentication import AuthenticationMiddleware
|
||||
from starlette.authentication import (
|
||||
AuthenticationBackend, AuthCredentials, SimpleUser, AuthenticationError
|
||||
)
|
||||
|
||||
# Import the main MCP app
|
||||
from mcp_server_main import app as mcp_server
|
||||
|
||||
# Simple token authentication backend
|
||||
class TokenAuthBackend(AuthenticationBackend):
|
||||
async def authenticate(self, request):
|
||||
auth_header = request.headers.get("Authorization")
|
||||
expected_token = os.getenv("API_TOKEN")
|
||||
|
||||
# Skip auth for health check and public endpoints
|
||||
if request.url.path in ["/health", "/", "/login"]:
|
||||
return None
|
||||
|
||||
if not expected_token:
|
||||
# No token configured, allow all
|
||||
return AuthCredentials(["authenticated"]), SimpleUser("anonymous")
|
||||
|
||||
if not auth_header:
|
||||
raise AuthenticationError("Authorization header required")
|
||||
|
||||
try:
|
||||
scheme, token = auth_header.split()
|
||||
if scheme.lower() != "bearer":
|
||||
raise AuthenticationError("Invalid authentication scheme")
|
||||
|
||||
if token != expected_token:
|
||||
raise AuthenticationError("Invalid token")
|
||||
|
||||
return AuthCredentials(["authenticated"]), SimpleUser("user")
|
||||
except ValueError:
|
||||
raise AuthenticationError("Invalid authorization header format")
|
||||
|
||||
# Homepage
|
||||
async def homepage(request: Request):
|
||||
return JSONResponse({
|
||||
"service": "Yargı MCP Server",
|
||||
"version": "0.1.0",
|
||||
"endpoints": {
|
||||
"mcp": "/mcp-server/mcp/",
|
||||
"api": "/api/",
|
||||
"health": "/health"
|
||||
}
|
||||
})
|
||||
|
||||
# API info endpoint
|
||||
async def api_info(request: Request):
|
||||
if not request.user.is_authenticated:
|
||||
return JSONResponse({"error": "Authentication required"}, status_code=401)
|
||||
|
||||
return JSONResponse({
|
||||
"authenticated_as": request.user.display_name,
|
||||
"available_tools": len(mcp_server._tool_manager._tools),
|
||||
"databases": [
|
||||
"Yargıtay", "Danıştay", "Emsal", "Uyuşmazlık",
|
||||
"Anayasa", "KIK", "Rekabet", "Bedesten"
|
||||
]
|
||||
})
|
||||
|
||||
# Health check
|
||||
async def health_check(request: Request):
|
||||
return JSONResponse({
|
||||
"status": "healthy",
|
||||
"service": "Yargı MCP Server"
|
||||
})
|
||||
|
||||
# Login example (returns token for demo)
|
||||
async def login(request: Request):
|
||||
token = os.getenv("API_TOKEN", "demo-token")
|
||||
return JSONResponse({
|
||||
"message": "Use this token in Authorization header",
|
||||
"example": f"Authorization: Bearer {token}",
|
||||
"note": "Set API_TOKEN environment variable to change token"
|
||||
})
|
||||
|
||||
# Create MCP ASGI app
|
||||
mcp_app = mcp_server.http_app(path='/mcp')
|
||||
|
||||
# Configure middleware
|
||||
middleware = [
|
||||
Middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=os.getenv("ALLOWED_ORIGINS", "*").split(","),
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
),
|
||||
Middleware(AuthenticationMiddleware, backend=TokenAuthBackend()),
|
||||
]
|
||||
|
||||
# Create routes
|
||||
routes = [
|
||||
Route("/", homepage),
|
||||
Route("/health", health_check),
|
||||
Route("/login", login),
|
||||
Route("/api/info", api_info),
|
||||
Mount("/mcp-server", app=mcp_app),
|
||||
]
|
||||
|
||||
# Create Starlette app
|
||||
app = Starlette(
|
||||
routes=routes,
|
||||
middleware=middleware,
|
||||
lifespan=mcp_app.lifespan
|
||||
)
|
||||
|
||||
# Nested mount example
|
||||
def create_nested_app():
|
||||
"""Example of nested mounting for complex routing structures"""
|
||||
|
||||
# Create inner app with MCP
|
||||
inner_app = Starlette(
|
||||
routes=[Mount("/services", app=mcp_app)],
|
||||
middleware=middleware
|
||||
)
|
||||
|
||||
# Create outer app
|
||||
outer_app = Starlette(
|
||||
routes=[
|
||||
Route("/", homepage),
|
||||
Mount("/v1", app=inner_app),
|
||||
],
|
||||
lifespan=mcp_app.lifespan
|
||||
)
|
||||
|
||||
# MCP would be available at /v1/services/mcp/
|
||||
return outer_app
|
||||
|
||||
# Export both apps
|
||||
nested_app = create_nested_app()
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
print("Starting Starlette app with authentication...")
