oimwiodev/ChatMock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Game_Time
2025-08-16 01:05:04 +05:00
committed by GitHub
parent 39536725a7
commit 1a99b7d3d1
6 changed files with 1804 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

675
chatmock.py Normal file
View File

@@ -0,0 +1,675 @@
from __future__ import annotations
import argparse
import errno
import json
import os
import sys
import time
import urllib.parse
import webbrowser
from typing import Any, Dict, Generator, List
import requests
from flask import Flask, Response, jsonify, make_response, request
from oauth import OAuthHTTPServer, OAuthHandler, REQUIRED_PORT, URL_BASE
from models import AuthBundle, PkceCodes, TokenData
from utils import (
convert_chat_messages_to_responses_input,
convert_tools_chat_to_responses,
eprint,
get_effective_chatgpt_auth,
get_home_dir,
load_chatgpt_tokens,
parse_jwt_claims,
read_auth_file,
sse_translate_chat,
sse_translate_text,
)
CLIENT_ID_DEFAULT = os.getenv("CHATGPT_LOCAL_CLIENT_ID") or "app_EMoamEEZ73f0CkXaXp7hrann"
CHATGPT_RESPONSES_URL = "https://chatgpt.com/backend-api/codex/responses"
def read_base_instructions() -> str:
try:
with open(os.path.join(os.path.dirname(__file__), "prompt.md"), "r", encoding="utf-8") as f:
content = f.read()
if isinstance(content, str) and content.strip():
return content
except FileNotFoundError:
raise Exception("Failed to read prompt.md, make sure it exists in the same directory you are running this script from!")
BASE_INSTRUCTIONS = read_base_instructions()
def create_app(
verbose: bool = False,
reasoning_effort: str = "medium",
reasoning_summary: str = "auto",
reasoning_compat: str = "think-tags",
debug_model: str | None = None,
) -> Flask:
app = Flask(__name__)
def vlog(*args: Any) -> None:
if verbose:
print(*args, file=sys.stderr)
def build_cors_headers() -> dict:
origin = request.headers.get("Origin", "*")
req_headers = request.headers.get("Access-Control-Request-Headers")
allow_headers = req_headers if req_headers else "Authorization, Content-Type, Accept"
return {
"Access-Control-Allow-Origin": origin,
"Access-Control-Allow-Methods": "POST, GET, OPTIONS",
"Access-Control-Allow-Headers": allow_headers,
"Access-Control-Max-Age": "86400",
}
@app.get("/")
@app.get("/health")
def health() -> Response:
return jsonify({"status": "ok"})
def _build_reasoning_param(overrides: Dict[str, Any] | None = None) -> Dict[str, Any] | None:
effort = (reasoning_effort or "").strip().lower()
summary = (reasoning_summary or "").strip().lower()
valid_efforts = {"low", "medium", "high", "none"}
valid_summaries = {"auto", "concise", "detailed", "none"}
if isinstance(overrides, dict):
o_eff = str(overrides.get("effort", "")).strip().lower()
o_sum = str(overrides.get("summary", "")).strip().lower()
if o_eff in valid_efforts and o_eff:
effort = o_eff
if o_sum in valid_summaries and o_sum:
summary = o_sum
if effort not in valid_efforts:
effort = "medium"
if summary not in valid_summaries:
summary = "auto"
reasoning: Dict[str, Any] = {"effort": effort}
if summary != "none":
reasoning["summary"] = summary
return reasoning
@app.route("/v1/chat/completions", methods=["POST", "OPTIONS"])
def chat_completions() -> Response:
if request.method == "OPTIONS":
resp = make_response("", 204)
for k, v in build_cors_headers().items():
resp.headers[k] = v
return resp
try:
if verbose:
body_preview = (request.get_data(cache=True, as_text=True) or "")[:2000]
vlog("IN POST /v1/chat/completions\n" + body_preview)
except Exception:
pass
access_token, account_id = get_effective_chatgpt_auth()
if not access_token or not account_id:
return jsonify({
"error": {
"message": "Missing ChatGPT credentials. Run 'python3 chatmock.py login' first.",
}
}), 401
raw = request.get_data(cache=True, as_text=True) or ""
try:
payload = json.loads(raw) if raw else {}
except Exception:
try:
payload = json.loads(raw.replace("\r", "").replace("\n", ""))
except Exception:
return jsonify({"error": {"message": "Invalid JSON body"}}), 400
model = _normalize_model_name(payload.get("model"))
messages = payload.get("messages")
if messages is None and isinstance(payload.get("prompt"), str):
messages = [{"role": "user", "content": payload.get("prompt") or ""}]
if messages is None and isinstance(payload.get("input"), str):
messages = [{"role": "user", "content": payload.get("input") or ""}]
if messages is None:
messages = []
if not isinstance(messages, list):
return jsonify({"error": {"message": "Request must include messages: []"}}), 400
is_stream = bool(payload.get("stream"))
tools_responses = convert_tools_chat_to_responses(payload.get("tools"))
tool_choice = payload.get("tool_choice", "auto")
parallel_tool_calls = bool(payload.get("parallel_tool_calls", False))
input_items = convert_chat_messages_to_responses_input(messages)
if not input_items and isinstance(payload.get("prompt"), str) and payload.get("prompt").strip():
input_items = [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": payload.get("prompt")}]}]
instructions = BASE_INSTRUCTIONS
reasoning_overrides = payload.get("reasoning") if isinstance(payload.get("reasoning"), dict) else None
upstream, error_resp = _start_upstream_request(
model,
input_items,
instructions=instructions,
tools=tools_responses,
tool_choice=tool_choice,
parallel_tool_calls=parallel_tool_calls,
reasoning_param=_build_reasoning_param(reasoning_overrides),
)
if error_resp is not None:
return error_resp
created = int(time.time())
if upstream.status_code >= 400:
try:
raw = upstream.content
err_body = json.loads(raw.decode("utf-8", errors="ignore")) if raw else {"raw": upstream.text}
except Exception:
err_body = {"raw": upstream.text}
if verbose:
vlog("Upstream error status=", upstream.status_code, " body:", json.dumps(err_body)[:2000])
return (
jsonify({"error": {"message": (err_body.get("error", {}) or {}).get("message", "Upstream error")}}),
upstream.status_code,
)
if is_stream:
resp = Response(
sse_translate_chat(
upstream,
model,
created,
verbose=verbose,
vlog=vlog,
reasoning_compat=reasoning_compat,
),
status=upstream.status_code,
mimetype="text/event-stream",
headers={"Cache-Control": "no-cache", "Connection": "keep-alive"},
)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
full_text = ""
reasoning_summary_text = ""
reasoning_full_text = ""
response_id = "chatcmpl"
tool_calls: List[Dict[str, Any]] = []
error_message: str | None = None
try:
for raw in upstream.iter_lines(decode_unicode=False):
if not raw:
continue
line = raw.decode("utf-8", errors="ignore") if isinstance(raw, (bytes, bytearray)) else raw
if not line.startswith("data: "):
continue
data = line[len("data: "):].strip()
if not data:
continue
if data == "[DONE]":
break
try:
evt = json.loads(data)
except Exception:
continue
kind = evt.get("type")
if isinstance(evt.get("response"), dict) and isinstance(evt["response"].get("id"), str):
