* Add customizable RAG embedding model setting and reorganize settings tabs
Chat with files, project sources, and knowledge bases previously always
embedded with unsloth/bge-small-en-v1.5. This adds a Settings option to
pick any Hugging Face embedding model (or local path), with HF search
autocomplete, server-side verification that the repo is actually an
embedding model, and a save anyway escape hatch for offline or local
models. The setting persists in app_settings and applies at runtime to
both the sentence-transformers and llama-server GGUF embedder backends
without a restart.
Also reorganizes the General settings tab: Documents & RAG sits above
Uploads, Helper LLM moved above the danger zone, and Model auto-switch
(OpenAI API) moved to the bottom of the API tab.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Support local model paths on the GGUF embedder and normalize default saves
Found by simulation testing of the embedding model setting:
Local paths saved as the embedding model now work on the llama-server
GGUF backend (the default backend on macOS and CPU). A path to a .gguf
file is used directly and a directory is scanned for a variant-matching
non-mmproj .gguf, with a clear error when none exists. Previously a
local path was sent to the HF hub API and failed with a repo lookup
error.
Saving the default model explicitly no longer stores an override, so
is_custom stays false and the UI does not show a reset button for the
default value.
* Address review: stale-vector handling, GGUF derivation, save-time guards
Review follow-ups, each verified by new tests:
Re-uploading a document after an embedding model change now re-indexes
instead of deduping by content hash. Documents record the embedder that
produced their vectors (lazy embedding_model column, NULL legacy rows
keep deduping) and a mismatch replaces the old document.
A vector width change no longer bricks the dense index. ensure_vec
drops and recreates chunks_vec when the dim changes (old vectors are in
a foreign space and only block inserts) and search_dense returns empty
on a width mismatch instead of surfacing a vec0 error, so lexical
search keeps working until documents are re-uploaded.
Saving a local sentence-transformers folder with no .gguf now returns
409 with a clear message when the install embeds via llama-server,
instead of failing at first index. force still saves.
A custom RAG_EMBEDDING_MODEL env without RAG_EMBED_GGUF_REPO now
derives the -GGUF companion repo instead of silently keeping the bge
GGUF on CPU and macOS installs.
The resolved GGUF path is tagged with the repo captured at entry, so a
setting change during a download cannot mark the old model as current.
GGUF repo detection matches gguf as a whole name segment rather than a
substring, hf_token is trimmed before verification, and the settings
combobox drops a redundant state mirror of its controlled value.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Shrink embedding model font to 11px in the input and dropdown
The combobox wrapper applies className to the outer input group, so the
size utility must target the inner input element; the previous text-xs
never reached it and the field rendered at the browser default.
* Show curated unsloth embedding models when the search field is empty
The empty-query listing was the global top-downloads page, which holds
no unsloth mirrors for the unsloth-first float to reorder, so the
dropdown opened on third-party models. Match the model picker: curated
unsloth listing when empty, whole-Hub search once a query is typed.
* Address review: settings resilience and index consistency
Keep the last known embedding model on settings store errors, remove the
re-entrant dim lock in the llama-server backend, accept local GGUF saves
and verify GGUF availability for HF repos on that backend, match local
path embedders exactly in model list filters, drop same-width stale
vectors from dense search, pin the embedder per ingestion job, and only
replace completed documents after the re-index succeeds.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Consolidate the GGUF repo derivation tests
* Trim to a single core embedding-model test
* Address review: GGUF repo saves and cache race
Accept a GGUF-named HF repo on the llama-server backend by verifying GGUF
availability instead of the sentence-transformers metadata gate, and guard
the settings cache with a generation counter so a read overlapping a save
cannot repopulate it with the pre-save value.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio RAG: fix RTL/Indic PDF corruption and dropped DOCX tables
The RAG parser prefers pymupdf4llm.to_markdown for PDFs, but that rebuilds text from
positioned glyphs and mangles complex-shaping scripts (RTL Arabic/Hebrew come back as
shaped Presentation Forms, Indic matras drop to U+FFFD) and can silently drop most of a
heavy-RTL page. _pdf now compares the Markdown against PyMuPDF's logical-order
get_text() per page and falls back to it when the Markdown looks corrupted (shaped
Presentation Forms or U+FFFD above a small floor/ratio) or holds far fewer letters than
the raw layer. Latin PDFs are unaffected and keep their Markdown tables/headings.
_docx walked document.paragraphs, which excludes table cells, so DOCX tables were
dropped entirely. It now walks body content in document order via iter_inner_content,
emitting each table row as pipe-joined cells (deduped across merged cells); the preview
locator already anchors on pipes.
Adds parser tests for the corruption and incompleteness fallbacks and for DOCX table
extraction. These mirror the chat document-extractor guard raised in the unslothai/
unsloth#5351 review; the RAG parser is a separate module and needed its own fix.
* RAG DOCX: keep empty table cells and collapse in-cell newlines
Skipping empty cells shifted later cells left and broke column alignment across rows;
a cell with internal paragraphs (newlines) also broke the pipe-joined row. Keep every
cell (dropping the row only when all are empty) and normalize each cell with
" ".join(split()) so multi-paragraph cells stay on one row. Adds a test for both.
* RAG DOCX: dedup merged table cells on the <w:tc> element directly
Store the shared <w:tc> lxml element in the seen set instead of its id(); it is
hashable and compares by the underlying node, so it dedups spanned/merged cells the
same way without relying on id(). Adds a merged-cell test.
* RAG DOCX: align merged cells, pad skipped grid columns, flatten nested tables
* RAG DOCX: walk cells in document order so nested tables keep in-cell position
* RAG DOCX: dedup vertically merged cells so a spanning label is indexed once
---------
Co-authored-by: danielhanchen <michaelhan2050@gmail.com>
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
* Studio: opt-in OpenAI /v1 model auto-switch and idle keep-warm
The OpenAI-compatible endpoints serve whichever GGUF is loaded and ignore the
request model field, so an OpenAI client that changes model never reloads. Add
an opt-in setting that, when a /v1 request names a downloaded local GGUF
different from the loaded one, loads it before serving by reusing the existing
/load path (its dedup, tensor fallback, and threading apply). Unknown names
still serve the loaded model, so drop-in compatibility is preserved and no
remote download is triggered.
Also add an optional idle auto-unload (TTL keep-warm): a pure-ASGI middleware
tracks in-flight inference requests so a stream is never unloaded mid-response,
and a lifespan loop unloads the model after the configured idle seconds. Both
settings default off and live in the app_settings store, exposed via
GET/PUT /api/settings/openai-auto-switch.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: variant-aware auto-switch, /v1/responses coverage, keep-warm load stamp
Follow-ups from review of the opt-in OpenAI auto-switch path:
1. Variant-aware dedup. _maybe_auto_switch_model compared only the repo id, so
requesting another quant of the loaded repo (e.g. Q4_K_M loaded, Q8_0 asked)
was served by the old quant. Compare hf_variant too, matching /load dedup.
2. Streaming /v1/responses now calls the auto-switch hook. It went straight into
_responses_stream and only checked is_loaded, so stream=True could serve the
old model or 400. Non-streaming already routed through chat completions; the
hook is idempotent once loaded.
3. resolve_local_gguf tries an exact id match before splitting a trailing
:VARIANT, so local ids that contain a colon (e.g. a Windows path) resolve
instead of being cut at the drive letter.
4. Idle keep-warm stamps activity on a load/swap transition. _last_active was
only refreshed by inference requests, so a model loaded after the server sat
idle past the TTL could be unloaded before its first request.
Tests cover each case.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: make the /v1/responses auto-switch test order-independent
The new streaming-responses test passed in isolation but failed under the CI's
randomized collection order with "object has no attribute 'state'": it passed a
bare object() as the request and stubbed only one dispatcher, so an ordering
where the real dispatcher ran hit request.state. Give the request a state and
stub both dispatchers; the test still asserts the hook fires before dispatch.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: assert /v1/responses auto-switch wiring on source, not at runtime
The behavioral version executed openai_responses and relied on stubbing its
callees, which a randomized collection order in CI could defeat (the real
dispatcher ran and hit request attributes). Assert on the function source that
the hook precedes both dispatchers instead; the hook's runtime behavior is
already covered by the direct _maybe_auto_switch_model tests.
* Studio: auto-switch on /v1/embeddings, GGUF-only targets, idle-unload race gate
Second-pass review follow-ups on the opt-in auto-switch path:
1. /v1/embeddings now calls the auto-switch hook before the loaded-state check,
matching the other model-bearing OpenAI endpoints (the keep-warm middleware
already treats embeddings as inference).
2. The resolver index is now GGUF-only. The local-model scanners also surface
Transformers/safetensors repos; without a filter, auto-switch could unload
the GGUF and route a request into the non-GGUF loader. _has_local_gguf checks
a direct .gguf, a models-dir folder, and the HF-cache snapshots layout.
3. Idle keep-warm now holds an asyncio gate across the idle check and the
unload, and a request bumps inflight under the same gate, so the loop can no
longer unload in the window between "looks idle" and the kill.
Tests cover each. Broader local-model source parity (LM Studio, Ollama, legacy
caches, custom scan folders) is a follow-up; missing one of those today just
falls through to the loaded model.
* Studio: variant-aware local resolver, count_tokens + audio auto-switch coverage
Third-pass review follow-ups on the opt-in auto-switch path:
1. The resolver is now variant-aware via list_local_gguf_variants. It indexes
only the quants actually on disk, recursing snapshots and quant subdirs such
as the nested per-quant folders, so a requested repo:VARIANT resolves only
when that quant is local and a bare repo resolves to a concrete local quant.
This fixes two gaps: the previous shallow glob rejected nested-variant GGUF
repos, and a request for an uncached quant could send /load down the remote
download path, breaking the local-only contract.
2. /v1/messages/count_tokens now auto-switches like its sibling /v1/messages, so
a count uses the requested model's tokenizer.
3. /api/inference/audio/generate (direct GGUF TTS) is now tracked as in-flight
inference, so the idle loop cannot unload the model mid-generation.
Tests cover each. Two reviewer items are left as follow-ups: indexing the
remaining local sources (LM Studio, Ollama, legacy/default caches, custom scan
folders), which fails safe today by falling through to the loaded model; and
fully serializing concurrent different-model requests, an inherent limit of the
single-slot llama backend that the opt-in feature is not designed around.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: make local GGUF resolver fail-safe so a bad model name cannot 500
The auto-switch hook calls resolve_local_gguf without its own guard, and
/v1/completions and /v1/embeddings pass body.get("model") through unchanged.
A non-string model (e.g. {"model": 123}) or any internal scan failure would
then raise out of the resolver and turn a request that would otherwise be
served by the loaded model into a 500, breaking the drop-in compatibility the
feature is built on.
Guard the resolver at its boundary: reject non-string input up front and wrap
the lookup so any failure returns None (fall through to the loaded model).
Add regression tests for both paths.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: per-model launch flags for auto-switched GGUF models
* Studio: list switch-eligible GGUFs in /v1/models when auto-switch is on
* Studio: settings UI for OpenAI model auto-switch and idle auto-unload
* Studio: show save error over the disabled-idle hint in auto-switch settings
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address gemini review (case-insensitive /v1/models retrieve, idle-input empty guard)
* Studio: address codex review (deterministic override args, exclude probe/embedding models from discovery)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: keep-warm count_tokens, gate idle on auto-switch, drop hidden models
Three hardening fixes to the opt-in auto-switch path surfaced while reviewing
the work that builds on it:
1. count_tokens keep-warm. /v1/messages/count_tokens counts via the loaded
tokenizer and already auto-switches, but the keep-warm middleware did not
track it, so idle auto-unload could free the model mid-count. It is now a
tracked in-flight path.
2. "Off means unchanged" for idle unload. get_auto_unload_idle_seconds now
reports 0 while auto-switch is disabled. Idle unload only makes sense with
auto-switch on (an unloaded model returns only via the next request's swap),
so a stray TTL can no longer trigger a destructive unload while the feature
is off, keeping the disabled state identical to pre-feature behavior.
3. Hidden models are not switch targets. The resolver index now skips what
Studio hides from its own pickers (the llama.cpp validation probe, RAG
embedding weights) via _is_hidden_model, so they can never be auto-switched
to by name.
Tests added for each.
* Studio: bare-id reuse, responses validation order, in-flight tracking
Review follow-ups after folding in the per-model overrides and discovery work:
1. A bare model id (no :VARIANT) is now satisfied by any loaded quant of that
repo. Previously a bare name resolved to the largest local quant, so it could
force a slow reload when a different quant of the same repo was already
serving. An explicit repo:VARIANT request still honors the quant.
2. /v1/responses now runs the auto-switch hook after the empty-input validation
so a request that 400s can no longer trigger a multi-minute model load before
being rejected. The hook still precedes both dispatchers, so streaming
requests switch.
3. The keep-warm middleware now tracks in-flight requests whenever auto-switch
is enabled rather than only when the idle TTL is already positive, so a stream
that starts with the TTL at 0 is still protected if idle-unload is enabled
mid-stream. Off still passes straight through.
Tests added for each.
* Studio: tighten auto-switch code comments
Comment/docstring-only pass over the OpenAI auto-switch feature: collapse
multi-line blocks, drop a comment that restated the gate it sits next to, and
trim verbose docstrings on internal helpers while keeping the load-bearing
rationale (concurrency, API behavior, drop-in compat, gotchas). No logic
change: verified comment-only with the AST/printer signature check.
* Studio: bind auto-switch locks per running loop
Review follow-up. The auto-switch swap lock and the keep-warm unload gate were
module-level asyncio.Lock objects. That is safe under the single uvicorn loop
and on Python 3.10+ (the Lock resolves the running loop lazily on acquire), but
a module-level Lock binds to one loop on pre-3.10, which can raise a loop
mismatch in multi-loop runners. Resolve each lock through a per-loop accessor
backed by a WeakKeyDictionary so every running loop gets its own Lock and stale
loops are collected. No behavior change under the server's single loop.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: auto-switch re-review fixes (body codes, coverage, swap, alias, tracking)
Follow-ups from a second review pass over the opt-in OpenAI auto-switch feature:
1. OFF-state status codes: /v1/completions and /v1/embeddings moved the body
read ahead of the loaded-state check, so a malformed/empty body with no model
loaded returned 500 instead of the prior 503. A shared helper reads the body
defensively (an unparseable/non-dict body yields no model), and the handler
re-reads after the 503 gate to surface the original parse error exactly as
before. OFF behavior is unchanged.
2. Local-model coverage: the resolver index only scanned ./models and the active
HF cache, while the model picker also lists the legacy/default HF caches, LM
Studio dirs, and user scan folders. A request for one of those named models
silently served the loaded model instead. _build_index now scans the same
roots (Ollama's symlink-creating scanner is skipped on the request path), and
resolution is offloaded with asyncio.to_thread so the wider scan never blocks
the event loop.
3. Swap vs in-flight stream: a cross-model swap killed the llama-server while
another client was still streaming from it. The hook now tracks how many
requests are streaming on the loaded model (in-flight minus those still inside
the hook) and returns 409 instead of swapping while one is active. Concurrent
same-model requests never reach this path, so they are unaffected.
4. Idle-unload + alias: after idle-unload freed the model, an unknown/alias name
resolved to nothing and 503'd, though it served the active model before the
TTL. Idle-unload now remembers the freed id and an alias request reloads it
(only an already-local model, so no remote download), cleared once a model is
loaded again.
5. In-flight tracking: the keep-warm middleware tracked in-flight only while the
feature was on, so a stream started while off could be unloaded if idle-unload
was enabled mid-stream. It now tracks on every inference path; counting is
cheap and invisible to clients.
Tests added for each.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Remove stray async_task_outputs files committed by mistake
* Studio: auto-switch review round 3 (revert swap guard, hardening)
Addressing a third review pass:
- Revert the cross-model swap guard. It counted keep-warm in-flight (which
includes external-provider calls that never touch the local model) and so
could 409 a local swap spuriously, and it still left a same-model request able
to start streaming on the model a concurrent swap was unloading. A correct fix
needs a request-lifetime reader/writer barrier; a partial guard was worse than
the honest single-slot behavior, so concurrent different-model use is back to
being serialized (documented), like llama-swap's single slot.
- Non-string request model (e.g. {"model": 123} on a raw-body endpoint) is now
treated as absent, so it falls through instead of raising in the membership
checks once an idle-unload stash exists.
- Idle-unload now stashes and replays the freed quant: an alias reload restores
the exact (id, variant) that was freed rather than the largest local quant.
- Anthropic /v1/messages validates max_tokens before the auto-switch hook, so a
request that 400s never triggers a model load.
- Keep-warm tracks a pending count for requests waiting on the unload gate, so
the idle loop cannot unload the model out from under a request that is blocked
on the gate but not yet counted as in-flight.
- The idle-unload task is awaited after cancel on shutdown to avoid pending-task
warnings.
- The resolver's HF cache scan is None-safe and logs at debug instead of letting
a bad root abort the whole index build.
- upsert_app_setting_map_entry rolls back explicitly on error.
Tests updated/added for each.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: keep saved idle-unload seconds when auto-switch is toggled off
* Studio: auto-switch hardening (thread-safe lock maps, body validation)
Defensive fixes from review:
- Guard the per-loop WeakKeyDictionary get-or-create for both the unload gate and
the auto-switch lock with a threading lock, since WeakKeyDictionary mutation is
not thread-safe when two event loops run on different threads.
- Build the resolver index under the cache lock so concurrent callers with an
expired cache don't all run the multi-dir scan at once.
- /v1/completions and /v1/embeddings return a clean 400 for a valid JSON body
that is not an object (e.g. a list), instead of a 500 from body.get(...).
- The keep-warm middleware only tracks POST requests (inference is always POST),
so CORS preflight (OPTIONS) is not counted, and tolerates a None path.
Tests added for the list-body 400 and the non-POST skip.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: auto-switch review round 4 (local-path load, swap guard, idle fixes)
From a 10-reviewer pass:
- HF-cache entries now load by a concrete local path, not the bare repo id. The
resolver records a load_path (the snapshot dir for a models--* cache repo, the
file/dir otherwise) so /load takes the local branch and can never trigger a
download to satisfy a partial cache. The advertised loader_id (repo id) is kept
as the launch-override key. resolve_local_gguf now returns
(load_path, variant, loader_id).
- Re-add a single-slot swap guard: a cross-model swap returns 409 model_switch_busy
while another inference request is active rather than killing its stream (the
caller is excluded from the count), and holds the keep-warm gate across the load
so no new inference starts mid-swap. Concurrent same-model requests never reach
this path. A residual spurious 409 is possible while a concurrent or external-
provider request is active; that is the documented single-slot tradeoff.
- Idle keep-warm tracks (model_identifier, hf_variant): reloading the same repo at
a different quant counts as a fresh model, so it is not unloaded before one TTL.
- Track Studio's own /api/inference/generate/stream so the idle loop can't unload
the model mid-stream on that route.
- A successful manual /load clears the idle-unload reload stash synchronously, not
only on the next idle poll.
Also merged origin/main (the branch had fallen behind, which would have reverted
unrelated files on merge). Tests added/updated for each.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: auto-switch review round 5 (concurrency, identity, load gate)
From a 10-reviewer pass (9 request-changes, 1 approve):
- Concurrent same-target requests load once instead of each returning 409. The
count-based busy guard could not tell "another request wants the same model"
(safe, load once) from "another request is using the loaded model" (refuse).
Track in-flight auto-switch requests per (target, variant) and subtract
same-target waiters from the busy count; a cross-model swap still 409s while a
genuinely different request is active.
- Fix the identity confusion introduced when round 4 began loading by concrete
local path: the backend identifier became a filesystem path. Record the
advertised repo id on the backend after an auto-switch load and use it so
(a) a model loaded manually by repo id is recognized as already serving
(no spurious reswap/409), (b) /v1/models reports the repo id, never a host
path or a duplicate, and (c) the idle-unload stash keeps the override keyed by
the repo id, so an alias reload after TTL keeps the user's saved launch flags.
- Gate the manual /load route with the keep-warm lifecycle gate so idle
auto-unload can't unload a model mid-load. load_model now wraps _load_model_impl
in the gate; auto-switch calls _load_model_impl directly since it already holds
the gate.
- Restore default-off parity on Anthropic /v1/messages: an unloaded backend with
auto-switch disabled 503s before the max_tokens 400 check, as it did pre-feature.
When the feature is on, request-shape validation still runs before any load.
Tests added for each; full backend suite diff vs baseline is unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: auto-switch review round 6 (concurrency ordering, leaks, unload gate)
From a second 10-reviewer pass (8 request-changes, 2 approve):
- Same-target concurrency: register a waiter by the raw requested model before
the (slow) resolve, and exclude pending requests from the swap busy count. The
middleware counts a concurrent same-model request as in-flight before it
resolves and joins the resolved-target waiter map, so the prior fix could still
409 it. The guard now subtracts max(same resolved-target, same raw-request)
waiters and ignores pending (a pending request is blocked in the middleware,
not generating, so a swap can't interrupt it).
- External-provider requests no longer block a local swap. The keep-warm
middleware counts every inference-path POST, but external-provider chat returns
before the auto-switch hook and never touches the local GGUF. The chat handler
now untracks itself before proxying, so its in-flight stream can't trip
model_switch_busy on a concurrent local auto-switch. The middleware skips its
own end-decrement for an untracked request.
- Manual /unload is gated like load and idle-unload: it holds the lifecycle gate
and returns 409 rather than tearing down llama-server while an inference request
is in flight.
- Response model id no longer leaks the load path. /v1/models already advertised
the repo id; chat, completions, embeddings, Anthropic messages, and audio
response bodies now use the same _llama_public_model_id helper instead of the
concrete on-disk model_identifier.
- Chat completions validates the non-system-message requirement before the
auto-switch hook (as /responses and /messages already do), so an invalid
request can't swap the resident model before returning 400.
Tests added for each; full backend suite diff vs baseline is unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: auto-switch review round 7 (teardown policy, Unsloth-active swap, training)
From a third 10-reviewer pass (9 request-changes, 1 approve), all on the same
asymmetric-teardown theme. Resolved per the intended policy that only automatic
paths defer to an active stream; deliberate user actions stay interrupting:
- Revert the manual /unload in-flight guard added last round. A manual /load or
/unload is a deliberate action and tears down immediately, as before; only the
automatic idle-unload loop and auto-switch defer to an active request. This
removes the asymmetry the reviewers flagged (manual /load, the /unload Unsloth
branch, and the opposite-backend swaps inside _load_model_impl) by not
extending the guard to deliberate paths, rather than spreading it.
- Auto-switch now refuses a swap whenever another inference request is in flight,
not only when a GGUF is already loaded. _load_model_impl also unloads an active
Unsloth/transformers backend before loading a GGUF, so the busy guard must cover
that case too; otherwise an Unsloth stream could be killed by an auto-switch.
- Refuse API-initiated training while inference is active. When Studio is driven
as an inference API (sk-unsloth key auth), POST /api/training/start returns 409
if a request is in flight, since training frees VRAM by unloading the chat
model and would kill the stream. The Studio UI (session auth) still starts
training and coexists/frees VRAM as before. A mixed UI+API session is not yet
special-cased. Adds auth.authentication.authenticated_via_api_key.
Tests added/updated for each; full backend suite diff vs baseline is unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: add UNSLOTH_MODEL_IDLE_TTL env override for idle-unload
Borrowed from PR 6517: a startup env var that sets the idle-unload TTL without
the settings UI. Unlike the stored setting (gated on auto-switch), the env value
is a standalone default that enables idle-unload even with auto-switch off, for
headless/container deploys. An explicit UI/API value still overrides it and stays
gated. The settings GET reflects the env default when nothing is stored.
* Studio: auto-switch fixes from review (paths, embeddings input, env idle reload)
- /v1/models advertises a client-facing alias instead of a filesystem path:
the ./models and LM Studio scanners report the on-disk path as the model id,
so the index now prefers model_id/display_name as the advertised/override id
and keeps the concrete path internal as load_path, still resolvable by path.
- /v1/embeddings validates input before auto-switch: a request with a model but
no input now 400s before the hook (like chat/responses/messages), so an
invalid embeddings request cannot unload or swap the resident model.
- Standalone UNSLOTH_MODEL_IDLE_TTL reloads the freed model: the hook now runs
when auto-switch or idle-unload is active, and with auto-switch off it skips
the resolver and only restores the idle-unloaded model, so the first idle
timeout no longer leaves later /v1 requests with nothing loaded.
- Do not resurrect a stale GGUF over an active Unsloth model: the reload-stash
path bails when a non-GGUF backend is loaded, so an unknown /v1 name cannot
tear down a live Transformers/Unsloth model.
- Defensive HF cache scan: each cache root's resolve/dedup is wrapped so a
missing or malformed root skips that root rather than aborting the index.
- Single-model retrieve checks the id is a string before lowercasing.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: fix automatic-load asymmetry, audio reload, preview, idle timer
The standalone UNSLOTH_MODEL_IDLE_TTL reload is a second automatic-load
trigger, but several validate-before-switch guards and reload hooks only
checked the auto-switch toggle. Add a shared _automatic_model_load_may_run()
(auto-switch on, or idle TTL > 0) and route every guard through it.
- /v1/completions validates prompt before any automatic load (it was the one
model-bearing route with no pre-check).
- /v1/chat/completions and /v1/embeddings pre-checks gate on the shared
predicate so a standalone idle TTL cannot reload then reject.
- /v1/messages no longer 503s before the reload hook can restore an idle-freed
model when auto-switch is off.
- Raw completions/embeddings with no model field pass a non-empty sentinel so
the idle-stash reload runs, restoring the legacy "omit model, use loaded" path.
- /api/inference/audio/generate gains the reload hook (after message validation)
so an idle-freed audio GGUF is restored.
- Public preview opts out of auto-switch via a request-scope flag, so a caller's
model field cannot swap away from the pinned checkpoint; preview chat streams
are now matched by _is_inference_path so idle-unload cannot kill them.
- Keep-warm no longer stamps activity on request start, and external-provider
untracking decrements without restamping, so periodic external traffic can no
longer keep the local GGUF warm forever.
Merges origin/main (the branch had fallen behind, which also brought in the
preview route the review flagged).
* Studio: surface model auto-switch in the API tab and demo it in examples
The OpenAI auto-switch toggle previously lived only in Settings -> General.
Add the same toggle to the API tab's usage-examples panel (it shares the
settings cache), and make the examples reflect it: when on, the Python
examples append a second call naming a different downloaded GGUF (so the
model field visibly selects which model serves), and the curl examples gain
a one-line note. Reuses the existing settings API client and i18n keys.
* Studio: harden OpenAI auto-switch reload-only path and Anthropic tool validation
- Omitted-model raw-body requests pass a reload-only sentinel so the idle-stash
reload still restores an idle-freed model, but the resolver never matches a
downloaded GGUF literally named "default".