|
||||
print("Set API_TOKEN environment variable to enable authentication")
|
||||
print("Example: API_TOKEN=secret-token python starlette_app.py")
|
||||
uvicorn.run(app, host="0.0.0.0", port=8000)
|
||||
@@ -1,25 +0,0 @@
|
||||
import os, stripe
|
||||
from clerk_backend_api import Clerk # Clerk backend SDK
|
||||
from fastapi import APIRouter, Request, HTTPException
|
||||
|
||||
router = APIRouter()
|
||||
stripe.api_key = os.getenv("STRIPE_SECRET")
|
||||
clerk = Clerk(bearer_auth=os.getenv("CLERK_SECRET_KEY"))
|
||||
|
||||
@router.post("/stripe/webhook")
|
||||
async def stripe_hook(req: Request):
|
||||
payload, sig = await req.body(), req.headers["stripe-signature"]
|
||||
try:
|
||||
event = stripe.Webhook.construct_event( # Stripe-recommended verify
|
||||
payload, sig, os.getenv("STRIPE_WEBHOOK_SECRET"))
|
||||
except stripe.error.SignatureVerificationError:
|
||||
raise HTTPException(400, "Bad sig")
|
||||
|
||||
if event["type"] == "customer.subscription.updated":
|
||||
item = event["data"]["object"]["items"]["data"][0]
|
||||
plan = item["price"]["nickname"] # "Pro", "Enterprise"…
|
||||
userID = event["data"]["object"]["metadata"]["clerk_user_id"]
|
||||
clerk.users.update_user_metadata( # merge into unsafe_metadata
|
||||
userID, unsafe_metadata={"plan": plan})
|
||||
return {"ok": True}
|
||||
|
||||
@@ -1,240 +0,0 @@
|
||||
# uyusmazlik_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
import aiohttp
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import Dict, Any, List, Optional, Union, Tuple
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from markitdown import MarkItDown
|
||||
from urllib.parse import urljoin, urlencode # urlencode for aiohttp form data
|
||||
|
||||
from .models import (
|
||||
UyusmazlikSearchRequest,
|
||||
UyusmazlikApiDecisionEntry,
|
||||
UyusmazlikSearchResponse,
|
||||
UyusmazlikDocumentMarkdown,
|
||||
UyusmazlikBolumEnum,
|
||||
UyusmazlikTuruEnum,
|
||||
UyusmazlikKararSonucuEnum
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
# --- Mappings from user-friendly Enum values to API IDs ---
|
||||
BOLUM_ENUM_TO_ID_MAP = {
|
||||
UyusmazlikBolumEnum.CEZA_BOLUMU: "f6b74320-f2d7-4209-ad6e-c6df180d4e7c",
|
||||
UyusmazlikBolumEnum.GENEL_KURUL_KARARLARI: "e4ca658d-a75a-4719-b866-b2d2f1c3b1d9",
|
||||
UyusmazlikBolumEnum.HUKUK_BOLUMU: "96b26fc4-ef8e-4a4f-a9cc-a3de89952aa1",
|
||||
UyusmazlikBolumEnum.TUMU: "", # Represents "...Seçiniz..." or all - empty string for API
|
||||
"ALL": "" # Also map the new "ALL" literal to empty string for backward compatibility
|
||||
}
|
||||
|
||||
UYUSMAZLIK_TURU_ENUM_TO_ID_MAP = {
|
||||
UyusmazlikTuruEnum.GOREV_UYUSMAZLIGI: "7b1e2cd3-8f09-418a-921c-bbe501e1740c",
|
||||
UyusmazlikTuruEnum.HUKUM_UYUSMAZLIGI: "19b88402-172b-4c1d-8339-595c942a89f5",
|
||||
UyusmazlikTuruEnum.TUMU: "", # Represents "...Seçiniz..." or all - empty string for API
|
||||
"ALL": "" # Also map the new "ALL" literal to empty string for backward compatibility
|
||||
}
|
||||
|
||||
KARAR_SONUCU_ENUM_TO_ID_MAP = {
|
||||
# These IDs are from the form HTML provided by the user
|
||||
UyusmazlikKararSonucuEnum.HUKUM_UYUSMAZLIGI_OLMADIGINA_DAIR: "6f47d87f-dcb5-412e-9878-000385dba1d9",
|
||||
UyusmazlikKararSonucuEnum.HUKUM_UYUSMAZLIGI_OLDUGUNA_DAIR: "5a01742a-c440-4c4a-ba1f-da20837cffed",
|
||||
# Add all other 'Karar Sonucu' enum members and their corresponding GUIDs
|
||||
# by inspecting the 'KararSonucuList' checkboxes in the provided form HTML.
|
||||
}
|
||||
# --- End Mappings ---
|
||||
|
||||
class UyusmazlikApiClient:
|
||||
BASE_URL = "https://kararlar.uyusmazlik.gov.tr"
|
||||
SEARCH_ENDPOINT = "/Arama/Search"
|
||||
# Individual documents are fetched by their full URLs obtained from search results.
|
||||
|
||||
def __init__(self, request_timeout: float = 30.0):