response_id = evt["response"].get("id") or response_id
if kind == "response.output_text.delta":
full_text += evt.get("delta") or ""
elif kind == "response.reasoning_summary_text.delta":
reasoning_summary_text += evt.get("delta") or ""
elif kind == "response.reasoning_text.delta":
reasoning_full_text += evt.get("delta") or ""
elif kind == "response.output_item.done":
item = evt.get("item") or {}
if isinstance(item, dict) and item.get("type") == "function_call":
call_id = item.get("call_id") or item.get("id") or ""
name = item.get("name") or ""
args = item.get("arguments") or ""
if isinstance(call_id, str) and isinstance(name, str) and isinstance(args, str):
tool_calls.append(
{
"id": call_id,
"type": "function",
"function": {"name": name, "arguments": args},
}
)
elif kind == "response.failed":
error_message = evt.get("response", {}).get("error", {}).get("message", "response.failed")
elif kind == "response.completed":
break
finally:
upstream.close()
if error_message:
resp = make_response(jsonify({"error": {"message": error_message}}), 502)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
message: Dict[str, Any] = {"role": "assistant", "content": full_text if full_text else None}
if tool_calls:
message["tool_calls"] = tool_calls
try:
compat = (reasoning_compat or "think-tags").strip().lower()
except Exception:
compat = "think-tags"
if compat == "o3":
rtxt_parts: List[str] = []
if isinstance(reasoning_summary_text, str) and reasoning_summary_text.strip():
rtxt_parts.append(reasoning_summary_text)
if isinstance(reasoning_full_text, str) and reasoning_full_text.strip():
rtxt_parts.append(reasoning_full_text)
rtxt = "\n\n".join([p for p in rtxt_parts if p])
if rtxt:
message["reasoning"] = {"content": [{"type": "text", "text": rtxt}]}
elif compat == "think-tags":
rtxt_parts: List[str] = []
if isinstance(reasoning_summary_text, str) and reasoning_summary_text.strip():
rtxt_parts.append(reasoning_summary_text)
if isinstance(reasoning_full_text, str) and reasoning_full_text.strip():
rtxt_parts.append(reasoning_full_text)
rtxt = "\n\n".join([p for p in rtxt_parts if p])
if rtxt:
think_block = f"<think>{rtxt}</think>"
content_text = message.get("content") or ""
if isinstance(content_text, str):
message["content"] = think_block + (content_text or "")
elif compat in ("legacy", "current"):
if reasoning_summary_text:
message["reasoning_summary"] = reasoning_summary_text
if reasoning_full_text:
message["reasoning"] = reasoning_full_text
else:
rtxt_parts: List[str] = []
if isinstance(reasoning_summary_text, str) and reasoning_summary_text.strip():
rtxt_parts.append(reasoning_summary_text)
if isinstance(reasoning_full_text, str) and reasoning_full_text.strip():
rtxt_parts.append(reasoning_full_text)
rtxt = "\n\n".join([p for p in rtxt_parts if p])
if rtxt:
think_block = f"<think>{rtxt}</think>"
content_text = message.get("content") or ""
if isinstance(content_text, str):
message["content"] = think_block + (content_text or "")
completion = {
"id": response_id or "chatcmpl",
"object": "chat.completion",
"created": created,
"model": model,
"choices": [
{
"index": 0,
"message": message,
"finish_reason": "stop",
}
],
}
resp = make_response(jsonify(completion), upstream.status_code)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
@app.route("/v1/models", methods=["GET", "OPTIONS"])
def list_models() -> Response:
if request.method == "OPTIONS":
resp = make_response("", 204)
for k, v in build_cors_headers().items():
resp.headers[k] = v
return resp
models = {
"object": "list",
"data": [
{"id":"gpt-5","object":"model","owned_by":"owner"}
]
}
resp = make_response(jsonify(models), 200)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
def _start_upstream_request(
model: str,
input_items: List[Dict[str, Any]],
instructions: str | None = None,
tools: List[Dict[str, Any]] | None = None,
tool_choice: Any | None = None,
parallel_tool_calls: bool = False,
reasoning_param: Dict[str, Any] | None = None,
):
access_token, account_id = get_effective_chatgpt_auth()
if not access_token or not account_id:
resp = make_response(
jsonify(
{
"error": {
"message": "Missing ChatGPT credentials. Run 'python3 chatmock.py login' first.",
}
}
),
401,
)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return None, resp
reasoning_param = reasoning_param if isinstance(reasoning_param, dict) else _build_reasoning_param()
include: List[str] = []
if isinstance(reasoning_param, dict) and reasoning_param.get("effort") != "none":
include.append("reasoning.encrypted_content")
responses_payload = {
"model": model,
"instructions": instructions if isinstance(instructions, str) and instructions.strip() else BASE_INSTRUCTIONS,
"input": input_items,
"tools": tools or [],
"tool_choice": tool_choice if tool_choice in ("auto", "none") or isinstance(tool_choice, dict) else "auto",
"parallel_tool_calls": bool(parallel_tool_calls),
"store": False,
"stream": True,
"include": include,
}
if reasoning_param is not None:
responses_payload["reasoning"] = reasoning_param
headers = {
"Authorization": f"Bearer {access_token}",
"Content-Type": "application/json",
"Accept": "text/event-stream",
"chatgpt-account-id": account_id,
}
headers["OpenAI-Beta"] = "responses=experimental"
try:
upstream = requests.post(
CHATGPT_RESPONSES_URL,
headers=headers,
json=responses_payload,
stream=True,
timeout=600,
)
except requests.RequestException as e:
resp = make_response(jsonify({"error": {"message": f"Upstream ChatGPT request failed: {e}"}}), 502)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return None, resp
return upstream, None
def _normalize_model_name(name: str | None) -> str:
if isinstance(debug_model, str) and debug_model.strip():
return debug_model.strip()
if not isinstance(name, str) or not name.strip():
return "gpt-5"
base = name.split(":", 1)[0].strip()
mapping = {
"gpt5": "gpt-5",
"gpt-5-latest": "gpt-5",
"gpt-5": "gpt-5",
"codex": "codex-mini-latest",
"codex-mini": "codex-mini-latest",
"codex-mini-latest": "codex-mini-latest"
}
return mapping.get(base, base)
@app.route("/v1/completions", methods=["POST", "OPTIONS"])
def completions() -> Response:
if request.method == "OPTIONS":
resp = make_response("", 204)
for k, v in build_cors_headers().items():
resp.headers[k] = v
return resp
raw = request.get_data(cache=True, as_text=True) or ""
try:
payload = json.loads(raw) if raw else {}
except Exception:
return jsonify({"error": {"message": "Invalid JSON body"}}), 400
model = _normalize_model_name(payload.get("model"))
prompt = payload.get("prompt")
if isinstance(prompt, list):
prompt = "".join([p if isinstance(p, str) else "" for p in prompt])
if not isinstance(prompt, str):
prompt = payload.get("suffix") or ""
stream_req = bool(payload.get("stream", False))
messages = [{"role": "user", "content": prompt or ""}]
input_items = convert_chat_messages_to_responses_input(messages)
