Initial commit: NexusOS project + desktop theme baseline
Captures the known-good state after theme consolidation and consistency reconciliation: - NexusOS GTK/xfwm4/icon theme assets (assets/themes, management/Mint-Y-Nexus) - Tightened right-click menus, visible separators, no menu icons - assets/themes/install-theme.sh: idempotent restore of all wiring (symlinks, xfconf xsettings+xfwm4, GTK 3/4 settings.ini) - .gitignore excludes venv/ollama/models/runtime/db Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
jon
+242
@@ -0,0 +1,242 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import threading
|
||||
from typing import AsyncGenerator, Dict, List, Optional, Any
|
||||
|
||||
from .nexus_config import settings
|
||||
from .ollama_manager import get_ollama_manager
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Logger setup
|
||||
# -------------------------
|
||||
_logger = logging.getLogger("nexus.chat")
|
||||
_logger.setLevel(logging.INFO)
|
||||
if not _logger.handlers:
|
||||
handler = logging.FileHandler(str(settings.chat_log)) if getattr(settings, "chat_log", None) else logging.StreamHandler()
|
||||
formatter = logging.Formatter("%(asctime)s %(levelname)s %(name)s: %(message)s")
|
||||
handler.setFormatter(formatter)
|
||||
_logger.addHandler(handler)
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Synapse tracer (real-time prompt/token view for control panel)
|
||||
# -------------------------
|
||||
_synapse_lock = threading.Lock()
|
||||
_synapse_fh = None
|
||||
|
||||
def _synapse_trace(text: str) -> None:
|
||||
global _synapse_fh
|
||||
try:
|
||||
log_path = getattr(settings, "chat_log", None)
|
||||
if not log_path:
|
||||
return
|
||||
with _synapse_lock:
|
||||
if _synapse_fh is None or _synapse_fh.closed:
|
||||
_synapse_fh = open(str(log_path), "a", buffering=1, encoding="utf-8")
|
||||
_synapse_fh.write(text)
|
||||
_synapse_fh.flush()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Non-streaming generation
|
||||
# -------------------------
|
||||
async def generate_chat_response(
|
||||
user_message: str,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
history: Optional[List[Dict[str, str]]] = None,
|
||||
timeout: Optional[float] = None,
|
||||
) -> Dict[str, Any]:
|
||||
metadata = metadata or {}
|
||||
timeout = timeout or getattr(settings, "ollama_timeout", 120)
|
||||
|
||||
manager = get_ollama_manager()
|
||||
system = metadata.get("system", "")
|
||||
model = metadata.get("model") or "mistral"
|
||||
temperature = metadata.get("temperature")
|
||||
|
||||
messages: List[Dict[str, str]] = []
|
||||
if system:
|
||||
messages.append({"role": "system", "content": system})
|
||||
for msg in (history or []):
|
||||
messages.append({"role": msg["role"], "content": msg["content"]})
|
||||
messages.append({"role": "user", "content": user_message})
|
||||
|
||||
_logger.info("generate_chat_response: model=%s turns=%d timeout=%s", model, len(messages), timeout)
|
||||
|
||||
sys_preview = (system or "")[:200].replace("\n", " ")
|
||||
_synapse_trace(f"\n── TURN [{model} | {len(messages)} msgs] {'─' * 30}\n")
|
||||
if system:
|
||||
_synapse_trace(f"SYS: {sys_preview}{'…' if len(system) > 200 else ''}\n")
|
||||
_synapse_trace(f"USR: {user_message}\n{'─' * 50}\n")
|
||||
|
||||
try:
|
||||
result = await asyncio.wait_for(
|
||||
manager.chat(messages=messages, model=model, stream=False, temperature=temperature),
|
||||
timeout=timeout,
|
||||
)
|
||||
response_text = result if isinstance(result, str) else str(result)
|
||||
preview = response_text[:500].replace("\n", " ")
|
||||
_synapse_trace(f"{preview}{'…' if len(response_text) > 500 else ''}\n{'─' * 50}\n")
|
||||
_logger.info("generate_chat_response: completed model=%s", model)
|
||||
return {"response": response_text, "model": model, "metadata": metadata}
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
_logger.exception("generate_chat_response: timeout after %s seconds", timeout)
|
||||
raise
|
||||
except Exception:
|
||||
_logger.exception("generate_chat_response: unexpected error")
|
||||
raise
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Async iterator timeout helper
|
||||
# -------------------------
|
||||
async def _aiter_with_timeout(aiterable, timeout: Optional[float]):
|
||||
if timeout is None or timeout <= 0:
|
||||
async for item in aiterable:
|
||||
yield item
|
||||
return
|
||||
|
||||
aiter = aiterable.__aiter__()
|
||||
while True:
|
||||
try:
|
||||
item = await asyncio.wait_for(aiter.__anext__(), timeout=timeout)
|
||||
yield item
|
||||
except StopAsyncIteration:
|
||||
break
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Normalizer for many return shapes
|
||||
# -------------------------
|