|
||||
self.request_timeout = request_timeout # Store timeout for aiohttp and httpx
|
||||
# Headers for aiohttp search. httpx for docs will create its own.
|
||||
self.default_aiohttp_search_headers = {
|
||||
"Accept": "*/*", # Mimicking browser headers provided by user
|
||||
"Accept-Encoding": "gzip, deflate, br, zstd",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
"Origin": self.BASE_URL,
|
||||
"Referer": self.BASE_URL + "/",
|
||||
|
||||
}
|
||||
|
||||
|
||||
async def search_decisions(
|
||||
self,
|
||||
params: UyusmazlikSearchRequest
|
||||
) -> UyusmazlikSearchResponse:
|
||||
|
||||
bolum_id_for_api = BOLUM_ENUM_TO_ID_MAP.get(params.bolum, "")
|
||||
uyusmazlik_id_for_api = UYUSMAZLIK_TURU_ENUM_TO_ID_MAP.get(params.uyusmazlik_turu, "")
|
||||
|
||||
form_data_list: List[Tuple[str, str]] = []
|
||||
|
||||
def add_to_form_data(key: str, value: Optional[str]):
|
||||
# API expects empty strings for omitted optional fields based on user payload example
|
||||
form_data_list.append((key, value or ""))
|
||||
|
||||
add_to_form_data("BolumId", bolum_id_for_api)
|
||||
add_to_form_data("UyusmazlikId", uyusmazlik_id_for_api)
|
||||
|
||||
if params.karar_sonuclari:
|
||||
for enum_member in params.karar_sonuclari:
|
||||
api_id = KARAR_SONUCU_ENUM_TO_ID_MAP.get(enum_member)
|
||||
if api_id: # Only add if a valid ID is found
|
||||
form_data_list.append(('KararSonucuList', api_id))
|
||||
|
||||
add_to_form_data("EsasYil", params.esas_yil)
|
||||
add_to_form_data("EsasSayisi", params.esas_sayisi)
|
||||
add_to_form_data("KararYil", params.karar_yil)
|
||||
add_to_form_data("KararSayisi", params.karar_sayisi)
|
||||
add_to_form_data("KanunNo", params.kanun_no)
|
||||
add_to_form_data("KararDateBegin", params.karar_date_begin)
|
||||
add_to_form_data("KararDateEnd", params.karar_date_end)
|
||||
add_to_form_data("ResmiGazeteSayi", params.resmi_gazete_sayi)
|
||||
add_to_form_data("ResmiGazeteDate", params.resmi_gazete_date)
|
||||
add_to_form_data("Icerik", params.icerik)
|
||||
add_to_form_data("Tumce", params.tumce)
|
||||
add_to_form_data("WildCard", params.wild_card)
|
||||
add_to_form_data("Hepsi", params.hepsi)
|
||||
add_to_form_data("Herhangibirisi", params.herhangi_birisi)
|
||||
add_to_form_data("NotHepsi", params.not_hepsi)
|
||||
# X-Requested-With is handled by default_aiohttp_search_headers
|
||||
|
||||
search_url = urljoin(self.BASE_URL, self.SEARCH_ENDPOINT)
|
||||
# For aiohttp, data for application/x-www-form-urlencoded should be a dict or str.
|
||||
# Using urlencode for list of tuples.
|
||||
encoded_form_payload = urlencode(form_data_list, encoding='UTF-8')
|
||||
|
||||
logger.info(f"UyusmazlikApiClient (aiohttp): Performing search to {search_url} with form_data: {encoded_form_payload}")
|
||||
|
||||
html_content = ""
|
||||
aiohttp_headers = self.default_aiohttp_search_headers.copy()
|
||||
aiohttp_headers["Content-Type"] = "application/x-www-form-urlencoded; charset=UTF-8"
|
||||
|
||||
try:
|
||||
# Create a new session for each call for simplicity with aiohttp here
|
||||
async with aiohttp.ClientSession(headers=aiohttp_headers) as session:
|
||||
async with session.post(search_url, data=encoded_form_payload, timeout=self.request_timeout) as response:
|
||||
response.raise_for_status() # Raises ClientResponseError for 400-599
|
||||
html_content = await response.text(encoding='utf-8') # Ensure correct encoding
|
||||
logger.debug("UyusmazlikApiClient (aiohttp): Received HTML response for search.")
|
||||
|
||||
except aiohttp.ClientError as e:
|
||||
logger.error(f"UyusmazlikApiClient (aiohttp): HTTP client error during search: {e}")
|
||||
raise # Re-raise to be handled by the MCP tool
|
||||
except Exception as e:
|
||||
logger.error(f"UyusmazlikApiClient (aiohttp): Error processing search request: {e}")
|
||||
raise
|
||||
|
||||
# --- HTML Parsing (remains the same as previous version) ---
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
total_records_text_div = soup.find("div", class_="pull-right label label-important")
|
||||
total_records = None
|
||||
if total_records_text_div:
|
||||
match_records = re.search(r'(\d+)\s*adet kayıt bulundu', total_records_text_div.get_text(strip=True))
|
||||
if match_records:
|
||||
total_records = int(match_records.group(1))
|
||||
|
||||
result_table = soup.find("table", class_="table-hover")
|
||||
processed_decisions: List[UyusmazlikApiDecisionEntry] = []
|
||||
if result_table:
|
||||
rows = result_table.find_all("tr")
|
||||
if len(rows) > 1: # Skip header row
|
||||
for row in rows[1:]:
|
||||
cols = row.find_all('td')
|
||||
if len(cols) >= 5:
|
||||
try:
|
||||
popover_div = cols[0].find("div", attrs={"data-rel": "popover"})
|
||||
popover_content_raw = popover_div["data-content"] if popover_div and popover_div.has_attr("data-content") else None
|
||||
|
||||
link_tag = cols[0].find('a')
|
||||