reasoning_overrides = payload.get("reasoning") if isinstance(payload.get("reasoning"), dict) else None
upstream, error_resp = _start_upstream_request(
model,
input_items,
instructions=BASE_INSTRUCTIONS,
reasoning_param=_build_reasoning_param(reasoning_overrides),
)
if error_resp is not None:
return error_resp
created = int(time.time())
if upstream.status_code >= 400:
try:
err_body = json.loads(upstream.content.decode("utf-8", errors="ignore")) if upstream.content else {"raw": upstream.text}
except Exception:
err_body = {"raw": upstream.text}
return (
jsonify({"error": {"message": (err_body.get("error", {}) or {}).get("message", "Upstream error")}}),
upstream.status_code,
)
if stream_req:
resp = Response(
sse_translate_text(upstream, model, created, verbose=verbose, vlog=vlog),
status=upstream.status_code,
mimetype="text/event-stream",
headers={"Cache-Control": "no-cache", "Connection": "keep-alive"},
)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
full_text = ""
response_id = "cmpl"
try:
for raw_line in upstream.iter_lines(decode_unicode=False):
if not raw_line:
continue
line = raw_line.decode("utf-8", errors="ignore") if isinstance(raw_line, (bytes, bytearray)) else raw_line
if not line.startswith("data: "):
continue
data = line[len("data: "):].strip()
if not data or data == "[DONE]":
if data == "[DONE]":
break
continue
try:
evt = json.loads(data)
except Exception:
continue
if isinstance(evt.get("response"), dict) and isinstance(evt["response"].get("id"), str):
response_id = evt["response"].get("id") or response_id
kind = evt.get("type")
if kind == "response.output_text.delta":
full_text += evt.get("delta") or ""
elif kind == "response.completed":
break
finally:
upstream.close()
completion = {
"id": response_id or "cmpl",
"object": "text_completion",
"created": created,
"model": model,
"choices": [
{"index": 0, "text": full_text, "finish_reason": "stop", "logprobs": None}
],
}
resp = make_response(jsonify(completion), upstream.status_code)
for k, v in build_cors_headers().items():
resp.headers.setdefault(k, v)
return resp
return app
def cmd_login(no_browser: bool, verbose: bool) -> int:
home_dir = get_home_dir()
client_id = CLIENT_ID_DEFAULT
if not client_id:
eprint("ERROR: No OAuth client id configured. Set CHATGPT_LOCAL_CLIENT_ID.")
return 1
try:
httpd = OAuthHTTPServer(("127.0.0.1", REQUIRED_PORT), OAuthHandler, home_dir=home_dir, client_id=client_id, verbose=verbose)
except OSError as e:
eprint(f"ERROR: {e}")
if e.errno == errno.EADDRINUSE:
return 13
return 1
auth_url = httpd.auth_url()
with httpd:
eprint(f"Starting local login server on {URL_BASE}")
if not no_browser:
try:
webbrowser.open(auth_url, new=1, autoraise=True)
except Exception as e:
eprint(f"Failed to open browser: {e}")
eprint(f"If your browser did not open, navigate to:\n{auth_url}")
try:
httpd.serve_forever()
except KeyboardInterrupt:
eprint("\nKeyboard interrupt received, exiting.")
return httpd.exit_code
def cmd_serve(
host: str,
port: int,
verbose: bool,
reasoning_effort: str,
reasoning_summary: str,
reasoning_compat: str,
debug_model: str | None,
) -> int:
app = create_app(
verbose=verbose,
reasoning_effort=reasoning_effort,
reasoning_summary=reasoning_summary,
reasoning_compat=reasoning_compat,
debug_model=debug_model,
)
app.run(host=host, debug=False, use_reloader=False, port=port, threaded=True)
return 0
def main() -> None:
parser = argparse.ArgumentParser(description="ChatGPT Local: login & OpenAI-compatible proxy")
sub = parser.add_subparsers(dest="command", required=True)
p_login = sub.add_parser("login", help="Authorize with ChatGPT and store tokens")
p_login.add_argument("--no-browser", action="store_true", help="Do not open the browser automatically")
p_login.add_argument("--verbose", action="store_true", help="Enable verbose logging")
p_serve = sub.add_parser("serve", help="Run local OpenAI-compatible server")
p_serve.add_argument("--host", default="127.0.0.1")
p_serve.add_argument("--port", type=int, default=8000)
p_serve.add_argument("--verbose", action="store_true", help="Enable verbose logging")
p_serve.add_argument(
"--debug-model",
dest="debug_model",
default=os.getenv("CHATGPT_LOCAL_DEBUG_MODEL"),
help="Forcibly override requested 'model' with this value",
)
p_serve.add_argument(
"--reasoning-effort",
choices=["low", "medium", "high", "none"],
default=os.getenv("CHATGPT_LOCAL_REASONING_EFFORT", "medium").lower(),
help="Reasoning effort level for Responses API (default: medium)",
)
p_serve.add_argument(
"--reasoning-summary",
choices=["auto", "concise", "detailed", "none"],
default=os.getenv("CHATGPT_LOCAL_REASONING_SUMMARY", "auto").lower(),
help="Reasoning summary verbosity (default: auto)",
)
p_serve.add_argument(
"--reasoning-compat",
choices=["legacy", "o3", "think-tags", "current"],
default=os.getenv("CHATGPT_LOCAL_REASONING_COMPAT", "think-tags").lower(),
help="Compatibility mode for exposing reasoning to clients (legacy|o3|think-tags). 'current' is accepted as an alias for 'legacy'",
)
p_info = sub.add_parser("info", help="Print current stored tokens and derived account id")
p_info.add_argument("--json", action="store_true", help="Output raw auth.json contents")
args = parser.parse_args()
if args.command == "login":
sys.exit(cmd_login(no_browser=args.no_browser, verbose=args.verbose))
elif args.command == "serve":
sys.exit(
cmd_serve(
host=args.host,
port=args.port,
verbose=args.verbose,
reasoning_effort=args.reasoning_effort,
reasoning_summary=args.reasoning_summary,
reasoning_compat=args.reasoning_compat,
debug_model=args.debug_model,
)
)
elif args.command == "info":
auth = read_auth_file()
if getattr(args, "json", False):
print(json.dumps(auth or {}, indent=2))
sys.exit(0)
access_token, account_id, id_token = load_chatgpt_tokens()
if not access_token or not id_token:
print("👤 Account")
print(" • Not signed in")
print(" • Run: python3 chatmock.py login")
sys.exit(0)
id_claims = parse_jwt_claims(id_token) or {}
access_claims = parse_jwt_claims(access_token) or {}
email = id_claims.get("email") or id_claims.get("preferred_username") or "<unknown>"
plan_raw = (access_claims.get("https://api.openai.com/auth") or {}).get("chatgpt_plan_type") or "unknown"
plan_map = {
"plus": "Plus",
"pro": "Pro",
"free": "Free",
"team": "Team",
"enterprise": "Enterprise",
}
plan = plan_map.get(str(plan_raw).lower(), str(plan_raw).title() if isinstance(plan_raw, str) else "Unknown")
print("👤 Account")
print(" • Signed in with ChatGPT")
print(f" • Login: {email}")
print(f" • Plan: {plan}")
if account_id:
print(f" • Account ID: {account_id}")
sys.exit(0)
else:
parser.error("Unknown command")
if __name__ == "__main__":
main()

24
models.py Normal file
View File

@@ -0,0 +1,24 @@
from dataclasses import dataclass
from typing import Optional
@dataclass
class TokenData:
id_token: str
access_token: str
refresh_token: str
account_id: str
@dataclass