- Reject malformed Anthropic client tools before _maybe_auto_switch_model so an
invalid request can no longer evict the loaded model.
* Studio: extend auto-switch reload-only and tool validation to schema endpoints
- Schema-backed endpoints (chat completions, responses, count_tokens, messages,
audio) defaulted an omitted model to "default" and passed it to the switch
hook, so a downloaded GGUF named "default" could be swapped to. Route the hook
through a helper that switches only on an explicitly set model, else reload-only.
- Propagate the explicit-set status when building the chat request from a
Responses request, so the non-streaming chat re-check stays reload-only too.
- Validate Responses function tools before the switch hook so a malformed tool
returns 400 without evicting the loaded model.
* Studio: serialize auto-switch swaps across event loops with a process-wide gate
The auto-switch lock is a per-event-loop asyncio.Lock, so two /v1 swaps on
different loops in one process could both pass it and race the single model slot
(the backend and _load_model_impl are process-wide). Add a process-wide
threading gate around the swap, acquired off the loop so a cross-loop wait never
blocks it, layered with the existing per-loop lock. Add a cross-loop test that
fails without the gate (two slow loads overlap) and passes with it.
* Studio: make the auto-switch swap gate wait cancellation-safe
_acquire_swap_gate awaited asyncio.to_thread(lock.acquire) when another loop held
the process-wide gate. to_thread cancellation doesn't stop the worker thread, so a
/v1 request cancelled mid-wait (client disconnect during a cross-loop swap) would
have its thread acquire the gate after the fact, while the finally that releases it
never runs -- permanently deadlocking later auto-switch swaps.
Poll a non-blocking acquire off a short asyncio.sleep instead: it still keeps the
wait off the loop and serializes across loops, but a cancel now lands during the
sleep, when the gate is not held, so nothing leaks. Add a test that deadlocks the
to_thread variant (it times out) and passes with the poll.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: validate modality and tool-confirmation before auto-switch
Two more request shapes could load a named GGUF and only then 400, evicting the
resident model:
- An image request naming a different text-only GGUF. The switch hook now takes
require_vision and rejects a swap to a non-vision target before loading it; a
GGUF's vision capability is its companion mmproj, knowable without a load, and
matches the post-load guard. Only the resolver branch is checked, never the
reload-stash restore.
- confirm_tool_calls=true with stream=false and local tools. /v1/chat/completions
now rejects that shape before the hook, mirroring the local tool path's
bypass_permissions exemption and intent signal.
The vision probe threads the ambient HF token to keep the capability-probe
invariant. Reload-only and idle-reload paths are unaffected.
* Studio: extend validate-before-switch and make the lifecycle gate process-wide
- /v1/messages/count_tokens now rejects malformed client tools before the switch
hook, like /messages (shared _validate_anthropic_client_tools helper), so a
count request can't evict the loaded model.
- /v1/chat/completions rejects a malformed tool_choice forcing object (a
{"type":"function","function":{}} with no name) before the switch hook.
- The inference lifecycle gate that blocks new inference during a swap is now
process-wide (a poll-acquired threading lock, cancellation-safe), not a
per-loop asyncio lock, so a request on another event loop can't start inference
while a swap tears the single backend down.
- Usage examples no longer hard-code a switch-demo repo most users lack; the
model is an explicit placeholder the user replaces.
* Studio: extend the auto-switch modality guard to /v1/responses and /v1/messages
The pre-load vision check that guards /v1/chat/completions now also runs on
/v1/responses and /v1/messages, so an image request naming a text-only GGUF is
rejected before the swap and never evicts the resident vision model. Run the
vision capability probe off the event loop. Make the /v1/models retrieve
loaded fast-path case-insensitive, and never advertise a host path from the
resolver. Remove the dead list_switch_eligible_ids helper, superseded by the
/v1/models catalog.
* Studio: filter /v1/models to GGUF, per-loop catalog lock, reject system-only Responses
Address review findings on the auto-switch path:
- /v1/models advertises only GGUF models the API can actually switch to; a
safetensors/LoRA entry would be selectable but never loadable via llama.cpp.
- The /v1/models catalog cache uses a per-loop lock (like the auto-switch path)
so a second event loop awaiting it can't hang in a multi-loop process.
- /v1/responses rejects system/developer-only input before the switch, mirroring
chat, so an invalid request can't evict the resident model.
- _build_index guards each scan source on its own so one bad root drops only
that source; the vision probe logs a real detection failure instead of
swallowing it.
* Studio: list cached GGUFs in /v1/models by inspecting files, not model_format
The HF-cache scanner leaves model_format unset for GGUF snapshots, so the
previous model_format == "gguf" filter dropped every downloaded HF-cache GGUF
from /v1/models and the retrieve fallback. Decide GGUF-ness from the on-disk
files via the resolver (info_has_local_gguf) instead, run off the event loop, so
the catalog advertises exactly what /v1 can serve.
* Studio: fix /v1/messages/count_tokens route binding plus auto-switch review fixes
The @router.post decorator for /messages/count_tokens had been separated from
anthropic_count_tokens by the _validate_anthropic_client_tools helper, so the
route bound to the validator and dropped its auth dependency. Move the decorator
back onto the handler. Add route-binding tests asserting each /v1 endpoint maps
to its handler with the auth dependency, so a decorator/handler split is caught
at the route level (the direct-call tests missed it).
Also from review:
- update_openai_auto_switch writes both settings keys in one transaction so a PUT
can't leave one updated and the other stale (drop the now-unused single setters).
- max_seq_length override rejects 0 at the boundary (ge=1) instead of accepting
then silently dropping it.
- Document that embeddings auto-switch is best-effort: GGUF pooling has no cheap
pre-load probe like vision's mmproj, so a guard would false-reject GGUF embedders.
- Add a positive idle-unload test (loop frees the model and stashes it for reload).
* Studio: validate Responses tool_choice + Anthropic mixed tools before switch, filter Ollama from catalog
More auto-switch review findings:
- /v1/responses rejects a forcing-function tool_choice with no name before the
switch, mirroring chat, so a malformed request can't evict the resident model.
- /v1/messages rejects mixing Anthropic server tools with custom client tools
before the switch (the check depends only on the payload, so it moves up cleanly).
- /v1/models no longer advertises Ollama-link models: info_has_local_gguf excludes
.studio_links / ollama_links entries, which the resolver skips and can't switch
to, so an advertised id never silently falls through.
* Studio: guard chat audio input before switch; surface env-backed idle unload in settings UI
A chat request carrying audio_base64 rides the same companion mmproj
projector as a vision request, so a text-only target cannot serve it
either. Flag require_vision for audio input as well so the multimodal
probe runs before the switch and a rejected request never evicts the
working model. Generalize the reject message to cover image and audio.
The settings response now reports idle_unload_active (effective TTL > 0)
so the UI can distinguish idle-unload that is active via the
UNSLOTH_MODEL_IDLE_TTL env var from the case where it needs the toggle
enabled.
* Studio: harden auto-switch eviction guards (count_tokens vision, TTS reload-only, mmproj/stash)
Four eviction/correctness fixes on the opt-in /v1 auto-switch path:
- /v1/messages/count_tokens now carries the same require_vision guard as
/messages, so an image count naming a text-only GGUF can't evict a loaded
vision model for a swap that can't serve the request.
- /audio/generate is now reload-only. A local GGUF's audio-input capability
is not a cheap pre-load probe (the companion mmproj signal can't tell an
audio projector from a vision one, and codec TTS ships no projector), so
resolving the client model could load a text/vision-only target and evict
the working audio model before the audio check fails. Only the idle-stash
restore runs here; switching TTS models is an explicit /load.
- The resolver no longer treats a standalone mmproj .gguf as a servable
model. _scan_models_dir's standalone-file pass does not filter mmproj the
way its directory scan does, so /v1/models could advertise a projector and
a switch could load it over the real weights.
- A non-GGUF (Transformers/Unsloth) load and a deliberate /unload now clear
the idle reload stash, so a manual load/unload is never superseded by a
stale idle-freed GGUF that the next /v1 request resurrects.
* Studio: report advertised repo id consistently after an auto-switch
Two model-id reporting fixes so an auto-switched cached HF GGUF is named by
its repo id everywhere, not its snapshot path:
- Streamed /v1/responses envelopes now derive the model id from
_llama_public_model_id (which prefers _openai_advertised_id) instead of the
raw model_identifier. After an auto-switch the identifier is the snapshot
path while the repo id lives in _openai_advertised_id, so the stream used to
report a snapshot basename while /v1/models, chat completions, and
non-streaming Responses all reported the repo id.
- When an advertised alias already resolves to the loaded model (a model
loaded by local path, requested by its repo or LM Studio id), the
already-serving early return now records the alias as the advertised id, so
/v1/models and responses report the alias and mark it loaded instead of the
path-derived basename. Resolver branch only; safe lock-free because an
in-flight request blocks any concurrent swap via the single-slot busy guard.
* Studio: validate request shapes before auto-switch (prompt/input/audio/mcp confirm)
Four more validate-before-switch guards so a deterministic client error never
evicts the resident model on the opt-in /v1 auto-switch path:
- /v1/completions rejects an object/number prompt (only a string or array is
valid) before the switch, instead of loading the named GGUF and letting
llama-server reject the shape afterward.
- /v1/embeddings rejects an object/number input the same way.
- Chat rejects an oversized audio_base64 upload (413) before the switch. The
size cap is a cheap, target-independent length check; the decode itself
stays post-switch to avoid decoding a valid upload twice.
- The chat confirm-without-stream pre-switch guard now mirrors the tool loop's
actual enablement: _effective_enable_tools (honoring a CLI --enable-tools
policy) and mcp_enabled (which opens the tool loop on its own but defers to a
CLI --disable-tools policy). Previously a confirm+no-stream request with only
mcp_enabled slipped past and 400'd after the swap.
* Studio: fix model-id retrieval, streaming n>1, resolver cache TTL, keep-warm auth
Four fixes from review:
- GET /v1/models/{id} legacy raw-path fallback now maps the raw identifier to
the same public id its /v1/models entry uses. After an auto-switch load the
identifier is the snapshot path while the entry is keyed by the advertised
repo id, so a client that cached the old absolute path no longer 404s on a
model that is in fact loaded.
- stream=true with n>1 is now rejected before the switch. Only the
non-streaming GGUF path returns multiple choices, so streaming n>1 is invalid
on every local serving path; both fields are known pre-switch, so it must not
load model B only to 400 and evict model A. Non-streaming n>1 stays
post-switch where the serving path decides.
- The resolver index cache is stamped after _build_index, not with the pre-scan
timestamp. On installs with enough local models for the multi-root scan to
exceed the 5s TTL, the cache was stored already expired and every request
rebuilt it.
- The keep-warm middleware no longer stamps model activity for 401/403
responses. It runs before FastAPI auth, so unauthenticated probes used to
refresh the idle timer without touching llama.cpp; they now decrement the
in-flight count without keeping the model warm.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
Extracted and narrowed from unslothai/unsloth#6543 by @TheJagStudio.
This keeps the startup/banner and text file encoding hardening separate from the already-merged Python code-exec UTF-8 fix in #6548.
Co-authored-by: Jagrat Patel <81472856+TheJagStudio@users.noreply.github.com>
* Studio RAG: disable trust_env on loopback llama-server httpx clients
The RAG embedder health probe (embed_llama_server.py), its pooled httpx.Client, and the vision captioner (captioner.py) call the local 127.0.0.1 llama-server with httpx's default trust_env=True, so an ambient HTTP(S)_PROXY that returns 503 for loopback breaks embedder startup and captioning. Set trust_env=False on these loopback clients, matching the existing fix on the main llama_cpp and inference clients. External provider calls are untouched.
Follow-up to the loopback trust_env fix; covers the remaining local llama-server clients in the RAG path.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio RAG tests: accept trust_env kwarg in captioner httpx.post mocks
The loopback captioner now passes trust_env=False; update the _vision_complete
fake_post stubs to accept it and assert it is False.
* Trim comments in Studio RAG trust_env fix (comment-only)
* RAG trust_env test: explicit UTF-8 read + scan all package .py files
Addresses review: utf-8 open avoids a Windows decode error, and scanning every
.py in core/rag catches any future file that adds an httpx call.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Condense the verbose comments and docstrings added by the recent
chat template, GPT-OSS detection, PEFT tensor-parallel, and Studio
inference proxy fixes. Comments and whitespace only; no code changes.
* add models for /update endpoint
* add logic for identifying out of date hf models
* add endpoint for updating hf models
* add relevant field to GgufVariantDetail
* make exception handling better
* add update_available flag for cached_models, and moved /update endpoint from inference -> models
* hook up /update endpoint on the frontend
* implement update scenarios for the model picker
* fix bug where downloaded flag for an older revision was being wrongly set to false
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix import and make hf calls async
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* remove has_vision from UpdateRequest
* fix ci
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* clear cancel event before updating gguf variant
* set _cancel_event back if it was set initially
* add hf_token to get_paths_info
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: harden model update endpoint and update checks
- update_hf_model: pass snapshot_download local_dir (local_path is not a
valid kwarg and 500s when updating bicodec audio models)
- get_gguf_variants: wrap the remote update check so a network, rate-limit,
gated, or offline failure degrades to "no update info" instead of failing
the whole variant listing, matching list_cached_models
- add regression tests for both paths
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: HF model update detection and Update action for cached models
Surface an "Update available" cue and a managed Update action for cached
on-device models. /api/hub/update-status compares each cached main GGUF
file's local blobs against the remote main revision using set membership
across all cached revisions, so a repo that was already updated (and still
holds the old snapshot alongside the new one) is not falsely flagged.
The Update action re-downloads through the download manager so it shows in
the Downloads panel with progress and cancel. The frontend wires the Update
button into the GGUF, on-device, and model-selector cards and keeps the
quant label fully visible when the action buttons crowd the row.
Adds regression tests for the multi-revision update check.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: accept force_download kwarg in hf_xet_fallback test double
The download seam now passes force_download to the attempt callable; the _FakeAttempt mock did not accept it, failing 6 tests with TypeError. Add the keyword (default False) so the scripted-results double matches the seam.
* Fix Studio model update regressions
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address Studio update review feedback
* Address Studio update edge cases
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Share GGUF update status helper
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix GGUF update detection and cache cleanup
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix cached GGUF update badges
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: shimmyshimmer <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Etherll <61019402+Etherll@users.noreply.github.com>
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
* fix(studio/llama_cpp): disable trust_env on the loopback health probe
_wait_for_health() polls http://127.0.0.1:<port>/health with the default
httpx trust_env=True, so an ambient HTTP(S)_PROXY in the environment is
applied to the loopback request. A proxy that returns 503 for 127.0.0.1
makes every probe fail, so the loop runs until timeout and Studio load
hangs (trust_env=False returns 200 immediately).
Pass trust_env=False so the local readiness probe never goes through a
proxy. This mirrors the existing trust_env=False handling in the sibling
llama_http / external_provider HTTP clients.
* test(offline_gguf_cache): accept trust_env kwarg in fake_get mock
_wait_for_health now calls httpx.get(..., trust_env=False); update the retry test's fake_get to accept the kwarg so it doesn't raise TypeError.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix(studio/llama_cpp): bypass proxies for loopback clients
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix(studio/routes): bypass proxies for llama streams
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: wasimysaid <wasimysdev@gmail.com>
* Add whole-document context mode to RAG chat attachments
Thread-attached files are injected in full when they fit a token budget,
instead of only top-K retrieved chunks, so the model reads the entire file
for summarize/reason-over-document requests. Oversized files fall back to
top-K retrieval so the context window is never blown. KB and project
corpora are unchanged (still retrieval).
- core/rag/store.py: all_chunks_for_scope returns every completed-document
chunk for a scope, ordered document-then-index, joined with filename.
- core/rag/tool.py: whole_document_context renders the chunks as the same
<chunk> blocks + citation source-map retrieval produces, returns None
when empty or over budget.
- core/inference/tools.py: build_rag_autoinject tries whole-document first
for thread scopes, falls through to search_for_autoinject otherwise.
- core/rag/config.py: THREAD_WHOLE_DOC + WHOLE_DOC_MAX_TOKENS (env-tunable).
- tests/test_rag_whole_document.py: store ordering, whole-doc render +
budget cutoff, auto-inject whole-doc vs top-K fallback, KB never whole-doc.
* Add scanned-PDF OCR fallback to RAG ingestion
A PDF page with no extractable text layer (a scanned or image-only page)
previously ingested as empty, so image PDFs were invisible to retrieval and
whole-document context. Such pages are now rendered and transcribed by the
loaded vision model during ingestion, so they become searchable and readable
like any other page. This restores OCR for the RAG document flow without a
separate extraction pipeline.
- core/rag/parsers.py: render_pdf_pages renders whole pages (1-based) to PNG.
- core/rag/captioner.py: factor the shared vision call into _vision_complete;
add _ocr_one + ocr_pages (transcribe rendered pages, OCR_MAX_PAGES bound).
- core/rag/ingestion.py: _ocr_scanned_pages runs right after parse, replacing
text on near-empty PDF pages. No-op when OCR is off, no page is scanned, or
no vision model is loaded (degrades like figure captioning).
- core/rag/config.py: OCR_SCANNED, OCR_MIN_CHARS, OCR_MAX_PAGES, OCR_DPI,
OCR_TIMEOUT_S, OCR_MAX_TOKENS (env-tunable).
- tests/test_rag_ocr_fallback.py: page render, ocr_pages gating + cap, scanned
PDF end-to-end OCR into chunks + whole-doc, born-digital skips OCR, disabled
leaves the page empty.
* Broaden OCR prompt to figures/tables and guard against repetition runaway
The OCR prompt now asks the vision model to also transcribe text inside figures,
diagrams, charts and tables, so labels and table cells on scanned pages are
indexed rather than skipped. Verified on real documents that this does not
regress plain-text transcription.
Some vision models loop on sparse images (e.g. a title-only cover) and emit the
same line hundreds of times. _collapse_runaway caps any run of identical
consecutive lines so a pathological page cannot flood the index; legitimate
short repeats (a label appearing a few times) survive. Applied in ocr_pages.
* Restrict whole-document injection to thread attachments only
whole_document_context resolved the combined project+thread scope, so a project
chat (the frontend sends both thread_id and project_id) injected the entire
project corpus in full, contradicting the design that project and KB corpora stay
retrieval-only. A large project corpus could also push the total over budget and
drop a small thread attachment back to top-K.
Resolve the thread scope alone in whole_document_context, and in
build_rag_autoinject only enter whole-doc mode when a thread attachment is present
and no KB is selected (a KB pick is exclusive: search that corpus). Project
sources and KBs keep top-K retrieval. Adds regression tests for the mixed
project+thread payload, the budget isolation, and KB precedence.
* Address review: keep project retrieval, harden budget + OCR guards
Follow-up to the 8-reviewer pass on the whole-document + OCR work.
- Preserve project grounding in project chats. The thread-scope-only fix made
whole-doc exclusive of retrieval, so a thread attachment silently dropped the
project corpus for that turn. build_rag_autoinject now whole-docs the thread
attachment AND retrieves the project sources top-K, merged under one citation
numbering via tool.render_sources. KB selection stays exclusive.
- Budget: a NULL/zero token_count no longer bypasses the cap (length-based
fallback in _row_token_count), so a malformed huge doc can't inject in full.
- OCR runaway guard: _collapse_runaway now also caps each distinct line at a
generous total across the page (not just consecutive), bounding the
interleaved/alternating loops weak models emit; blank-line floods collapse too.
- OCR: warn when a scanned PDF exceeds OCR_MAX_PAGES (pages past the cap stay
untranscribed) instead of silently dropping them.
- Document the known limits: OCR'd pages have no PDF highlight regions; vision
models need a micro-batch >= image tokens (Gemma-family) or the server aborts.
- Tests for project-retrieval composition, NULL-token budget, and interleaved
runaway; drop the now-superseded exclude-project test.
* Add OCR toggle to RAG retrieval settings
Make scanned-PDF OCR user-controllable per upload instead of only via the
RAG_OCR_SCANNED config default. The retrieval settings panel gains an OCR
scanned pages switch (persisted in localStorage, on by default); the chosen
value is read fresh at upload time and sent with each document upload.
Backend: the three upload routes accept an optional ocr form field and pass it
through start_ingestion to _ocr_scanned_pages, which now treats None as use the
config default and an explicit bool as an override. The on/off policy lives only
in _ocr_scanned_pages now, so ocr_pages no longer re-checks the config (that
double gate would have blocked a per-upload ocr=True while the default was off).
Tests cover both override directions (force on while config off, force off while
config on).
* Add "Describe figures & charts" toggle with chart-aware captions
Surface RAG figure captioning as a user control and make it actually useful for
graphs and plots. The figure detection already clustered vector drawings and
raster images into regions and rendered them, but captioning was off by default,
had no UI, and used a thin generic prompt.
Accuracy: the caption prompt now asks for chart type, axis titles and units,
legend or series, salient trends and readable values, and table columns, while
forbidding invented numbers. The token budget is configurable (CAPTION_MAX_TOKENS)
and captions pass through the same runaway guard as OCR so a looping vision model
cannot flood the index.
Control: a per-upload caption override threads from the three upload routes through
start_ingestion and _run, with the on/off policy single-sourced in _run (caption
self-gating removed from caption_images, mirroring the OCR change) so a force-on
override works when the config default is off. The frontend adds a "Describe
figures & charts" switch in the retrieval settings, persisted in localStorage and
sent with each upload. Default on; it is a no-op without a vision model and bounded
to CAPTION_MAX_IMAGES figures per document.
Tests cover the new caption_images contract, the runaway guard on captions, the
chart-aware prompt and token budget (and that OCR keeps its own prompt and budget),
and both override directions end to end through ingestion.
* Generalize figure understanding: transcribe-first prompt + high-DPI tiling
Make figure/chart description work across any visual and any model strength, not
just a strong VLM on simple figures. Two changes, validated by a recall benchmark
on authoritative documents (ResNet/Attention papers, USDA, UN UDHR).
1. Transcribe-first caption prompt. The caption now asks the model to transcribe
every visible label verbatim (titles, axis labels and units, legends, every
box/node/arrow label, table cells, equations) and then add a one-line summary,
instead of only describing the figure. Transcription is the most model-robust
visual task, so weak models that cannot reason about a chart still recover its
labels.
2. High-DPI tiling of figure pages. Figure-bearing pages are rendered as an
overlapping grid of high-DPI tiles (plus a full-page pass for context); each
tile is transcribed, then merged and de-duplicated. This keeps small diagram
labels legible and covers every sub-figure without relying on exact region
detection, which previously missed sub-figures and small labels.
Supporting changes: figure render DPI 130 -> 200 with a clip margin so edge labels
are not lost; vision calls are deterministic (temperature 0) so transcription does
not randomly drop labels; the repetition guard now applies to captions too. New
config knobs: FIGURE_DPI, FIGURE_MARGIN_FRAC, FIGURE_TILE_ROWS/COLS, FIGURE_TILE_
OVERLAP, FIGURE_FULLPAGE, CAPTION_MAX_PAGES, larger CAPTION_MAX_TOKENS, and
CAPTION_MAX_IMAGES as a per-document tile budget.
Measured figure context recall (per-label, dense academic figures):
Qwen2.5-VL: 0.50 -> 0.83 (overall 0.81 -> 0.94)
Gemma-4-E2B (weak): ~0 with loops -> 0.83 (overall 0.91)
Born-digital text and scanned-page recall are unchanged (no regression).
parsers gains _figure_boxes (shared detection), pages_with_figures, and
render_pdf_figure_tiles; captioner gains merge_page_captions and a temperature
parameter; ingestion routes figure captioning through the tiled path.
* Fix RAG review issues: whole-doc budget pre-check, figure gating, empty re-ingest, vision auth
Whole-document context now runs a cheap token-sum pre-check (store.scope_token_estimate)
before hydrating every chunk's text, so an attachment that cannot fit the budget is
rejected without loading the whole corpus into memory. The estimate mirrors
all_chunks_for_scope's filter and the per-row token-count fallback exactly.
Ingestion skips all figure work (PDF rasterization and detection, not just the caption
call) unless a vision model is loaded, so a text-only deployment pays nothing. When OCR
is enabled, scanned/image-only pages are excluded from figure tiling since OCR already
transcribes them whole, avoiding double vision work and overlapping index entries; a
scanned figure page is still tiled when OCR is off.
start_ingestion no longer dedupes forever to a prior ingest that produced zero chunks
(e.g. a scanned PDF uploaded before a vision model was loaded): the empty record is
dropped and the content is re-ingested.
Vision OCR and caption requests now send the backend Authorization header, so they
match the chat endpoint and do not 401 under direct-stream (--api-key) mode.
Adds tests for the budget estimate, scanned-page exclusion, the vision-model gate, the
empty re-ingest path, and the auth-header passthrough.
* Trim RAG vision-ingestion comments and docstrings
Tighten the verbose multi-line docstrings and comments added across the RAG vision
ingestion work (captioner, config, parsers, ingestion, store, tool, build_rag_autoinject,
the RAG tests, and the chat-store/upload-hook frontend toggles) to one or two lines while
keeping their intent. No code changed: verified comment/docstring-only against the prior
commit, and the RAG test suite still passes.
* Fix figure-tiling exclusion and client dedupe for re-ingestable docs
Figure tiling now excludes only the pages OCR actually transcribed, not every
text-less page. _ocr_scanned_pages returns the set of pages it OCR'd, and _run passes
that to pages_with_figures as exclude_pages (replacing the ocr_on-keyed min_text_chars
heuristic). A scanned page that OCR skipped (past OCR_MAX_PAGES, or whose OCR returned
empty) is no longer dropped from captioning, so a chart on such a page still gets a
caption.
The document panel's upload dedupe no longer skips re-selecting a file whose only
matching doc completed with zero chunks. Such a doc is re-ingestable (e.g. a scan
attached before a vision model loaded), and the backend re-ingests on the same content
hash, so the client must let it reach the backend; healthy or still-indexing docs are
still skipped. The SSE complete frame's chunk count is recorded on the doc so the
check is exact.
Adds a regression test for the un-OCR'd scanned figure page and updates the
pages_with_figures test to the exclude_pages interface.
* Address review findings: whole-doc budget guard, job numChunks, dead code, upload cap
whole_document_context now treats a non-positive max_tokens as "never inject" instead
of injecting the whole corpus unbounded, so RAG_WHOLE_DOC_MAX_TOKENS=0 tightens rather
than disables the budget (the real off switch stays RAG_THREAD_WHOLE_DOC=0).
The job-status endpoint and get_job_status now expose num_chunks (joined from the
document), and the upload hook threads it through the SSE-fallback completion paths
(reconcile + poll). Previously a document that finished via the connection-cap fallback
had no chunk count client-side, so the re-ingest dedupe wrongly treated it as empty and
re-uploaded it. IndexJob/JobEvent gain the field and the untyped cast is dropped.