doc_relative_url = link_tag['href'] if link_tag and link_tag.has_attr('href') else None
|
||||
|
||||
if not doc_relative_url: continue
|
||||
document_url_str = urljoin(self.BASE_URL, doc_relative_url)
|
||||
|
||||
pdf_link_tag = cols[5].find('a', href=re.compile(r'\.pdf$', re.IGNORECASE)) if len(cols) > 5 else None
|
||||
pdf_url_str = urljoin(self.BASE_URL, pdf_link_tag['href']) if pdf_link_tag and pdf_link_tag.has_attr('href') else None
|
||||
|
||||
decision_data_parsed = {
|
||||
"karar_sayisi": cols[0].get_text(strip=True),
|
||||
"esas_sayisi": cols[1].get_text(strip=True),
|
||||
"bolum": cols[2].get_text(strip=True),
|
||||
"uyusmazlik_konusu": cols[3].get_text(strip=True),
|
||||
"karar_sonucu": cols[4].get_text(strip=True),
|
||||
"popover_content": html.unescape(popover_content_raw) if popover_content_raw else None,
|
||||
"document_url": document_url_str,
|
||||
"pdf_url": pdf_url_str
|
||||
}
|
||||
decision_model = UyusmazlikApiDecisionEntry(**decision_data_parsed)
|
||||
processed_decisions.append(decision_model)
|
||||
except Exception as e:
|
||||
logger.warning(f"UyusmazlikApiClient: Could not parse decision row. Row content: {row.get_text(strip=True, separator=' | ')}, Error: {e}")
|
||||
|
||||
return UyusmazlikSearchResponse(
|
||||
decisions=processed_decisions,
|
||||
total_records_found=total_records
|
||||
)
|
||||
|
||||
def _convert_html_to_markdown_uyusmazlik(self, full_decision_html_content: str) -> Optional[str]:
|
||||
"""Converts direct HTML content (from an Uyuşmazlık decision page) to Markdown."""
|
||||
if not full_decision_html_content:
|
||||
return None
|
||||
|
||||
processed_html = html.unescape(full_decision_html_content)
|
||||
# As per user request, pass the full (unescaped) HTML to MarkItDown
|
||||
html_input_for_markdown = processed_html
|
||||
|
||||
markdown_text = None
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_input_for_markdown.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_text = conversion_result.text_content
|
||||
logger.info("UyusmazlikApiClient: HTML to Markdown conversion successful.")
|
||||
except Exception as e:
|
||||
logger.error(f"UyusmazlikApiClient: Error during MarkItDown HTML to Markdown conversion: {e}")
|
||||
return markdown_text
|
||||
|
||||
async def get_decision_document_as_markdown(self, document_url: str) -> UyusmazlikDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Uyuşmazlık decision from its full URL and returns content as Markdown.
|
||||
"""
|
||||
logger.info(f"UyusmazlikApiClient (httpx for docs): Fetching Uyuşmazlık document for Markdown from URL: {document_url}")
|
||||
try:
|
||||
# Using a new httpx.AsyncClient instance for this GET request for simplicity
|
||||
async with httpx.AsyncClient(verify=False, timeout=self.request_timeout) as doc_fetch_client:
|
||||
|
||||
get_response = await doc_fetch_client.get(document_url, headers={"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"})
|
||||
get_response.raise_for_status()
|
||||
html_content_from_api = get_response.text
|
||||
|
||||
if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
|
||||
logger.warning(f"UyusmazlikApiClient: Received empty or non-string HTML from URL {document_url}.")
|
||||
return UyusmazlikDocumentMarkdown(source_url=document_url, markdown_content=None)
|
||||
|
||||
markdown_content = self._convert_html_to_markdown_uyusmazlik(html_content_from_api)
|
||||
return UyusmazlikDocumentMarkdown(source_url=document_url, markdown_content=markdown_content)
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"UyusmazlikApiClient (httpx for docs): HTTP error fetching Uyuşmazlık document from {document_url}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"UyusmazlikApiClient (httpx for docs): General error processing Uyuşmazlık document from {document_url}: {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
|
||||
logger.info("UyusmazlikApiClient: No persistent client session from __init__ to close.")
|
||||
@@ -1,86 +0,0 @@
|
||||
# uyusmazlik_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl
|
||||
from typing import List, Optional
|
||||
from enum import Enum
|
||||
|
||||
# Enum definitions for user-friendly input based on the provided HTML form
|
||||
class UyusmazlikBolumEnum(str, Enum):
|
||||
"""User-friendly names for 'BolumId'."""
|
||||
TUMU = "ALL" # Represents "...Seçiniz..." or all
|
||||
CEZA_BOLUMU = "Ceza Bölümü"
|
||||
GENEL_KURUL_KARARLARI = "Genel Kurul Kararları"
|
||||
HUKUK_BOLUMU = "Hukuk Bölümü"
|
||||
|
||||
class UyusmazlikTuruEnum(str, Enum):
|
||||
"""User-friendly names for 'UyusmazlikId'."""
|
||||
TUMU = "ALL" # Represents "...Seçiniz..." or all
|
||||
GOREV_UYUSMAZLIGI = "Görev Uyuşmazlığı"
|
||||
HUKUM_UYUSMAZLIGI = "Hüküm Uyuşmazlığı"
|
||||
|
||||
class UyusmazlikKararSonucuEnum(str, Enum): # Based on checkbox text in the form
|
||||
"""User-friendly names for 'KararSonucuList' items."""