class AuthBundle:
api_key: Optional[str]
token_data: TokenData
last_refresh: str
@dataclass
class PkceCodes:
code_verifier: str
code_challenge: str

260
oauth.py Normal file
View File

@@ -0,0 +1,260 @@
from __future__ import annotations
import datetime
import http.server
import json
import secrets
import threading
import time
import urllib.parse
import urllib.request
from typing import Any, Dict, Tuple
from models import AuthBundle, PkceCodes, TokenData
from utils import eprint, generate_pkce, parse_jwt_claims, write_auth_file
REQUIRED_PORT = 1455
URL_BASE = f"http://localhost:{REQUIRED_PORT}"
DEFAULT_ISSUER = "https://auth.openai.com"
LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
<html lang=\"en\">
<head>
<meta charset=\"utf-8\" />
<title>Login successful</title>
</head>
<body>
<div style=\"max-width: 640px; margin: 80px auto; font-family: system-ui, -apple-system, Segoe UI, Roboto, Helvetica, Arial, sans-serif;\">
<h1>Login successful</h1>
<p>You can now close this window and return to the terminal and run <code>python3 chatmock.py serve</code> to start the server.</p>
</div>
</body>
</html>
"""
class OAuthHTTPServer(http.server.HTTPServer):
def __init__(
self,
server_address: tuple[str, int],
request_handler_class: type[http.server.BaseHTTPRequestHandler],
*,
home_dir: str,
client_id: str,
verbose: bool = False,
) -> None:
super().__init__(server_address, request_handler_class, bind_and_activate=True)
self.exit_code = 1
self.home_dir = home_dir
self.verbose = verbose
self.issuer = DEFAULT_ISSUER
self.token_endpoint = f"{self.issuer}/oauth/token"
self.client_id = client_id
port = server_address[1]
self.redirect_uri = f"http://localhost:{port}/auth/callback"
self.pkce = generate_pkce()
self.state = secrets.token_hex(32)
def auth_url(self) -> str:
params = {
"response_type": "code",
"client_id": self.client_id,
"redirect_uri": self.redirect_uri,
"scope": "openid profile email offline_access",
"code_challenge": self.pkce.code_challenge,
"code_challenge_method": "S256",
"id_token_add_organizations": "true",
"codex_cli_simplified_flow": "true",
"state": self.state,
}
return f"{self.issuer}/oauth/authorize?" + urllib.parse.urlencode(params)
class OAuthHandler(http.server.BaseHTTPRequestHandler):
server: "OAuthHTTPServer"
def do_GET(self) -> None:
path = urllib.parse.urlparse(self.path).path
if path == "/success":
self._send_html(LOGIN_SUCCESS_HTML)
try:
self.wfile.flush()
except Exception as e:
eprint(f"Failed to flush response: {e}")
self._shutdown_after_delay(2.0)
return
if path != "/auth/callback":
self.send_error(404, "Not Found")
self._shutdown()
return
query = urllib.parse.urlparse(self.path).query
params = urllib.parse.parse_qs(query)
code = params.get("code", [None])[0]
if not code:
self.send_error(400, "Missing auth code")
self._shutdown()
return
try:
auth_bundle, success_url = self._exchange_code(code)
except Exception as exc:
self.send_error(500, f"Token exchange failed: {exc}")
self._shutdown()
return
auth_json_contents = {
"OPENAI_API_KEY": auth_bundle.api_key,
"tokens": {
"id_token": auth_bundle.token_data.id_token,
"access_token": auth_bundle.token_data.access_token,
"refresh_token": auth_bundle.token_data.refresh_token,
"account_id": auth_bundle.token_data.account_id,
},
"last_refresh": auth_bundle.last_refresh,
}
if write_auth_file(auth_json_contents):
self.server.exit_code = 0
self._send_html(LOGIN_SUCCESS_HTML)
else:
self.send_error(500, "Unable to persist auth file")
self._shutdown_after_delay(2.0)
def do_POST(self) -> None:
self.send_error(404, "Not Found")
self._shutdown()
def log_message(self, fmt: str, *args):
if getattr(self.server, "verbose", False):
super().log_message(fmt, *args)
def _send_redirect(self, url: str) -> None:
self.send_response(302)
self.send_header("Location", url)
self.end_headers()
def _send_html(self, body: str) -> None:
encoded = body.encode()
self.send_response(200)
self.send_header("Content-Type", "text/html; charset=utf-8")
self.send_header("Content-Length", str(len(encoded)))
self.end_headers()
self.wfile.write(encoded)
def _shutdown(self) -> None:
threading.Thread(target=self.server.shutdown, daemon=True).start()
def _shutdown_after_delay(self, seconds: float = 2.0) -> None:
def _later():
try:
time.sleep(seconds)
finally:
self._shutdown()
threading.Thread(target=_later, daemon=True).start()
def _exchange_code(self, code: str) -> Tuple[AuthBundle, str]:
data = urllib.parse.urlencode(
{
"grant_type": "authorization_code",
"code": code,
"redirect_uri": self.server.redirect_uri,
"client_id": self.server.client_id,
"code_verifier": self.server.pkce.code_verifier,
}
).encode()
with urllib.request.urlopen(
urllib.request.Request(
self.server.token_endpoint,
data=data,
method="POST",
headers={"Content-Type": "application/x-www-form-urlencoded"},
)
) as resp:
payload = json.loads(resp.read().decode())
id_token = payload.get("id_token", "")
access_token = payload.get("access_token", "")
refresh_token = payload.get("refresh_token", "")
id_token_claims = parse_jwt_claims(id_token)
access_token_claims = parse_jwt_claims(access_token)
auth_claims = (id_token_claims or {}).get("https://api.openai.com/auth", {})
chatgpt_account_id = auth_claims.get("chatgpt_account_id", "")
token_data = TokenData(
id_token=id_token,
access_token=access_token,
refresh_token=refresh_token,
account_id=chatgpt_account_id,
)
api_key, success_url = self._maybe_obtain_api_key(
id_token_claims or {}, access_token_claims or {}, token_data
)
last_refresh_str = (
datetime.datetime.now(datetime.timezone.utc).isoformat().replace("+00:00", "Z")
)
bundle = AuthBundle(api_key=api_key, token_data=token_data, last_refresh=last_refresh_str)
return bundle, success_url or f"{URL_BASE}/success"
def _maybe_obtain_api_key(
self,
token_claims: Dict[str, Any],
access_claims: Dict[str, Any],
token_data: TokenData,
) -> Tuple[str | None, str | None]:
org_id = token_claims.get("organization_id")
project_id = token_claims.get("project_id")
if not org_id or not project_id:
query = {
"id_token": token_data.id_token,
"needs_setup": "false",
"org_id": org_id or "",
"project_id": project_id or "",
"plan_type": access_claims.get("chatgpt_plan_type"),
"platform_url": "https://platform.openai.com",
}
return None, f"{URL_BASE}/success?{urllib.parse.urlencode(query)}"
today = datetime.datetime.now(datetime.timezone.utc).strftime("%Y-%m-%d")
exchange_data = urllib.parse.urlencode(
{
"grant_type": "urn:ietf:params:oauth:grant-type:token-exchange",
"client_id": self.server.client_id,
"requested_token": "openai-api-key",
"subject_token": token_data.id_token,
"subject_token_type": "urn:ietf:params:oauth:token-type:id_token",
"name": f"ChatGPT Local [auto-generated] ({today})",
}
).encode()
with urllib.request.urlopen(
urllib.request.Request(
self.server.token_endpoint,
data=exchange_data,
method="POST",