Removes the dead render_pdf_figures function (superseded by the tiling path), its test,
and the unused FIGURE_MARGIN_FRAC config knob.
Adds an upload size cap (RAG_MAX_UPLOAD_BYTES, default 200 MB; 413 on exceed with the
partial file cleaned up) so a pathological file can't drive unbounded parse + vision
work. render_pdf_figure_tiles clamps rows/cols to >= 1 (no ZeroDivisionError on a
misconfigured grid). Captioning progress is reported after OCR so the bar is monotonic.
sqlite connections set busy_timeout=5000 so a long figure/scan ingest holding its
connection doesn't make a concurrent ingest/read fail with "database is locked".
Adds tests for the non-positive budget, the zero-grid clamp, job-status num_chunks, and
the oversize-upload rejection.
* Extract PDF text as layout-aware Markdown via pymupdf4llm
parsers._pdf now extracts each PDF page as Markdown with pymupdf4llm.to_markdown
(page_chunks=True) instead of flat page.get_text("text"), so tables, headings and lists
keep their structure in the indexed chunks and retrieve far better (a table's cells stay
associated with their row instead of flattening into a token stream). Gated by
RAG_PDF_MARKDOWN (default on); falls back to plain PyMuPDF text when the toggle is off,
pymupdf4llm is missing, extraction fails, or a page yields no Markdown. The scanned-page
OCR and figure-tiling passes operate on rendered pixels and are unaffected; docx/html/txt
keep their existing extractors.
The preview-highlight locator already strips Markdown punctuation when building anchors;
it now also splits anchor tokens on pipes so a Markdown table row still anchors to the
raw PDF word stream.
Declares pymupdf4llm as a studio/RAG dependency (was only transitively present via the
data-designer plugin). Adds parser tests (Markdown table reaches the page text, the
plain-text fallback, the missing-lib fallback) and a locator test for table-pipe anchoring.
* Pin pymupdf4llm to 0.3.4 so the package scan does not pull onnxruntime
The lockstep pymupdf4llm 1.27.x line makes pymupdf-layout a hard dependency,
which in turn pulls onnxruntime (plus numpy/networkx/protobuf). The security-audit
pip scan-packages job resolves requirements --with-deps, so adding pymupdf4llm to
no-torch-runtime.txt and studio.txt surfaced onnxruntime's un-baselined CRITICAL
finding and flipped the hf-stack shard from pass to fail.
pymupdf4llm 0.3.x keeps pymupdf-layout behind an optional [layout] extra, so a plain
install resolves to pymupdf + tabulate only and never touches onnxruntime. 0.3.4
requires pymupdf>=1.27.1, satisfied by our pinned pymupdf==1.27.2.3, and to_markdown
(page_chunks=True) produces equivalent layout-aware Markdown on real PDFs (verified on
the Attention, ResNet and USDA documents). Production already installs these files
--no-deps, so onnxruntime was never shipped at runtime; this only fixes the scanner.
The parser test now asserts Markdown markup (heading or table pipes) rather than table
pipes specifically, since 0.3.4 emits a heading but not a pipe table on the tiny
borderless synthetic fixture; both markers are absent from the plain-text fallback.
* Fix RAG whole-doc review findings
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address RAG whole-doc review follow-ups
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address RAG review follow-up edge cases
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Reserve image budget for whole-document RAG
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: danielhanchen <michaelhan2050@gmail.com>
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
Co-authored-by: wasimysaid <wasimysdev@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: wire imatrix GGUF option and FP8/NVFP4 compressed export into the export UI
GGUF export gains an importance-matrix toggle. When enabled it auto-downloads the
upstream Unsloth imatrix for the base model (or uses a custom path), which unlocks
the IQ low-bit quants iq2_xxs, iq2_m, iq3_xxs and iq4_xs. Merged export gains an
FP8 / NVFP4 compressed-tensors precision selector that runs llm-compressor for vLLM.
Backend threads imatrix_file through routes -> orchestrator -> worker -> export_gguf
(both the local save and the hub push), and maps the new compressed format_type
values onto the fp8/nvfp4 save_method, reporting the "<dir>-<suffix>" sibling output
directory. Frontend adds the imatrix Switch on the GGUF card and a merged precision
picker on the merged card, threaded through the export runtime store.
Depends on unslothai/unsloth#6706 (save.py imatrix_file and compressed-tensors
export) and unslothai/unsloth-zoo#839 (quantize_gguf imatrix flag).
* Studio export: guard imatrix/compressed against older unsloth builds and force imatrix for IQ quants
Addresses review feedback on the export wiring:
- GGUF: pass imatrix_file only when set, so a plain no-imatrix export (e.g. Q4_K_M) no
longer fails with an unexpected-keyword error against an unsloth build that predates the
imatrix_file parameter. When imatrix is requested but unsupported, return a clear
upgrade message instead of a TypeError.
- Merged: gate FP8/NVFP4 compressed-tensors export on the installed unsloth actually
supporting it, returning a clear message rather than a cryptic save_method failure.
- Frontend: IQ quants (iq2_xxs, iq2_m, iq3_xxs, iq4_xs) are imatrix-only, so force the
imatrix on when one is selected and lock the toggle, instead of submitting an IQ quant
with no imatrix that llama.cpp would reject.
Extends the backend tests for the new capability guards and the conditional kwarg wiring.
* Studio: upload compressed merged models to the Hub without recompressing
For an FP8/NVFP4 Hub export the model is already produced locally in the "<dir>-<suffix>"
output. Uploading it directly with HfApi.upload_folder (mirroring export_base_model) avoids
re-running the expensive compressed-tensors quantization a second time inside
push_to_hub_merged, which for NVFP4 also re-runs calibration and risks OOM. Falls back to
push_to_hub_merged when there is no local compressed output to reuse.
* (feat) Add project names to studio training runs to avoid models being overwritten when doing similar training runs
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Update studio/frontend/src/features/export/export-page.tsx
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* Update studio/frontend/src/features/export/export-page.tsx
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* Update studio/frontend/src/features/export/export-page.tsx
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* better project name sanitization, removed duplicated project name normalization
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* implement checkpoint scanning utilities and tests for base model inference
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Guard project_name against null and use leading important modifiers
* Fix/adjust training project names for PR #6512
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix/adjust training project names for PR #6512
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address project-name review feedback
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Show project names in training recents
* Keep GGUF export directories source-specific
---------
Co-authored-by: NZ-Linix <nz-linix@outlook.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: NZ-Linix <linus.ordowski@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: wasimysaid <wasimysdev@gmail.com>
* Studio: restore tensor parallelism for vision/mmproj GGUFs
#6416 disabled --split-mode tensor for any GGUF that ships an mmproj projector to
dodge a GGML_ASSERT crash (#6415) seen on an older llama.cpp build with consumer
Blackwell (sm_120). The blanket skip silently dropped tensor_parallel=true for
every multimodal/MTP GGUF (e.g. Qwen3.6-35B-A3B-MTP); on hardware where the model
fits on one GPU the load then collapsed to a single GPU. mmproj + --split-mode
tensor works on current builds (verified end to end on B200/sm_100), so the skip
was disabling a working configuration.
Make the vision skip self-healing per binary:
- attempt tensor for vision models by default
- skip upfront only on a binary already seen to abort on tensor + mmproj this
session (_vision_tensor_split_aborts), recorded when such a launch crashes at
startup (_record_vision_tensor_split_abort). Process scoped, so a studio update
re-probes the new build. The route-level layer-split fallback stays the net.
- add _select_gpus(min_gpus=...) so a downgraded tensor request can keep multiple
GPUs instead of collapsing to one (default 1, no behavior change).
Add tests/test_tp_vision_regression.py: an AST allowlist guard over the
tensor_parallel drop sites (which would have flagged #6416), plus cache and
_select_gpus coverage. No GPU required.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address review on vision tensor-parallel self-healing
Three fixes from the PR review:
- Record a vision-tensor abort only after every startup retry fails. The first
version cached the binary on the first spawn crash, which on every build
(including capable ones) is the benign --fit step abort that the existing
--fit off retry resolves. That poisoned the cache so the next vision load in
the same process skipped tensor. Recording now happens at the post-retry
failure block (after fit-off, flash-attn-off and MTP-drop), so a binary that
actually works is never cached.
- Gate the record on the tensor/mmproj crash signature: a hard signal fault
(_is_signal_crash) with no non-tensor cause (_output_has_nonprojector_diagnostic
excludes OOM and unknown-arch), so an OOM, bad extra args, or MTP/flash-attn
crash no longer marks an otherwise capable binary incompatible.
- Preserve the multi-GPU request on the cached downgrade. The vision gate now
raises _layer_min_gpus to the visible GPU count and threads it through the
layer-split GPU selection (_select_gpus min_gpus and the subset loops), so a
downgraded tensor request still spreads across GPUs instead of collapsing to a
single card the model happens to fit.
Verified two vision+tensor loads in one backend process both tensor-split across
4 GPUs (the benign fit abort no longer poisons the cache). Tests updated.
* Studio: harden vision tensor-parallel self-healing (review round 2)
Address the second review round on the vision/mmproj tensor-parallel fix:
- Preserve vision on the first load: a --split-mode tensor + --mmproj
GGML_ASSERT now raises so the route-level tensor->layer fallback retries
layer split with the projector intact, instead of stripping --mmproj and
silently loading text-only (which returned success and skipped the fallback,
losing vision on the first load until the next cached load).
- Symmetric multi-GPU preservation: the pooled-VRAM tensor downgrade now raises
_layer_min_gpus from the usable tensor GPUs like the vision downgrade, so it
no longer collapses a multi-GPU request to a single card.
- Base the layer fallback minimum on usable GPUs: _select_gpus caps min_gpus to
the count of cards with usable VRAM, so a downgrade never forces a nearly-full
card in (or trips --fit) just to hit the count.
- Re-probe after in-app updates: key the per-binary abort cache on (path, mtime)
like _capability_cache, so POST /api/llama/update swapping the binary in place
(no backend restart) re-probes the new build instead of inheriting the old
build's abort.
- Bump _layer_min_gpus for a known-bad vision binary independent of the tensor
drop, so the route fallback's layer retry (tensor already off) still spreads
across GPUs.
Adds deterministic non-GPU regression tests for each.
* Studio: gate cached-vision layer minimum on the current tensor request
The cached-vision _layer_min_gpus bump fired for every later vision load on a
binary recorded as tensor+mmproj-incompatible, including loads that did not
request tensor parallelism. A plain non-tensor vision load that fits on one card
would then grab every GPU just because an earlier TP attempt aborted in the same
backend process.
Re-tie the bump to the current tensor request (back inside the tensor-drop
guard), so only a downgraded tensor request preserves the multi-GPU spread; a
non-tensor vision load minimizes device count as before.
* Studio: preserve GPU count + confirm assert on vision tensor fallback
Third review round on the vision/mmproj tensor-parallel fix:
- Preserve multi-GPU on the first tensor->layer fallback. The route-level retry
runs tensor-off, so the in-function downgrades can't see the original tensor
request and a fits-on-one-card model loaded the first successful fallback on a
single GPU. The GGUF load closure now passes preserve_multi_gpu_on_layer (the
toggle asked for tensor, this attempt is layer) and load_model raises
_layer_min_gpus for it, so the downgrade still spreads across GPUs.
- Cap the auto-context layer loops to usable GPUs. They bypass _select_gpus, so a
raised _layer_min_gpus could force a nearly-full card into the subset (or trip
--fit). They now start from _auto_min_gpus, capped to the GPUs with usable VRAM.
- Confirm the tensor/mmproj assert before caching. Recording (and the layer-retry
raise) now require the ggml assert marker via _is_tensor_split_assert, not the
bare-signal predicate shared with the projector-incompat branch, so a corrupt
or too-new projector that SIGSEGVs independent of split mode is no longer cached
as tensor/mmproj-incompatible.
Adds deterministic non-GPU regression tests for each.
* Studio: extend multi-GPU fallback to extra/env tensor + overhead-aware cap
Fourth review round on the vision/mmproj tensor-parallel fix:
- Preserve multi-GPU fallback for all tensor requests, not just the UI toggle.
Tensor can also be requested via --split-mode tensor in extra args or an
inherited LLAMA_ARG_SPLIT_MODE=tensor env; the fallback retries those too, so
the preserve_multi_gpu_on_layer hint now keys off _effective_tensor_parallel
(the same check the fallback uses), comparing the overall request against the
current attempt instead of only request.tensor_parallel.
- Cap the auto-context layer fallback to GPUs that can pay the per-device layer
overhead. The cap counted any card with positive usable VRAM, so a nearly-full
GPU with a few MiB free stayed eligible and could be exposed to llama.cpp and
OOM. It now mirrors _select_gpus: a card counts only if usable VRAM exceeds the
per-device pipeline overhead.
Adds deterministic non-GPU regression tests for both.
* Studio: match the #6415 split-axis assert + replay layer-preserve hint
Fifth review round on the vision/mmproj tensor-parallel fix:
- Narrow the tensor/mmproj crash signature. _is_tensor_split_assert matched any
GGML_ASSERT/GGML_ABORT, so an unrelated invariant a corrupt GGUF or projector
trips with --mmproj present could be cached as tensor/mmproj-incompatible. It
now matches the specific #6415 warmup assertion
(GGML_ASSERT(src_ss[0].axis != GGML_BACKEND_SPLIT_AXIS_0) in ggml-backend-meta),
whose split-axis signature is inherent to tensor splitting. A reworded future
assert just re-crashes-then-falls-back (vision preserved via layer split)
instead of poisoning the cache for other models.
- Persist the layer-preserve hint for respawns. A successful tensor->layer
fallback committed _last_load_kwargs without preserve_multi_gpu_on_layer, so
_respawn_if_dead replayed only --split-mode layer + tensor_parallel=False and a
mid-session respawn of a fits-on-one-card model came back single-GPU. The hint
is now in the replay snapshot, so recovery keeps the multi-GPU placement.
Adds deterministic non-GPU regression tests for both.
* Studio: tighten comments on the vision tensor-parallel fix
Make the comments and docstrings added by this PR succinct: collapse the
multi-line block comments in llama_cpp.py / inference.py to one or two lines,
trim the verbose test docstrings (the names and assert messages already carry the
intent), and shorten the module docstring. No code changes; verified comment-only
with scripts/comment_tools.py check --strip-docstrings.
* Studio: cache vision tensor abort only on the split-axis token
_is_tensor_split_assert also accepted any GGML_ASSERT/GGML_ABORT from
ggml-backend-meta, but that file holds many asserts, so an unrelated
scheduler/projector/model invariant on an --mmproj launch could cache the binary
as tensor/mmproj-incompatible and make later compatible vision models skip tensor
parallelism. Match the GGML_BACKEND_SPLIT_AXIS_* token itself (unique to the
#6415 warmup assert), not the source file name.
* Studio: don't leak the httpx test stub into later tests
The regression module stubbed httpx via sys.modules.setdefault, which installs
the lightweight stub even when real httpx is present but not yet imported. The
stub then persists for the whole pytest process, so provider/HF tests collected
later (importing httpx or huggingface_hub.errors) got a module missing
HTTPError/Response. Mirror the neighboring llama_cpp helper tests: import real
httpx first and only fall back to a stub on ImportError.
* Studio: latch the #6415 tensor-split abort on the first spawn, key it per model
The self-heal recorded the --split-mode tensor abort only in the post-retry
failure block, after the flash-attn-off retry. But SPLIT_MODE_TENSOR requires
flash_attn, so the flash-off retry can't run tensor and its output no longer
carries the warmup split-axis assert (ggml-backend-meta :541). The record
therefore never fired on the real reproducer and the crash loop repeated on
every load (reported by oobabooga on #6659).
Latch instead on the first spawn that shows the signal crash + split-axis
marker: record it, kill the process, and raise straight to the route's layer
fallback, skipping the futile flash-attn/MTP retry ladder for this crash.
The crash is a tensor-split geometry limit (e.g. MQA n_head_kv=1 splitting to
GGML_BACKEND_SPLIT_AXIS_0), not a vision/mmproj property: it reproduces without
--mmproj and even single-GPU tensor. So drop the vision/mmproj scoping, rename
_vision_tensor_* -> _tensor_split_*, and key the session cache on
(binary, mtime, model) rather than (binary, mtime) so one model's abort no
longer skips tensor for every other model on the same build.
Regression tests updated to pin the early-spawn record, the per-model cache,
and that an unrelated ggml-backend-meta assert is not treated as the marker.
* Studio: reload on explicit tensor-off after a multi-GPU layer fallback
When a tensor load is downgraded to layer but kept multi-GPU to honor the
tensor request (preserve_multi_gpu_on_layer, the geometry-cache gate, or the
budget downgrade), the server reports tensor_parallel=False with --split-mode
layer stored. A later Apply that explicitly turns the tensor toggle off then
matched the loaded state and deduped to already_loaded, so Studio kept the
fallback's all-GPU CUDA_VISIBLE_DEVICES placement instead of re-selecting
normal placement (a single GPU for a model that fits on one card).
Latch a _layer_preserves_tensor_intent flag in load_model whenever a tensor
request is downgraded to layer with the multi-GPU floor raised
(_layer_min_gpus > 1), clear it when tensor stays on or on unload, and force a
reload in _request_matches_loaded_settings when the user explicitly turns the
tensor toggle off while that flag is set. An Apply that does not touch the
toggle still dedupes, so a working multi-GPU layer server is not churned.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address reviewer.py findings on the tensor-split self-heal
P1 (dedup): tensor intent can be dropped via extras, not only the toggle. An
explicit llama_extra_args=["--split-mode", "layer"] matches the stored fallback
extras, so _request_matches_loaded_settings deduped to the preserved all-GPU
placement instead of reloading. Now reload when layer_preserves_tensor_intent
and the user explicitly drops tensor via the toggle OR via extras
(_effective_tensor_parallel of the explicit extras is false).
P1 (downgrade symmetry): the len(tp_gpus) < 2 compute-buffer downgrade cleared
tensor_parallel without raising _layer_min_gpus, unlike the budget and geometry
downgrades. GPUs below tensor's replicated compute-buffer reserve can still take
layer split's lower overhead, so keep the multi-GPU request (len(gpus) >= 2) and
let _select_gpus cap unusable cards.
P2 (cache key): key the tensor-split abort cache on st_mtime_ns, so a binary
replaced in place within the same second after an abort is re-probed instead of
inheriting the stale entry.
P2 (test hygiene): load routes/inference.py via importlib in the regression
tests instead of importing the routes package, which runs routes/__init__.py and
pulls in every router (e.g. python-multipart). Added regression coverage for the
extras-off reload, the compute-buffer multi-GPU preservation, and the same-second
nanosecond cache invalidation.
* Studio: record the tensor-split abort on the Windows CRT abort exit too
The first-spawn split-axis latch only recorded when _is_signal_crash matched
(POSIX signal or 0xC0000000+ NTSTATUS). On MSVC builds GGML_ASSERT terminates
through the CRT abort() path with exit code 3, which is neither, so the cache
never filled on Windows and every later load of the same bad binary/model
repeated the tensor crash before falling back to layer.
The split-axis marker is definitive, so accept either a signal crash or the
Windows abort() exit (3) when the marker is present. Add _is_abort_exit and a
unit test, and assert the early latch honors it.
* Studio: fix UnboundLocalError on --fit-on fallback, reload backend fast path
Two follow-ups from review on the tensor-split self-heal:
UnboundLocalError: _layer_min_gpus was initialized inside the GPU-selection try.
If NVML probing or GGUF/mmproj sizing raised, the except path logged "using
--fit on" and fell through to the command builder, where the new
self._layer_preserves_tensor_intent = _layer_min_gpus > 1 then raised, turning a
safe --fit-on layer fallback into a hard load failure. Bind _layer_min_gpus
before the try so the except path always has it.
Backend fast path: _request_matches_loaded_settings forces a reload when a
preserved tensor->layer fallback gets an explicit tensor-off request, but
load_model's own _already_in_target_state still matched the tensor-off/layer
settings and short-circuited, so the placement re-selection never ran. Mirror
the guard there: reload when layer_preserves_tensor_intent and the request drops
tensor intent. The flag clears on that reload, so there's no loop.
Added regression coverage for both.
* Studio: testable tensor-split record decision; skip futile fit-off retry
Follow-ups from a deeper review of the tensor-split self-heal:
Extract the record decision into _should_record_tensor_split_abort(rc, output)
(marker AND (signal crash OR Windows abort)) and call it from the early latch.
The combined boolean was only covered by source-inspection substring checks, so
an or->and typo would silently stop recording on Windows (CRT abort exit 3 is
not a signal) with every test still green. Add a behavioral test over the
POSIX / Windows / NTSTATUS / clean-exit / SIGKILL / no-marker matrix.
Skip the --fit off retry inside _spawn_and_wait when the crash already shows the
split-axis marker: that abort is fit-independent, so the retry just warms up and
crashes a second time before the latch records it. Skipping it lets the caller
latch immediately and corrects the latch comment.
Also clarify the dedup-guard comments (toggle read from model_fields_set vs
extras via _effective_tensor_parallel without env; the backend fast path is
intentionally broader and only ever forces a reload).
* Studio: don't reload-loop tensor-off requests under env tensor
The preserved-fallback reload guard fired on the raw tensor toggle, ignoring
LLAMA_ARG_SPLIT_MODE=tensor. For an env-driven tensor user, an explicit
tensor_parallel=false request then forced a reload that re-engaged tensor via
the env and re-created the same preserved layer fallback, so every /load
reloaded -- bypassing the env-downgrade matching that exists to avoid exactly
this loop.
Gate the guard on the env-aware effective tensor state: reload only when an
explicit toggle/extras change leaves _effective_tensor_parallel (which consults
the env) off. If the env still forces tensor, fall through to the existing
env-downgrade match, which dedupes instead of looping. Added a regression test
with LLAMA_ARG_SPLIT_MODE=tensor set.
* Studio: tighten comments and test docstrings on the TP self-heal
Condense the verbose comments and test docstrings added across the review rounds
into fewer, succinct lines without changing their intent: the early-latch and
downgrade-site rationale, the cache/key and helper docstrings, the dedup-guard
comments, and the per-test docstrings. No code changes (AST-verified comments
and docstrings only); tests and lint unchanged.
* Studio: clear preserved tensor flag on diffusion; carry it across non-drop reloads
Two follow-ups on the preserved-fallback machinery:
Diffusion: the DiffusionGemma path early-returns from load_model before the
command builder that sets/clears _layer_preserves_tensor_intent, so the flag
from a prior tensor->layer fallback leaked onto a later diffusion load and
forced needless reloads of the diffusion server on tensor-off/extra Applies.
Clear it when starting diffusion.
Settings reload: the preserve hint was recomputed only from the new request, so
a reload for an unrelated setting (e.g. max_seq_length) with the tensor toggle
omitted dropped a preserved multi-GPU layer placement back to one GPU. Carry
llama_backend.layer_preserves_tensor_intent into the hint when the request is
not an explicit tensor-off/extras-off drop, so a fitting model stays multi-GPU.
Added regression tests for the diffusion clear, the carry-forward, and the
updated tensor-intent computation.
* Studio: gate the preserve carry-forward on the same model being loaded
The tensor-intent carry-forward read llama_backend.layer_preserves_tensor_intent
without checking it belonged to the model being loaded. On a direct model switch
(load B without an explicit /unload of A), the flag is still set from A's
downgrade (it isn't reset until B's load_model reaches the command builder, after
the route reads it), so a plain load of B got preserve_multi_gpu_on_layer=True
and was spread across all GPUs even though it fits on one and the user never
requested tensor for it. The backend dedup doesn't have this leak (it checks
model_identifier first); the leak was only in the route hint.
Extract the decision into _carry_preserved_tensor_intent(preserved, same_model,
explicit_drop) and gate it on the backend still holding the same model. Add a
behavioral truth-table test (catches a `not` inversion and a missing same-model
guard) and tighten the compute-buffer downgrade test to bound its source window.
* Studio: match the HF quant too when carrying preserved tensor intent
The same-model guard on the preserve carry-forward compared only model_identifier,
which is variant-agnostic for HF repos. A later load of the same repo with a
different gguf_variant (which already bypassed dedupe on the variant mismatch)
was treated as the same model, so a request that omits tensor settings inherited
the prior variant's preserved intent and forced multi-GPU layer placement for a
quant that never requested tensor. Also require the loaded hf_variant to match for
HF repos (local direct-file loads already differ by model_identifier path). Added
a regression test for the variant guard.
* Studio: match the loaded GGUF by path too when carrying preserved tensor intent
A local directory holding multiple GGUF variants keeps one variant-agnostic
model_identifier (the directory) while config.gguf_file selects the file, so the
same-model guard let variant B inherit variant A's preserved tensor->layer
fallback and forced B onto multi-GPU. Mirror _already_in_target_state's identity
logic: match by resolved path when both sides have a local file, else by HF
variant. #6659
* Studio: let implicit same-settings reloads dedupe after a preserved fallback
The backend _already_in_target_state mirror forced a reload on ANY effective
tensor-off request once a tensor->layer fallback was preserved. In the HF
auto-pick / local-directory flows the route-level dedup is skipped, so an
identical /load with tensor omitted reached this guard and reloaded every time
even without an explicit drop. Thread the route's preserve_multi_gpu_on_layer
decision in so only an explicit drop reloads; implicit carry-forward dedupes. #6659
* Studio: only an explicit tensor/split-mode change drops preserved intent
The explicit-drop test treated request.llama_extra_args is not None as a drop,
so a same-model reload that merely added an unrelated pass-through arg (e.g.
--top-k 20) without touching the tensor field or --split-mode disabled the
carry-forward and collapsed a fitting model back to one GPU. A drop now requires
an explicit tensor_parallel field change or a non-tensor --split-mode override,
via a shared _is_explicit_tensor_drop helper used by both the already-loaded
dedup and the load carry-forward so the two readers agree. #6659
* Studio: treat an explicit clear of extras as a tensor drop
When tensor intent was extras-driven (--split-mode tensor) and fell back to a
preserved layer split, a later request that explicitly clears extras
(llama_extra_args=[]) but omits tensor_parallel left the empty list with no
split-mode override, so the carry-forward kept the model pinned multi-GPU instead
of returning to normal layer selection. _is_explicit_tensor_drop now also counts
an explicit empty-list clear as a drop, while an unrelated extra (--top-k) or
inherit (None) still carries the preserved intent. #6659
* Studio: don't treat the UI's tensor_parallel echo as a tensor drop
The Studio frontend always sends tensor_parallel and copies the /load response's
resolved value back into its state, so after a tensor->layer fallback every
ctx/settings reload carries tensor_parallel=false even though the user never
changed it. Keying the drop on the field (or on an empty extras clear) collapsed
the preserved multi-GPU placement on the next reload. A fallback also always
stores --split-mode layer, never a tensor split mode, so a clear never wipes
tensor intent. _is_explicit_tensor_drop now drops only on an explicit non-tensor
--split-mode override; the bare field echo, an empty clear, an unrelated extra,
and inherit all keep the preserved placement, and --split-mode tensor /
tensor_parallel=true re-engage tensor. #6659
* Studio: match the resolved config.identifier when carrying tensor intent
The same-model guard for the carry-forward compared the raw request id, but
ModelConfig.from_identifier normalizes it (adds the unsloth/ prefix for a
shorthand, fixes repo-id case) before load_model stores config.identifier. So a
ctx/settings reload using the shorthand id missed the match, dropped
_carry_preserved_tensor_intent, and could collapse a preserved multi-GPU layer
placement to one GPU. Compare against config.identifier (what the backend stores),
keeping it symmetric with _already_in_target_state. #6659
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: harden the data-recipe and inference consumer loops against pump death
Follow-up to #6643. The same single-unsupervised-consumer pattern the training
pump had lives in two sibling loops, with the same failure mode: one bad event
kills the only thread that updates the in-memory state every UI surface reads,
while the worker subprocess keeps running.