|
||||
HUKUM_UYUSMAZLIGI_OLMADIGINA_DAIR = "Hüküm Uyuşmazlığı Olmadığına Dair"
|
||||
HUKUM_UYUSMAZLIGI_OLDUGUNA_DAIR = "Hüküm Uyuşmazlığı Olduğuna Dair"
|
||||
# Add other "Karar Sonucu" options from the form's checkboxes as Enum members
|
||||
# Example: GOREVLI_YARGI_YERI_ADLI = "Görevli Yargı Yeri Belirlenmesine Dair (Adli Yargı)"
|
||||
# The client will map these enum values (which are strings) to their respective IDs.
|
||||
|
||||
class UyusmazlikSearchRequest(BaseModel): # This is the model the MCP tool will accept
|
||||
"""Model for Uyuşmazlık Mahkemesi search request using user-friendly terms."""
|
||||
icerik: Optional[str] = Field("", description="Search text")
|
||||
|
||||
bolum: Optional[UyusmazlikBolumEnum] = Field(
|
||||
UyusmazlikBolumEnum.TUMU,
|
||||
description="Department"
|
||||
)
|
||||
uyusmazlik_turu: Optional[UyusmazlikTuruEnum] = Field(
|
||||
UyusmazlikTuruEnum.TUMU,
|
||||
description="Dispute type"
|
||||
)
|
||||
|
||||
# User provides a list of user-friendly names for Karar Sonucu
|
||||
karar_sonuclari: Optional[List[UyusmazlikKararSonucuEnum]] = Field( # Changed to list of Enums
|
||||
default_factory=list,
|
||||
description="Decision types"
|
||||
)
|
||||
|
||||
esas_yil: Optional[str] = Field("", description="Case year")
|
||||
esas_sayisi: Optional[str] = Field("", description="Case no")
|
||||
karar_yil: Optional[str] = Field("", description="Decision year")
|
||||
karar_sayisi: Optional[str] = Field("", description="Decision no")
|
||||
kanun_no: Optional[str] = Field("", description="Law no")
|
||||
|
||||
karar_date_begin: Optional[str] = Field("", description="Start date (DD.MM.YYYY)")
|
||||
karar_date_end: Optional[str] = Field("", description="End date (DD.MM.YYYY)")
|
||||
|
||||
resmi_gazete_sayi: Optional[str] = Field("", description="Gazette no")
|
||||
resmi_gazete_date: Optional[str] = Field("", description="Gazette date (DD.MM.YYYY)")
|
||||
|
||||
# Detailed text search fields from the "icerikDetail" section of the form
|
||||
tumce: Optional[str] = Field("", description="Exact phrase")
|
||||
wild_card: Optional[str] = Field("", description="Wildcard search")
|
||||
hepsi: Optional[str] = Field("", description="All words")
|
||||
herhangi_birisi: Optional[str] = Field("", description="Any word")
|
||||
not_hepsi: Optional[str] = Field("", description="Exclude words")
|
||||
|
||||
class UyusmazlikApiDecisionEntry(BaseModel):
|
||||
"""Model for an individual decision entry parsed from Uyuşmazlık API's HTML search response."""
|
||||
karar_sayisi: Optional[str] = Field(None)
|
||||
esas_sayisi: Optional[str] = Field(None)
|
||||
bolum: Optional[str] = Field(None)
|
||||
uyusmazlik_konusu: Optional[str] = Field(None)
|
||||
karar_sonucu: Optional[str] = Field(None)
|
||||
popover_content: Optional[str] = Field(None, description="Summary")
|
||||
document_url: HttpUrl # Full URL to the decision document HTML page
|
||||
pdf_url: Optional[HttpUrl] = Field(None, description="PDF URL")
|
||||
|
||||
class UyusmazlikSearchResponse(BaseModel): # This is what the MCP tool will return
|
||||
"""Response model for Uyuşmazlık Mahkemesi search results for the MCP tool."""
|
||||
decisions: List[UyusmazlikApiDecisionEntry]
|
||||
total_records_found: Optional[int] = Field(None, description="Total number of records found for the query, if available.")
|
||||
|
||||
class UyusmazlikDocumentMarkdown(BaseModel):
|
||||
"""Model for an Uyuşmazlık decision document, containing only Markdown content."""
|
||||
source_url: HttpUrl # The URL from which the content was fetched
|
||||
markdown_content: Optional[str] = Field(None, description="The decision content converted to Markdown.")
|
||||
@@ -1,182 +0,0 @@
|
||||
# yargitay_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup # Still needed for pre-processing HTML before markitdown
|
||||
from typing import Dict, Any, List, Optional
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import io
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
YargitayDetailedSearchRequest,
|
||||
YargitayApiSearchResponse,
|
||||
YargitayApiDecisionEntry,
|
||||
YargitayDocumentMarkdown,
|
||||
CompactYargitaySearchResult
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
# Basic logging configuration if no handlers are configured
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
class YargitayOfficialApiClient:
|
||||
"""
|
||||
API Client for Yargitay's official decision search system.
|
||||
Targets the detailed search endpoint (e.g., /aramadetaylist) based on user-provided payload.
