feat: add User-Agent header to all GitHub API calls

Adds a CollectOSS User-Agent header to all outgoing GitHub API requests
so GitHub can identify traffic from our tooling. This helps with bot
detection, allows GitHub staff to reach out if needed, and will benefit
future support for other forge instances (Forgejo etc).

The User-Agent format is:
  CollectOSS/1.0.0 (github:chaoss/collectoss; CHAOSS/Linux Foundation)

A get_user_agent() helper is added to metadata.py so the version number
is always in sync with the project version. The header is applied in:
- github_data_access.py (REST API)
- github_graphql_data_access.py (GraphQL API)
- github_api_key_handler.py (key validation calls)
- github_paginator.py (deprecated hit_api path)

Fixes #408

Signed-off-by: Diptesh Roy <droy88333@gmail.com>

Author: Dipro-cyber

collectoss/tasks/github/util/github_api_key_handler.py

@@ -7,7 +7,8 @@
 
 from collectoss.tasks.util.redis_list import RedisList
 from collectoss.application.db.lib import get_value, get_worker_oauth_keys
-from sqlalchemy import func 
+from sqlalchemy import func
+from metadata import get_user_agent
 
 RATE_LIMIT_URL = "https://api.github.com/rate_limit"
 
@@ -156,7 +157,7 @@ def is_bad_api_key(self, client: httpx.Client, oauth_key: str) -> bool:
             True if key is bad. False if the key is good
         """
 
-        headers = {'Authorization': f'token {oauth_key}'}
+        headers = {'Authorization': f'token {oauth_key}', 'User-Agent': get_user_agent()}
 
         data = client.request(method="GET", url=RATE_LIMIT_URL, headers=headers, timeout=180).json()
 
@@ -171,7 +172,7 @@ def is_bad_api_key(self, client: httpx.Client, oauth_key: str) -> bool:
     @staticmethod
     def get_key_rate_limit(client, github_key):
 
-        headers = {'Authorization': f'token {github_key}'}
+        headers = {'Authorization': f'token {github_key}', 'User-Agent': get_user_agent()}
 
         data = client.request(method="GET", url=RATE_LIMIT_URL, headers=headers, timeout=180).json()
 

collectoss/tasks/github/util/github_data_access.py

@@ -5,6 +5,7 @@
 from urllib.parse import urlparse, parse_qs, urlencode
 from keyman.KeyClient import KeyClient
 from collectoss.util.keys import mask_key
+from metadata import get_user_agent
 
 GITHUB_RATELIMIT_REMAINING_CAP = 50
 
@@ -152,7 +153,7 @@ def make_request(self, url, method="GET", timeout=100):
             if not self.key:
                 self.key = self.key_client.request()
 
-            headers = {"Authorization": f"token {self.key}"}
+            headers = {"Authorization": f"token {self.key}", "User-Agent": get_user_agent()}
 
             response = client.request(method=method, url=url, headers=headers, timeout=timeout, follow_redirects=True)
 

collectoss/tasks/github/util/github_graphql_data_access.py

@@ -2,6 +2,7 @@
 import time
 import httpx
 from tenacity import retry, stop_after_attempt, wait_fixed, retry_if_exception, RetryError
+from metadata import get_user_agent
 
 URL = "https://api.github.com/graphql"
 
@@ -79,7 +80,8 @@ def make_request(self, query, variables, timeout=40):
             if variables:
                 json_dict['variables'] = variables
 
-            response = client.post(url=URL,auth=self.key_manager,json=json_dict, timeout=timeout)
+            response = client.post(url=URL, auth=self.key_manager, json=json_dict, timeout=timeout,
+                                   headers={"User-Agent": get_user_agent()})
 
         response.raise_for_status()
 

collectoss/tasks/github/util/github_paginator.py

@@ -8,6 +8,7 @@
 from typing import Optional
 from enum import Enum
 from typing_extensions import deprecated
+from metadata import get_user_agent
 
 @deprecated("Deprecated. Use GithubDataAccess class instead") 
 def hit_api(key_manager, url: str, logger: logging.Logger, timeout: float = 10, method: str = 'GET', follow_redirects=True) -> Optional[httpx.Response]:
@@ -22,7 +23,9 @@ def hit_api(key_manager, url: str, logger: logging.Logger, timeout: float = 10,
 
         try:
             response = client.request(
-                method=method, url=url, auth=key_manager, timeout=timeout, follow_redirects=follow_redirects)
+                method=method, url=url, auth=key_manager, timeout=timeout,
+                follow_redirects=follow_redirects,
+                headers={"User-Agent": get_user_agent()})
 
         except TimeoutError:
             logger.info(f"Request timed out. Sleeping {round(timeout)} seconds and trying again...\n")

metadata.py

@@ -11,3 +11,11 @@
 
 __license__ = "MIT"
 __copyright__ = "CHAOSS and the collective contributors to the CollectOSS and Augur projects. A full listing of all contributors may be found at https://github.com/chaoss/collectoss/blob/main/CREDITS.md"
+
+
+def get_user_agent() -> str:
+    """Return the User-Agent string CollectOSS should send with API requests.
+
+    Format: CollectOSS/<version> (github:chaoss/collectoss; CHAOSS/Linux Foundation)
+    """
+    return f"CollectOSS/{__version__} (github:chaoss/collectoss; CHAOSS/Linux Foundation)"