- data_recipe JobManager._pump_loop: a malformed worker log line that makes
parse_log_message raise no longer kills the pump. Guard _handle_event, the
queue read, and the worker-exit finalize, and broaden _drain_queue so a drain
error still finalizes the job instead of leaving it wedged "active" (which also
leaked the workflow-scoped API key until its 24h expiry).
- inference InferenceOrchestrator._dispatcher_loop: guard the routing body so a
malformed response or a mailbox put error can't kill the dispatcher and hang
every in-flight generation (callers key liveness on the subprocess, not on
this thread).
Adds regression tests for both.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: extend consumer-loop hardening to RAG, hub, auth, and stream-reader paths
Continuation of the data-recipe and inference pump hardening: the same
"background producer updates in-memory state that a single unsupervised
consumer surfaces to the UI" pattern shows up in several more Studio paths,
each able to silently freeze a UI surface while the worker keeps running.
RAG ingestion SSE (core/rag/ingestion.py):
- job_events polled the queue with a blocking get and never noticed client
disconnect or a dead worker, so a closed tab or a producer that died
without emitting a terminal event left the stream hanging. It now polls
with a timeout, emits heartbeats, ends on terminal job status, caps idle
time, and always pops the job registry in finally.
- Added _reap_finished_jobs() and call it from start_ingestion so finished
job state does not accumulate.
Startup reconcile (storage/rag_db.py, main.py):
- reconcile_orphaned_ingestion_jobs() marks ingestion jobs (and their
documents) that were left non-terminal by a previous crash as failed, so
the UI does not show jobs stuck "running" forever after a restart. Wired
in at startup next to cleanup_orphaned_runs().
Hub download watcher (hub/services/download_lifecycle.py):
- _watch() could leave a job pinned "running" if finalize raised. Body is
now guarded: on failure it logs and sets the job to error, and always
invalidates the hf cache scan in finally.
External provider stream (core/inference/external_provider.py):
- read timeout was None (no stall ceiling); set to 300s so a wedged
upstream surfaces as an error instead of an indefinitely hung stream.
Auth store (auth/storage.py):
- Enable WAL + busy_timeout on the auth DB so token validation (read on
every request) and login writes stop serialising on the rollback journal.
Matches studio_db / rag_db / providers_db.
Login rate limiter (routes/auth.py):
- _LOGIN_IP_BUCKETS could grow unbounded under spoofed-IP traffic; cap it
and prune stale buckets, mirroring the per-account bucket handling.
Training progress SSE (routes/training.py):
- Break promptly on client disconnect instead of waiting for the next
yield to fail on a closed socket, matching the export / data-recipe SSE
routes.
llama-server stdout drain (core/inference/llama_cpp.py):
- Broaden the drain guard so an unexpected decode/read error logs at debug
and stops the drainer cleanly instead of escaping the thread.
Frontend stream readers (chat-api.ts, rag-api.ts):
- Wrap the SSE read loops in try/finally + reader.cancel() so early return
([DONE]), thrown errors, and consumer aborts release the reader lock
instead of holding it until GC.
Tests:
- test_training_progress_stream_nan: fake request now implements the async
is_disconnected() the route polls, matching the other SSE route fakes.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address Codex review feedback on the consumer-loop hardening
Four follow-ups from the automated review, all on code this PR introduced:
- Data-recipe pump (manager.py): a queue read that keeps raising an error
outside the read's narrow catch set (e.g. a broken queue pipe after the
child died) hit the `continue` guard and skipped the dead-worker finalize
below, spinning forever and leaving the job wedged "active" with its
workflow key unretired. On a read failure, fall through to finalize when
the worker is no longer alive. Added a regression test.
- RAG ingestion SSE (ingestion.py): the 5-minute idle cap could end the
stream while the job was still pending/running (a large document spends
minutes in embedding/storing with no per-batch progress event). The route
then sends [DONE], and the client treats a no-terminal-frame end as
completion, marking the document indexed mid-ingestion. Drop the idle cap:
while the worker is alive and non-terminal we keep heartbeating; the stream
ends only on terminal DB status, the None sentinel, or client disconnect.
- Login rate limiter (auth.py): the per-IP path pruned but then added the
new IP unconditionally, so a spoofed-source-IP spray kept _LOGIN_IP_BUCKETS
unbounded and made every new IP pay a full-dict prune scan. Gate the add on
the cap, mirroring the account path.
- Hub download watcher (download_lifecycle.py): if finalize raised before it
reaped (proc.wait) and dropped the worker (e.g. an I/O error draining
stderr), the crash path published a terminal state while the live Popen
stayed registered and kept writing the cache, and the terminal set_job let
claim() admit a retry on the same repo. Terminate + drop the worker before
setting the terminal state.
* Studio: keep login throttling working when the per-IP bucket dict saturates
Review follow-up. The previous cap fix skipped creating a bucket for a new IP
once _LOGIN_IP_BUCKETS was full, returning ip_fails=0. Under a sustained spray
that also fills the account dict, every failure from such an IP then looked
first-seen and _login_blocked had no bucket to enforce, so the cap effectively
disabled throttling once saturated.
Bound the dict with a FIFO eviction instead: if the IP is new and the dict is
full, reclaim expired buckets (rate-limited so a burst of distinct IPs can't
make each failure an O(n) sweep) and, if still full, evict the oldest-inserted
IP. The new IP always gets a real bucket, so a saturating (e.g. spoofed
X-Forwarded-For) spray stays throttled while memory stays bounded. Added a
regression test that saturates the dict and asserts a later IP is still blocked.
* Studio: address Codex review (RAG queue lifecycle, stream error, orphan chunks)
Three follow-ups on the Phase 6 changes:
- RAG ingestion SSE (ingestion.py): job_events removed the per-job queue in its
finally on ANY exit, including an early client disconnect while the worker is
still running. That dropped the worker's later events (the queue is the only
one _emit writes to) and made a reconnect find no queue and receive only
[DONE], which the client treats as completion. Only drop the queue on a
terminal exit (None sentinel / terminal DB status); leftover terminal queues
are still swept by _reap_finished_jobs. Added queue-lifecycle tests.
- External provider stream (routes/inference.py): once the 300s read timeout can
fire, the stream's except path failed the monitor but ended without an error
frame or [DONE], so the chat client saw a bare EOF and saved the timed-out
answer as a successful partial with no error. Emit an SSE error frame (and
[DONE]) on stream failure so the client surfaces it.
- RAG startup reconcile (storage/rag_db.py): marking a half-ingested document
failed left its chunks/fts/vec rows intact, and retrieval filters by scope not
status, so a failed document could still be retrieved and cited. Purge the
document's chunks when reconciling it to failed (the doc row stays for
re-ingest).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: release the remaining SSE stream readers (training, data-recipe, export)
reviewer.py follow-up. The chat and RAG SSE readers were wrapped in
try/finally + reader.cancel(), but the other three readers built on the same
response.body.getReader() pattern were left without it: streamTrainingProgress,
streamRecipeJobEvents, and streamExportLogs leak the ReadableStreamDefaultReader
lock (held until GC) when the consumer aborts, returns early, or a parse/callback
throws. Wrap each in try/finally + reader.cancel() (export already had a
try/catch, so it only needed the finally). All five frontend SSE readers now
release the reader symmetrically.
* Tighten resilience comments and docstrings
Condense the verbose explanatory comments and internal-helper docstrings added
in this branch to shorter, clearer forms. Comment/whitespace only; verified no
code changed via AST diff. No behaviour change.
* Studio: keep chunks for completed docs during ingestion reconcile
Startup reconciliation flips orphaned (non-terminal) ingestion jobs to failed and
purges the document's chunks so a failed source can't be retrieved. But it dropped
the chunks unconditionally, so a document the worker had already committed as
'completed' before the crash (only its job row left non-terminal) lost every chunk
while still reporting 'completed'. That leaves an empty source that retrieval can't
return and dedup (status != 'failed') blocks from re-ingest.
Only purge chunks when the document UPDATE actually transitions it to failed; an
already-completed document keeps its chunks. Adds reconcile regression tests for
both the completed-doc and genuine in-flight-orphan cases.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: drop a finished RAG job's queue when the client disconnects
job_events kept the per-job queue until it consumed the None sentinel, so a UI
that stops on the terminal event (its reader.cancel aborts the stream before
[DONE]) left the queue registered until the next _reap_finished_jobs sweep; a
batch of uploads followed by idling retained them all.
_run writes the terminal DB status before emitting the terminal event, so on
generator exit, drop the queue when the job's DB row is already terminal (worker
done, nothing to resume) and keep it only while the worker is still running. Adds
a disconnect-after-terminal-event regression test.
* Remove stray async task output files committed by mistake
* Studio: harden login IP throttle and end progress stream on disconnect
Two Codex review items:
Login per-IP throttle: when the per-IP bucket dict saturated, FIFO eviction could
drop a still-hot (blocked) bucket, so an IP could flood the dict with distinct
(or spoofed) source IPs to push out its own bucket and retry as first-seen. Stop
evicting hot buckets; a new IP that can't fit now shares a bounded overflow
counter that still trips the per-IP threshold, so a saturating spray stays
throttled and no live counter is reset.
Progress SSE: on client disconnect the polling loop only broke and fell through
to the unconditional final 'complete' frame, so a buffered or proxying consumer
could read a still-active run as completed. Return from the generator instead.
Adds regression tests for both (spray cannot reset a hot bucket; disconnect while
active emits no complete frame).
* Studio: shard the login overflow counter and stop cancelling chat stream after [DONE]
Two Codex review items:
Login throttle overflow: the single shared overflow counter meant that once a
saturating spray pushed it past the per-IP threshold, _login_blocked returned 429
for every new unbucketed source IP, before credentials were checked -- a global
login denial. Shard the overflow into a fixed array of counters keyed by hash(ip),
so a hot shard only throttles the IPs that map to it while a single source's
repeated failures still concentrate in one shard and stay throttled. Memory stays
bounded and no live bucket is evicted. Adds a regression test that a hot overflow
shard does not block an unrelated IP.
Chat stream: the reader.cancel() in the SSE finally fired even after a natural
[DONE]/EOF. The backend finalizes its api-monitor entry right after yielding the
sentinel (the local pass-through finishes after the last yield), so a client
cancel there can be observed as a disconnect and mark a completed request as
cancelled. Track natural completion and only cancel on an early/abnormal exit.
(No frontend unit test: the Studio frontend has no test harness.)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: give prep-timeout test fakes an is_disconnected method
The progress stream now ends on client disconnect (await request.is_disconnected()
before falling through to the terminal frame). After merging that into the
prep-timeout tests added later on main, their _FakeRequest/_ReconnectRequest must
provide is_disconnected or the generator raises AttributeError under CI.
* Studio: keep the login overflow throttle when bucket capacity frees up
_login_blocked only consulted the per-IP overflow shard while the bucket dict was
still at capacity. If a slot freed before the 60s window expired (e.g. another
IP's successful login calls _clear_login_bucket), a source counted in a hot shard
stopped being blocked and its next failure got a fresh per-IP bucket, resetting
the throttle the overflow path exists to preserve. Always max in the IP's shard
(shards are empty outside saturation, so it is a no-op in the common case). Adds a
regression test that a hot source stays throttled after a bucket frees.
* Studio: clear a login IP's overflow throttle on successful login
_clear_login_bucket reset the per-IP and per-account buckets on a successful
login but not the overflow shard, so after the dict saturated and an IP was
counted in overflow, a later successful login left those entries behind and the
next failed attempt could immediately return 429.
Store overflow entries as (timestamp, ip) so a source is throttled by its own
count within the shard (also removing cross-IP collateral within a shard), and
drop just that IP's entries in _clear_login_bucket. Adds a regression test that a
successful login clears the overflow throttle.
* Studio: bound the login overflow shard memory under high-cardinality spray
The per-IP overflow tracked failures in a time-pruned deque of (timestamp, ip)
tuples, so a spoofed-X-Forwarded-For spray of distinct one-off IPs grew memory and
the per-check scan with request cardinality for the whole window -- undermining
the bucket cap that exists to bound memory. Replace each shard with a fixed-
capacity dict (ip -> [count, window_start]): O(1) lookups, and when a shard is
full a one-off IP evicts the lowest-count entry (Space-Saving) so memory is hard-
bounded while a persistent attacker keeps a high count and is never evicted. Adds
a regression test that shards stay within the per-shard cap under a 5000-IP spray.
* Studio: purge chunks for already-failed docs during ingestion reconcile
The reconcile chunk-purge was gated on the documents UPDATE actually flipping a
non-terminal doc to failed. A doc the worker had already marked 'failed' before
the crash (job row left non-terminal) was not re-flipped, so its committed chunks
were kept and stayed retrievable/citable, since retrieval filters by scope not
status. Purge chunks whenever the document is not 'completed' (failed, in-flight,
or gone), preserving the completed-doc carve-out. Adds a regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: don't inherit an evicted IP's count onto a new overflow source
When a full overflow shard evicted the lowest-count entry, the new source
inherited that count (Space-Saving base + 1). If a shard was saturated with hot
entries, an unrelated new IP could land at/over the threshold and be 429'd after a
single attempt -- cross-IP collateral despite the per-source-isolation intent.
New entries now start clean at count 1; the only cost is that a heavy hitter that
is the lowest-count entry in a fully saturated shard can briefly reset, which is
preferable to blocking a bystander. Adds a regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: carry overflow failures into a new IP bucket on transition
_login_blocked took max(per-IP bucket, overflow shard) rather than combining them,
so a source could log (threshold-1) failures in overflow during saturation and,
once a bucket slot freed, another (threshold-1) in a fresh bucket within the same
window -- roughly doubling the per-IP limit. When a saturated-era IP first gets a
real bucket, migrate its windowed overflow count into that bucket (and drop the
overflow entry) so the combined failures throttle at the intended limit. Adds a
regression test.
* Studio: reconcile a completed doc's orphaned job to completed, not failed
When a crash left an ingestion job non-terminal after its document was already
committed as completed, reconcile marked the job failed. After restart the upload
UI has no in-memory SSE queue and falls back to getJob(), which treats a failed
job as an indexing failure and removes/toasts a document that is actually
searchable. Mark the job completed (keeping its chunks) when its document is
completed. Extends the completed-doc reconcile test to assert the job status.
* Studio: clamp the overflow failure count migrated into a login bucket
A saturated source could accrue an unbounded overflow count, then materialize
one deque entry per recorded failure when a bucket slot freed, allocating an
arbitrarily large deque under the login lock. Only at-or-above the per-IP
threshold matters for blocking, so cap the count there at the record and take
sites; the migration is now bounded without weakening the limit.
* Studio: keep the RAG job stream alive on a transient status read
The heartbeat poll read the job row unguarded; a momentarily-locked DB would
raise out of job_events, which the SSE route turns into a terminal error frame,
and the UI drops a document whose worker is still running. Treat a failed status
read as non-terminal: heartbeat and retry, and keep the queue so a reconnect can
resume.
* Studio: set busy_timeout before journal_mode on the auth DB
Switching journal_mode needs a lock, so if a refresh-token write already holds
one, journal_mode=WAL raises SQLITE_BUSY and the shared try leaves the
connection on SQLite's default zero lock wait. Set busy_timeout first so the
switch waits instead of failing.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Fix offline checkpoint load/export failing with "tokenizer is weirdly not loaded"
Loading a fine-tuned checkpoint with no internet (e.g. a Studio export) crashed
with "Unsloth: The tokenizer is weirdly not loaded? Please check if there is one."
For a LoRA adapter the loader reassigns model_name to the base model repo id and
only keeps the local checkpoint dir as tokenizer_name when it contains
tokenizer_config.json, tokenizer.json AND special_tokens_map.json. Modern
tokenizers (e.g. Gemma) store special tokens inside tokenizer_config.json and
omit special_tokens_map.json, so tokenizer_name fell back to the base repo id.
The tokenizer/processor loads in vision.py then hit the Hub with no
local_files_only, so with no network they failed (AutoProcessor) or hung for
minutes (AutoTokenizer) even though every file was already cached.
loader.py: keep the local checkpoint dir as tokenizer_name when it has a
tokenizer config plus the actual tokenizer files (tokenizer.json / tokenizer.model
/ vocab files); special_tokens_map.json is no longer required.
vision.py: compute an effective local_files_only (explicit kwarg plus the
HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE env vars, mirroring loader.py and
diffusion.py) and thread it through every AutoConfig, AutoProcessor,
AutoTokenizer and the manual VLM processor fallback, including the
hf_hub_download in that fallback (which now prefers a local file). When a load
fails and no offline env var is set, retry against the local cache. The retry
forces HF offline mode because local_files_only alone does not stop
AutoProcessor / AutoTokenizer from issuing a /api/models request during class
resolution. The final error now explains the offline/cache cause instead of the
misleading "weirdly not loaded" message.
studio export: probe Hub reachability once per checkpoint load and pass
local_files_only when offline so exports use the local checkpoint dir / cache
instead of hanging or crashing with no internet.
Online behavior is unchanged: the new flags default to off and the retry only
runs after a network related failure.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: safer offline forcing, cached fallback config, proxy-aware probe
Follow-up to the offline checkpoint load fix, addressing review feedback:
- vision.py: only flip the process-wide HF offline flag when offline is actually
requested (local_files_only / env) or after a real network failure, never
pre-emptively while we might be online. The flip is now guarded by a lock +
depth counter so nested or concurrent windows restore the flag correctly
(no stale value).
- vision.py: guard the get_auto_processor fallback so a network error there
returns None and the local-cache retry still runs instead of escaping.
- vision.py: in the manual VLM processor fallback, read tokenizer_config.json
via hf_hub_download(..., local_files_only=...) so a cached repo-id config is
still resolved offline and the model-specific image/video tokens are restored.
- studio export: make the reachability probe proxy aware (probe the configured
HTTP(S) proxy egress, honour NO_PROXY, use the endpoint port) so a proxy-only
setup is not wrongly marked offline; allow UNSLOTH_OFFLINE_PROBE=0 to disable.
- studio export: run the audio/vision type-detection probes inside the
forced-offline window when offline, so their config/tokenizer reads hit the
local cache instead of waiting out connection timeouts.
Online behavior remains unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: gate offline retry, safer tokenizer_name pop, skip audio net probe offline
- vision.py: only force the process-wide HF offline flag on the tokenizer
retry when offline was requested or the captured primary error is actually
network related, so a permanent tokenizer error no longer toggles global
offline mode for other concurrent loads.
- loader.py: always pop tokenizer_name out of kwargs and let a caller-supplied
value win, avoiding a "multiple values for keyword argument 'tokenizer_name'"
TypeError when it is also passed explicitly downstream.
- model_config.py / export.py: add local_files_only to detect_audio_type so the
raw requests.get tokenizer_config fetch is skipped offline (it ignores the HF
offline flag), and pass it from the export probe.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: classify LocalEntryNotFoundError as offline-related
huggingface_hub's LocalEntryNotFoundError subclasses FileNotFoundError, so the
"not isinstance(cur, FileNotFoundError)" guard in _is_offline_related_error was
swallowing it and it could never be recognised as offline, despite being listed
in the network error types. It means "not in cache and the Hub is unreachable",
which is genuinely offline. Capture the class into an isinstance-checkable tuple
(empty, hence a no-op, if the import is unavailable) and exclude it from the
FileNotFoundError guard, so a real offline failure now triggers the local-cache
retry while a plain missing-file error still propagates.
* Address review: require merges.txt for BPE, status-gate HTTP errors, isolate local-only audio cache
- loader.py: a local dir with vocab.json but no merges.txt (and no tokenizer.json)
is not a loadable BPE tokenizer, so do not treat it as self-sufficient; require
merges.txt alongside vocab.json in both gate blocks, otherwise fall back to the
base model tokenizer as before.
- vision.py: _is_offline_related_error no longer buckets every HfHubHTTPError /
requests HTTPError as offline. HTTP errors are judged by status code: only a
transient 5xx triggers the forced local-cache retry, while 401/403 (auth/gated)
and 404 (missing) propagate as the real error instead of being masked. Hard
signals (connection/timeout/OfflineModeIsEnabled/LocalEntryNotFoundError) still
classify as offline.
- model_config.py: include local_files_only in the audio-detection cache key so a
local-only (offline) negative result cannot be reused by a later online probe,
which would otherwise route an audio model through the text loader until restart.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address re-review: fix studio test stubs, force offline env in probe window, drop redundant retry
- studio/backend/tests/test_vision_cache.py: the three _detect_audio_from_tokenizer
stubs were called with the new local_files_only kwarg and raised TypeError, failing
Backend CI. Add local_files_only to the stub signatures and add a test that a
local-only negative does not poison a later online audio probe.
- export.py: the type-detection probe window now also sets HF_HUB_OFFLINE /
TRANSFORMERS_OFFLINE env vars (saved/restored), not just the in-process flag.
transformers_version._load_config_json / _check_tokenizer_config_needs_v5 gate
their urllib fetches on the env vars, and is_vision_model may spawn a subprocess
that inherits os.environ but not the in-process flag; without the env vars a
probe-detected offline export could still block on a network timeout.
- vision.py: only retry the processor load when the first attempt was online and
failed with a network error. When local_files_only was already requested the first
attempt was forced offline, so the previous retry just repeated identical failing
work before the last-resort path.
- model_config.py: correct the _audio_detection_cache type annotation to the 3-tuple
key (name, token_fingerprint, local_files_only).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: thread-safe probe-offline env window, clear error for local dir without config
- export.py: guard the HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE mutation in
_force_offline_probe_window with a lock + depth counter (mirrors _force_hf_offline),
so concurrent / nested export probes only flip on first entry and restore on last
exit. This prevents overlapping export requests from permanently poisoning those
env vars or restoring a stale value.
- vision.py: in the VLM processor fallback, when tokenizer_name is a local directory,
read its tokenizer_config.json directly and raise a clear FileNotFoundError if it is
absent, instead of handing the local path to hf_hub_download (which would treat it as
a repo id and raise a confusing HFValidationError / RepositoryNotFoundError).
hf_hub_download is now only used for actual repo ids.
* Address review: classify raw socket.gaierror DNS failures as offline
Add the platform-specific getaddrinfo / DNS-resolution wording to the offline
detection list in _is_offline_related_error so a bare socket.gaierror (an OSError
subclass) is recovered from the local cache: "Name or service not known" and
"Temporary failure in name resolution" (Linux) and "nodename nor servname
provided" (macOS). Genuine non-network OSErrors (disk full, permission denied)
and plain FileNotFoundError still propagate.
* Address review: retry degraded VLM offline, force offline for text export + patch-tokenizer fallback
- vision.py: a degraded VLM processor (text-only, no image_processor) whose manual
fallback fails offline used to be kept, so image inputs broke even with cached
files. _construct_vlm_processor_fallback now returns its failure error;
_acquire_processor surfaces it, and the caller retries forced-offline when the
result is None OR a degraded VLM and the failure was network related, keeping the
original result if the retry is not strictly better (never regress). The retry is
still gated on an online first attempt + offline-related error so a permanent
error never flips the global offline flag.
- vision.py: wrap the patch_tokenizer except-branch AutoTokenizer.from_pretrained in
the same forced-offline-on-network-error pattern as the primary / last-resort
loads, so an offline export where patch_tokenizer raises does not hang or fail.
- export.py: force HF offline around the two FastLanguageModel loads (text and SNAC)
when the probe detected offline. Their text tokenizer path (load_correct_tokenizer
-> AutoTokenizer) does not forward local_files_only, so without this a text export
could still contact the Hub. Added a small _offline_window_if helper reused by the
probe and load windows.
* Consolidate offline loading into one entry-point decision
Decide offline once per entry point instead of at every HF call site. The
prior approach threaded local_files_only into ~15 scattered config / tokenizer
/ processor / weight loads, each wrapped in its own try-online, classify-error,
retry-forced-offline dance, which is what kept surfacing "another call site you
missed", "another error shape misclassified", and global-flag thread-safety in
review.
FastLanguageModel / FastModel / FastBaseModel.from_pretrained now share an
@_offline_aware_load decorator: when offline (explicit local_files_only kwarg or
HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE env) it sets local_files_only and runs the
whole load inside one _force_hf_offline() window so every nested HF call inherits
it; when online it runs normally and, only if the load fails with a genuinely
network-related error, retries once forced-offline. The online path is unchanged
(no probe added) and 401 / 403 / 404 / permanent errors still propagate.
Centralise the offline helpers in loader_utils.py as the single source of truth
(shared by loader.py, re-exported from vision.py, and reused by the Studio
exporter):
- _force_hf_offline now sets the HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE env vars
AND the in-process huggingface_hub / transformers flags, refcounted under one
lock so nested / concurrent windows restore correctly. Setting the env vars
covers env-gated urllib probes and spawned subprocesses too.
- _get_effective_local_files_only, _is_offline_related_error (unchanged
classifier, retains the 5xx-vs-4xx, LocalEntryNotFound and gaierror handling),
_offline_aware_load, and _resolve_checkpoint_tokenizer_name.
loader.py: wrap both entry points; drop the two duplicated env-var fallback
blocks and the two byte-identical local-tokenizer-gate blocks (now
_resolve_checkpoint_tokenizer_name).
vision.py: drop the per-site force_offline params and the three retry gates
(processor, patch_tokenizer fallback, last-resort). They now just surface the
underlying error so the single entry-point safety net retries forced-offline. A
network fallback error now takes precedence over a permanent primary error so the
offline retry still fires when the manual VLM fallback needs cached repo files.
studio/backend export.py: reuse the unified core _force_hf_offline (env + flags)
and drop the duplicate probe-window primitive; the snac / text branches no longer
need their own window. model_config.py: also gate the raw requests.get audio
fallback on the HF offline env vars so it is covered even without the kwarg.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address 10-reviewer P1 findings: vision cache split, PEFT offline, retry OOM
Split the Studio vision-detection cache by local_files_only, mirroring the audio
cache fix. is_vision_model / _is_vision_model_uncached / _raw_config_has_vision_config
/ load_model_config now thread local_files_only, the cache key includes it, and the
exporter passes it. Offline detection also skips the transformers-5 network
subprocess and stays on the local cache, so an offline negative can no longer be
keyed under the online entry and poison a later online probe. Adds a regression
test mirroring the audio poison test.