|
||||
"""
|
||||
BASE_URL = "https://karararama.yargitay.gov.tr"
|
||||
# The form action was "/detayliArama". This often maps to an API endpoint like "/aramadetaylist".
|
||||
# This should be confirmed with the actual API.
|
||||
DETAILED_SEARCH_ENDPOINT = "/aramadetaylist"
|
||||
DOCUMENT_ENDPOINT = "/getDokuman"
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Content-Type": "application/json; charset=UTF-8",
|
||||
"Accept": "application/json, text/plain, */*",
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
"X-KL-KIS-Ajax-Request": "Ajax_Request", # Seen in a Yargitay client example
|
||||
"Referer": f"{self.BASE_URL}/" # Some APIs might check referer
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=False # SSL verification disabled as per original user code - use with caution
|
||||
)
|
||||
|
||||
async def search_detailed_decisions(
|
||||
self,
|
||||
search_params: YargitayDetailedSearchRequest
|
||||
) -> YargitayApiSearchResponse:
|
||||
"""
|
||||
Performs a detailed search for decisions in Yargitay
|
||||
using the structured search_params.
|
||||
"""
|
||||
# Create the main payload structure with the 'data' key
|
||||
request_payload = {"data": search_params.model_dump(exclude_none=True, by_alias=True)}
|
||||
|
||||
logger.info(f"YargitayOfficialApiClient: Performing detailed search with payload: {request_payload}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.post(self.DETAILED_SEARCH_ENDPOINT, json=request_payload)
|
||||
response.raise_for_status() # Raise an exception for HTTP 4xx or 5xx status codes
|
||||
response_json_data = response.json()
|
||||
|
||||
logger.debug(f"YargitayOfficialApiClient: Raw API response: {response_json_data}")
|
||||
|
||||
# Handle None or empty data response from API
|
||||
if response_json_data is None:
|
||||
logger.warning("YargitayOfficialApiClient: API returned None response")
|
||||
response_json_data = {"data": {"data": [], "recordsTotal": 0, "recordsFiltered": 0}}
|
||||
elif not isinstance(response_json_data, dict):
|
||||
logger.warning(f"YargitayOfficialApiClient: API returned unexpected response type: {type(response_json_data)}")
|
||||
response_json_data = {"data": {"data": [], "recordsTotal": 0, "recordsFiltered": 0}}
|
||||
elif response_json_data.get("data") is None:
|
||||
logger.warning("YargitayOfficialApiClient: API response data field is None")
|
||||
response_json_data["data"] = {"data": [], "recordsTotal": 0, "recordsFiltered": 0}
|
||||
|
||||
# Validate and parse the response using Pydantic models
|
||||
api_response = YargitayApiSearchResponse(**response_json_data)
|
||||
|
||||
# Populate the document_url for each decision entry
|
||||
if api_response.data and api_response.data.data:
|
||||
for decision_item in api_response.data.data:
|
||||
decision_item.document_url = f"{self.BASE_URL}{self.DOCUMENT_ENDPOINT}?id={decision_item.id}"
|
||||
|
||||
return api_response
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"YargitayOfficialApiClient: HTTP request error during detailed search: {e}")
|
||||
raise # Re-raise to be handled by the calling MCP tool
|
||||
except Exception as e: # Catches Pydantic ValidationErrors as well
|
||||
logger.error(f"YargitayOfficialApiClient: Error processing or validating detailed search response: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown(self, html_from_api_data_field: str) -> Optional[str]:
|
||||
"""
|
||||
Takes raw HTML string (from Yargitay API 'data' field for a document),
|
||||
pre-processes it, and converts it to Markdown using MarkItDown.
|
||||
Returns only the Markdown string or None if conversion fails.
|
||||
"""
|
||||
if not html_from_api_data_field:
|
||||
return None
|
||||
|
||||
# Pre-process HTML: unescape entities and fix common escaped sequences
|
||||
# Based on user's original fix_html_content
|
||||
processed_html = html.unescape(html_from_api_data_field)
|
||||
processed_html = processed_html.replace('\\"', '"')
|
||||
processed_html = processed_html.replace('\\r\\n', '\n')
|
||||
processed_html = processed_html.replace('\\n', '\n')
|
||||
processed_html = processed_html.replace('\\t', '\t')
|
||||
|
||||
# MarkItDown often works best with a full HTML document structure.
|
||||
# The Yargitay /getDokuman response already provides a full <html>...</html> string.
|
||||
# If it were just a fragment, we might wrap it like:
|
||||
# html_to_convert = f"<html><head><meta charset=\"UTF-8\"></head><body>{processed_html}</body></html>"
|
||||
# But since it's already a full HTML string in "data":
|
||||
html_to_convert = processed_html
|
||||
|
||||
markdown_output = None
|
||||
try:
|
||||
# Convert HTML string to bytes and create BytesIO stream
|
||||
html_bytes = html_to_convert.encode('utf-8')
|
||||
html_stream = io.BytesIO(html_bytes)
|
||||
|
||||
# Pass BytesIO stream to MarkItDown to avoid temp file creation
|
||||
md_converter = MarkItDown()
|
||||
conversion_result = md_converter.convert(html_stream)
|
||||
markdown_output = conversion_result.text_content
|
||||
|
||||
logger.info("Successfully converted HTML to Markdown.")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error during MarkItDown HTML to Markdown conversion: {e}")
|
||||
|
||||
return markdown_output
|
||||
|
||||
async def get_decision_document_as_markdown(self, id: str) -> YargitayDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Yargitay decision by its ID and returns its content
|
||||
as Markdown.