headers={"Content-Type": "application/x-www-form-urlencoded"},
)
) as resp:
exchange_payload = json.loads(resp.read().decode())
exchanged_access_token = exchange_payload.get("access_token")
chatgpt_plan_type = access_claims.get("chatgpt_plan_type")
success_url_query = {
"id_token": token_data.id_token,
"needs_setup": "false",
"org_id": org_id,
"project_id": project_id,
"plan_type": chatgpt_plan_type,
"platform_url": "https://platform.openai.com",
}
success_url = f"{URL_BASE}/success?{urllib.parse.urlencode(success_url_query)}"
return exchanged_access_token, success_url

326
prompt.md Normal file
View File

@@ -0,0 +1,326 @@
You are a coding agent running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
Your capabilities:
- Receive user prompts and other context provided by the harness, such as files in the workspace.
- Communicate with the user by streaming thinking & responses, and by making & updating plans.
- Emit function calls to run terminal commands and apply patches. Depending on how this specific run is configured, you can request that these function calls be escalated to the user for approval before running. More on this in the "Sandbox and approvals" section.
Within this context, Codex refers to the open-source agentic coding interface (not the old Codex language model built by OpenAI).
# How you work
## Personality
Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
## Responsiveness
### Preamble messages
Before making tool calls, send a brief preamble to the user explaining what you’re about to do. When sending preamble messages, follow these principles and examples:
- **Logically group related actions**: if you’re about to run several related commands, describe them together in one preamble rather than sending a separate note for each.
- **Keep it concise**: be no more than 1-2 sentences (8–12 words for quick updates).
- **Build on prior context**: if this is not your first tool call, use the preamble message to connect the dots with what’s been done so far and create a sense of momentum and clarity for the user to understand your next actions.
- **Keep your tone light, friendly and curious**: add small touches of personality in preambles feel collaborative and engaging.
**Examples:**
- “I’ve explored the repo; now checking the API route definitions.”
- “Next, I’ll patch the config and update the related tests.”
- “I’m about to scaffold the CLI commands and helper functions.”
- “Ok cool, so I’ve wrapped my head around the repo. Now digging into the API routes.”
- “Config’s looking tidy. Next up is patching helpers to keep things in sync.”
- “Finished poking at the DB gateway. I will now chase down error handling.”
- “Alright, build pipeline order is interesting. Checking how it reports failures.”
- “Spotted a clever caching util; now hunting where it gets used.”
**Avoiding a preamble for every trivial read (e.g., `cat` a single file) unless it’s part of a larger grouped action.
- Jumping straight into tool calls without explaining what’s about to happen.
- Writing overly long or speculative preambles — focus on immediate, tangible next steps.
## Planning
You have access to an `update_plan` tool which tracks steps and progress and renders them to the user. Using the tool helps demonstrate that you've understood the task and convey how you're approaching it. Plans can help to make complex, ambiguous, or multi-phase work clearer and more collaborative for the user. A good plan should break the task into meaningful, logically ordered steps that are easy to verify as you go. Note that plans are not for padding out simple work with filler steps or stating the obvious. Do not repeat the full contents of the plan after an `update_plan` call — the harness already displays it. Instead, summarize the change made and highlight any important context or next step.
Use a plan when:
- The task is non-trivial and will require multiple actions over a long time horizon.
- There are logical phases or dependencies where sequencing matters.
- The work has ambiguity that benefits from outlining high-level goals.
- You want intermediate checkpoints for feedback and validation.
- When the user asked you to do more than one thing in a single prompt
- The user has asked you to use the plan tool (aka "TODOs")
- You generate additional steps while working, and plan to do them before yielding to the user
Skip a plan when:
- The task is simple and direct.
- Breaking it down would only produce literal or trivial steps.
Planning steps are called "steps" in the tool, but really they're more like tasks or TODOs. As such they should be very concise descriptions of non-obvious work that an engineer might do like "Write the API spec", then "Update the backend", then "Implement the frontend". On the other hand, it's obvious that you'll usually have to "Explore the codebase" or "Implement the changes", so those are not worth tracking in your plan.
It may be the case that you complete all steps in your plan after a single pass of implementation. If this is the case, you can simply mark all the planned steps as completed. The content of your plan should not involve doing anything that you aren't capable of doing (i.e. don't try to test things that you can't test). Do not use plans for simple or single-step queries that you can just do or answer immediately.
### Examples
**High-quality plans**
Example 1:
1. Add CLI entry with file args
2. Parse Markdown via CommonMark library
3. Apply semantic HTML template
4. Handle code blocks, images, links
5. Add error handling for invalid files
Example 2:
1. Define CSS variables for colors
2. Add toggle with localStorage state
3. Refactor components to use variables
4. Verify all views for readability
5. Add smooth theme-change transition
Example 3:
1. Set up Node.js + WebSocket server
2. Add join/leave broadcast events
3. Implement messaging with timestamps
4. Add usernames + mention highlighting
5. Persist messages in lightweight DB
6. Add typing indicators + unread count
**Low-quality plans**
Example 1:
1. Create CLI tool
2. Add Markdown parser
3. Convert to HTML
Example 2:
1. Add dark mode toggle
2. Save preference
3. Make styles look good
Example 3:
1. Create single-file HTML game
2. Run quick sanity check
3. Summarize usage instructions
If you need to write a plan, only write high quality plans, not low quality ones.
## Task execution
You are a coding agent. Please keep going until the query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability, using the tools available to you, before coming back to the user. Do NOT guess or make up an answer.
You MUST adhere to the following criteria when solving queries:
- Working on the repo(s) in the current environment is allowed, even if they are proprietary.
- Analyzing code for vulnerabilities is allowed.
- Showing user code and tool call details is allowed.
- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`): {"command":["apply_patch","*** Begin Patch\\n*** Update File: path/to/file.py\\n@@ def example():\\n- pass\\n+ return 123\\n*** End Patch"]}
If completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:
- Fix the problem at the root cause rather than applying surface-level patches, when possible.
- Avoid unneeded complexity in your solution.
- Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
- Update documentation as necessary.
- Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.
- Use `git log` and `git blame` to search the history of the codebase if additional context is required.
- NEVER add copyright or license headers unless specifically requested.
- Do not waste tokens by re-reading files after calling `apply_patch` on them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.
- Do not `git commit` your changes or create new git branches unless explicitly requested.
- Do not add inline comments within code unless explicitly requested.
- Do not use one-letter variable names unless explicitly requested.
- NEVER output inline citations like "【F:README.md†L5-L14】" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.
## Testing your work
If the codebase has tests or the ability to build or run, you should use them to verify that your work is complete. Generally, your testing philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests, or where the patterns don't indicate so.
Once you're confident in correctness, use formatting commands to ensure that your code is well formatted. These commands can take time so you should run them on as precise a target as possible. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
## Sandbox and approvals
The Codex CLI harness supports several different sandboxing, and approval configurations that the user can choose from.
Filesystem sandboxing prevents you from editing files without user approval. The options are:
- *read-only*: You can only read files.
- *workspace-write*: You can read files. You can write to files in your workspace folder, but not outside it.
- *danger-full-access*: No filesystem sandboxing.
Network sandboxing prevents you from accessing network without approval. Options are
- *ON*
- *OFF*
Approvals are your mechanism to get user consent to perform more privileged actions. Although they introduce friction to the user because your work is paused until the user responds, you should leverage them to accomplish your important work. Do not let these settings or the sandbox deter you from attempting to accomplish the user's task. Approval options are
- *untrusted*: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
- *on-failure*: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
- *on-request*: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for it in the `shell` command description.)
- *never*: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is pared with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
When you are running with approvals `on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /tmp)
- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval.
- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
- (For all of these, you should weigh alternative paths that do not require approval.)
Note that when sandboxing is set to read-only, you'll need to request approval for any command that isn't a read.
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing ON, and approval on-failure.
## Ambition vs. precision
For tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.
If you're operating in an existing codebase, you should make sure you do exactly what the user asks with surgical precision. Treat the surrounding codebase with respect, and don't overstep (i.e. changing filenames or variables unnecessarily). You should balance being sufficiently ambitious and proactive when completing tasks of this nature.
You should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.
## Sharing progress updates
For especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.
Before doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.
The messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.
## Presenting your work and final message
Your final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the user’s style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.
You can skip heavy formatting for single, simple actions or confirmations. In these cases, respond in plain sentences with any relevant next step or quick option. Reserve multi-section structured responses for results that need grouping or explanation.
The user is working on the same computer as you, and has access to your work. As such there's no need to show the full contents of large files you have already written unless the user explicitly asks for them. Similarly, if you've created or modified files using `apply_patch`, there's no need to tell users to "save the file" or "copy the code into a file"—just reference the file path.
If there's something that you think you could help with as a logical next step, concisely ask the user if they want you to do so. Good examples of this are running tests, committing changes, or building out the next logical component. If there’s something that you couldn't do (even with approval) but that the user might want to do (such as verifying changes by running the app), include those instructions succinctly.
Brevity is very important as a default. You should be very concise (i.e. no more than 10 lines), but can relax this requirement for tasks where additional detail and comprehensiveness is important for the user's understanding.
### Final answer structure and style guidelines
You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
**Section Headers**
- Use only when they improve clarity — they are not mandatory for every answer.
- Choose descriptive names that fit the content
- Keep headers short (1–3 words) and in `**Title Case**`. Always start headers with `**` and end with `**`
- Leave no blank line before the first bullet under a header.
- Section headers should only be used where they genuinely improve scanability; avoid fragmenting the answer.
**Bullets**
- Use `-` followed by a space for every bullet.
- Bold the keyword, then colon + concise description.
- Merge related points when possible; avoid a bullet for every trivial detail.
- Keep bullets to one line unless breaking for clarity is unavoidable.
- Group into short lists (4–6 bullets) ordered by importance.
- Use consistent keyword phrasing and formatting across sections.
**Monospace**
- Wrap all commands, file paths, env vars, and code identifiers in backticks (`` `...` ``).
- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
- Never mix monospace and bold markers; choose one based on whether it’s a keyword (`**`) or inline code/path (`` ` ``).
**Structure**
- Place related bullets together; don’t mix unrelated concepts in the same section.
- Order sections from general → specific → supporting info.
- For subsections (e.g., “Binaries” under “Rust Workspace”), introduce with a bolded keyword bullet, then list items under it.
- Match structure to complexity:
- Multi-part or detailed results → use clear headers and grouped bullets.
- Simple results → minimal headers, possibly just a short list or paragraph.
**Tone**
- Keep the voice collaborative and natural, like a coding partner handing off work.
- Be concise and factual — no filler or conversational commentary and avoid unnecessary repetition
- Use present tense and active voice (e.g., “Runs tests” not “This will run tests”).
- Keep descriptions self-contained; don’t refer to “above” or “below”.
- Use parallel structure in lists for consistency.
**Don’t**
- Don’t use literal words “bold” or “monospace” in the content.
- Don’t nest bullets or create deep hierarchies.
- Don’t output ANSI escape codes directly — the CLI renderer applies them.
- Don’t cram unrelated keywords into a single bullet; split for clarity.
- Don’t let keyword lists run long — wrap or reformat for scanability.
Generally, ensure your final answers adapt their shape and depth to the request. For example, answers to code explanations should have a precise, structured explanation with code references that answer the question directly. For tasks with a simple implementation, lead with the outcome and supplement only with what’s needed for clarity. Larger changes can be presented as a logical walkthrough of your approach, grouping related steps, explaining rationale where it adds value, and highlighting next actions to accelerate the user. Your answers should provide the right level of detail while being easily scannable.
For casual greetings, acknowledgements, or other one-off conversational messages that are not delivering substantive information or structured results, respond naturally without section headers or bullet formatting.
# Tools
## `apply_patch`
Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
**_ Begin Patch
[ one or more file sections ]
_** End Patch
Within that envelope, you get a sequence of file operations.
You MUST include a header to specify the action you are taking.
Each operation starts with one of three headers:
**_ Add File: <path> - create a new file. Every following line is a + line (the initial contents).
_** Delete File: <path> - remove an existing file. Nothing follows.
\*\*\* Update File: <path> - patch an existing file in place (optionally with a rename).
May be immediately followed by \*\*\* Move to: <new path> if you want to rename the file.
Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
Within a hunk each line starts with:
- for inserted text,
* for removed text, or
space ( ) for context.
At the end of a truncated hunk you can emit \*\*\* End of File.