Forward local_files_only to both PeftModel.from_pretrained adapter-attach sites in
loader.py so a cached remote LoRA adapter resolves from the local cache under
explicit local-only / offline loads (defence-in-depth alongside the forced-offline
window).
_offline_aware_load: run the forced-offline retry OUTSIDE the except block and
collect + empty the device cache first. An except-scoped exception keeps its
__traceback__, which pins the failed attempt's frame locals (a partially loaded
model) until the block exits; loading the model again while that copy is still
alive could OOM a large VLM. Letting the except block close drops the traceback so
the partial load is freed before the retry reallocates.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address Codex review: env-offline cache key + rebuild HF sessions in offline window
Key the Studio audio and vision detection caches on the EFFECTIVE offline state
(local_files_only OR the HF offline env vars), not just the kwarg. detect_audio_type
and is_vision_model both skip the remote fetch / network subprocess when
HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE is set even with the default
local_files_only=False, so the result reflects offline; storing it under the online
(False) key let an env-offline negative poison a later online lookup once the env var
was cleared. Both now compute effective_offline once and use it for the cache key and
the downstream call. Adds a regression test for the env-offline dimension.
_force_hf_offline now rebuilds huggingface_hub's cached sessions on enter and exit
(best-effort _reset_hf_sessions). On hub 0.x the offline adapter is baked into the
per-thread requests.Session at creation, so flipping the constant alone leaves an
already-cached online session able to hit the network inside the window (and an
offline one stuck offline after restore); resetting forces the next get_session() to
match the current flag. On hub 1.x offline is checked dynamically per request, so
reset_sessions does not exist and the helper is a safe no-op.
The third review point (release the failed load before retrying) was already fixed in
af0f58a: the forced-offline retry now runs outside the except block and frees the
device cache first, so the failed attempt's traceback-pinned partial model is
released before the retry reallocates.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Align Studio _env_offline parsing with the canonical offline helper
model_config._env_offline gates the raw requests.get tokenizer-config fallback in
detect_audio_type and the audio/vision detection cache keys, but it only accepted
unstripped "1"/"true"/"yes". unsloth's offline helpers (loader_utils._env_says_offline
and the from_pretrained env fallback) accept the canonical set {1,true,yes,on} after
strip + lowercase, so HF_HUB_OFFLINE=on or HF_HUB_OFFLINE=" 1 " was treated as offline
by the loaders but online here, leaving the raw network fetch reachable while
"offline". Use the same strip + lowercase {1,true,yes,on} set. Adds parsing tests.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix lint: drop dead offline-helper re-exports from vision.py
The import-hoist verifier (scripts/verify_import_hoist.py) flagged vision.py's
re-export block as HOISTED-IMPORT-UNUSED blockers: it imported eight offline
helpers from loader_utils but only used three internally
(_get_effective_local_files_only, _is_offline_related_error, _offline_aware_load).
The other five were imported purely to preserve `from unsloth.models.vision import
X`, but nothing imports four of them from vision, and loader.py already imports
_resolve_checkpoint_tokenizer_name straight from loader_utils.
Import only the three names vision.py actually uses, and point the Studio exporter
at the canonical source (from unsloth.models.loader_utils import _force_hf_offline)
instead of re-exporting it through vision. loader_utils stays the single source of
truth; no behaviour change.
* Address Opus review: chain probe errors, unify env-offline, status-less HTTP
Chain the original AutoConfig/PeftConfig probe exception into the combined
RuntimeError in both FastLanguageModel.from_pretrained and FastModel.from_pretrained
(`raise RuntimeError(combined_error) from (autoconfig_exc or peft_exc)`). The probes
caught every Exception and stringified it, so the re-raised RuntimeError had no
__cause__/__context__ and _is_offline_related_error could not classify it -- the
network-down-but-cached auto-retry never fired for these entry points. With the
cause chained, the decorator sees a ConnectionError/LocalEntryNotFoundError/5xx and
retries forced-offline from cache; a permanent cause (404 / bad config) is still not
offline-classified and propagates without a wasted retry.
Unify the third offline-env parser: studio/backend/utils/transformers_version._env_offline
now uses the canonical {1,true,yes,on} + strip + lowercase set (matching
loader_utils._env_says_offline and model_config._env_offline), so HF_HUB_OFFLINE=on
or " 1 " no longer leaks the direct urllib metadata fetches to the network.
_is_offline_related_error: a status-less HTTP error (no response / unparseable code)
now falls back to the network-wording check instead of being dropped, so a transient
HTTP failure with clear "couldn't connect" wording is treated as offline. HTTP errors
with a real status code still decide by code (4xx propagates, 5xx is offline).
* Condense offline-loading code comments, drop dead helper, dedupe import for PR #6554
* Add unit tests for offline-loading helpers for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Guard load cleanup with try/finally and add retry-contract tests for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add gc.collect retry-step test for PR #6554
* Tighten offline-loading comments and docstrings for PR #6554
* Raise the both-config-failed error before model-type lookup so offline retry fires for PR #6554
* Prefer offline cause for retry and bound export reachability probe for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Skip remote mapper while offline, harden text-load cleanup, and stop stacked offline retries for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Surface VLM fallback offline errors, probe offline before export version activation, and restore progress bars across retries for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Restore offline env after export version activation so the persistent worker re-decides per load for PR #6554
* Classify socket.gaierror and urllib URLError as offline by type for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Probe offline around export load preflights and never offline-retry TLS failures for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Force in-process offline for export preflights, verify proxy egress in probe, and skip caching offline version negatives for PR #6554
* Snapshot offline constants before forcing env and require local processor files for VLM checkpoints for PR #6554
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: keep the training event pump alive so progress can't silently freeze
The parent-side event pump is the only writer of the in-memory progress state
that SSE /progress, /status, /metrics and the DB history all read. It ran in a
single unsupervised daemon thread with no guard around event handling, so one
malformed event or a transient queue/DB error would terminate it permanently.
The worker subprocess keeps training regardless (mp.Queue puts never block on an
unbounded queue), so a run kept burning GPU for hours while every progress
surface froze on the last step the pump saw.
- Guard each pump iteration: a bad event or queue-read error is logged and
skipped instead of ending the loop. _read_queue now reads any error as
"no event", not just Empty/EOFError/OSError/ValueError.
- Add a _pump_running flag and an _ensure_pump_alive watchdog wired into
is_training_active, so a pump that dies while the worker is alive is restarted
on the next status poll and the UI catches up from the still-open queue.
- Start respawned and restarted pumps under the lock so the watchdog can never
spawn a duplicate during the brief start window.
Adds tests/test_training_pump_resilience.py covering both guarantees.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio training pump: address review (drain guard, start race, read backoff, respawn flag)
Follow-up to the event-pump resilience change, closing four edge cases a
review surfaced in the same pump/queue surface:
- _drain_queue now tolerates any error during the worker-exit drain and
finalizes with whatever it drained, instead of skipping finalization and
leaving the run wedged "active" with a dead worker.
- start_training clears a stale _pump_running flag during reset and assigns
the subprocess handles plus starts the pump under the lock, so a concurrent
status/SSE poll can't spawn a duplicate pump during setup.
- _read_queue goes back to the narrow EOFError/OSError/ValueError catch;
truly unexpected errors are left to _pump_loop's guarded read, which logs
and backs off so a persistently raising queue can't spin a hot loop.
- The xet respawn-failure path clears _pump_running so a later run can't
inherit a stale flag.
Adds regression tests for all four.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: revive a crashed pump after worker exit + stop test module pollution
Two review follow-ups on the training event pump:
- _ensure_pump_alive refused to restart once the worker had exited
(not self._proc.is_alive()), so a pump that crashed just before the worker
finished never drained the terminal complete/error events still sitting in
the queue. progress.is_training stayed True and is_training_active() returned
True forever, leaving the run stuck "running" behind a dead pump. A True
_pump_running flag with a dead thread is an unambiguous crash regardless of
worker state, so restart there too: the fresh pump drains the backlog and
finalizes. Updated the watchdog test to assert the revive-and-finalize.
- The resilience test imports core.training.training while heavy module-level
deps are stubbed, then restores the stubs -- but the cached training module
kept the stubs bound in its globals, so a later test in the same session
could exercise the fakes (e.g. prepare_gpu_selection) instead of the real
code. Evict the training module (and its package) after import when this file
created it, so subsequent tests re-import it cleanly.
* Studio: finalize training run when queue reads keep failing on a dead worker
reviewer.py follow-up. _read_queue only swallows EOFError/OSError/ValueError;
an unexpected error escapes to the pump's outer guard, which logged, slept and
`continue`d. If those reads keep raising after the worker has already exited
(e.g. a broken queue pipe), the loop never reaches the dead-worker finalize
block, so the pump spins on with _pump_running True and progress.is_training
stuck True -- the run looks like it is still training forever. On a read failure
now fall through to finalize when the worker is gone, only backing off and
retrying while it is still alive. Mirrors the data-recipe pump fix; added a
regression test.
* Tighten training pump resilience comments and docstrings
Condense the verbose explanatory comments and docstrings on the training event
pump and its tests to shorter, clearer forms. Comment/whitespace only; verified
no code changed via AST diff. No behaviour change.
* Studio: create the training DB run before starting the event pump
start_training started the event pump before the eager _ensure_db_run_created()
call, so for a worker that completes or fails immediately the pump could race the
main thread into creating and finalizing the same run row (duplicate INSERT, or a
finalize skipped while _db_run_created was still false). Create the run first; the
pump then only ever finalizes. Adds a regression test asserting the pump observes
an already-created run.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
The post-filter safety net for 'Train on completions' fires when
train_on_responses_only() masks every token in too many rows. Its trigger is
a row-drop ratio, not a token-length check, but the message hardcoded
"max_seq_length is too short, try increasing (e.g. 8192)" -- advice that
fires identically at any max_seq_length and can recommend a value below the
user's current setting (telling someone already at 16384 to use 8192).
The dominant real cause is that the model's response template is not found in
the formatted samples: the dataset is already formatted, or its structure
doesn't match the model's chat template, so every token gets masked and the
rows are dropped. Reword the error (and the comment above it) to lead with
that cause and the actionable fix (turn off 'Train on completions'), and
mention max_seq_length only as a secondary possibility without a hardcoded
recommendation.
* Studio: honor stream=false on the GGUF agentic tool path (#6570)
* Studio: dedup the #6570 non-streaming tool tests and cover cached_tokens
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: cover the cached_tokens metadata fix and clarify the drain comment (#6570)
* Studio: align the GGUF tool drain naming and tighten its comment (#6570)
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
* Studio: cap GGUF context to unified memory on Apple Silicon
* Studio: tighten Apple ctx-cap comments and drop the overstated MLX-sync claim
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: reserve flat MTP fraction and floor sparse-KV ctx in the Apple unified-memory cap
The Apple Silicon GGUF context cap mirrored the discrete-GPU auto-fit branch but
missed two protections the discrete path already applies:
- It passed the full unified-memory budget with budget_frac=1.0 without first
reserving the flat MTP fraction the discrete path takes off via _pin_fraction.
With an MTP draft whose KV cannot be byte-sized (e.g. Qwen3.6-MTP, #6529), the
cap filled the whole budget and left nothing for the draft, so unified memory
could still over-commit. Reserve _flat_mtp_reserve up front; this is a no-op
when MTP is not engaged.
- It required _can_estimate_kv(), so a GGUF with sparse KV metadata skipped the
cap entirely and launched at full native context. Mirror the discrete
file-size-only fallback and floor the auto context to 4096 when the cache
cannot be sized.
Adds regression tests for both paths.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: tighten comments in the Apple unified-memory context cap
Condense the verbose comment blocks in the Apple budget helper, the no-GPU
Metal branch, and the context-fit tests. Comments only, no code change
(verified with ast-based comment_tools check); suite still green.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <danielhanchen@gmail.com>
* Studio: lazy-import matplotlib so the server starts when the wheel is blocked
matplotlib.pyplot was imported at the top of core/training/training.py, on the
server boot path. When matplotlib's native extension fails to load (e.g. an
unsigned wheel blocked by Windows Smart App Control), that import crashed the
whole Studio server at startup instead of just disabling loss plots.
Move it into a lazy _load_pyplot() helper called from _create_loss_plot, using
the headless Agg backend, and return None when matplotlib is unavailable so
plotting degrades gracefully. The plot return was already Optional, so callers
need no changes. Keep the type-only import under TYPE_CHECKING and quote the
annotations.
Fixes#6588
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: pin matplotlib==3.11.0
Pin matplotlib to the current latest so a new unsigned release does not
reintroduce the Smart App Control block on Windows. Belt-and-suspenders on
top of the lazy import. Pinned in both studio.txt and extras.txt.
* Pin matplotlib to 3.10.9 so Studio still installs on Python 3.10
matplotlib 3.11.0 requires Python >=3.11, so the pin had no installable wheel on
Python 3.10 (still supported) and pip install failed there. 3.10.9 is the latest
3.10.x (requires-python >=3.10) and covers Python 3.10 through 3.13. Also tighten
the lazy-import docstrings.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <danielhanchen@gmail.com>
* Fix Gemma 4 GGUF OpenAI API streams
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Avoid duplicate Responses stream disconnect watcher
* Keep reasoning-only Responses output hidden
* Address Gemma stream review comments
* Avoid Responses stream task-group cleanup
* Harden OpenAI chat completion streams
* Address OpenAI stream review issues
* Clean up Studio OpenAI stream helpers
* Fix Studio passthrough cold stream timeout
* Fix tool parser compatibility exports lint
* Preserve audio stream disconnect cancellation
* Avoid synthetic finish after passthrough errors
* Address stream cleanup and Gemma parser reviews
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Gemma 4: parse bare-string tool args and keep safetensors tools for native <|tool_call>
- Quote bare unquoted string values in Gemma native tool-call args (e.g.
{location:Tokyo,unit:celsius}) so they parse; JSON scalars stay typed.
- Stop _detect_safetensors_features from suppressing supports_tools for
templates that emit Gemma native <|tool_call>, which the shared parser
now reads.
- Add tests for both.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Harden Gemma tool-call parsing and stream-error detection
Address three issues in the Gemma-native tool-call path:
- _quote_gemma_object_keys stopped a bare (unquoted) string value at the
first comma, so an argument like `location:New York, NY` was split
mid-value and the synthesized JSON failed to parse, dropping the whole
tool call. A bare value now ends only at `}` or a comma that begins the
next `key:` pair.
- parse_tool_calls_from_text scanned the entire response for Gemma markers
even inside a tool call already parsed from a `<tool_call>{...}` JSON
block, so a marker-like string inside an argument (data) was promoted to
a second, unintended tool call. Matches inside an already-consumed call
span are now skipped.
- _openai_passthrough_stream relied on _monitor_openai_sse_line to flag a
stream error, which returns early when monitor_id is None
(skip_api_monitor), so an upstream error chunk left saw_stream_error
unset and the synthetic-finish guard emitted a successful finish_reason
after a failed stream. Error chunks are now detected independently of API
monitoring.
Adds tests/test_gemma_tool_parse_edge_cases.py covering the comma and
marker-injection cases.
* Emit the terminal finish_reason chunk in GGUF streams
The OpenAI chat-completions GGUF tool stream and plain stream both built a
final ChatCompletionChunk carrying finish_reason but never yielded it, so
clients received the optional usage chunk and [DONE] with no chunk carrying
finish_reason. OpenAI-compatible consumers rely on that terminal choice to
distinguish stop/length/tool_calls. Yield it before the usage chunk and
[DONE], matching the other streaming paths.
* Parse tool calls in document order and skip nested markers both ways
Unify the JSON- and Gemma-format tool-call passes into a single
position-ordered scan:
- Calls are now emitted in byte order across both formats, so a mixed
output like `<|tool_call>call:create{...}<tool_call|> ... <tool_call>
{"name":"read",...}</tool_call>` executes create before read, matching
the order they appear in (tools run in returned order).
- A candidate that starts inside an already-accepted call's span is
skipped, in both directions: a JSON marker inside a Gemma argument and a
Gemma marker inside a JSON argument are treated as data, not promoted to
a second executable tool call.
Extends tests/test_gemma_tool_parse_edge_cases.py with the ordering and
JSON-in-Gemma nesting cases.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Quote bare Gemma array elements; order finish before trailing usage
- _quote_gemma_object_keys skipped array values, so a Gemma call with a
bare-string array argument like labels:[bug,ui] produced invalid JSON and
the whole tool call was dropped. Array values are now scanned and bare
string elements quoted, while numbers, quoted strings, and JSON literals
are preserved.
- In the OpenAI passthrough stream, a trailing usage-only chunk
(stream_options.include_usage) that arrived before any finish chunk was
relayed before the synthetic finish, producing usage -> finish -> [DONE].
Emit the synthetic finish before that usage chunk so the order matches the
other streams (finish -> usage -> [DONE]).
Extends tests/test_gemma_tool_parse_edge_cases.py with the bare-array cases.
* Harden Gemma array parsing, XML-parameter guard, and stream teardown
Address five review findings on the Gemma tool-call and OpenAI passthrough
streaming paths:
- parse_tool_calls_from_text collected JSON and Gemma markers without the
_inside_open_parameter guard, so a marker embedded in an existing
<function=...><parameter=...> value was promoted to a separate tool call.
Candidates that start inside an open XML parameter are now skipped, matching
the guard the XML-style parser already applies.
- _quote_gemma_array_elements preserved array elements starting with { or [
verbatim, so an array of objects (items:[{path:a}]) or a nested array failed
json.loads and the whole call was dropped. Object and nested-array elements
are now normalised recursively.
- _openai_passthrough_stream synthesized a finish chunk before a trailing
usage-only chunk and set saw_finish_reason, which made the EOF guard skip the
[DONE] sentinel. The EOF path now emits [DONE] whenever the upstream omitted
it, even after a finish chunk was already synthesized.
- /generate/stream drove generation through asyncio.to_thread with no
disconnect watcher, so a client disconnect during a long generation went
unnoticed until the next send. It now runs _await_disconnect_then_cancel
against the request, matching the other local streaming endpoints.
- _SameTaskStreamingResponse closed the body iterator with aclose() on a
send-side disconnect, raising GeneratorExit so the generators' cancellation
handlers (which finish the api_monitor entry) never ran. It now throws
CancelledError, falling back to aclose() when athrow is unavailable.
Extends tests/test_gemma_tool_parse_edge_cases.py with array-of-objects,
nested-array, and marker-inside-XML-parameter cases.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Watch disconnects on Anthropic streams; keep timestamps in Gemma values
Two follow-ups on the streaming and tool-parse paths:
- _anthropic_tool_stream and _anthropic_plain_stream drove generation through
asyncio.to_thread(next, gen, ...) and only polled is_disconnected() between
events, so a client disconnect during prefill or a long generation/tool step
held the decode slot until the next event or a failed send. Both now run the
_await_disconnect_then_cancel watcher used by the other local streams, stop it
in finally, and break promptly when cancel_event is set.
- _GEMMA_NEXT_KEY_RE treated any comma followed by word-chars-then-colon as the
next key, so a bare value such as "meet at 10:00, 11:00 tomorrow" was split
into bogus keys. The next-key token must now be identifier-shaped (start with
a letter or underscore), so a comma before a timestamp, ratio, or other
numeric-then-colon text stays part of the value.
Adds a timestamp-in-bare-value regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Guard nested markers, reset on disconnect, clean unstarted streams
Three follow-ups on the tool-parse and streaming paths:
- parse_tool_calls_from_text only skipped markers that fell inside a span it
had already parsed successfully, so when an unquoted Gemma argument contained
a literal marker (code:<|tool_call>call:terminal{...}<tool_call|>) the outer
object failed to normalize, its span was never recorded, and the inner marker
was promoted to a standalone terminal call. Candidates nested inside any other
candidate's brace span are now skipped regardless of whether the enclosing
candidate parsed, so a marker in malformed outer data is never executed.
- /generate/stream skipped backend.reset_generation_state() when the disconnect
watcher set cancel_event between chunks: the loop broke and the finally's reset
is guarded on cancel_event being unset. A subprocess backend kept decoding
after the client left. The cancel-break path now resets the backend.
- _SameTaskStreamingResponse threw CancelledError / called aclose() on the body
iterator on a send-side disconnect, but neither runs the try/finally of a
generator that never started (early disconnect on http.response.start), so the
passthrough's eagerly-opened upstream httpx stream and cancel-registry entry
leaked. It now tracks whether the body started and, when it did not, runs an
optional unstarted_cleanup hook; the OpenAI passthrough wires it to close the
upstream resp/client and exit the cancel tracker.
Adds a nested-unquoted-marker regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* studio: report the true reasoning duration and fix the Stop button for thinking models
For a local GGUF the "Thought for N" label was timed entirely on the client by a
brittle edge-detector, so an always-think model (Qwen3 MTP) that buffers its whole
reasoning and flushes it in one chunk showed "1 second" instead of the real
minute-plus. The client cannot time reasoning it receives atomically, so make the
timing backend-authoritative.
Backend: generate_chat_completion_with_tools measures wall-clock reasoning and
emits a Studio reasoning_summary event (duration_ms) at the moment reasoning ends
-- the first answer token, or end-of-stream for a reasoning-only reply -- for both
the tool-detection pass and the final-answer pass. Timing resets per tool
iteration so the final answer's thinking time wins on the client (which takes the
latest reasoning_summary). routes/inference.py forwards the event in the GGUF tool
stream.
Frontend: parse the reasoning_summary SSE into a _reasoningDurationMs chunk and
use it as the authoritative reasoning duration (last write wins), clamped to >= 0
and guarded to a finite number so a malformed or proxied chunk cannot produce a
NaN label; the persisted value wins for the final "Thought for N" label, with the
previous live timer kept only as a fallback when no metadata arrives.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
torchao has no working Windows ROCm build. transformers.quantizers imports it,
and it loads torch's c10d distributed backend at module level, which the AMD
Windows wheels omit (no RCCL). The import aborts, transformers can no longer
expose PreTrainedModel, and the sentence-transformers embedder silently falls
back to the llama-server GGUF embedder. Linux ROCm and NVIDIA are unaffected
(the c10d ops are present / torchao is real there).
The training and export workers already install the shared torchao stub before
importing transformers, but the RAG embedder runs in the main backend process,
which never did. Two fixes, both no-ops off Windows ROCm:
- embeddings.py: install_torchao_windows_rocm_stub() before the first
sentence-transformers import, so an already-installed torchao is neutralized
(fixes existing venvs).
- install_python_stack.py: stop installing torchao on Windows ROCm; it can only
crash on import there, so new venvs never ship it.
Add tests covering the embedder stub call and the install skip.
* fix(studio): handle multimodal list content in inference text paths
Studio receives chat message content in two shapes: the legacy string
form, and the OpenAI multimodal list form
([{"type": "text", "text": ...}, {"type": "image_url", ...}]).
Several string-only paths called .strip()/re.sub()/f-string interpolation
on content directly, raising "'list' object has no attribute 'replace'"
for vision models (issue #4383), or rendering the list repr into the
prompt for the manual chat-template formatters.
Add core/inference/message_content.py with content_to_text(), a pure
helper (no heavy imports) that returns strings unchanged and joins the
text parts of a list while dropping image/audio parts. Apply it at every
string-only content site: _generate_vision_response, the audio user-text
extraction, format_chat_prompt, and the llama3/mistral/chatml/alpaca/
generic template formatters. The plain-string path is a no-op, so
existing behavior is unchanged.
Adds tests/test_message_content.py covering str/None/list/tuple,
multimodal drop, multi-part join and empty-part skipping.
* Tighten code comments (no logic change)
* studio: join multimodal text parts with newline for llama.cpp parity
llama.cpp joins multiple text content parts with a newline (common/chat.cpp),
so match that in content_to_text instead of a single space.
---------
Co-authored-by: Daniel Han <michaelhan2050@gmail.com>
* Use UTF-8 for Python code-execution subprocess I/O
Studio's code-execution tool already tells the child to emit UTF-8
(PYTHONIOENCODING=utf-8 in _build_safe_env), but _python_exec writes the
temp script and decodes the subprocess pipe with the OS default codec.
On Windows (cp1252), non-ASCII in model-written code or its output --
arrows, CJK, emoji -- raises UnicodeEncodeError / UnicodeDecodeError and
breaks execution.
Complete the UTF-8 wiring in core/inference/tools.py:
- write the temp script with encoding="utf-8"
- decode _python_exec stdout as utf-8, errors="replace"
- set PYTHONIOENCODING=utf-8 in _build_bypass_env too (matches
_build_safe_env, so the bypass path's child also emits utf-8)
The child is python with PYTHONIOENCODING=utf-8, so it emits UTF-8
regardless of the console code page and the decode is always correct.
Shell execution via cmd.exe has a separate console-code-page story and
is left to a follow-up.
Refs unslothai/unsloth#6489
* Scope Python exec UTF-8 env to Python tool
* Make bash bypass test robust to a host-set PYTHONIOENCODING for PR #6548
Bypass mode preserves benign host env vars, so a host-set PYTHONIOENCODING was
inherited into the bash bypass env and tripped the new assertion even though
_bash_exec never adds it. Clear it in the test so the assertion checks _bash_exec,
not the runner environment.
---------
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Resolve the transformers tier by probing AutoConfig instead of guessing
When the only signal is a 5.x tokenizer class, get_transformers_tier guessed the
lowest 5.x sidecar (530). That misroutes models whose built-in config parser needs
a higher tier: dense NemotronH ships a 5.x tokenizer but its '-' (MLP) layer only
transformers 5.10 can parse, so 5.3/5.5 raise KeyError '-'. The config.json
transformers_version field records the saving version, not the minimum to load, so
it cannot drive routing either.
Replace the weak tokenizer->530 guesses (local and remote) with a probe: parse
config.json with the built-in parser (trust_remote_code=False) in each sidecar,
escalating 530->550->510, and pick the first that succeeds. This generalizes to any
architecture without hardcoded lists. Strong signals stay fast paths (no subprocess);
the probe runs only when the tier is otherwise ambiguous and is cached by (model,
commit sha). It never executes repo code, never downloads weights, never raises, and
falls back to the legacy 530 guess on a transient/auth/offline failure or when no
sidecar is available. UNSLOTH_DISABLE_TIER_PROBE restores the old behavior.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: tier probe fallbacks and cross-platform robustness
Codex:
- Never escalate to 510 on uncertainty. When every sidecar was probed and none
parsed with the built-in parser, the model is a remote-code / custom model_type
that loads via its own code; keep the legacy 530 route instead of jumping to
510 (which would change the behavior of models that worked on the 5.3 stack).
- Only cache the 530 fallback when the result is conclusive (every tier actually
probed). If a sidecar was missing/uninstallable the environment is incomplete,
so return 530 uncached and retry on the next call.