|
||||
Based on user-provided /getDokuman response structure.
|
||||
"""
|
||||
document_api_url = f"{self.DOCUMENT_ENDPOINT}?id={id}"
|
||||
source_url = f"{self.BASE_URL}{document_api_url}" # The original URL of the document
|
||||
logger.info(f"YargitayOfficialApiClient: Fetching document for Markdown conversion (ID: {id})")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(document_api_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Expecting JSON response with HTML content in the 'data' field
|
||||
response_json = response.json()
|
||||
html_content_from_api = response_json.get("data")
|
||||
|
||||
if not isinstance(html_content_from_api, str):
|
||||
logger.error(f"YargitayOfficialApiClient: 'data' field in API response is not a string or not found (ID: {id}).")
|
||||
raise ValueError("Expected HTML content not found in API response's 'data' field.")
|
||||
|
||||
markdown_content = self._convert_html_to_markdown(html_content_from_api)
|
||||
|
||||
return YargitayDocumentMarkdown(
|
||||
id=id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=source_url
|
||||
)
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"YargitayOfficialApiClient: HTTP error fetching document for Markdown (ID: {id}): {e}")
|
||||
raise
|
||||
except ValueError as e: # For JSON parsing errors or missing 'data' field
|
||||
logger.error(f"YargitayOfficialApiClient: Error processing document response for Markdown (ID: {id}): {e}")
|
||||
raise
|
||||
except Exception as e: # For other unexpected errors
|
||||
logger.error(f"YargitayOfficialApiClient: General error fetching/processing document for Markdown (ID: {id}): {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Closes the HTTPX client session."""
|
||||
await self.http_client.aclose()
|
||||
logger.info("YargitayOfficialApiClient: HTTP client session closed.")
|
||||
@@ -1,103 +0,0 @@
|
||||
# yargitay_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl, ConfigDict
|
||||
from typing import List, Optional, Dict, Any, Literal
|
||||
|
||||
# Yargıtay Chamber/Board Options
|
||||
YargitayBirimEnum = Literal[
|
||||
"ALL", # "ALL" for all chambers
|
||||
# Hukuk (Civil) Chambers
|
||||
"Hukuk Genel Kurulu",
|
||||
"1. Hukuk Dairesi", "2. Hukuk Dairesi", "3. Hukuk Dairesi", "4. Hukuk Dairesi",
|
||||
"5. Hukuk Dairesi", "6. Hukuk Dairesi", "7. Hukuk Dairesi", "8. Hukuk Dairesi",
|
||||
"9. Hukuk Dairesi", "10. Hukuk Dairesi", "11. Hukuk Dairesi", "12. Hukuk Dairesi",
|
||||
"13. Hukuk Dairesi", "14. Hukuk Dairesi", "15. Hukuk Dairesi", "16. Hukuk Dairesi",
|
||||
"17. Hukuk Dairesi", "18. Hukuk Dairesi", "19. Hukuk Dairesi", "20. Hukuk Dairesi",
|
||||
"21. Hukuk Dairesi", "22. Hukuk Dairesi", "23. Hukuk Dairesi",
|
||||
"Hukuk Daireleri Başkanlar Kurulu",
|
||||
# Ceza (Criminal) Chambers
|
||||
"Ceza Genel Kurulu",
|
||||
"1. Ceza Dairesi", "2. Ceza Dairesi", "3. Ceza Dairesi", "4. Ceza Dairesi",
|
||||
"5. Ceza Dairesi", "6. Ceza Dairesi", "7. Ceza Dairesi", "8. Ceza Dairesi",
|
||||
"9. Ceza Dairesi", "10. Ceza Dairesi", "11. Ceza Dairesi", "12. Ceza Dairesi",
|
||||
"13. Ceza Dairesi", "14. Ceza Dairesi", "15. Ceza Dairesi", "16. Ceza Dairesi",
|
||||
"17. Ceza Dairesi", "18. Ceza Dairesi", "19. Ceza Dairesi", "20. Ceza Dairesi",
|
||||
"21. Ceza Dairesi", "22. Ceza Dairesi", "23. Ceza Dairesi",
|
||||
"Ceza Daireleri Başkanlar Kurulu",
|
||||
# General Assembly
|
||||
"Büyük Genel Kurulu"
|
||||
]
|
||||
|
||||
class YargitayDetailedSearchRequest(BaseModel):
|
||||
"""
|
||||
Model for the 'data' object sent in the request payload
|
||||
to Yargitay's detailed search endpoint (e.g., /aramadetaylist).
|
||||
Based on the payload provided by the user.
|
||||
"""
|
||||
arananKelime: Optional[str] = Field("", description="Turkish keywords (supports +word -word \"phrase\" operators)")
|
||||
# Department/Board selection - Complete Court of Cassation chamber hierarchy
|
||||
birimYrgKurulDaire: Optional[str] = Field("ALL", description="Chamber (ALL or specific chamber name)")
|
||||
|
||||
esasYil: Optional[str] = Field("", description="Case year (YYYY)")
|
||||
esasIlkSiraNo: Optional[str] = Field("", description="Start case no")
|
||||
esasSonSiraNo: Optional[str] = Field("", description="End case no")
|
||||
|
||||
kararYil: Optional[str] = Field("", description="Decision year (YYYY)")
|
||||
kararIlkSiraNo: Optional[str] = Field("", description="Start decision no")
|
||||
kararSonSiraNo: Optional[str] = Field("", description="End decision no")
|
||||
|
||||
baslangicTarihi: Optional[str] = Field("", description="Start date (DD.MM.YYYY)")
|
||||
bitisTarihi: Optional[str] = Field("", description="End date (DD.MM.YYYY)")
|
||||
|
||||
|
||||
pageSize: int = Field(10, ge=1, le=10, description="Results per page (1-100)")
|
||||
pageNumber: int = Field(1, ge=1, description="Page number (1-indexed)")
|
||||
|
||||
class YargitayApiDecisionEntry(BaseModel):
|
||||
"""Model for an individual decision entry from the Yargitay API search response."""