Patch := Begin { FileOp } End
Begin := "**_ Begin Patch" NEWLINE
End := "_** End Patch" NEWLINE
FileOp := AddFile | DeleteFile | UpdateFile
AddFile := "**_ Add File: " path NEWLINE { "+" line NEWLINE }
DeleteFile := "_** Delete File: " path NEWLINE
UpdateFile := "**_ Update File: " path NEWLINE [ MoveTo ] { Hunk }
MoveTo := "_** Move to: " newPath NEWLINE
Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
HunkLine := (" " | "-" | "+") text NEWLINE
A full patch can combine several operations:
**_ Begin Patch
_** Add File: hello.txt
+Hello world
**_ Update File: src/app.py
_** Move to: src/main.py
@@ def greet():
-print("Hi")
+print("Hello, world!")
**_ Delete File: obsolete.txt
_** End Patch
It is important to remember:
- You must include a header with your intended action (Add/Delete/Update)
- You must prefix new lines with `+` even when creating a new file
You can invoke apply_patch like:
```
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
```
## `update_plan`
A tool named `update_plan` is available to you. You can use it to keep an up‑to‑date, step‑by‑step plan for the task.
To create a new plan, call `update_plan` with a short list of 1‑sentence steps (no more than 5-7 words each) with a `status` for each step (`pending`, `in_progress`, or `completed`).
When steps have been completed, use `update_plan` to mark each finished step as `completed` and the next step you are working on as `in_progress`. There should always be exactly one `in_progress` step until everything is done. You can mark multiple items as complete in a single `update_plan` call.
If all steps are complete, ensure you call `update_plan` to mark all steps as `completed`.

2
requirements.txt Normal file
View File

@@ -0,0 +1,2 @@
flask
requests

517
utils.py Normal file
View File

@@ -0,0 +1,517 @@
from __future__ import annotations
import base64
import hashlib
import json
import os
import secrets
import sys
from typing import Any, Dict, List
def eprint(*args, **kwargs) -> None:
print(*args, file=sys.stderr, **kwargs)
def get_home_dir() -> str:
home = os.getenv("CHATGPT_LOCAL_HOME") or os.getenv("CODEX_HOME")
if not home:
home = os.path.expanduser("~/.chatgpt-local")
return home
def read_auth_file() -> Dict[str, Any] | None:
for base in [
os.getenv("CHATGPT_LOCAL_HOME"),
os.getenv("CODEX_HOME"),
os.path.expanduser("~/.chatgpt-local"),
os.path.expanduser("~/.codex"),
]:
if not base:
continue
path = os.path.join(base, "auth.json")
try:
with open(path, "r", encoding="utf-8") as f:
return json.load(f)
except FileNotFoundError:
continue
except Exception:
continue
return None
def write_auth_file(auth: Dict[str, Any]) -> bool:
home = get_home_dir()
try:
os.makedirs(home, exist_ok=True)
except Exception as exc:
eprint(f"ERROR: unable to create auth home directory {home}: {exc}")
return False
path = os.path.join(home, "auth.json")
try:
with open(path, "w", encoding="utf-8") as fp:
if hasattr(os, "fchmod"):
os.fchmod(fp.fileno(), 0o600)
json.dump(auth, fp, indent=2)
return True
except Exception as exc:
eprint(f"ERROR: unable to write auth file: {exc}")
return False
def parse_jwt_claims(token: str) -> Dict[str, Any] | None:
if not token or token.count(".") != 2:
return None
try:
_, payload, _ = token.split(".")
padded = payload + "=" * (-len(payload) % 4)
data = base64.urlsafe_b64decode(padded.encode())
return json.loads(data.decode())
except Exception:
return None
def generate_pkce() -> "PkceCodes":
from models import PkceCodes
code_verifier = secrets.token_hex(64)
digest = hashlib.sha256(code_verifier.encode()).digest()
code_challenge = base64.urlsafe_b64encode(digest).rstrip(b"=").decode()
return PkceCodes(code_verifier=code_verifier, code_challenge=code_challenge)
def convert_chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
def _normalize_image_data_url(url: str) -> str:
try:
if not isinstance(url, str):
return url
if not url.startswith("data:image/"):
return url
if ";base64," not in url:
return url
header, data = url.split(",", 1)
try:
from urllib.parse import unquote
data = unquote(data)
except Exception:
pass
data = data.strip().replace("\n", "").replace("\r", "")
data = data.replace("-", "+").replace("_", "/")
pad = (-len(data)) % 4
if pad:
data = data + ("=" * pad)
try:
base64.b64decode(data, validate=True)
except Exception:
return url
return f"{header},{data}"
except Exception:
return url
input_items: List[Dict[str, Any]] = []
for message in messages:
role = message.get("role")
if role == "system":
continue
if role == "tool":
call_id = message.get("tool_call_id") or message.get("id")
if isinstance(call_id, str) and call_id:
content = message.get("content", "")
if isinstance(content, list):
texts = []
for part in content:
if isinstance(part, dict):
t = part.get("text") or part.get("content")
if isinstance(t, str) and t:
texts.append(t)
content = "\n".join(texts)
if isinstance(content, str):
input_items.append(
{
"type": "function_call_output",
"call_id": call_id,
"output": content,
}
)
continue
if role == "assistant" and isinstance(message.get("tool_calls"), list):
for tc in message.get("tool_calls") or []:
if not isinstance(tc, dict):
continue
tc_type = tc.get("type", "function")
if tc_type != "function":
continue
call_id = tc.get("id") or tc.get("call_id")
fn = tc.get("function") if isinstance(tc.get("function"), dict) else {}
name = fn.get("name") if isinstance(fn, dict) else None
args = fn.get("arguments") if isinstance(fn, dict) else None
if isinstance(call_id, str) and isinstance(name, str) and isinstance(args, str):
input_items.append(
{
"type": "function_call",
"name": name,
"arguments": args,
"call_id": call_id,
}
)
content = message.get("content", "")
content_items: List[Dict[str, Any]] = []
if isinstance(content, list):
for part in content:
if not isinstance(part, dict):
continue
ptype = part.get("type")
if ptype == "text":
text = part.get("text") or part.get("content") or ""
if isinstance(text, str) and text:
kind = "output_text" if role == "assistant" else "input_text"
content_items.append({"type": kind, "text": text})
elif ptype == "image_url":
image = part.get("image_url")
url = image.get("url") if isinstance(image, dict) else image
if isinstance(url, str) and url:
content_items.append({"type": "input_image", "image_url": _normalize_image_data_url(url)})
elif isinstance(content, str) and content:
kind = "output_text" if role == "assistant" else "input_text"
content_items.append({"type": kind, "text": content})
if not content_items:
continue
role_out = "assistant" if role == "assistant" else "user"
input_items.append({"type": "message", "role": role_out, "content": content_items})
return input_items
def convert_tools_chat_to_responses(tools: Any) -> List[Dict[str, Any]]:
out: List[Dict[str, Any]] = []
if not isinstance(tools, list):
return out
for t in tools:
if not isinstance(t, dict):
continue
if t.get("type") != "function":
continue
fn = t.get("function") if isinstance(t.get("function"), dict) else {}
name = fn.get("name") if isinstance(fn, dict) else None
if not isinstance(name, str) or not name:
continue
desc = fn.get("description") if isinstance(fn, dict) else None
params = fn.get("parameters") if isinstance(fn, dict) else None
if not isinstance(params, dict):
params = {"type": "object", "properties": {}}
out.append(
{