- Do not pin the tier cache under an unknown revision: _resolve_commit_sha no
longer memoizes a None sha (a transient Hub failure is retried), and _probe_tier
only caches a tier when the commit sha is known.
Gemini:
- Wrap Path.exists() in the sha resolver in try/except OSError (a remote repo id
can raise WinError 123 on Windows).
- Probe script writes the error to sys.stderr.buffer as UTF-8 bytes so a non-ASCII
message cannot itself raise UnicodeEncodeError under cp1252.
- subprocess.run decodes stderr with errors="replace" to avoid UnicodeDecodeError
on non-UTF-8 consoles.
Tests: 72 passed (added partial-sidecar uncached, sha-unresolved not cached,
all-failed stays 530 + cached, sha resolver retries None / handles OSError).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review round 2: authenticate tier checks, stop memoizing local sigs
Codex:
- Thread hf_token through _check_config_needs_510/550 and
_check_tokenizer_config_needs_v5 (and the underlying raw fetches). Previously a
gated/private model whose only 5.x signal is tokenizer_config.json never reached
the authenticated probe: the unauthenticated raw fetch failed and cached False,
so the model fell through to the default 4.x tier. The per-check caches are now
keyed by (model, token) so an unauthenticated miss cannot poison a later authed
read, mirroring _load_config_json.
- _resolve_commit_sha no longer memoizes a local directory signature. A local
signature is mutable (size/mtime of config/tokenizer), so a reused/overwritten
checkpoint path would otherwise keep selecting the previous tier; it is now
recomputed every call. Only the immutable remote commit sha is memoized.
Tests: 75 passed (added token-cache isolation + auth header, local signature not
memoized, token threaded into all checks/probe).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review round 3: reach activation with the token, drop SHA tier cache
Codex round 3:
- Thread hf_token into the activation path that actually selects a sidecar. The
token-aware tier checks added last round were unreachable:
activate_transformers_for_subprocess called get_transformers_tier without a
token, and the inference/training/export workers passed only the model name even
though they hold a request-scoped hf_token. activate_transformers_for_subprocess
now takes hf_token and the three workers forward config["hf_token"], so a
gated/private model whose only 5.x signal is an authenticated config/tokenizer is
routed to the right sidecar instead of falling to default 4.x.
- Stop importing huggingface_hub during tier detection. _probe_tier no longer
resolves a commit sha, so it never pulls huggingface_hub into the worker before
the sidecar venv is prepended to sys.path (activation only prepends, never
purges), which would otherwise pin the default-env hub over the sidecar's
pinned huggingface_hub==1.8.0.
- The tier cache is now keyed by model_name for the process lifetime (a model's
required tier is a property of its architecture; cleared on restart). This drops
the mutable-SHA memo that masked remote revision changes and the mutable
local-signature memo, removing _resolve_commit_sha / _local_dir_signature /
_probe_sha_cache entirely.
- Do not cache a probe success that depended on a skipped lower tier: if a lower
sidecar was unavailable, the lowest valid tier may change once it installs, so
the result is returned uncached and re-probed next call.
Tests: 73 passed (probe imports no hub; success uncached when a lower tier is
skipped; activation forwards the token).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim comments to be more succinct
* Re-probe overwritten local checkpoints and authenticate the probe child
The AutoConfig tier probe cached its result under the bare model_name, so a
local checkpoint overwritten in place (same path, new config.json) kept serving
the stale sidecar. Fold a cheap config.json signature (size + mtime) into the
cache key for local paths; remote ids stay name-keyed so no huggingface_hub
import lands before the sidecar is activated.
The probe relies on the implicit HF_TOKEN env, so an inherited
HF_HUB_DISABLE_IMPLICIT_TOKEN=1 left it unauthenticated and a gated repo 401ed
into the 530 fail-safe. Clear that flag in the child env when a token is set.
* Keep tier probes off the log-only path and probe new 5.x archs default-first
- get_transformers_tier gains probe=True/False. needs_transformers_5 (a coarse
4-vs-5 boolean used only for a spawn log and a vision-check branch) now passes
probe=False, so a parent/log-only caller never spawns sidecar probes. The real
activation path keeps probe=True and resolves the exact tier in the worker.
- A config.json saved by transformers 5.x but matched by no fast path is now probed
default-first: _probe_tier gains include_default + floor, prepending the ambient
4.57.x tier to the escalation. A model that still parses on the default is left on
it (no mis-route onto a sidecar); only a config the default parser cannot read
escalates to the lowest 5.x tier that parses. The transformers_version field is a
cheap 'worth probing' hint only, read from the already-fetched config (no extra
network); ordinary 4.x configs never probe.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Separate probe cache by mode and keep version-field 5.x visible to needs_transformers_5
- _probe_tier cache was keyed only by config.json signature, so a default-first probe
that returned 'default' could be handed back to a later tokenizer/known-5.x caller
(floor=530), leaving a model with a 5.x-only tokenizer on transformers 4.x. Key the
cache by probe mode (floor + include_default); the legacy 530 mode keeps the bare key.
- The version-field 5.x detection is a cheap config read, not a probe, so run it even
when probe=False: a standard-tokenizer model whose only signal is transformers_version
>= 5 now classifies as 5.x via needs_transformers_5 (returns '530' without spawning a
probe), so the vision-routing fallback uses the 5.x subprocess instead of failing the
default parser and marking it non-vision. The real activation path still probes
default-first and may resolve 'default'.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Don't treat local checkpoints as Hub ids, and fix stale activation test double
- _load_config_json / _check_tokenizer_config_needs_v5: a local checkpoint dir whose
config.json / tokenizer_config.json is not yet present was being fetched from the Hub
as if the path were a repo id, and the 404 miss was cached. A later call after the
file is written (in-progress checkpoint) then served the stale miss, so a
TokenizersBackend checkpoint fell through to the default tier. Skip the Hub fetch for
local dirs and do not cache the miss, so the file is read once it appears.
- test_activate_transformers_version_or_warn_*: the worker now threads hf_token into
_activate_transformers_version (model_name, hf_token); update the one-arg test doubles
to the real two-arg signature so the silent-success path stays silent.
* Tighten comments in the AutoConfig probe and tier-selection paths
* Address review: canonical probe cache key and reuse _token_cache_key
- _probe_cache_key resolves config.json to its absolute realpath before
keying, so a relative path or a changed cwd can't collide with or miss a
prior probe result. Remote ids still fall back to the name (stat raises,
caught).
- _cached_config_json reuses _token_cache_key instead of re-hashing the
token inline, keeping the (model, token) key derivation in one place.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Add HF dataset streaming mode to Studio
* Added default value for datasetStreaming in training-config-store.ts
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Handle None max_steps for streaming validation
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: fast-fail streaming validation and guard incompatible modes
Reject dataset_streaming at the API boundary when hf_dataset is empty,
the dataset is vision/audio, or max_steps is not set. Probe eval split
with get_dataset_split_names before the streaming load so typos fail
immediately instead of mid-training. Guard column_names=None after map
on iterables. Hide the UI toggle for non-text configurations and clear
the stale flag when config becomes incompatible.
* studio: add streaming dataset tests, iterable helper, and streaming template/format support (WIP)
Work-in-progress on top of feat/studio-dataset-streaming-mode (PR #4946):
- new test_training_streaming.py and iterable.py dataset helper
- streaming support in chat_templates.py and format_conversion.py
- additional streaming guards in trainer.py / models / routes
- frontend streaming wiring in params-section and training-config-store
Committed to preserve uncommitted work before merging latest main.
* studio: fix review-team findings for streaming + main merge
BLOCKER: streaming + raw-text/CPT crashed on len(IterableDataset). Guard it in the
start route (reject format_type=="raw" or training_type=="Continued Pretraining")
and in isStreamingSupported (datasetFormat !== "raw").
Also:
- models/training.py: validate hf_dataset/subset/split (charset+length, block ..//);
cap dataset slice indices (le=1e9); note validator ordering
- chat_templates.py: guard _apply_custom_mapping .map() for streaming
- trainer.py: warn when packing+streaming
- training-config-store.ts: persist-migration bump to v11 (standalone datasetStreaming
backfill); add isVisionModel to NON_PERSISTED; toast on silent streamingCompatiblePatch
mutations in the 4 indirect setters
- tests: route rejections (max_steps, raw/cpt), slice cap, unsafe hf_dataset
* studio: enable raw-text/CPT dataset streaming + streaming UX polish
- raw_text: keep the lazy filter but skip len()-based row counting for
IterableDatasets so raw-text / CPT can stream; guard the eval-size log
- routes/trainer: drop the raw/CPT streaming block; add a defensive
not-streaming guard on the eval auto-split (train_test_split)
- dataset-section: streaming toggle is visible-but-disabled and lists the
exact unmet requirement(s) in its tooltip; block embedding models
- training-start-overlay: show "streaming (no full download)" instead of a
stuck download bar for streaming runs
- trim the streaming test suite to the high-value cases
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: address streaming review (MLX/embedding guards, sliced eval split, rehydrate timing)
- routes: reject dataset_streaming for embedding training and on Apple Silicon
(MLX); both loaders materialize the full dataset instead of streaming
- trainer: validate the base eval split name so streaming eval accepts HF slice
syntax such as "validation[:1000]"
- training-config-store: defer the onRehydrateStorage setState to a microtask so
it doesn't hit the store's TDZ during synchronous hydration
- test: streaming start rejects embedding models
* studio: harden HF dataset streaming (column_names, split slicing, empty/eval bounds, gating)
Address a deeper streaming review:
- raw_text: resolve_column_names() guards IterableDataset.column_names=None
(from_generator / unresolved features) so raw-text and CPT streaming no longer
raise TypeError before training
- models/routes: reject HF slice syntax in train_split/eval_split when streaming
(load_dataset(streaming=True) raises "Bad split"); reject mixed sources
(local/S3) and embedding/MLX streaming at the API, not just in the UI
- trainer: an empty post-slice/filter stream fails preflight with a clear message;
streaming eval is capped (STREAMING_EVAL_MAX_SAMPLES) so each eval terminates;
the manual-slice shortcut falls back to a regular load when train_split is sliced
- format_conversion: streaming conversions preflight the first mapped row so
format errors surface before training, not mid-iteration
- frontend: block streaming on Apple Silicon; clear datasetStreaming when a
dataset is detected as image/audio at start
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: fix CI for streaming PR (lint blocker + no-torch sandbox + preflight test)
- trainer.py: drop unused `IterableDataset` import (hoist safety-net blocker).
- test_training_streaming.py: only select real classes (isinstance type) when
locating the trainer class, so a MagicMock-stubbed global is never passed to
object.__new__ (fixes TypeError on the Python 3.10-3.13 jobs).
- no-torch import sandboxes (test_e2e_no_torch_sandbox.py,
test_studio_import_no_torch.py): teach the chat_templates/format_conversion
exec stubs and the full-import-chain copy list about the new `.iterable`
module so the AFTER/runtime cases import without torch again.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Roland Tannous <115670425+rolandtannous@users.noreply.github.com>
Co-authored-by: Roland Tannous <rolandtannous@gravityq.ai>
Co-authored-by: Etherll <61019402+Etherll@users.noreply.github.com>
* Studio: show tool-call progress for large GGUF tool arguments
The GGUF agentic tool loop only surfaced an early provisional tool card
for render_html, so any other tool (python, terminal, ...) was invisible
in the UI while its arguments streamed. For a large argument such as a
full HTML or code file this left the chat sitting on "Generating..." with
zero progress for tens of seconds while the model was clearly working.
Generalize the provisional tool_start to any enabled tool once its
streamed arguments grow past a threshold (render_html still surfaces
immediately, small-argument tools are unchanged). The provisional and the
real tool_start share the tool_call_id so the frontend reconciles them
into one card. Close the provisional on no-op, denial, parallel-drop,
post-loop, and on stream errors so a card can never spin forever, surface
each parallel call, and skip the early card while a human confirmation
gate is active. Apply the same confirmation-gate guard to the safetensors
agentic loop.
Additional hardening:
- Only emit a provisional card once a real, non-empty tool_call_id is
known. llama.cpp can stream a tool call with an empty id, and a card
keyed by "" cannot reconcile with the real tool_start (the frontend
mints its own id per event), so it would dangle.
- On a connection drop or other mid-iteration failure, close the dangling
provisional card with an error result instead of an empty success so the
UI renders it as failed rather than completed.
- Mirror the provisional cleanup in the safetensors loop: close a
provisional render_html card if the model generator raises mid-stream or
the controller turns the call into an internal no-op.
Adds regression tests for the empty-id guard, the error-result on a
dropped connection, and the safetensors mid-stream exception cleanup.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: wasimysaid <wasimysdev@gmail.com>
* Studio: persistent per-user trust_remote_code approval cache
The consent gate pins each approval to a content fingerprint (sha256 over every
repo .py), but nothing was persisted, so the dialog reappeared on every fresh
load of the same unchanged repo. This adds an on-disk, per-user approval cache
that lets the gate skip the dialog when the same user reloads the same code,
while keeping the safety guarantees intact.
Two-tier validation, both must hold or the user is re-prompted:
- Commit SHA (cheap, one HfApi.model_info().sha, no download): a match means a
byte-identical tree to the approved revision, so the scan/download is skipped.
- Content fingerprint (authoritative): used whenever the SHA is unavailable
(local path / offline) and always recomputed on a SHA miss. A new or edited
.py changes both the SHA and the fingerprint, so it is caught in every mode.
Safety:
- Keyed per subject; one user's approval never auto-runs code for another.
- CRITICAL is never stored or honored (guarded on both write and read), so a
hand-edited store cannot smuggle in an auto-approval.
- The malware (HF unsafe-file) gate stays unconditional.
- Fail-safe: a corrupt store, an unresolvable SHA, or any error degrades to
"ask again", never to "auto-approve". UNSLOTH_TRC_APPROVAL_CACHE_DISABLE=1
turns the cache off entirely.
New module utils/security/remote_code_approvals.py holds the store
(studio_root()/security/remote_code_approvals.json, atomic write, 0600, RLock)
plus the SHA resolvers. Recording happens at the single gate chokepoint when the
caller supplies the matching fingerprint, so subject is just threaded through
inference/training/export (orchestrators, routes, workers). The scan endpoint
returns already_approved so the frontend can skip the dialog on a cache hit.
Tests: new tests/test_trc_approval_cache.py covers cache miss, SHA-match skip,
SHA-moved re-scan, new-file re-consent, CRITICAL never cached (write + forged
read), disable flag, subject isolation, combined adapter+base key, corrupt
store, and no-subject bypass. Full security suite: 101 passed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: make the approval cache skip only the prompt, never the scan
Codex found that the SHA "no-scan" fast path could run untrusted code without
re-consent. Removed it; the gate now always re-scans and the cache only seeds the
authoritative fingerprint check, so it can skip the dialog but never the scan.
- CRITICAL is hard-blocked on every load (the scan always runs), so a hand-edited
store that downgrades a CRITICAL repo's severity can no longer auto-run it
(P2: do not trust editable severity for SHA approvals).
- The fingerprint covers external auto_map repos, so changed third-party code
always re-prompts even when the primary commit SHA is unchanged; there is no
longer a SHA path that bypasses the fingerprint (P1: external auto_map repos).
- resolve_commit_sha is resolved fresh on every call (no memoization), so a repo
whose default branch moves after approval re-prompts instead of reusing a stale
cached SHA (P1: revalidate mutable Hub SHAs). The SHA is now only a conservative
secondary gate: a fresh resolvable SHA must match the approved revision, else the
seed is withheld; a None (local/offline) falls back to the fingerprint.
- Approvals record the scanner ruleset version (SCAN_RULES_VERSION); the gate
ignores approvals from an older ruleset so reclassified bytes are re-scanned and
re-shown instead of silently auto-approved (P2: invalidate on scan-policy change).
Tests: test_trc_approval_cache.py rewritten around the prompt-skip semantics
(unchanged repo still scans; SHA move / changed code / scanner-version bump /
disable flag all re-prompt; forged downgraded severity still blocks CRITICAL).
105 passed with test_consent_gate.py.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim comments to be more succinct
* Keep run-owner subject out of persisted config; serialize approval writes
Threading subject (the run owner's username / API-key id) into the training
config meant _sanitize_db_config persisted it into config_json, which
training-history GET returns to any authenticated user, leaking who started a run
in multi-user installs. Filter subject alongside the token fields; the worker
still receives it from the live config.
The approval store's RLock only guards one process, but approvals are recorded
from separate inference/export/training subprocesses, so concurrent writers could
clobber each other on os.replace and drop an approval (re-prompt). Hold a
best-effort cross-process file lock around the read-modify-write.
* Fail safe on a malformed approval store
A store with the right version but a non-dict shape (e.g. a hand-edited
"subjects": []) passed _load()'s check, then lookup chained .get() on a list and
raised, breaking every remote-code load until the file was removed. Validate that
subjects is a dict in _load(), and tolerate a non-dict per-subject entry in
lookup/record/forget, so a corrupt store fails safe (re-prompt) instead.
* Keep subject out of the MLX W&B run config
_run_mlx_training uploads the whole training config to W&B minus a sensitive set
that only listed hf_token/wandb_token/s3_config, so the authenticated subject
(username / API-key id) was sent to W&B as run config even though DB history
already strips it. Add subject to the W&B-sensitive filter, mirroring
training._sanitize_db_config.
* Tighten the W&B subject-filter comment
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Auto-install SSM kernels (causal-conv1d, mamba-ssm) for inference loads
Mamba/SSM hybrids (Nemotron-H/Nano, Falcon-H1, Granite-4.0-H, ...) lazily import
mamba_ssm / causal_conv1d during from_pretrained, so loading them for chat failed
with 'mamba-ssm is required by the Mamba model but cannot be imported'. The training
worker already wheel-first installs these before a fine-tune; the inference worker
did not. Add utils/ssm_runtime.ensure_ssm_runtime and call it from the inference load
path so the same models load for inference. Training worker is untouched; a drift
test keeps the shared detection and pinned versions in lockstep.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* ssm_runtime: invalidate import caches, skip MLX, cover LoRA base
- Invalidate importlib finder caches in _is_importable and after a successful
wheel install, so a kernel installed earlier in this same process is actually
importable when the modeling code lazy-imports it during from_pretrained.
- Skip the SSM kernel install entirely on the MLX (Apple Silicon) load path:
these are CUDA/ROCm Torch kernels with no MLX use and no macOS prebuilt wheel,
so the source build would fail before the MLX backend loads the model.
- For LoRA loads, also run detection over the resolved base model, since an
adapter id like 'me/my-lora' won't match the SSM heuristics but its SSM base
(Nemotron-H, ...) is what needs the kernels.
Adds tests for cache invalidation and the MLX-skip / LoRA-base worker wiring.
* Tighten SSM autoinstall comments
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* ssm_runtime: verify wheel imports, HIP-aware source build, build heartbeat
Address review feedback:
- Verify a prebuilt wheel actually imports before trusting it; a CUDA/ABI-mismatched
wheel now falls back to a source build instead of returning success and failing later
with the cryptic lazy-import error.
- HIP-aware source build: require hipcc on ROCm, inject clang --gcc-install-dir, and use
the 1800s timeout, mirroring the training worker (ROCm has no prebuilt wheel).
- Emit a status heartbeat every 60s during the source build so a long (ROCm) build does
not trip the orchestrator's 300s inactivity timeout.
Tests cover the wheel-not-importable fallback and the missing-hipcc ROCm bail.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Make causal-conv1d best-effort and harden the SSM source build
- causal-conv1d is a fast path: models that merely want it (Qwen3-Next, LFM2)
fall back to torch, so a failed install must not reject an otherwise loadable
chat model on Windows/CPU/macOS or an ABI without a wheel. Only a true SSM
model's mamba-ssm requirement stays fatal, matching the training worker which
treats causal-conv1d as best-effort.
- The source build is reached only when not importable, including a wheel that
installed but failed to import; add --reinstall/--force-reinstall so it
replaces the broken install instead of no-opping as already satisfied.
- Add --no-cache to the ROCm uv source build to avoid reusing stale artifacts
from a partial HIP build, mirroring the training worker.
* Address review: install SSM kernels before transformers, harden import + Windows
Codex:
- Install the SSM kernels before importing transformers. run_inference_process
imported core.inference.inference (which imports unsloth/transformers) before the
load, and a sidecar transformers can evaluate its optional-backend gates against
the import state; installing causal_conv1d/mamba_ssm afterwards left those gates
unsatisfied and a Nemotron/Falcon/Granite load still failed with "mamba-ssm is
required". The initial model's kernels are now installed in run_inference_process
before the ML import, via a shared _ensure_ssm_kernels helper; _handle_load keeps
calling it (idempotent) for a LoRA's base and for later in-process loads.
- _is_importable now treats any import failure as "not importable", not only
ImportError. An ABI-incompatible native kernel (undefined symbol after a torch/CUDA
upgrade) raises OSError/RuntimeError; letting those escape reported
ssm_runtime_install_failed instead of falling back to reinstall/source build.
- Skip causal-conv1d on Windows (no prebuilt wheel), mirroring the training worker.
A causal-conv1d-only model (Qwen3-Next/LFM2) no longer drops a chat load into a
multi-minute untimed source build; it uses the torch fallback. mamba-ssm is still
attempted for true SSM hybrids.
Tests: test_ssm_runtime.py +5 (broken-kernel exceptions read as not-importable;
causal-conv1d skipped on win32 while mamba-ssm still installs). 36 passed.
* Trim comments to be more succinct
* Run security gates before installing SSM kernels
The SSM kernel auto-install is name-based (model_is_ssm is a substring match, no
config fetch), so a model id merely containing an SSM substring triggered a
native-package install (possibly a slow source build) before the malware and
remote-code consent gates ran. Extract those gates into _run_security_gates and
call it before the kernel install in both the pre-import path of
run_inference_process and in _handle_load, so a blocked or nonexistent model is
refused before any build. The gates are metadata-only and do not import
transformers, so they are safe to run before the pre-import install.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Resolve remote LoRA bases before importing transformers
_resolve_base_model only reads a local adapter_config.json, so a remote LoRA
adapter whose own id has no SSM substring but whose base is a Nemotron/Falcon/
Granite model had its base discovered only by ModelConfig in _handle_load, after
transformers was imported and its optional-backend availability snapshotted, so
the SSM kernel install there was too late. Add _remote_lora_base, a metadata-only
adapter_config.json fetch (no huggingface_hub / transformers import), and use it
in the pre-import path so the base is gated and its kernels pre-installed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Gate only loaded roots, tier on the resolved base, read offline LoRA cache
Three follow-ups to the pre-import resolution:
- The security gate reused the SSM target list, which for a local full fine-tune
includes the config.json-recorded base. That base is never loaded, so scanning
it could falsely block a safe local checkpoint. Gate only the model plus a
genuine LoRA base (matching _handle_load's mc.is_lora), separate from the
broader SSM-install list.
- Tier activation ran on the raw adapter id, so a remote LoRA whose base needs a
sidecar transformers version imported the default and failed. Resolve the base
once up front and activate on it.
- _remote_lora_base bailed on offline before checking the hub cache, missing a
cached adapter's base. Read the cached adapter_config.json when offline or when
the fetch fails.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Keep the pre-import gate transformers-free; harden remote LoRA resolution
The pre-import security gate called security_load_subdirs, which imports
model_config and thus transformers, snapshotting optional-backend availability
before the SSM kernels are installed and defeating the ordering. Add
compute_subdirs to _run_security_gates and pass False in the preflight so it scans
from the root only (transformers-free); _handle_load still runs the authoritative
gate with full subdir scoping after the import.
_remote_lora_base now skips existing local relative paths (is_local_path) so a
checkpoint like outputs/run1 is never treated as a Hub repo, and distinguishes a
definitive 404 (not a LoRA -> None) from transient/offline failures (read the
cache), so a repo that is now a full model no longer resolves a stale cached base.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Probe a real model id for SSM kernels; respect HF_ENDPOINT
model_is_ssm is a substring match, so an arbitrary name could false-match and
force a mamba-ssm install that fails the load for a non-SSM model:
- a LoRA adapter id like user/falcon-h1-lora (the SSM-relevant code is the base's);
- a local checkpoint under an SSM-named parent dir, e.g. /runs/falcon-h1/llama-ckpt.
Add ssm_probe_identifier, which resolves the base (or a bare local checkpoint's
basename) and feed that to ensure_ssm_runtime from both the pre-import path and
_handle_load, so detection runs against a real model id, never an adapter id or
parent folders.
_remote_lora_base now honors HF_ENDPOINT so enterprise/mirror deployments resolve
the adapter base instead of always hitting huggingface.co.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Tighten comments in the pre-import SSM gate/install path
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <michaelhan2050@gmail.com>
* Studio: self-heal unsloth namespace-package shadows in all subprocess workers
A directory named `unsloth` (or `unsloth_zoo`) without an __init__.py on
PYTHONPATH/sys.path, a stray source checkout or a polluted PYTHONPATH, makes
`import unsloth` resolve to an empty namespace package, so a worker's
`from unsloth import FastLanguageModel` dies with a cryptic
"cannot import name ... (unknown location)".
The LLM training path already recovered from this via `_ensure_real_packages`
in trainer.py (PR #6269), but the inference, export, and embedding-training
subprocesses imported Unsloth directly with no guard. Extract that helper into
a shared, dependency-free core/import_guards.py and call it before the Unsloth
import in every subprocess: it drops the offending sys.path entries, imports
the real packages (unsloth before unsloth_zoo so the pre-zoo GPU fixes run),
then restores sys.path. trainer.py now imports the shared helper instead of its
local copy.
Covers both unsloth and unsloth_zoo and both namespace origin forms (None and
"namespace"). The existing PR #6269 test now exercises the shared helper.
* Studio: distinguish a failed model load from no model in the attach gates
A failed load never sets the checkpoint, so the image and audio attach gates
fell through to "Load a model before adding images/audio", which reads as if
the user simply forgot to pick a model rather than that the load errored. Add a
dedicated lastModelLoadError to the chat runtime store, set only when an actual
load attempt fails (not on refresh, list, status, or unload errors, which keep
using modelsError) and cleared when the next load starts. The image gate (all
three call sites) and the audio gate now use it to report a failed load and
point at the server logs, while still blocking in exactly the same cases.
* Tighten namespace-shadow guard and load-error comments
* Studio: use an isolated Node.js for the frontend build instead of replacing the system Node/npm
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address Node isolation review (no-Node probe crash, PATH refresh, OXC provisioning, venv python, runtime node resolver)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix/adjust Node isolation for PR #6533
* Studio Node: don't cache a negative node resolution; accept Node metadata in setup.sh ownership guard
- node_runtime: memoize only a version-adequate executable so a Node installed
by a separate-process 'studio update' is picked up without a backend restart.