|
||||
id: str # Unique system ID of the decision
|
||||
daire: Optional[str] = Field(None, description="Chamber")
|
||||
esasNo: Optional[str] = Field(None, alias="esasNo", description="Case no")
|
||||
kararNo: Optional[str] = Field(None, alias="kararNo", description="Decision no")
|
||||
kararTarihi: Optional[str] = Field(None, alias="kararTarihi", description="Date")
|
||||
# 'index' and 'siraNo' from API response are not critical for MCP tool, so omitted for brevity
|
||||
|
||||
# This field will be populated by the client after fetching the search list
|
||||
document_url: Optional[HttpUrl] = Field(None, description="Document URL")
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True) # To allow populating by alias from API response
|
||||
|
||||
|
||||
class YargitayApiResponseInnerData(BaseModel):
|
||||
"""Model for the inner 'data' object in the Yargitay API search response."""
|
||||
data: List[YargitayApiDecisionEntry] = Field(default_factory=list)
|
||||
# draw: Optional[int] = None # Typically used by DataTables, not essential for MCP
|
||||
recordsTotal: int = Field(default=0) # Total number of records matching the query
|
||||
recordsFiltered: int = Field(default=0) # Total number of records after filtering (usually same as recordsTotal)
|
||||
|
||||
class YargitayApiSearchResponse(BaseModel):
|
||||
"""Model for the complete search response from the Yargitay API."""
|
||||
data: Optional[YargitayApiResponseInnerData] = Field(default_factory=lambda: YargitayApiResponseInnerData())
|
||||
# metadata: Optional[Dict[str, Any]] = None # Optional metadata from API
|
||||
|
||||
class YargitayDocumentMarkdown(BaseModel):
|
||||
"""Model for a Yargitay decision document, containing only Markdown content."""
|
||||
id: str = Field(..., description="Document ID")
|
||||
markdown_content: Optional[str] = Field(None, description="Content")
|
||||
source_url: HttpUrl = Field(..., description="Source URL")
|
||||
|
||||
class CleanYargitayDecisionEntry(BaseModel):
|
||||
"""Clean decision entry without arananKelime field to reduce token usage."""
|
||||
id: str
|
||||
daire: Optional[str] = Field(None, description="Chamber")
|
||||
esasNo: Optional[str] = Field(None, description="Case no")
|
||||
kararNo: Optional[str] = Field(None, description="Decision no")
|
||||
kararTarihi: Optional[str] = Field(None, description="Date")
|
||||
document_url: Optional[HttpUrl] = Field(None, description="Document URL")
|
||||
|
||||
class CompactYargitaySearchResult(BaseModel):
|
||||
"""A more compact search result model for the MCP tool to return."""
|
||||
decisions: List[CleanYargitayDecisionEntry]
|
||||
total_records: int
|
||||
requested_page: int
|
||||
page_size: int
|
||||
@@ -1,47 +0,0 @@
|
||||
"""
|
||||
Setup script with post-install hook for Playwright Chromium installation.
|
||||
This runs during `pip install .` to ensure browser binaries are available.
|
||||
"""
|
||||
import subprocess
|
||||
import sys
|
||||
from setuptools import setup
|
||||
from setuptools.command.install import install
|
||||
from setuptools.command.develop import develop
|
||||
|
||||
|
||||
def install_playwright_chromium():
|
||||
"""Install Playwright Chromium browser."""
|
||||
print("Installing Playwright Chromium browser...")
|
||||
try:
|
||||
subprocess.run(
|
||||
[sys.executable, "-m", "playwright", "install", "chromium"],
|
||||
check=True
|
||||
)
|
||||
print("Playwright Chromium installed successfully!")
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"Warning: Playwright Chromium installation failed: {e}")
|
||||
except Exception as e:
|
||||
print(f"Warning: Could not install Playwright Chromium: {e}")
|
||||
|
||||
|
||||
class PostInstallCommand(install):
|
||||
"""Post-installation command to install Playwright browsers."""
|
||||
def run(self):
|
||||
install.run(self)
|
||||
install_playwright_chromium()
|
||||
|
||||
|
||||
class PostDevelopCommand(develop):
|
||||
"""Post-develop command to install Playwright browsers."""
|
||||
def run(self):
|
||||
develop.run(self)
|
||||
install_playwright_chromium()
|
||||
|
||||
|
||||
# Minimal setup - main config is in pyproject.toml
|
||||
setup(
|
||||
cmdclass={
|
||||
'install': PostInstallCommand,
|
||||
'develop': PostDevelopCommand,
|
||||
},
|
||||
)
|
||||
Reference in New Issue
Block a user