v0.27.1:0 - fix model download: prepend ~/.local/bin so SSH finds uvx
hf-download.sh shells out to uvx (the uv installer drops it in ~/.local/bin), but the non-interactive SSH session doesn't source the user's profile, so ~/.local/bin was off PATH and downloads died with "uvx: command not found". build_download_command now prepends $HOME/.local/bin. Adds test_download.py.
This commit is contained in:
Keysat
@@ -55,6 +55,7 @@ Subsystem guidance lives in `docs/guides/` and loads when matching files are tou
|
||||
|
||||
## Current state
|
||||
|
||||
- **Live: v0.27.1:0 — fix: "Download a new model" button (uvx PATH).** Installed on `immense-voyage` (`start-cli package list` confirms `0.27.1:0`); **not yet committed/pushed/published as of this write.** Root cause: `hf-download.sh` shells out to `uvx`, which the uv installer puts in `~/.local/bin`; Spark Control's *non-interactive* SSH session doesn't source the user's profile, so `~/.local/bin` is off PATH and the download died with "uvx: command not found" (same class as the matrix-bridge non-interactive-SSH gotcha). Fix: `download.build_download_command` prepends `export PATH="$HOME/.local/bin:$PATH"` (server-side `$HOME`, generic for any adopter); extracted to a pure helper with regression tests (`test_download.py`: PATH prefix, no-trailing-space, cluster flags, shlex round-trip). 161 pytest green; verified live (`uvx` resolves under the shipped PATH on Spark 1). Prompted by Grant hitting it while adding **Gemma-4-26B** — next: download `nvidia/Gemma-4-26B-A4B-NVFP4` (recipe `gemma4-26b` already in catalog) via the now-fixed button, then swap-test + business-card OCR.
|
||||
- **Live: v0.27.0:0 — in-app Settings gear + two bug fixes** (commit `7e07598`; installed on `immense-voyage` — `start-cli package list` confirms `0.27.0:0`; published to Clankistry; pushed to gitea master). Prompted by the second adopter's v0.25 feedback. (1) StartOS "Configure Sparks" action trimmed to the **four required fields**; all optional knobs moved to a **⚙ Settings gear** in the dashboard, backed by a `/data/app_settings.json` overlay (`app_settings.py`) keyed by env-var names, overlaid on `os.environ`, applied **live** via in-place `Settings.reload()` (architecture + the snapshot-holder gotcha are in the fastapi-image guide). Existing installs' values **migrate automatically** on first boot (`seed_from_env`). (2) **Support-service ports now configurable** (`PARAKEET_PORT`/`KOKORO_PORT`/`EMBED_PORT`/`QDRANT_PORT`; `VLLM_PORT` surfaced) — fixes the adopter's false "vLLM down" (theirs is on 8000, not launch-cluster.sh's 8888) and Parakeet 404 (remapped off 8000). (3) **Bug fix:** `GET /api/swap/lock` 404 (was shadowed by `/api/swap/{job_id}`; lock routes now register first). Code review caught a real P1 (the `WebhookNotifier` snapshot — fixed via `swap_webhook.update()` after reload, regression-tested). 157 pytest + live smoke all green.
|
||||
- **Next on this thread (small, externally gated):** (a) **adopter reply is drafted** (in the session — corrects the vLLM-port misconception → set 8000 in the gear, confirms the port knobs + swap/lock fix, asks the disk-scan diagnostic) — **pending Grant to send** + pick the distribution-channel wording. (b) **Optional Gitea tag + `make release`** so the adopter can pull v0.27 from Gitea Releases (NOT done this session — only registry + sideload shipped); do it only if that adopter pulls from Gitea Releases rather than subscribing to Clankistry. (c) **Un-diagnosed:** adopter's disk-scan shows Gemma "not on disk" — needs them to run `ls ~/.cache/huggingface/hub` as the SSH user vs `disk.py`'s `$HOME/.cache/huggingface/hub` assumption (likely a custom `HF_HOME`/container-volume/different-user cache path → would need a configurable cache path).
|
||||
- **Live: v0.26.0:0 — disk-driven model menu** (installed on the server 2026-06-18, `installed-version` confirms; also published to the self-hosted StartOS registry). The dashboard lists what's *actually downloaded* on the Sparks; `models.yaml`/overrides are **launch recipes** matched by `repo`, not the menu; an on-disk model with no recipe shows `needs_setup` and infers its launch flags from `config.json` (operator confirms once). Delete removes weights **and** the card; dropped the two legacy Qwen recipes. Architecture (`discovery.py`/`build_menu`/`infer_recipe`, the recipe-vs-disk split) is in the fastapi-image guide.
|
||||
|
||||
+15
-1
@@ -23,6 +23,20 @@ from .ssh import ssh_stream, StreamHandle
|
||||
Mode = Literal["spark1", "spark2", "cluster"]
|
||||
|
||||
|
||||
def build_download_command(repo: str, flags: str = "") -> str:
|
||||
"""Remote shell command that drives hf-download.sh on a Spark.
|
||||
|
||||
Prepends ~/.local/bin to PATH. hf-download.sh shells out to `uvx` (Astral's
|
||||
uv), and the official uv installer drops its binaries in ~/.local/bin — but
|
||||
our SSH session is non-interactive, so it never sources the user's profile
|
||||
and ~/.local/bin is off PATH, leaving `uvx` as "command not found". $HOME
|
||||
expands server-side, so this stays correct for any adopter/user. `repo` is
|
||||
shlex-quoted at the sink (validate_repo gates the charset upstream).