- setup.sh: _studio_owned_adoptable also accepts UNSLOTH_NODE_PREBUILT_INFO.json,
matching the setup.ps1 Node ownership guard (custom-home parity).
* Studio setup.ps1: skip OXC npm install gracefully when npm is absent
Mirror setup.sh's `command -v npm` guard so a pip-installed Studio with no
system Node skips the OXC runtime install (validator degrades at runtime) instead
of exit 1 aborting the whole setup. Tighten test_node_probe_guard.ps1's probe
regex so it only matches the two system-version probes, not this new npm guard.
* Wire test_node_probe_guard.ps1 into Windows CI for PR #6533
* Harden isolated Node install and probes for PR #6533
- install_node_prebuilt.py: keep an existing, still-usable isolated Node
when nodejs.org's dist index is unreachable instead of aborting the
update on a transient outage (existing_install_usable + tolerant fetch).
- install_node_prebuilt.py: pin NPM_CONFIG_PREFIX/npm_config_prefix and
drop NODE_PATH in _run_node so any npm -g stays inside the isolated
prefix; Windows npm otherwise writes to %APPDATA%\npm.
- install_node_prebuilt.py: resolve tar hard-link targets against the
archive root (symlink targets stay link-parent relative).
- setup.ps1: wrap the system node/npm probes in try/catch so a present
but broken shim degrades to the bundled Node instead of aborting setup.
- setup.ps1: run the isolated Node install with the handed-off/venv Python
(ReusedSetupPython); the main resolver runs later and bare python may be
a Store stub this early.
- setup.sh: log when the OXC validator runtime is skipped for missing npm,
matching setup.ps1.
- node_runtime.py: move the version-floor comment onto _version_meets_floor.
- Tests for the offline-reuse and broken-shim paths.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim verbose comments across the Studio Node installer for PR #6533
Comments-only pass: collapse the multi-line section banners to single lines,
drop comments that restate obvious code, and tighten the remaining docstrings
and "why" notes without losing intent. No code changes (verified with an AST
comment-only check on the Python files and a non-comment-diff scan on setup.sh
and setup.ps1). Net 109 fewer lines; the install, decision, and probe-guard
suites stay green.
* Harden Node install from review: validated Python, version floor, legacy home, lock race
For PR #6533, addressing the latest review pass:
- setup.ps1: run the isolated Node install with the validated reused/venv Python.
An incompatible reused interpreter (old venv, conda, stale UNSLOTH_SETUP_PYTHON)
is no longer used; fall back to the resolved python instead.
- setup.ps1: a STUDIO_HOME/UNSLOTH_STUDIO_HOME override equal to the legacy default
now uses the legacy sibling node dir (~/.unsloth/node), matching the runtime
resolver and setup.sh, so OXC can find the Node it installed.
- install_node_prebuilt.py: reject an explicit --node-version below the floor
(^20.19 || >=22.12 || >=23) instead of installing a Node the build cannot use.
- install_node_prebuilt.py: atomically rename a stale install lock before unlinking
so two concurrent runs without filelock cannot both acquire it.
Tests added for the version floor (parametrized + explicit-below-floor rejection).
Full install suite: 937 passed, 1 skipped; setup.ps1 parses; decision tests green.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address latest review: armv7l + later-fetch offline reuse for PR #6533
- install_node_prebuilt.py: reject 32-bit ARM (armv7l) up front. Node 24 LTS
ships no linux-armv7l build, so the old path failed late with a confusing
"no sha256"; it now fails fast with a clear unsupported-architecture error.
- install_node_prebuilt.py: extend the offline-reuse fallback to the SHASUMS and
archive fetches. If index.json resolves a newer Node but a later download fails
and a usable isolated Node is already on disk, keep it instead of aborting a
non-force update.
Tests added: armv7l/armhf are unsupported; a SHASUMS failure keeps an existing
usable Node and re-raises when none is present. Full install suite: 941 passed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add UNSLOTH_STUDIO_HOME node-dir tests (install side + resolver) for PR #6533
* Add regression tests pinning the reuse path read-only and isolating installer writes
Lock in the two invariants behind the isolated-Node design: reusing a good
system Node never mutates the user's Node/npm, and the installer's own npm
calls only ever write inside its install_dir.
- tests/studio/install/test_install_node_prebuilt_logic.py: assert _run_node
redirects NPM_CONFIG_PREFIX/npm_config_prefix into install_dir and drops an
inherited NODE_PATH; assert _ensure_npm_floor scopes the npm self-upgrade to
install_dir (never -g against the system) and is a no-op once npm meets the floor.
- tests/sh/test_system_node_readonly.sh (new, wired into studio-backend-ci.yml):
the setup.sh NODE_SOURCE=system arm runs no global install and sets no
NPM_CONFIG_PREFIX, with a positive control that the bundled arm does.
- tests/studio/test_node_decision.ps1: symmetric structural guard that the prefix
pin and the only global install (bun) live in the bundled branch, not the system arm.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: wasimysaid <wasimysdev@gmail.com>
Recognise the Gemma 4 separate-drafter MTP family, auto-download the drafter with retry, fall back to n-gram with a clear reason when it cannot be resolved, and retry the download on reload. Gemma 3n (ships no drafter) and embedded-MTP models (Qwen) are unaffected.
Fixes#6406
_estimate_mtp_overhead_bytes is also reached for the separate-drafter spec modes
(draft-simple / draft-eagle3) through _user_draft_via_extras. Those modes load a
small distinct drafter with its own KV -- already counted in the draft KV +
weights -- and keep no duplicated full target context; only MTP runs a second
context over the target model's own KV geometry (llama.cpp ctx_tgt). Charging the
~main-KV-sized f16 copy there over-reserved by tens of GiB on an MLA model and
needlessly shrank the advertised context, the same under-advertising #6312 set
out to fix.
Thread mtp_keeps_target_ctx through _estimate_mtp_overhead_bytes (True for MTP,
False for separate-drafter modes) and derive _engaged_is_mtp at the fit call site
so the target copy is added only when the engaged mode is actually MTP. MLA + MTP
(GLM-5.2 / DeepSeek / Kimi) is unchanged, so the GLM-5.2 OOM fix is preserved;
non-MLA and the draft-simple / draft-eagle3 paths no longer pay the copy.
test_mtp_mla_target_ctx.py adds a case asserting the separate-drafter reserve
collapses to the draft KV (no target copy) while the default MTP path keeps it.
* Studio: Auto disables MTP for MLA models (GLM-5.2 et al.); UNSLOTH_MLA_MTP_ENABLED to re-enable
Studio's Auto speculative mode promotes any embedded-MTP model >=3B to
--spec-type draft-mtp. For MLA models (GLM-5.2/DeepSeek/Kimi) that is a
regression: llama.cpp's MLA/DSA MTP path keeps a duplicated full target-KV
context and recomputes the sparse-attention indexer every draft step, so it
runs ~2x slower than no speculation (GLM-5.2 UD-IQ1_S bench: 27 vs 45 tok/s,
flat across draft depth 1..6 and 96-100% acceptance, on both prose and code).
vLLM/SGLang get a speedup from the same model, so this is a llama.cpp
implementation gap, not a model property.
Auto now drops embedded MTP for MLA models and falls back to ngram-mod (or
spec-off when the binary lacks ngram-mod), mirroring the existing sub-3B
fallback. The metadata separator is kv_lora_rank: it is present on MLA models
and absent on non-MLA embedded-MTP models (Qwen3.x-MTP), whose MTP module is
structurally identical but fast, so a "full layer" heuristic cannot tell them
apart. Qwen MTP, separate drafters (Gemma, --model-draft), and non-MTP models
are unchanged.
Explicit overrides still engage the slower MTP route: choosing MTP / MTP+Ngram
in Settings, or passing --spec-type in extra args. UNSLOTH_MLA_MTP_ENABLED=1
re-enables Auto promotion for MLA once the upstream path is optimized.
A new spec_fallback_reason value "mla_mtp_disabled" surfaces this as an
Auto-mode policy downgrade (not a binary/update problem), with a settings
banner that points users at the MTP override. It is deliberately kept out of
the "Update llama.cpp" affordance since updating does not help.
Tests: resolver-matrix rows for MLA->ngram-mod / MLA-no-ngram->off /
non-MLA-Qwen->draft-mtp / MLA-separate-drafter->draft-mtp /
non-MTP-MLA->default / forced mtp|mtp+ngram on MLA->draft-mtp / env flag;
kv_lora_rank metadata fixtures; and reload-skip coverage (Auto ngram-mod is
idempotent, forced mtp bounces a reload).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: reserve the duplicated MTP target KV context for MLA models
GLM-5.2 UD-IQ1_S advertised its native 1,048,576-token context, loaded, then
crashed cublasCreate on the first generation with "CUDA error: the resource
allocation failed" on a 2x B200 box. The model loaded fine; the decode OOMed.
Cause: when MTP speculative decoding is engaged, llama.cpp keeps a second full
copy of the target model's KV context for draft verification (ctx_tgt=yes in the
spec log), at f16. On an MLA model that copy is ~the main KV again -- for GLM-5.2
at 1M ctx llama.cpp sized it at ~97.5 GiB -- but the auto-fit reserve only
counted the tiny embedded draft head (~2 GiB), 46x too low. So weights (~202 GiB)
+ main KV (~83 GiB) + a 2 GiB reserve looked like it fit in 2x182 GiB, when the
real footprint with the ~97 GiB MTP copy is ~382 GiB and overruns the cards.
Disabling speculative decoding removed the copy and the same context ran fine.
_estimate_mtp_overhead_bytes now adds the duplicated target context (the main KV
re-estimated at f16) for MLA models, so auto-fit backs the context off (or selects
more GPUs) instead of advertising one that OOMs. It is gated strictly on MLA
(kv_lora_rank present), which is exactly the family that keeps the extra copy
(GLM-5.x, DeepSeek, Kimi-K2); non-MLA MTP (Qwen, Gemma) is byte-for-byte
unchanged. The reserve stays deterministic from GGUF dims, matching #6312.
test_mtp_mla_target_ctx.py covers it: the MLA reserve includes the f16 target
copy and dominates the draft head, the copy is f16 regardless of the main cache
type and scales with context, non-MLA embedded heads keep overhead == draft KV,
and _fit_context_to_vram on the GLM-5.2 / 2x B200 budget now returns a context
below the requested 1M where the old draft-only reserve kept the full 1M.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: stub structlog/loggers in MTP-MLA test so it is import-order-independent
The new test imports core.inference.llama_cpp, which pulls in orchestrator ->
structlog. In the lightweight test env structlog is absent, so when this file is
collected before test_mtp_vram_budget.py (it sorts first) or run directly,
collection aborted with ModuleNotFoundError. Install the same loggers/structlog
(+ conditional httpx) stubs the sibling MTP tests use before the import, matching
the established per-file convention.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: fix Bypass Permissions menu freeze and show decimal GB for model sizes
Bypass Permissions freeze: the warning dialog lived inside the composer
"+"/More dropdown and kept the menu mounted via onSelect preventDefault,
so confirming or cancelling the dialog left both popovers frozen open.
Lift the dialog out of the menu into a store-driven
BypassPermissionsConfirmDialog mounted at a stable spot in the composer.
The menu item now closes normally on select and just toggles a new
bypassConfirmOpen store flag, so the popovers dismiss as expected.
Model search sizes: formatBytes divided bytes by 1024 but labelled the
result "GB", so unsloth/GLM-5.2-GGUF:UD-IQ1_S showed 201.8 GB where
Hugging Face reports 217 GB. Switch the search display to decimal
(base-1000) units to match what Hugging Face reports. The GPU-fit math
stays base-1024 since VRAM capacity is binary.
* Studio: address review feedback and add GLM-5.2 high/max/disabled thinking
Review feedback on the Bypass Permissions and size-format changes:
- Mount the Bypass Permissions warning dialog once at the chat-page root
instead of inside each Composer. It is driven by global store state, so
the per-composer mount meant Compare mode (multiple composers) rendered
duplicate dialogs and the shared-composer menu had none. A single root
mount fixes both.
- Defer opening the dialog past Radix's menu-close focus restoration with
setTimeout(0), so the dropdown does not steal focus back and break the
dialog's focus trap.
- Clamp the unit index in formatBytes so units[i] cannot go out of bounds
past TB (and to absorb log() float error at exact powers of 1000).
GLM-5.2 reasoning levels:
GLM-5.2's template gates thinking with enable_thinking and also reads a
reasoning_effort level ('high' or 'max'), so it needs high / max /
disabled rather than the binary toggle it got before (its style was
detected as enable_thinking, which made 'high' unreachable). Add a new
reasoning style 'enable_thinking_effort' that reuses the effort dropdown
but, unlike gpt-oss, can be fully disabled:
- detect_reasoning_flags classifies a template that has both
enable_thinking and reasoning_effort, extracting the discrete levels
from the quoted effort literals it branches on. Templates with only one
of the two (gpt-oss, Qwen3, DeepSeek, GLM-4.6) are unchanged.
- _request_reasoning_kwargs maps the new style to enable_thinking plus an
in-range reasoning_effort; disabling sends enable_thinking=false. The
gpt-oss reasoning_effort path is left untouched.
- The backend reports reasoning_effort_levels on the load/status response;
the frontend carries them through to the effort dropdown and sends
enable_thinking + reasoning_effort for this style.
Verified: backend reasoning kwargs render the real GLM-5.2 template to
"Reasoning Effort: High/Max" (thinking) and an empty <think></think>
(disabled); tsc, eslint, i18n parity and the production build all pass.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address review feedback on reasoning effort and formatBytes
- chat-adapter localReasoningEffort: accept 'minimal' so a template that
branches on it (extracted into reasoning_effort_levels) is sent through
instead of being coerced to 'low' and then dropped by the backend.
- formatBytes: return '0 B' for non-finite / non-positive sizes (missing
metadata -> NaN, Infinity, negatives) and clamp the unit index lower
bound to 0, so sub-1-byte values can't produce a negative index.
* Studio: hybrid reasoning none gate and decimal GB in load progress
- _request_reasoning_kwargs: for enable_thinking_effort models, treat a
raw reasoning_effort='none' (OpenAI 'no reasoning' sentinel) as the
enable_thinking=false off gate, so a direct API caller can disable
thinking even without passing enable_thinking. The frontend already
sends enable_thinking=false; this only affects raw API callers.
- use-chat-model-runtime: the download / 'X of Y GB in memory' load
progress divided bytes by 1024**3 but labelled GB, so it disagreed with
the model picker and Hugging Face. Use decimal GB (1e9) to match.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: carry hybrid reasoning levels on all load paths and harden formatBytes
Review follow-ups on the enable_thinking_effort work:
- Every model-load path now copies reasoning_effort_levels and derives
supportsReasoningOff, via a shared reasoningCapsFromLoad() helper. The
shared/Compare composer load and the three chat-adapter auto-load paths
previously set only reasoningStyle, so a GLM-style hybrid model loaded
through Compare or first-chat auto-load fell back to the default
low|medium|high and lost its Max / Off controls.
- The local send path clamps the effort to the loaded model's advertised
levels (clampReasoningEffortToLevels) instead of a hard-coded list. A
stale "max" carried over from an external provider no longer reaches a
pure reasoning_effort (gpt-oss) model that only accepts none|low|medium|
high, where the backend would have dropped it.
- formatBytes divides iteratively instead of via Math.log, which has float
error at exact powers of 1000 (log(1e12)/log(1000) = 3.9999... would
label 1 TB as "1000 GB"). Keeps the non-finite/non-positive guard.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: fall back to text-only when a vision projector hard-crashes llama-server
The text-only mmproj fallback (#6075) only fired when llama-server printed a
recognizable projector-format error ("Unknown projector type", exit -6). An
installed llama.cpp that predates a model's projector can instead SIGSEGV
(exit -11) with no parseable output, e.g. unsloth/Qwen3.5-4B-MTP-GGUF +
mmproj-F16 on an older gfx1151 prebuilt: llama-server crashes on load, the
--fit off retry crashes the same way, and load_model gives up with a hard 500
instead of dropping vision.
Generalize the decision: a vision (--mmproj) launch killed by a signal (POSIX
returncode < 0, e.g. -11 SIGSEGV / -6 SIGABRT; Windows 0xC0000000+ access
violation) is treated like a projector incompatibility, so the load retries
once text-only. The retry is skipped if a cancel/unload is pending, mirroring
the MTP guard. Clean non-zero exits (bad GGUF, port bind) and hung processes
keep their own handling; non-vision launches are unaffected.
Reproduced and verified on gfx1151 (Radeon 8060S, ROCm 7.2.1): a current
prebuilt (llama.cpp b9596) loads the exact model + args fine, confirming the
crash is a stale prebuilt. With a wrapper that SIGSEGVs on --mmproj, Studio now
recovers: the load returns 200 (is_vision=false) and serves at ~31 tok/s
text-only instead of failing. New _is_signal_crash helper plus tests pin the
decision.
Also normalize a few em-dashes to ASCII punctuation in existing comments.
* Studio: refine mmproj hard-crash fallback (signal scope + last argv)
- Limit _is_signal_crash to genuine program faults (SIGSEGV, SIGABRT,
SIGILL, SIGFPE, SIGBUS) and Windows 0xC0000000+ statuses. SIGKILL,
SIGTERM and SIGINT no longer count, so an OOM-killer, unload or
supervisor kill is not masked as a projector incompatibility.
- Strip --mmproj from the last attempted argv so the text-only retry
keeps --fit off / --spec-default instead of resurrecting the original
spec flags (matters for MTP vision models on an older llama.cpp).
- Drop stray temp files committed by mistake and gitignore the "~" dir
so they cannot be re-added.
* Studio: tighten comments in mmproj hard-crash fallback
* Studio: retry --flash-attn off before dropping vision on a startup crash
When llama-server hard-crashes at startup, the recovery chain now tries the
least-destructive mitigation first. Flash-attention kernels SIGSEGV at load on
some ROCm/GPU builds (often inside the vision tower's attention); disabling
flash attention keeps BOTH vision and MTP, so a hard program fault with
--flash-attn on now retries once with --flash-attn off before the MTP-drop or
the text-only (mmproj-strip) fallbacks. _is_signal_crash already gates this to
genuine faults (SIGSEGV/SIGABRT/SIGILL/SIGFPE/SIGBUS), so an OOM-kill or unload
(SIGKILL/SIGTERM/SIGINT) does not trigger a retry.
Field context: a gfx1151 user crashes loading a vision GGUF even on the latest
prebuilt, so an update cannot help, and the same model and args load fine on
another gfx1151 box, pointing at a runtime/flash-attn fault. New
_with_flash_attn_off helper plus tests. Verified on hardware with a wrapper
that SIGSEGVs on --flash-attn on: Studio recovers with is_vision=true (vision
and MTP intact) instead of failing or losing vision.
* Studio: name the OOM kill on a too-large model load
When the OS kills llama-server with no diagnostic output (SIGKILL/SIGTERM,
almost always the OOM killer, e.g. a BF16 model too large for the WSL VM's
RAM cap), the recovery ladder correctly does not retry an external kill, so
this is the message the user sees. It fell through to the generic "is the
GGUF valid / out of memory" text. Make it actionable: name the signal and
point at a smaller or more quantized GGUF, a lower context length, or raising
the WSL memory limit. Output-based diagnoses still win and a hard fault keeps
the generic fallback.
* Studio: refuse a model too large for system RAM on a unified-memory APU
On gfx1150/gfx1151 APUs the weights load into shared system RAM (GGML
unified memory). _get_gpu_free_memory reports the full ROCm/APU budget as
free (often ~100 GB), but under WSL the VM's RAM cap is the real ceiling.
Studio trusted the budget, spawned a load larger than RAM, and the OS killed
it mid-flight, taking the Studio process with it (a silent "Terminated" with
no error, the model resident in RAM not VRAM).
Add a pre-flight guard on the APU path: if the weights exceed available
system RAM (psutil, then /proc/meminfo), refuse before spawning with a clear
message (smaller/more-quantized GGUF, lower context, or raise the WSL memory
limit). Weights only so KV/context auto-reduction is not double-counted;
unknown RAM never refuses; non-APU and discrete-GPU paths are untouched.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: refine recovery ladder (keep diagnosed errors, flip all flash-attn)
Two review points on the hard-crash recovery ladder:
1. The signal-only text-only fallback stripped --mmproj on any hard fault,
even when llama-server had already printed a non-projector cause (an OOM
such as "cudaMalloc failed: out of memory", an unsupported architecture, or
a tensor-parallel limit). That masked the real error and told the user to
update llama.cpp for vision. New _output_has_nonprojector_diagnostic gates
the signal path: it fires only when no such marker is present, so a bare
SIGSEGV with no output still retries text-only, but a diagnosed OOM surfaces
the real error instead of silently dropping vision.
2. _with_flash_attn_off only flipped the first --flash-attn. llama.cpp is
last-wins, so a leftover enable from extra_args (--flash-attn on, -fa on, or
the = form) could keep flash attention on and re-crash the retry. It now
flips every occurrence and returns None only when nothing is flippable.
test_llama_cpp_mmproj_fallback.py and the classification/APU suites: 103 passed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: pass the text-only retry's exit code to the failure classifier
When the text-only fallback retry itself fails, read its exit code before
_kill_process() clears it and forward it to _classify_llama_start_failure, so an
OS-killed retry surfaces the actionable out-of-memory message instead of the
generic one (matching the primary failure path).
* Studio: scope APU RAM guard to selected GPUs, count MTP drafter, neutral SIGTERM
Three refinements to the startup recovery work in this PR:
- The unified-memory APU RAM guard fired whenever any visible GPU was a
gfx1150/gfx1151 APU, so on a mixed APU+dGPU host it could refuse a valid
load placed on the discrete GPU. Scope _amd_apu_wants_unified_memory to the
selected gpu_indices (physical ids, mapped via CUDA_VISIBLE_DEVICES like
_is_datacenter_gpu); None still means every visible GPU. Applied to both the
RAM guard and the GGML_CUDA_ENABLE_UNIFIED_MEMORY env set.
- The RAM guard counted only the main GGUF plus mmproj, so a separate MTP
drafter (also resident in unified system RAM, even when offloaded to CPU)
could push the load past the RAM cap and still get OS-killed mid-load. Add
the drafter weights to the APU RAM total.
- The startup classifier reported SIGTERM (-15) as 'most likely out of memory',
but SIGTERM is also how an unload/cancel or a supervisor stops the server.
Keep the OOM wording for SIGKILL (-9, the OOM killer) and report -15
neutrally.
Tests updated/added accordingly.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address review on the APU guard and decode-probe ladder
- Map APU physical ids via the active ROCm mask (HIP, then ROCR, then CUDA),
mirroring _get_gpu_memory, so a HIP_VISIBLE_DEVICES-selected APU is matched.
- Only add the MTP drafter to the APU RAM total when MTP will actually engage,
so a stale LLAMA_ARG_SPEC_DRAFT_MODEL cannot refuse a non-MTP load.
- After an MTP first-decode hard fault, retry --flash-attn off (keeps MTP)
before dropping speculative decoding, matching the startup rung.
- Fold the --flash-attn= / -fa= rewrite into one branch.
Tests: tensor-parallel decode-probe assertion updated for the FA-off rung.
* Studio: tighten two comments in the APU guard and RAM preflight
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: refine flash-attn retry and APU RAM guard per review
- _with_flash_attn_off now decides on the effective last-wins value: it returns
None when FA is already off (no wasted retry), and neutralizes a bare
--flash-attn / -fa (which llama.cpp reads as on) so the retry cannot re-enable
it. Length is preserved so downstream index slices stay valid.
- _amd_apu_wants_unified_memory uses 'gpu_indices is not None' so an empty
selection is respected (not treated as all-visible).
- The APU RAM refusal now checks the base model only (main + mmproj); an
optional MTP drafter is dropped by the existing MTP-drop fallback rather than
causing a hard pre-spawn refusal of an otherwise loadable model.
Tests: bare-flag / effective-off / empty-selection / HIP-mask cases added.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: free chat model VRAM at training start only when the GPU is tight
The training start route unconditionally tore down the transformers/MLX
inference subprocess before training, and never stopped the llama.cpp GGUF
server at all, so a loaded GGUF chat model kept holding VRAM for the whole
run. Conversely the HF model was always unloaded even when there was plenty
of room to keep it.
Make the unload VRAM aware and cover every inference backend:
- Add routes/training_vram.py with summarize_resident_chat(),
can_keep_chat_during_training() and free_chat_models_for_training(). The
keep/unload decision reuses the same estimator and live per device free
VRAM reader the training GPU selection already uses (auto_select_gpu_ids,
estimate_required_model_memory_gb, get_visible_gpu_utilization), so the
probe agrees with the placement computed later in start_training.
- When a chat model is resident and training fits alongside it with a
conservative margin (required_gb * 1.15 + 4 GB), keep it loaded so the
user can train and chat at the same time; on a multi GPU box training
lands on a different GPU and both coexist. Otherwise unload the HF/MLX
orchestrator and the llama.cpp GGUF server before training starts.
- The export subprocess shutdown stays unconditional and now runs first so
its freed VRAM is reflected in the decision.
Default deny: non CUDA backends, unestimable models, or any probe error
fall back to the previous always unload behavior.
Adds tests/test_training_vram_coexistence.py and updates two existing route
tests in test_gpu_selection.py.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: per-GPU floor for explicit GPU lists + don't unload chat on invalid gpu_ids
Address review feedback on the chat coexistence probe:
- Explicit gpu_ids mode now enforces a per-GPU floor in addition to the
aggregate free-VRAM check, mirroring auto_select_gpu_ids' min_per_gpu_N.
Without it, an uneven split such as free [45, 10] for a 40 GB job passed
the aggregate threshold and kept chat loaded even though the 10 GB GPU
could not hold its training shard, risking an OOM.
- Invalid explicit gpu_ids (ids outside the visible set, or a UUID/MIG
mask) make resolve_requested_gpu_ids raise. That request is rejected with
a 400 before training starts, so leave the resident chat model untouched
instead of unloading it.
- Tighten the target_modules / gpu_ids type hints to List[str] / List[int].
Adds tests for the per-GPU floor (uneven split unloads, even split keeps)
and for invalid gpu_ids keeping the chat model loaded.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: only free chat VRAM once training will start; handle in-flight and CPU-only chat
Address the second review pass on the chat-coexistence path:
- Run the chat/export VRAM teardown as a before_spawn hook inside
TrainingBackend.start_training, fired only after the start guards pass.
Previously the route freed chat VRAM before calling start_training, so a
refused start (e.g. a lingering pump thread) would tear down the resident
chat model even though no training job began.
- Treat an in-flight HF chat load (loading_models set, no active model yet)
as not safely sizeable: free it rather than risk both OOMing as the load
keeps allocating after training starts.
- Do not count or tear down a GGUF llama-server confirmed to run entirely on
CPU (_gpu_offload_active is False): it holds no VRAM, so killing it cannot
help training fit.
