Jaroslav Beneš
dd9e0e9440
LLeMbas now runs end to end. Register, add an OpenAI-compatible connection, and hold a real streaming conversation organised into folders. Verified against the local llama-swap instance. Streaming is the one genuinely tricky part. Sending a message returns two HTML fragments -- the user bubble and an empty assistant bubble carrying an sse-connect -- and that attribute is the ONLY thing that starts a generation. Rendering an incomplete assistant message as a streaming shell falls out of the same template, which means loading a page whose last reply never finished simply picks it up again. Details worth knowing about, each commented where it matters: - SSE payloads are split across several data: lines. A raw newline in one data: line truncates the event, which shows up the first time a model emits a code block. - Markdown is rendered server-side by the same helper for both the page and the final streamed frame, so the two cannot disagree. The fence renderer is replaced outright rather than using markdown-it's highlight option, which re-wraps output in a second <pre>. - escape_text is html.escape, not nh3.clean_text: it escapes character by character, so escaping stream chunks separately equals escaping the whole string. - The stream opens its own session via session_scope(); it outlives the request handler and the dependency-scoped session may be closed. - Deleting a folder keeps the chats inside it (FK is SET NULL). Losing a conversation to a mis-clicked folder delete is unforgivable. - Login failures use one message for "no such account" and "wrong password" so the form cannot enumerate registered addresses. Also adds deploy/ for the gamebox install at https://chat.lan: system unit, nginx vhost with buffering off (buffering on turns streaming into one lump at the end), and install/update scripts following the same service-user and /srv bind-mount conventions as llama-swap and comfyui. 70 tests, ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
68 lines
1.6 KiB
TOML
68 lines
1.6 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "lembas"
|
|
version = "0.1.0"
|
|
description = "LLeMbas - a Middle-earth themed web UI for OpenAI-compatible LLM endpoints"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
license = { file = "LICENSE" }
|
|
authors = [{ name = "Jaroslav Benes", email = "admin@ecoposta.sk" }]
|
|
keywords = ["llm", "webui", "openai", "chat", "self-hosted"]
|
|
classifiers = [
|
|
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
|
|
"Programming Language :: Python :: 3",
|
|
"Topic :: Communications :: Chat",
|
|
]
|
|
|
|
dependencies = [
|
|
"fastapi>=0.115",
|
|
"uvicorn[standard]>=0.32",
|
|
"jinja2>=3.1",
|
|
"sqlalchemy>=2.0",
|
|
"pydantic>=2.9",
|
|
"pydantic-settings>=2.6",
|
|
"httpx>=0.27",
|
|
"python-multipart>=0.0.12",
|
|
"argon2-cffi>=23.1",
|
|
"cryptography>=43.0",
|
|
"markdown-it-py>=3.0",
|
|
"mdit-py-plugins>=0.4",
|
|
"linkify-it-py>=2.0", # bare URLs in model output become links
|
|
"pygments>=2.18",
|
|
"nh3>=0.2.18",
|
|
"typer>=0.12",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.3",
|
|
"pytest-asyncio>=0.24",
|
|
"ruff>=0.7",
|
|
]
|
|
|
|
[project.scripts]
|
|
lembas = "lembas.cli:app"
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/homer/LLeMbas"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/lembas"]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py311"
|
|
src = ["src", "tests"]
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "UP", "B", "SIM", "C4"]
|
|
ignore = ["B008"] # FastAPI Depends() in defaults is idiomatic
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|
|
filterwarnings = ["ignore::DeprecationWarning"]
|