||||
async def _normalize_to_async_generator(maybe_iterable) -> AsyncGenerator[str, None]:
|
||||
if hasattr(maybe_iterable, "__aiter__"):
|
||||
async for item in maybe_iterable:
|
||||
yield str(item)
|
||||
return
|
||||
|
||||
if asyncio.iscoroutine(maybe_iterable):
|
||||
result = await maybe_iterable
|
||||
if hasattr(result, "__aiter__"):
|
||||
async for item in result:
|
||||
yield str(item)
|
||||
return
|
||||
if hasattr(result, "__iter__") and not isinstance(result, (str, bytes)):
|
||||
for item in result:
|
||||
yield str(item)
|
||||
return
|
||||
yield str(result)
|
||||
return
|
||||
|
||||
if hasattr(maybe_iterable, "__iter__") and not isinstance(maybe_iterable, (str, bytes)):
|
||||
for item in maybe_iterable:
|
||||
yield str(item)
|
||||
return
|
||||
|
||||
yield str(maybe_iterable)
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Streaming implementation
|
||||
# -------------------------
|
||||
async def stream_chat_response(
|
||||
user_message: str,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
history: Optional[List[Dict[str, str]]] = None,
|
||||
timeout: Optional[float] = None,
|
||||
) -> AsyncGenerator[str, None]:
|
||||
metadata = metadata or {}
|
||||
timeout = timeout or getattr(settings, "ollama_timeout", 120)
|
||||
|
||||
manager = get_ollama_manager()
|
||||
system = metadata.get("system", "")
|
||||
model = metadata.get("model") or "mistral"
|
||||
temperature = metadata.get("temperature")
|
||||
|
||||
# Build messages array for /api/chat multi-turn format
|
||||
messages: List[Dict[str, str]] = []
|
||||
if system:
|
||||
messages.append({"role": "system", "content": system})
|
||||
for msg in (history or []):
|
||||
messages.append({"role": msg["role"], "content": msg["content"]})
|
||||
messages.append({"role": "user", "content": user_message})
|
||||
|
||||
_logger.info("stream_chat_response: starting stream (model=%s, turns=%d, timeout=%s)", model, len(messages), timeout)
|
||||
|
||||
sys_preview = (system or "")[:200].replace("\n", " ")
|
||||
_synapse_trace(f"\n── TURN [{model} | {len(messages)} msgs] {'─' * 30}\n")
|
||||
if system:
|
||||
_synapse_trace(f"SYS: {sys_preview}{'…' if len(system) > 200 else ''}\n")
|
||||
_synapse_trace(f"USR: {user_message}\n{'─' * 50}\n")
|
||||
|
||||
try:
|
||||
maybe_iter = manager.chat(messages=messages, model=model, stream=True, temperature=temperature)
|
||||
async_gen = _normalize_to_async_generator(maybe_iter)
|
||||
|
||||
buffer_parts: list[str] = []
|
||||
buffer_len = 0
|
||||
FLUSH_THRESHOLD = 24
|
||||
|
||||
async for piece in _aiter_with_timeout(async_gen, timeout):
|
||||
if piece is None:
|
||||
continue
|
||||
text = str(piece)
|
||||
if not text:
|
||||
continue
|
||||
|
||||
# Pass stats sentinel through immediately, don't buffer it
|
||||
if text.startswith("__meta__"):
|
||||
if buffer_parts:
|
||||
chunk = "".join(buffer_parts)
|
||||
buffer_parts = []
|
||||
buffer_len = 0
|
||||
_synapse_trace(chunk.replace("\n", " ") + "\n")
|
||||
yield chunk
|
||||
yield text
|
||||
continue
|
||||
|
||||
buffer_parts.append(text)
|
||||
buffer_len += len(text)
|
||||
|
||||
if buffer_len >= FLUSH_THRESHOLD or any(text.endswith(c) for c in (".", "!", "?", "\n")):
|
||||
chunk = "".join(buffer_parts)
|
||||
buffer_parts = []
|
||||
buffer_len = 0
|
||||
_synapse_trace(chunk.replace("\n", " ") + "\n")
|
||||
yield chunk
|
||||
|
||||
if buffer_parts:
|
||||
chunk = "".join(buffer_parts)
|
||||
_synapse_trace(chunk.replace("\n", " ") + "\n")
|
||||
yield chunk
|
||||
|
||||
_synapse_trace(f"{'─' * 50}\n")
|
||||
_logger.info("stream_chat_response: stream completed")
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
_logger.exception("stream_chat_response: timeout after %s seconds", timeout)
|
||||
raise
|
||||
except Exception:
|
||||
_logger.exception("stream_chat_response: unexpected error during streaming")
|
||||
raise
|
||||
|
||||
|
||||
# -------------------------
|
||||
# Synchronous convenience wrappers
|
||||
# -------------------------
|
||||
def generate_chat_response_sync(user_message: str, metadata: Optional[Dict[str, Any]] = None, timeout: Optional[float] = None) -> Dict[str, Any]:
|
||||
return asyncio.run(generate_chat_response(user_message, metadata=metadata, timeout=timeout))
|
||||
|
||||
|
||||
def stream_chat_response_sync(user_message: str, metadata: Optional[Dict[str, Any]] = None, timeout: Optional[float] = None):
|
||||
async def _collect():
|
||||
chunks = []
|
||||
async for c in stream_chat_response(user_message, metadata=metadata, timeout=timeout):
|
||||
chunks.append(c)
|
||||
return chunks
|
||||
return asyncio.run(_collect())
|
||||
Reference in New Issue
Block a user
GitNexus · part of the Nexus stack