progress 235b

pyinfra/framework/deploy.py

@@ -101,9 +101,10 @@ server.shell(
     _sudo=True,
 )
 
-# huggingface_hub CLI for `huggingface-cli download <repo> --local-dir ...`
-# Lands at ~/.local/bin/huggingface-cli for the SSH user. Other users can
-# repeat the command themselves.
+# huggingface_hub CLI for `hf download <repo> --local-dir ...`. Lands as
+# ~/.local/bin/hf for the SSH user (the old `huggingface-cli` name is
+# still installed as a deprecated alias). Other users can repeat the
+# command themselves.
 server.shell(
     name="Install / upgrade huggingface_hub CLI",
     commands=["uv tool install --upgrade 'huggingface_hub[cli]'"],
@@ -378,7 +379,14 @@ files.directory(
     mode="755",
     _sudo=True,
 )
-for sub in ("moonshotai", "qwen", "deepseek", "zai", "mistralai"):
+for sub in (
+    "moonshotai",
+    "qwen",
+    "deepseek",
+    "zai",
+    "mistralai",
+    "black-forest-labs",   # Flux.1-Dev for ComfyUI (gated on HF)
+):
     files.directory(
         name=f"{MODELS_DIR}/{sub}",
         path=f"{MODELS_DIR}/{sub}",
@@ -424,6 +432,9 @@ for svc in (
     "vllm",
     "ollama",
     "kimi-linear",
+    "qwen3-235b",
+    "litellm",
+    "comfyui",
     "openwebui",
     "beszel",
     "openlit",
@@ -460,6 +471,19 @@ files.directory(
     mode="2775",
     _sudo=True,
 )
+# Sibling .env for KAGI_API_KEY (used by RAG_WEB_SEARCH_ENGINE=kagi).
+# Placeholder created here; fill in by hand on first deploy. Same shared
+# key the kagimcp MCP on the Mac uses. Mode 640 root:docker so the
+# docker group can read it at compose parse time, not world-readable.
+files.file(
+    name="OpenWebUI .env (placeholder — fill in KAGI_API_KEY)",
+    path=f"{COMPOSE_DIR}/openwebui/.env",
+    present=True,
+    mode="640",
+    user="root",
+    group="docker",
+    _sudo=True,
+)
 
 # Beszel persistent state (admin account, system list, metric history).
 files.directory(
@@ -565,6 +589,114 @@ for cfg in (
         _sudo=True,
     )
 
+# llama.cpp (kyuz0 rocm-7.2.2) operator assets — smoke + readme. The
+# image and weights live elsewhere; this dir is just the scripts +
+# doc that ride alongside the compose file.
+for asset, mode in (
+    ("smoke.sh", "0775"),
+    ("README.md", "0664"),
+):
+    files.put(
+        name=f"llama: {asset}",
+        src=f"compose/llama/{asset}",
+        dest=f"{COMPOSE_DIR}/llama/{asset}",
+        group="docker",
+        mode=mode,
+        _sudo=True,
+    )
+
+# Qwen3-235B operator assets. Same image as llama (kyuz0 rocm-7.2.2);
+# this dir just ships the smoke script + README documenting the
+# coexistence/swap pattern. Weights live at /models/qwen/ via manual
+# `hf download` per the README.
+for asset, mode in (
+    ("smoke.sh", "0775"),
+    ("README.md", "0664"),
+):
+    files.put(
+        name=f"qwen3-235b: {asset}",
+        src=f"compose/qwen3-235b/{asset}",
+        dest=f"{COMPOSE_DIR}/qwen3-235b/{asset}",
+        group="docker",
+        mode=mode,
+        _sudo=True,
+    )
+
+# LiteLLM router assets. config.yaml is the source-of-truth model
+# routing table — pyinfra syncs it on every run; edits on the box get
+# overwritten. The .env file holds LITELLM_MASTER_KEY + LITELLM_SALT_KEY
+# (same pattern as compose/beszel.yml — placeholder file created here,
+# filled in by hand on first deploy).
+for asset, mode in (
+    ("config.yaml", "0664"),
+    ("smoke.sh", "0775"),
+    ("README.md", "0664"),
+):
+    files.put(
+        name=f"litellm: {asset}",
+        src=f"compose/litellm/{asset}",
+        dest=f"{COMPOSE_DIR}/litellm/{asset}",
+        group="docker",
+        mode=mode,
+        _sudo=True,
+    )
+files.file(
+    name="LiteLLM .env (placeholder — fill in LITELLM_MASTER_KEY)",
+    path=f"{COMPOSE_DIR}/litellm/.env",
+    present=True,
+    mode="640",
+    user="root",
+    group="docker",
+    _sudo=True,
+)
+
+# ComfyUI persistent state. The toolbox image runs as root and writes
+# into these dirs (models read RW so custom nodes can install, output
+# for generated images, custom_nodes for plugin installs that survive
+# container recreate, workflows for user-saved graphs). Owned 2775
+# root:docker so docker group members can drop in model files.
+for sub in ("models", "output", "custom_nodes", "workflows"):
+    files.directory(
+        name=f"ComfyUI {sub} dir",
+        path=f"{COMPOSE_DIR}/comfyui/{sub}",
+        group="docker",
+        mode="2775",
+        _sudo=True,
+    )
+# ComfyUI's expected model subdir layout — ComfyUI itself creates these
+# at first start, but pre-creating means `hf download --local-dir ...`
+# works without needing the container running.
+for model_sub in (
+    "checkpoints",
+    "diffusion_models",
+    "vae",
+    "text_encoders",
+    "loras",
+    "controlnet",
+    "clip_vision",
+    "upscale_models",
+):
+    files.directory(
+        name=f"ComfyUI models/{model_sub} dir",
+        path=f"{COMPOSE_DIR}/comfyui/models/{model_sub}",
+        group="docker",
+        mode="2775",
+        _sudo=True,
+    )
+# Smoke test + operator doc.
+for asset, mode in (
+    ("smoke.sh", "0775"),
+    ("README.md", "0664"),
+):
+    files.put(
+        name=f"comfyui: {asset}",
+        src=f"compose/comfyui/{asset}",
+        dest=f"{COMPOSE_DIR}/comfyui/{asset}",
+        group="docker",
+        mode=mode,
+        _sudo=True,
+    )
+
 # Kimi-Linear container assets (build script, smoke test, operator doc).
 # The compose file itself is copied by the for-loop above; the rest of
 # the build context lives under compose/kimi-linear/ on the source side