|
||||
"""
|
||||
serve = f"./hf-download.sh {quote_arg(repo)} {flags}".strip()
|
||||
return f'export PATH="$HOME/.local/bin:$PATH" && cd ~/spark-vllm-docker && {serve}'
|
||||
|
||||
|
||||
_TQDM_RE = re.compile(
|
||||
r"(\d+(?:\.\d+)?)\s*%\s*\|.*?\|\s*"
|
||||
r"([\d.]+[KMG]?B?)\s*/\s*([\d.]+[KMG]?B?)\s*"
|
||||
@@ -126,7 +140,7 @@ class DownloadManager:
|
||||
if not target_host or not target_user:
|
||||
raise RuntimeError(f"{job.mode} host not configured")
|
||||
|
||||
cmd = f"cd ~/spark-vllm-docker && ./hf-download.sh {quote_arg(job.repo)} {flags}".strip()
|
||||
cmd = build_download_command(job.repo, flags)
|
||||
job.append(f"$ {cmd}")
|
||||
job.state = "downloading"
|
||||
job.progress.phase = "Connecting to Hugging Face…"
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
"""build_download_command: the ~/.local/bin PATH fix + shell-injection quoting.
|
||||
|
||||
hf-download.sh on the Spark shells out to `uvx`, which the uv installer puts in
|
||||
~/.local/bin — off the PATH of our non-interactive SSH session. The command must
|
||||
prepend ~/.local/bin (via $HOME, expanded server-side) or the download dies with
|
||||
"uvx: command not found". The repo value must also be shlex-quoted at the sink so
|
||||
a crafted value can't break out of the command (validate_repo gates it upstream).
|
||||
"""
|
||||
import shlex
|
||||
|
||||
from app.download import build_download_command
|
||||
|
||||
|
||||
def test_prepends_local_bin_to_path():
|
||||
cmd = build_download_command("org/name")
|
||||
assert cmd.startswith('export PATH="$HOME/.local/bin:$PATH" && ')
|
||||
assert "cd ~/spark-vllm-docker" in cmd
|
||||
assert "./hf-download.sh org/name" in cmd
|
||||
|
||||
|
||||
def test_no_trailing_space_without_flags():
|
||||
assert build_download_command("org/name", "").endswith("./hf-download.sh org/name")
|
||||
|
||||
|
||||
def test_cluster_flags_appended():
|
||||
cmd = build_download_command("org/name", "-c --copy-parallel")
|
||||
assert cmd.endswith("./hf-download.sh org/name -c --copy-parallel")
|
||||
|
||||
|
||||
def test_repo_is_shlex_quoted():
|
||||
# Everything after the script name must shlex-split back to the exact repo,
|
||||
# the same round-trip invariant build_launch_command relies on.
|
||||
cmd = build_download_command("org/na;me")
|
||||
after = cmd.split("./hf-download.sh ", 1)[1]
|
||||
assert shlex.split(after) == ["org/na;me"]
|
||||
@@ -1,10 +1,10 @@
|
||||
import { VersionInfo, IMPOSSIBLE } from '@start9labs/start-sdk'
|
||||
|
||||
export const v0_1_0 = VersionInfo.of({
|
||||
version: '0.27.0:0',
|
||||
version: '0.27.1:0',
|
||||
releaseNotes: {
|
||||
en_US:
|
||||
'v0.27.0:0 — settings move into the dashboard, plus two bug fixes. (1) New ⚙ Settings gear in the dashboard: all the optional cluster knobs — vLLM and support-service ports, container names, Parakeet/Kokoro/embeddings/Qdrant hosts, Open WebUI link, NGC key, swap webhook — are now edited here, in plain English, and apply immediately without a restart. The StartOS "Configure Sparks" action is now just the four required fields (two Spark IPs + SSH users); your existing optional values migrate into the gear automatically on first launch, and the settings are stored on the server and included in StartOS backups. (2) NEW: support-service ports are now configurable. If your vLLM runs on 8000 (vLLM\'s own default) and you moved Parakeet to another port, set them under ⚙ Settings → that fixes the false "vLLM down" and the Parakeet 404 some setups saw. (3) Bug fix: GET /api/swap/lock returned 404 (a routing bug where it was shadowed by the swap-job lookup); the swap reservation status now reads correctly. No breaking consumer-API changes; the /v1 proxy and swap API are unchanged.',
|
||||
'v0.27.1:0 — bug fix: "Download a new model" now works on its own. The downloader on the Spark relies on a helper tool (uvx, part of Astral\'s uv) that the standard installer places under your home directory in ~/.local/bin. Spark Control runs downloads over an automated SSH session that wasn\'t looking there, so a download failed immediately with "uvx: command not found" even though the tool was installed. Spark Control now includes ~/.local/bin on the path when it runs a download, so the Download button works with no manual setup. No other changes; the /v1 proxy, swap, and coordination APIs are unchanged.',
|
||||
},
|
||||
migrations: {
|
||||
up: async ({ effects }) => {},
|
||||
|
||||
Reference in New Issue
Block a user