"""OpenAI-compatible chat endpoint over the reasoning engine. Serves ``/v1/chat/completions`` and ``/v1/models`` so any OpenAI-API chat client can talk to a hybrid checkpoint with its own sampler — the model cannot run under llama.cpp-family runtimes, whose autoregressive decoding never matches the block-denoising objective. Clients resend the full message history on every request and carry no thinking notes, while the training layout replaces messages outside the visible window with the ledger of notes taken on them. The server therefore caches each turn's notes keyed by a hash of the exact history that produced it: a client that resends history verbatim reconstructs the same ledger the playground would hold. On a cache miss (server restart, edited history) the older turns simply contribute nothing, which is the playground's restart behaviour as well. """ from __future__ import annotations import argparse import hashlib import json import threading import time import uuid from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer from pathlib import Path from diffusion_lm.claims import ( KEEP_MESSAGES, SYSTEM, chat_prefix, ledger_line, ledger_notes, merge_notes, ) from diffusion_lm.reasoning_playground import ReasoningEngine from diffusion_lm.train import resolve_device MAX_ANSWER_TOKENS = 384 NOTE_CACHE_LIMIT = 4096 def _turn_key(system: str, messages: list[dict[str, str]]) -> str: payload = json.dumps( [system] + [[m['role'], m['content']] for m in messages], ensure_ascii=False, sort_keys=False, ) return hashlib.sha256(payload.encode('utf-8')).hexdigest() class ChatService: """One engine plus the note cache; generation is serialized on the GPU.""" def __init__(self, engine: ReasoningEngine, model_id: str, keep_messages: int) -> None: self.engine = engine self.model_id = model_id self.keep_messages = keep_messages self.notes: dict[str, str] = {} self.lock = threading.Lock() def _attach_notes(self, system: str, messages: list[dict[str, str]]) -> list[dict[str, str]]: attached = [] for index, message in enumerate(messages): entry = {'role': message['role'], 'content': message['content']} if message['role'] == 'assistant': note = self.notes.get(_turn_key(system, messages[: index + 1])) if note: entry['note'] = note attached.append(entry) return attached def build_prefix(self, system: str, messages: list[dict[str, str]]) -> str: attached = self._attach_notes(system, messages) older = merge_notes(ledger_notes(attached, self.keep_messages)) window = attached[max(0, len(attached) - self.keep_messages):] return chat_prefix( [{'role': m['role'], 'content': m['content']} for m in window], system=system, extra=ledger_line(older), ) def remember(self, system: str, messages: list[dict[str, str]], answer: str, note: str) -> None: if not note: return if len(self.notes) >= NOTE_CACHE_LIMIT: self.notes.clear() turn = messages + [{'role': 'assistant', 'content': answer}] self.notes[_turn_key(system, turn)] = note def generate(self, system: str, messages: list[dict[str, str]], *, temperature: float, top_p: float, max_tokens: int, seed: int): """Yield ``(answer_so_far, note, done)``; the note arrives with the final snapshot.""" prefix = self.build_prefix(system, messages) blocks: list[tuple[int, str]] = [] answer = '' with self.lock: for _, answer, _ in self.engine.stream_chat( prefix, temperature=temperature, # 16 measured optimal on qwen06b-genchat-sft (2026-08-12 five-point sweep): # best numeric fidelity, clean doubling, half the latency of 32. Below 8 both # fidelity and fluency degrade while latency barely moves. steps_per_block=16, max_answer_tokens=min(MAX_ANSWER_TOKENS, max_tokens), top_p=top_p, seed=seed, blocks_out=blocks, ): yield answer, '', False note = '; '.join(text for _, text in blocks if text) self.remember(system, messages, answer.strip(), note) yield answer, note, True def _split_messages(raw: list[dict]) -> tuple[str, list[dict[str, str]]]: system = SYSTEM messages = [] for message in raw: role, content = message.get('role'), str(message.get('content') or '') if role == 'system': system = content or system elif role in ('user', 'assistant'): messages.append({'role': role, 'content': content}) return system, messages class Handler(BaseHTTPRequestHandler): service: ChatService def log_message(self, format: str, *args) -> None: # noqa: A002 pass def _json(self, status: int, body: dict) -> None: data = json.dumps(body, ensure_ascii=False).encode('utf-8') self.send_response(status) self.send_header('Content-Type', 'application/json') self.send_header('Content-Length', str(len(data))) self.send_header('Access-Control-Allow-Origin', '*') self.end_headers() self.wfile.write(data) def do_OPTIONS(self) -> None: # noqa: N802 self.send_response(204) self.send_header('Access-Control-Allow-Origin', '*') self.send_header('Access-Control-Allow-Methods', 'GET, POST, OPTIONS') self.send_header('Access-Control-Allow-Headers', 'Content-Type, Authorization') self.end_headers() def do_GET(self) -> None: # noqa: N802 if self.path.rstrip('/') in ('/v1/models', '/models'): self._json(200, {'object': 'list', 'data': [ {'id': self.service.model_id, 'object': 'model', 'owned_by': 'mini-mdlm'}, ]}) else: self._json(404, {'error': 'not found'}) def do_POST(self) -> None: # noqa: N802 if self.path.rstrip('/') not in ('/v1/chat/completions', '/chat/completions'): self._json(404, {'error': 'not found'}) return try: length = int(self.headers.get('Content-Length', 0)) request = json.loads(self.rfile.read(length)) system, messages = _split_messages(request.get('messages') or []) if not messages or messages[-1]['role'] != 'user': raise ValueError('last message must be from the user') except (ValueError, json.JSONDecodeError) as error: self._json(400, {'error': {'message': str(error), 'type': 'invalid_request_error'}}) return temperature = float(request.get('temperature') or 0.8) top_p = float(request.get('top_p') or 0.95) max_tokens = int(request.get('max_tokens') or MAX_ANSWER_TOKENS) seed = int(request.get('seed') or 0) stream = bool(request.get('stream')) completion_id = f'chatcmpl-{uuid.uuid4().hex[:24]}' created = int(time.time()) snapshots = self.service.generate( system, messages, temperature=temperature, top_p=top_p, max_tokens=max_tokens, seed=seed, ) if not stream: answer = note = '' for answer, note, _ in snapshots: pass message = {'role': 'assistant', 'content': answer.strip()} if note: message['reasoning_content'] = note self._json(200, { 'id': completion_id, 'object': 'chat.completion', 'created': created, 'model': self.service.model_id, 'choices': [{'index': 0, 'message': message, 'finish_reason': 'stop'}], }) return self.send_response(200) self.send_header('Content-Type', 'text/event-stream') self.send_header('Cache-Control', 'no-cache') self.send_header('Access-Control-Allow-Origin', '*') self.end_headers() def chunk(delta: dict, finish: str | None = None) -> bytes: body = { 'id': completion_id, 'object': 'chat.completion.chunk', 'created': created, 'model': self.service.model_id, 'choices': [{'index': 0, 'delta': delta, 'finish_reason': finish}], } return f'data: {json.dumps(body, ensure_ascii=False)}\n\n'.encode('utf-8') try: self.wfile.write(chunk({'role': 'assistant'})) sent = '' for answer, _, done in snapshots: if len(answer) > len(sent): self.wfile.write(chunk({'content': answer[len(sent):]})) self.wfile.flush() sent = answer self.wfile.write(chunk({}, finish='stop')) self.wfile.write(b'data: [DONE]\n\n') except (BrokenPipeError, ConnectionResetError): pass def main() -> None: parser = argparse.ArgumentParser(description=__doc__) parser.add_argument('--checkpoint', type=Path, default=Path('outputs/qwen06b-genchat-sft/inference-latest.pt')) parser.add_argument('--tokenizer', type=Path, default=Path('artifacts/tokenizer-qwen3-adaptive.json')) parser.add_argument('--model-id', default=None, help='name reported to clients; defaults to the checkpoint directory') parser.add_argument('--keep-messages', type=int, default=KEEP_MESSAGES) parser.add_argument('--host', default='127.0.0.1') parser.add_argument('--port', type=int, default=7998) parser.add_argument('--device', default='auto') args = parser.parse_args() device = resolve_device(args.device) engine = ReasoningEngine(args.checkpoint, args.tokenizer, device) if not engine.chat_ready: raise SystemExit(f'{args.checkpoint} is not an adaptive hybrid over a ChatML tokenizer') Handler.service = ChatService( engine, args.model_id or args.checkpoint.parent.name, args.keep_messages, ) server = ThreadingHTTPServer((args.host, args.port), Handler) print(f'serving {Handler.service.model_id} on http://{args.host}:{args.port}/v1') server.serve_forever() if __name__ == '__main__': main()