"type": "function",
"name": name,
"description": desc or "",
"strict": False,
"parameters": params,
}
)
return out
def load_chatgpt_tokens() -> tuple[str | None, str | None, str | None]:
auth = read_auth_file()
if not auth:
return None, None, None
tokens = auth.get("tokens", {}) if isinstance(auth, dict) else {}
return tokens.get("access_token"), tokens.get("account_id"), tokens.get("id_token")
def get_effective_chatgpt_auth() -> tuple[str | None, str | None]:
access_token, account_id, id_token = load_chatgpt_tokens()
if not account_id and id_token:
claims = parse_jwt_claims(id_token) or {}
auth_claims = claims.get("https://api.openai.com/auth", {}) or {}
if isinstance(auth_claims, dict):
account_id = auth_claims.get("chatgpt_account_id")
return access_token, account_id
def sse_translate_chat(
upstream,
model: str,
created: int,
verbose: bool = False,
vlog=None,
reasoning_compat: str = "think-tags",
):
response_id = "chatcmpl-stream"
compat = (reasoning_compat or "think-tags").strip().lower()
think_open = False
think_closed = False
saw_output = False
saw_any_summary = False
pending_summary_paragraph = False
try:
for raw in upstream.iter_lines(decode_unicode=False):
if not raw:
continue
line = raw.decode("utf-8", errors="ignore") if isinstance(raw, (bytes, bytearray)) else raw
if verbose and vlog:
vlog(line)
if not line.startswith("data: "):
continue
data = line[len("data: "):].strip()
if not data:
continue
if data == "[DONE]":
break
try:
evt = json.loads(data)
except Exception:
continue
kind = evt.get("type")
if isinstance(evt.get("response"), dict) and isinstance(evt["response"].get("id"), str):
response_id = evt["response"].get("id") or response_id
if kind == "response.output_text.delta":
delta = evt.get("delta") or ""
if compat == "think-tags" and think_open and not think_closed:
close_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": "</think>"}, "finish_reason": None}],
}
yield f"data: {json.dumps(close_chunk)}\n\n".encode("utf-8")
think_open = False
think_closed = True
saw_output = True
chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif kind == "response.output_item.done":
item = evt.get("item") or {}
if isinstance(item, dict) and item.get("type") == "function_call":
call_id = item.get("call_id") or item.get("id") or ""
name = item.get("name") or ""
args = item.get("arguments") or ""
if isinstance(call_id, str) and isinstance(name, str) and isinstance(args, str):
delta_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [
{
"index": 0,
"delta": {
"tool_calls": [
{
"index": 0,
"id": call_id,
"type": "function",
"function": {"name": name, "arguments": args},
}
]
},
"finish_reason": None,
}
],
}
yield f"data: {json.dumps(delta_chunk)}\n\n".encode("utf-8")
finish_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {}, "finish_reason": "tool_calls"}],
}
yield f"data: {json.dumps(finish_chunk)}\n\n".encode("utf-8")
elif kind == "response.reasoning_summary_part.added":
if compat in ("think-tags", "o3"):
if saw_any_summary:
pending_summary_paragraph = True
else:
saw_any_summary = True
elif kind in ("response.reasoning_summary_text.delta", "response.reasoning_text.delta"):
delta_txt = evt.get("delta") or ""
if compat == "o3":
if kind == "response.reasoning_summary_text.delta" and pending_summary_paragraph:
nl_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [
{
"index": 0,
"delta": {"reasoning": {"content": [{"type": "text", "text": "\n"}]}},
"finish_reason": None,
}
],
}
yield f"data: {json.dumps(nl_chunk)}\n\n".encode("utf-8")
pending_summary_paragraph = False
chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [
{
"index": 0,
"delta": {"reasoning": {"content": [{"type": "text", "text": delta_txt}]}},
"finish_reason": None,
}
],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif compat == "think-tags":
if not think_open and not think_closed:
open_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": "<think>"}, "finish_reason": None}],
}
yield f"data: {json.dumps(open_chunk)}\n\n".encode("utf-8")
think_open = True
if think_open and not think_closed:
if kind == "response.reasoning_summary_text.delta" and pending_summary_paragraph:
nl_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": "\n"}, "finish_reason": None}],
}
yield f"data: {json.dumps(nl_chunk)}\n\n".encode("utf-8")
pending_summary_paragraph = False
content_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": delta_txt}, "finish_reason": None}],
}
yield f"data: {json.dumps(content_chunk)}\n\n".encode("utf-8")
else:
pass
else:
if kind == "response.reasoning_summary_text.delta":
chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [
{
"index": 0,
"delta": {"reasoning_summary": delta_txt},
"finish_reason": None,
}
],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
else:
chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [
{"index": 0, "delta": {"reasoning": delta_txt}, "finish_reason": None}
],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif isinstance(kind, str) and kind.endswith(".done"):
pass
elif kind == "response.output_text.done":
chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif kind == "response.failed":
err = evt.get("response", {}).get("error", {}).get("message", "response.failed")
chunk = {"error": {"message": err}}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif kind == "response.completed":
if compat == "think-tags" and think_open and not think_closed:
close_chunk = {
"id": response_id,
"object": "chat.completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "delta": {"content": "</think>"}, "finish_reason": None}],
}
yield f"data: {json.dumps(close_chunk)}\n\n".encode("utf-8")
think_open = False
think_closed = True
yield b"data: [DONE]\n\n"
break
finally:
upstream.close()
def sse_translate_text(upstream, model: str, created: int, verbose: bool = False, vlog=None):
response_id = "cmpl-stream"
try:
for raw_line in upstream.iter_lines(decode_unicode=False):
if not raw_line:
continue
line = raw_line.decode("utf-8", errors="ignore") if isinstance(raw_line, (bytes, bytearray)) else raw_line
if verbose and vlog:
vlog(line)
if not line.startswith("data: "):
continue
data = line[len("data: "):].strip()
if not data or data == "[DONE]":
if data == "[DONE]":
chunk = {
"id": response_id,
"object": "text_completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "text": "", "finish_reason": "stop"}],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
continue
try:
evt = json.loads(data)
except Exception:
continue
kind = evt.get("type")
if isinstance(evt.get("response"), dict) and isinstance(evt["response"].get("id"), str):
response_id = evt["response"].get("id") or response_id
if kind == "response.output_text.delta":
delta_text = evt.get("delta") or ""
chunk = {
"id": response_id,
"object": "text_completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "text": delta_text, "finish_reason": None}],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif kind == "response.output_text.done":
chunk = {
"id": response_id,
"object": "text_completion.chunk",
"created": created,
"model": model,
"choices": [{"index": 0, "text": "", "finish_reason": "stop"}],
}
yield f"data: {json.dumps(chunk)}\n\n".encode("utf-8")
elif kind == "response.completed":
yield b"data: [DONE]\n\n"
break
finally:
upstream.close()