File size: 8,732 Bytes
3754f8b |
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 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 |
from __future__ import annotations
import json
from datetime import datetime
from pathlib import Path
from typing import Iterable, List
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse, StreamingResponse
from fastapi.staticfiles import StaticFiles
from config import settings
from ollama_utils import (
ask_ollama_stream,
list_models,
pull_model_with_progress,
start_ollama,
verify,
)
from ui_logic import (
concat_code_blocks,
extract_code_blocks,
generate_diff,
prepare_inputs,
)
from backend.schemas import (
ChatRequest,
ContinueRequest,
DiffRequest,
HistoryPayload,
UploadedFilePayload,
)
from backend.utils import messages_to_pairs
from ui_logic import do_export, do_load_chat, do_save_chat
app = FastAPI(
title="Llama Dev Suite PRO Backend",
version="1.0.0",
description="API conversacional para Llama Dev Suite PRO",
)
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_methods=["*"],
allow_headers=["*"],
)
def _decode_files(files: Iterable[UploadedFilePayload]):
return [payload.to_file() for payload in files]
def _normalize_text(value: str | None) -> str:
return value.strip() if value else ""
@app.get("/api/health")
def health():
return {"status": "ok", "time": datetime.utcnow().isoformat()}
@app.get("/api/status")
def status():
return {"status": verify()}
@app.post("/api/ollama/start")
def start():
return {"status": start_ollama()}
@app.get("/api/models")
def models():
return {"models": list_models()}
@app.post("/api/ollama/pull")
def pull_model(payload: dict):
model_name = payload.get("model")
if not model_name:
raise HTTPException(status_code=400, detail="Falta 'model'.")
messages: List[str] = []
for update in pull_model_with_progress(model_name):
messages.append(update)
return {"events": messages}
def _build_chat_stream(req: ChatRequest):
decoded_files = _decode_files(req.files)
system_prompt, user_prompt, preview, first_code = prepare_inputs(
decoded_files,
_normalize_text(req.exclude),
_normalize_text(req.extra),
req.mode,
req.language,
req.message,
_normalize_text(req.template),
)
history_pairs = messages_to_pairs(req.history)
def event_iterator():
assistant_accum = ""
try:
for chunk in ask_ollama_stream(
req.model,
system_prompt,
history_pairs,
user_prompt,
req.temperature,
req.top_p,
req.max_tokens,
):
assistant_accum += chunk
payload = {"type": "chunk", "content": chunk}
yield f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
code_blocks = extract_code_blocks(assistant_accum)
lang_main, code_concat = concat_code_blocks(code_blocks)
legacy_history = [
{"role": msg.role, "content": msg.content} for msg in req.history
]
legacy_history.append({"role": "user", "content": req.message})
legacy_history.append({"role": "assistant", "content": assistant_accum})
payload = {
"type": "final",
"message": {"role": "assistant", "content": assistant_accum},
"history": legacy_history,
"code": code_concat,
"code_language": lang_main,
"preview": preview,
"first_code": first_code,
"system_prompt": system_prompt,
"user_prompt": user_prompt,
}
yield f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
except Exception as exc: # pragma: no cover
error_payload = {
"type": "error",
"message": str(exc),
}
yield f"data: {json.dumps(error_payload, ensure_ascii=False)}\n\n"
return event_iterator
@app.post("/api/chat")
def chat(req: ChatRequest):
iterator = _build_chat_stream(req)
return StreamingResponse(iterator(), media_type="text/event-stream")
@app.post("/api/chat/continue")
def chat_continue(req: ContinueRequest):
cont_prompt = (
req.user_prompt
+ "\n\nEl asistente respondi贸 esto parcialmente:\n"
+ req.assistant_text[-2000:]
+ "\n\nContin煤a exactamente donde lo dejaste, sin repetir."
)
history_pairs = messages_to_pairs(req.history)
def event_iterator():
accumulated = req.assistant_text
try:
for chunk in ask_ollama_stream(
req.model,
req.system_prompt,
history_pairs,
cont_prompt,
req.temperature,
req.top_p,
req.max_tokens,
):
accumulated += chunk
payload = {"type": "chunk", "content": chunk}
yield f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
code_blocks = extract_code_blocks(accumulated)
lang_main, code_concat = concat_code_blocks(code_blocks)
legacy_history = [
{"role": msg.role, "content": msg.content} for msg in req.history
]
if legacy_history and legacy_history[-1]["role"] == "assistant":
legacy_history[-1]["content"] = accumulated
else:
legacy_history.append({"role": "assistant", "content": accumulated})
payload = {
"type": "final",
"message": {"role": "assistant", "content": accumulated},
"history": legacy_history,
"code": code_concat,
"code_language": lang_main,
}
yield f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
except Exception as exc: # pragma: no cover
error_payload = {"type": "error", "message": str(exc)}
yield f"data: {json.dumps(error_payload, ensure_ascii=False)}\n\n"
return StreamingResponse(event_iterator(), media_type="text/event-stream")
@app.post("/api/diff")
def diff(req: DiffRequest):
return {"diff": generate_diff(req.before, req.after)}
@app.get("/api/chats")
def list_saved():
files = sorted(
settings.CHAT_SAVE_PATH.glob("*.json"),
key=lambda x: x.stat().st_mtime,
reverse=True,
)
return {"items": [str(f) for f in files]}
@app.get("/api/chats/{path:path}")
def load_chat(path: str):
history, status = do_load_chat(path)
if not history:
raise HTTPException(status_code=404, detail=status)
return {"history": history, "status": status}
@app.post("/api/chats/save")
def save_chat(payload: HistoryPayload):
message = do_save_chat(
[{"role": msg.role, "content": msg.content} for msg in payload.history],
payload.name or "",
)
if message.startswith("鈿狅笍"):
raise HTTPException(status_code=400, detail=message)
return {"status": message}
@app.post("/api/export")
def export_chat(payload: HistoryPayload):
file_component = do_export(
[{"role": msg.role, "content": msg.content} for msg in payload.history]
)
if not file_component or not getattr(file_component, "value", None):
raise HTTPException(status_code=400, detail="No hay conversaci贸n para exportar.")
file_path = Path(file_component.value)
if not file_path.exists():
raise HTTPException(status_code=500, detail="Archivo de exportaci贸n no disponible.")
return FileResponse(path=file_path, filename=file_path.name)
FRONTEND_DIST = Path(__file__).resolve().parent.parent / "frontend" / "dist"
if FRONTEND_DIST.exists():
app.mount(
"/assets",
StaticFiles(directory=str(FRONTEND_DIST / "assets")),
name="assets",
)
@app.get("/", include_in_schema=False)
async def serve_index():
index_path = FRONTEND_DIST / "index.html"
if index_path.exists():
return FileResponse(index_path)
raise HTTPException(status_code=404, detail="Recurso no encontrado.")
@app.get("/{full_path:path}", include_in_schema=False)
async def serve_frontend(full_path: str):
if full_path.startswith("api/"):
raise HTTPException(status_code=404, detail="Ruta API no encontrada.")
index_path = FRONTEND_DIST / "index.html"
if index_path.exists():
return FileResponse(index_path)
raise HTTPException(status_code=404, detail="Recurso no encontrado.") |