Adds tests for the before_spawn hook (runs on start, skipped when a
subprocess is alive or a pump thread will not die, survives a hook error),
the in-flight load flag, and the CPU-only GGUF exclusion in both the resident
summary and the unload path.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: treat any in-flight chat load (HF swap / mid-start GGUF) as unsafe to keep
Tighten the in-flight detection in summarize_resident_chat so the keep check
never sizes a load that is still allocating:
- Flag loading on ANY non-empty loading_models, not only when active_model_name
is empty. load_model adds the new model to loading_models before clearing the
old active_model_name, so a replacement load during a swap was previously
sized as a normal resident and could OOM as the new model finishes loading.
- Flag a GGUF server that is active but not yet healthy (is_loaded False) as
in-flight: it is still mmaping/offloading layers, so its final VRAM footprint
is unknown.
Consolidates the signal into a single resident["loading"] flag; the route frees
the chat model whenever it is set. Adds tests for the replacement HF load and
the mid-start GGUF cases.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: tighten comments in chat/training VRAM coexistence (comments only)
* Studio: run before_spawn VRAM hook only after GPU-selection validation
Reviewers found the before_spawn hook fired before prepare_gpu_selection
validated gpu_ids (and before config build), so a refused start (invalid
gpu_ids -> 400, or a bad grad-clip value) could still tear down chat/export
VRAM. Move the hook to immediately before proc.start(), once all synchronous
validation and process construction have passed. This also fixes the route's
in-flight-chat loading branch, since that teardown runs inside the same hook.
Add test_hook_skipped_when_gpu_selection_rejects.
* Studio: recompute GPU auto-selection after the before_spawn VRAM hook
Codex P2: with before_spawn moved after prepare_gpu_selection, placement was
frozen against the pre-teardown VRAM state while the hook freed export/chat
afterward. Auto-selection could pin training onto a GPU the hook then cleared
(or onto a kept chat model). Split validation from placement: explicit gpu_ids
are still validated before the hook (raise -> 400, no teardown; explicit
placement is VRAM-independent), but VRAM-dependent auto-selection now runs
after the hook so it sees the freed memory.
Add test_auto_placement_runs_after_hook and test_explicit_placement_validated_before_hook.
* Studio: allow chatting during training (lift sidebar gate + VRAM-aware load guard) (#6335)
* Studio: allow chatting during training (lift sidebar gate + VRAM-aware load guard)
The sidebar disabled New Chat, project, and home navigation while a training
run was active, so users could not chat during training even though the backend
serves inference fine alongside a run. This removes that gate and adds a backend
guard so the one genuinely risky operation, loading a new local chat model
mid-training, is refused with a clear 409 when it would not fit beside the run.
Frontend (app-sidebar.tsx): drop the chatDisabled = isTrainingRunning gate and
its consumers. Navigation triggers no model load on its own, so chat stays
usable during training.
Backend (routes/training_vram.py, routes/inference.py): add
can_load_chat_during_training plus a load/validate guard that sizes the same
effective load the loader performs (LoRA 4-bit to 16-bit resolved first, HF auto
placement via auto_select_gpu_ids, explicit multi-GPU per-GPU floor, GGUF sized
from on-disk shards and companions or the selected remote variant). It is a
no-op when training is inactive, never blocks external providers or
already-resident models, and default-denies only on a CUDA sizing failure so a
load can never OOM the run. Validate refuses early with the real settings so the
frontend does not unload the resident chat model for a load that would be
rejected.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address review feedback for chat-during-training load guard
- Run the load/validate VRAM guard via asyncio.to_thread so the sync
nvidia-smi + HF metadata work never blocks the event loop.
- Size the GGUF KV cache at the requested context (_estimate_gguf_kv_gb)
and add it to the local GGUF estimate so large-context picks are not
under-counted.
- Keep the requested quantization when adapter_config.json is malformed
(not a JSON object) instead of raising in _effective_load_in_4bit.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: size the training load guard at the launcher's effective GGUF context
The GGUF KV-cache estimate used max_seq_length only, but the llama.cpp
launcher honors a user --ctx-size/-c in llama_extra_args. A load such as
max_seq_length=4096 with --ctx-size 131072 was sized against a 4k cache
while the server allocates 131k, so the guard could approve a long-context
GGUF load that then OOMs training. Size the guard's KV at the larger of
max_seq_length and the parsed --ctx-size (reusing the launcher's own
parse_ctx_override), keeping the conservative f16 cache so the estimate is
never smaller than what the server allocates.
The chat model picker also validated with the raw max_seq_length while
/load sizes with resolveLoadMaxSeqLength, so validate could pass, unload
the current model, then have /load reject the native-context load. Validate
now uses the same effective context; the load path is unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: size the GGUF training guard at the server parallel-slot count
The KV-cache estimate assumed a single slot, but llama-server allocates the
cache across --parallel slots (app.state.llama_parallel_slots). On a Studio
launched with --parallel N>1 the guard under-sized the cache N-fold and could
approve a GGUF chat load that then OOMs training. Thread the same slot count
the loader uses into the guard's KV estimate; default 1 leaves single-slot
setups unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim comments for chat-during-training guard
* Studio: keep chat generation alive across navigation; Train spinner + Return to Chat
Hoist the base chat runtime above the routed outlet so navigating to Train (or any tab) no longer aborts an in-flight generation; only an explicit Stop cancels. Add a Train sidebar spinner and swap New Chat to Return to Chat while a run is active, with a lightweight completion watch so the spinner clears from any tab. Also respawn a chat llama-server killed mid-session and guard unreadable HF cache dirs that 500'd the hub model list.
* Studio: show Return to Chat on the Train tab whenever a chat is live
Previously the top sidebar item only swapped to Return to Chat while training was running; on the Train tab with an idle/just-finished run it stayed New Chat, which started a fresh thread and cancelled an in-flight generation. Show Return to Chat (and navigate back, preserving the run) whenever a generation is running or its thread is still active, or training is in progress.
* Studio: keep a running chat alive when starting a New Chat
Starting a New Chat (or switching threads) while a generation was in flight
remounted the single-chat runtime provider, which detached the in-flight run
and cut the previous chat off (it showed up frozen / empty when reopened).
Key the single-chat view by project instead of by thread or new-chat nonce so
the provider stays mounted and assistant-ui switches to a fresh thread in place.
The previous generation keeps streaming in the background and autosaves on
completion, and returning to that thread reattaches the live run instead of
reloading a half-saved one.
Also:
- "Return to Chat" now lands on the thread that is still generating rather than
the empty new chat that became active after New Chat.
- Skip the explicit /inference/cancel POST when an abort comes from a runtime
detach (navigation / background switch) rather than an explicit Stop, so a
backgrounded generation is never cancelled behind the scenes.
* Studio: make model export non-blocking and inline
The Export tab opened a full-screen modal that trapped focus, could not be
closed or cancelled while running, and showed no progress. It also stopped
training and unloaded the chat model before loading, so export could not run
alongside them.
Export now mirrors the training runtime pattern:
- Inline panel embedded where the Export Model button was, with no modal or
backdrop, so the rest of the UI stays usable during an export.
- Global export runtime store plus an app-root lifecycle hook, so a run keeps
going and streaming across navigation and is reflected on the Export nav item
from any tab.
- The worker log stream now stays connected across the load to export phase
boundary instead of stranding on "Waiting for worker output".
- Progress bar driven by phase and quant index (quant N of M for GGUF), with
elapsed time and a working Cancel.
- load-checkpoint no longer stops training or unloads inference; export loads in
its own subprocess in parallel and surfaces out-of-memory as a clear error.
- Add POST /api/export/cancel and is_export_active on /api/export/status.
* Studio: show Return to Chat on the Export tab too
Extend the New Chat to Return to Chat swap to the Export route so leaving a
running chat for Export offers a way back to the live generation, matching the
Train tab.
* Studio: smooth out Export animations and polish the panel
- Drop the height-based reveal animations (source switch, run panel, quant
picker, hub fields) that caused flashing and reflow; use instant swaps and
quick opacity fades instead.
- Method and quant cards now transition colors only, with no transition-all or
hover lift, so selecting a method or quant is crisp instead of jumpy.
- Auto-scroll the export panel into view when it opens and add a scroll-to-bottom
button when its output is below the fold, like Chat.
- Show Return to Chat on the Export tab while an export is running, matching how
training drives it on the Train tab.
- Surface the current phase or stage in the live output before the first worker
line arrives so the panel never looks stuck while progress is advancing.
* Studio: show Return to Chat on every non-chat tab
Generalize the Return to Chat swap from just Train/Export to any non-chat route
(Recipes, Projects, Hub, ...) so a running or active chat is always one click
away, instead of showing New Chat there.
* Studio: stream export logs over the Cloudflare tunnel; drop janky export animations
Exporting over a --secure Cloudflare quick tunnel showed "connecting..." with no
logs while the progress bar advanced. Cloudflare buffers text/event-stream and
only flushes when the stream closes, so the SSE log stream never reached the
browser during the run (direct localhost is unaffected, which is why this only
showed up over the tunnel).
Add a tunnel-safe JSON poll fallback (GET /api/export/logs?since=) that the
runtime lifecycle hook polls while a run is active. Short JSON responses are not
buffered by the proxy, so logs show up in near real time over the tunnel. It
shares the orchestrator's monotonic seq cursor with the SSE stream and the store
de-dupes by seq, so the two transports run together (SSE on localhost, poll over
the tunnel) without double-printing. A successful poll marks the panel
"streaming" instead of leaving it stuck on "connecting...".
Also remove the framer-motion AnimatePresence reveals from the export config and
run panel (quant picker, hub fields, the inline run panel, and the live log
section). The expand/slide animations flashed and felt clunky; the sections now
render in place.
* Studio: recover export over the Cloudflare tunnel when the blocking POST times out (524)
A model export over a --secure Cloudflare quick tunnel showed "Request failed
(524)" even though the export succeeded on the backend (the GGUF was written).
Cloudflare returns 524 when a single request takes longer than ~100s to respond,
and a GGUF conversion routinely runs for minutes, so the blocking per-method
export POST is cut off while the backend keeps going.
Confirm completion via short status polls instead of relying on the long POST
response (the same approach that fixed log streaming):
- The orchestrator records each finished op's outcome (status / output_path /
error) with a monotonic seq, exposed on GET /api/export/status.
- parseJson now preserves the HTTP status; a 524/520/522/523/502/503 or a
status-less network drop is classified as a recoverable transport error.
- runExport wraps each phase (load, every export method, each GGUF quant): on a
recoverable failure it keeps the run alive (logs keep streaming, the panel
shows "reconnecting...") and polls status until the still-running op finishes,
then settles from the recorded result, recovering the output path for the
success banner. A real 4xx still fails immediately; localhost still uses the
fast POST response. applyBackendStatus also settles a reloaded run from the
last-op record.
Verified over the tunnel: a 3m14s gemma-4-E4B-it GGUF export now ends on the
success banner with the output path instead of 524.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: keep the export method + logs visible after navigating away mid-export
While an export was running, navigating to another tab and back to Export
remounted the page and reset the local form state (exportMethod, quant levels),
so the method card showed unselected and the run panel's log area was hidden
until the card was re-clicked. The run itself lives in the global store and was
unaffected.
Seed exportMethod / quantLevels from the active run's summary via lazy useState
initializers on (re)mount, and gate the panel's log area on the live run
(isExporting / logLines / the run's method) rather than only the local form
selection. The card stays selected and the logs/progress stay visible across
navigation; nothing changes when no run is active.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: address export/training review findings
- Export: guard Start against an empty GGUF quant selection so an inline-panel
run with no quant can't settle as success with no file produced.
- Export: thread the source HF token into the background load so gated/private
HF source exports (and gated bases) authenticate, matching the consent path.
- Export: only settle a recovered (non-owned) run as a finished export when the
last backend op was an export, not a standalone load_checkpoint.
- Training: free the export subprocess whenever an export is active, not only
once a checkpoint is loaded, so an in-flight export load can't race training
for VRAM (current_checkpoint is unset during the load phase).
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: fail fast on an invalid first training batch
Training a base vision-language model (e.g. Qwen/Qwen2-VL-7B or
unsloth/Qwen2-VL-7B) on a conversational image dataset crashed on the first
step with 'Expected ... Long, Int; but got torch.cuda.FloatTensor (embedding)'.
Root cause: the base model's chat template is a flat, media-only template that
renders to an empty string for role-based messages, so UnslothVisionDataCollator
hands the processor empty text, the processor returns empty input_ids, torch
defaults the empty tensor to float32, and the embedding lookup rejects it.
Add a preflight that runs one real batch through the trainer's own tokenization
and collation right before train(), and stops the run with an actionable message
when input_ids is empty or non-integer (pointing to the instruction-tuned variant
for the base-model case). Faithful across text, vision and audio-VLM paths, and
never blocks a run whose first batch is valid.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim comments in the training preflight
* Stub unsloth/trl in preflight test so backend CI collection passes
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: show an actionable message when the GGUF runtime is missing
Selecting a GGUF model with no llama-server installed surfaced a generic
"Invalid model" in the UI, because validate_model's catch-all discarded the
real cause. Add LlamaServerNotFoundError (a RuntimeError subclass) raised by the
GGUF preflight in ModelConfig.from_identifier, and catch it in the validate
route so users get an actionable message: run `unsloth studio setup` to
download the prebuilt llama.cpp runtime. Other validation failures keep the safe
generic message. Adds a regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: also map missing GGUF runtime to a 400 in load_model
validate_model already surfaces the actionable 'install the runtime'
message for LlamaServerNotFoundError; load_model fell through to the
generic 500 'Failed to load model'. Catch it there too so a GGUF load
without llama-server gives the same install hint instead of a 500.
* Trim comments for PR #6327
* Studio: fix stale validate test after #6398 and surface missing GGUF runtime on /load
- test_other_runtime_errors_do_not_get_gguf_message: after merging #6398,
validate_model surfaces a RuntimeError's own message, so a plain RuntimeError
no longer returns "Invalid model". Assert it does not receive the GGUF
install message instead (the prior assertion was stale after the main merge).
- Raise LlamaServerNotFoundError (not a plain RuntimeError) at the backend
load-time missing-binary branch, after diffusion routing, so /load returns the
actionable 400 like remote validation, instead of a generic 500.
- Share LLAMA_SERVER_NOT_FOUND_DETAIL between the from_identifier preflight and
the load-time raise so the message stays in sync.
- Add a propagation regression test for the non-tensor load path.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Reap Studio child processes when the parent dies abnormally
Standalone `unsloth studio` launches orphaned cloudflared and llama-server when
the parent exited without running the cooperative shutdown path (terminal-window
close, Task Manager End Task, SIGKILL): the children reparented to init and kept
running, leaving an authenticated Cloudflare tunnel up for days.
Add utils/process_lifetime.py: a parent-owned Windows Job Object
(JOB_OBJECT_LIMIT_KILL_ON_JOB_CLOSE, children auto-inherit) plus Linux
PR_SET_PDEATHSIG, behind a best-effort helper that mirrors the desktop app's
windows_job.rs. initialize_parent_lifetime() runs at the top of run_server;
long-lived spawns (cloudflared, llama-server, RAG embedder, llama.cpp updater)
get the PDEATHSIG preexec, multiprocessing workers are adopted into the job, and
_graceful_shutdown plus atexit gain a terminate_all() backstop sweep. The
cooperative shutdown path is otherwise unchanged.
Verified on Linux: killing the parent now reaps cloudflared and llama-server
within ~2s instead of orphaning them.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* test: add real Windows kill-on-job-close integration test
Spawn a parent that installs the job and a child that inherits it, terminate
the parent, and assert the child is reaped. Skipped off Windows. Also make the
liveness probe Windows-safe (os.kill(pid, 0) terminates on Windows).
* Fix Win64 handle truncation in the Job Object calls
Set explicit argtypes so the 64-bit job/process handles are not marshaled as
c_int (which truncated them on Win64, failing AssignProcessToJobObject). Assert
install success in the Windows integration test.
* Bind multiprocessing workers to parent death; harden the sweep
Review follow-ups:
- Multiprocessing workers (inference/export/training/data-recipe/Xet) cannot be
given a preexec_fn by the parent, so adopt_pid alone left them orphanable on a
Linux SIGKILL. They now bind themselves with PR_SET_PDEATHSIG at startup via
bind_current_process_to_parent_lifetime(), wired into the shared
run_without_native_path_secret entrypoint and the Xet child entry.
- Wire the previously-missed data-recipe worker through adopt_pid.
- terminate_all now honors its timeout: SIGTERM, wait, then SIGKILL the
survivors, so cooperative children can exit cleanly.
- Track adopted pids with a /proc starttime identity and add forget_pid, so the
shutdown sweep never signals a recycled pid.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: cross-session backstop to reap a leftover llama-server on startup
Builds on the parent-lifetime reaper: the Windows Job Object / PR_SET_PDEATHSIG
path kills children when the parent dies, and terminate_all() sweeps the living
parent's children. Neither covers an orphan left by an already-dead Studio:
terminate_all()'s registry is in-memory, PR_SET_PDEATHSIG has no macOS
equivalent, and both are best-effort.
This records the spawned llama-server PID to a pidfile under the active studio
root (removed on _kill_process). The startup reaper kills that exact PID first,
verifying it is still a llama-server to guard against PID reuse, then clears the
pidfile. It is path-independent, so it also catches an orphan the install-root
match would miss; the pidfile only ever names a Studio-spawned server, so
unrelated user processes (vllm, games) are never candidates. The existing
root-gated enumeration stays as a further fallback.
Adds tests: kills a recorded live server (real subprocess, verifies the actual
SIGKILL), skips a reused non-llama PID, cleans a stale/missing pidfile, and
clears the pidfile on kill.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: only reap a recorded llama-server when it is a true orphan
Harden the pidfile cross-session reaper so it cannot kill a live server
and does not crash on Windows.
- Reap the recorded PID only when its parent is gone (a genuine orphan),
so constructing a second LlamaCppBackend in-process (the helper and
advisor paths each build one) can never kill the active chat server.
The check is topology independent: it holds whether the sweep runs in
the main process or a worker.
- Record pid:starttime and verify the start-time identity before killing,
so a PID recycled to another process is never reaped.
- Fall back to SIGTERM when signal.SIGKILL is undefined (Windows), where
os.kill maps it to TerminateProcess, instead of raising and leaving the
orphan alive while clearing the record.
Update and extend the pidfile tests: a live server with a running parent
is spared and its record kept, an identity mismatch is skipped, the
record-to-reap round trip kills a matching orphan, and the Windows
SIGKILL fallback uses SIGTERM.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: Michael Han <michaelhan2050@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Reap Studio child processes when the parent dies abnormally
Standalone `unsloth studio` launches orphaned cloudflared and llama-server when
the parent exited without running the cooperative shutdown path (terminal-window
close, Task Manager End Task, SIGKILL): the children reparented to init and kept
running, leaving an authenticated Cloudflare tunnel up for days.
Add utils/process_lifetime.py: a parent-owned Windows Job Object
(JOB_OBJECT_LIMIT_KILL_ON_JOB_CLOSE, children auto-inherit) plus Linux
PR_SET_PDEATHSIG, behind a best-effort helper that mirrors the desktop app's
windows_job.rs. initialize_parent_lifetime() runs at the top of run_server;
long-lived spawns (cloudflared, llama-server, RAG embedder, llama.cpp updater)
get the PDEATHSIG preexec, multiprocessing workers are adopted into the job, and
_graceful_shutdown plus atexit gain a terminate_all() backstop sweep. The
cooperative shutdown path is otherwise unchanged.
Verified on Linux: killing the parent now reaps cloudflared and llama-server
within ~2s instead of orphaning them.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* test: add real Windows kill-on-job-close integration test
Spawn a parent that installs the job and a child that inherits it, terminate
the parent, and assert the child is reaped. Skipped off Windows. Also make the
liveness probe Windows-safe (os.kill(pid, 0) terminates on Windows).
* Fix Win64 handle truncation in the Job Object calls
Set explicit argtypes so the 64-bit job/process handles are not marshaled as
c_int (which truncated them on Win64, failing AssignProcessToJobObject). Assert
install success in the Windows integration test.
* Bind multiprocessing workers to parent death; harden the sweep
Review follow-ups:
- Multiprocessing workers (inference/export/training/data-recipe/Xet) cannot be
given a preexec_fn by the parent, so adopt_pid alone left them orphanable on a
Linux SIGKILL. They now bind themselves with PR_SET_PDEATHSIG at startup via
bind_current_process_to_parent_lifetime(), wired into the shared
run_without_native_path_secret entrypoint and the Xet child entry.
- Wire the previously-missed data-recipe worker through adopt_pid.
- terminate_all now honors its timeout: SIGTERM, wait, then SIGKILL the
survivors, so cooperative children can exit cleanly.
- Track adopted pids with a /proc starttime identity and add forget_pid, so the
shutdown sweep never signals a recycled pid.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: Michael Han <michaelhan2050@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Disable MTP speculative decoding under tensor parallelism
Follow-up to #6040 (Studio tensor-parallel support).
MTP-draft speculative decoding plus --split-mode tensor crashes the CUDA
flash-attn kernel at decode time. The startup /health probe only checks that
llama-server comes up, so the existing MTP-drop fallback (keyed on startup
health) never fires and the server dies on the first generation instead.
Gate MTP off when a tensor attempt actually engages: this runs before the
VRAM planner (so no drafter memory is reserved) and before the speculative
flag build (so no --model-draft / --spec-type is emitted). Ngram modes use no
draft model and are kept, and mtp+ngram degrades to ngram rather than off. The
layer-split fallback re-runs with tensor_parallel False and restores MTP.
The reason is surfaced as spec_fallback_reason "tensor_parallel" so the
settings sheet explains why MTP is off instead of prompting a llama.cpp update.
Verified on unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_XL across 4x B200: the
load now emits --split-mode tensor with no MTP flags and generation completes
without the prior decode crash.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Make tensor-parallel MTP gate test format-independent
The assertion pinned the multi-line `speculative_type = (` form, but ruff
collapses it onto one line, so match `speculative_type =` instead.
* Recover from MTP+tensor-parallel crashes at runtime instead of banning MTP
MTP-draft speculative decoding under --split-mode tensor usually works, but can
crash llama-server's CUDA flash-attn kernel at decode time (the prompt-cache
checkpoint-restore path). The earlier fix statically disabled MTP whenever
tensor parallelism was on, which is not future-proof and gives up the MTP
speedup even though it normally works.
Replace the static ban with a try/recover, mirroring the existing load-time
MTP-drop fallback:
- Load-time decode probe: after the server passes /health under tensor +
MTP, run one tiny /completion to exercise the draft path. A failure flips
the load unhealthy so the existing fallback respawns with --spec-default.
Catches a hard incompatibility that crashes on the first decode.
- Generation-time recovery: snapshot the load kwargs after a healthy load,
and if llama-server exits mid-generation while MTP + tensor parallelism were
active, quietly reload the same model with speculative decoding off (one
single-flight background reload) and surface spec_fallback_reason=runtime_error.
Catches the rare mid-generation crash the probe and load-time fallback miss.
No persistent ban: a later fresh load re-tries MTP, so this self-heals if a
future llama.cpp supports the combo. Verified on gemma-4-26B-A4B + 4x B200:
MTP runs normally, and killing llama-server mid-generation reloads it without
MTP and serves the next request cleanly.
* Address review feedback on the MTP runtime fallback
- Authenticate the decode probe: direct-stream mode runs llama-server with
--api-key, so the unauthenticated /completion probe got a 401 and falsely
dropped MTP. Attach the same bearer auth the other internal requests use.
- Re-check the cancel flag inside the recovery thread after the death poll,
so an /unload that races the reload can't resurrect the dropped model.
- Schedule the no-MTP recovery on the connection-error paths it was missing:
generate_chat_completion's ConnectError branch, the OpenAI passthrough
typed (RemoteProtocolError/ReadError/CloseError) stream catch, and the
Anthropic passthrough generic stream catch. Previously a server that died
before reconnect, or a typed mid-stream error, skipped the reload.
* Cover every request path with the MTP+tensor crash recovery via a watchdog
The runtime MTP-crash recovery only fired from request handlers that
observed the failure, so the direct llama-server proxy endpoints
(/v1/completions, /v1/responses, the OpenAI/Anthropic passthrough
transports) -- and a crash with no request in flight -- could leave a
dead server. Add a single background watchdog, armed only on a healthy
MTP + tensor-parallel load, that polls the subprocess and routes an
unexpected death into the existing single-flight no-MTP reload. It is
stopped inside _kill_process (the one deliberate-termination chokepoint)
so a planned reload/unload is never mistaken for a crash, and re-checks
the stop flag after a detected exit to close the kill-vs-poll race. The
reload turns MTP off, so the replacement server arms no watchdog and the
fallback cannot loop; a later fresh load still re-tries MTP.
* Harden MTP+tensor crash recovery: stale-load race, pass-through MTP, requested mode
Address review findings on the runtime MTP-crash recovery:
- Stale-load race: the recovery thread snapshotted the crashed load, waited up
to 5s for the process to confirm dead, then only checked the cancel flag
before replaying load_model. A concurrent user load clears that flag, so the
stale snapshot could reload the old model over the user's new one. Make the
load lock re-entrant and run the staleness check (cancel + same process +
unchanged snapshot) under it, atomically with the reload.
- Pass-through MTP: MTP can also be requested via a user --spec-type in
extra_args or LLAMA_ARG_SPEC_TYPE, where Studio emits no spec flags and
_speculative_type stays unset, so the probe/watchdog/recovery never engaged.
Track _mtp_runtime_fallback_active from the actual launched config and gate on
it; on the no-MTP reload, append a last-wins --spec-default so the replay drops
MTP regardless of source (and the load-time fallback does the same).
- Requested mode: the off-reload reset _requested_spec_mode to off, so after a
status refresh the UI showed a bare Off with the runtime-error note suppressed
and would not retry MTP. Restore the original requested mode after the reload,
matching the startup MTP fallback.
- Snapshot the extra_args list by value so a caller mutating it cannot corrupt
the recovery snapshot.
Tests: test_tensor_parallel.py + test_llama_server_args.py green (303 passed).
* Trim verbose comments in the MTP+tensor crash recovery
Tighten the docstrings and inline comments added for the runtime MTP recovery
(watchdog, probe, reload, gating) to succinct one/two-line forms; no code
change (verified comment-only).
---------
Co-authored-by: danielhanchen <michaelhan2050@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Harden model fetching: consent gate for trust_remote_code
Add a load-path consent gate that scans a model's auto_map repository code
before it executes and blocks CRITICAL/HIGH findings unless the user pins
approval of that exact code version. Capability detection stays code-free,
reading raw config.json instead of AutoConfig.
- Scan config.json and tokenizer_config.json auto_map, nested local helpers,
and external owner/name--module repos; fail closed on partial downloads.
- Gate inference, training, and export workers, including the MLX path and a
LoRA's base model, and report requires_trust_remote_code from the raw config
so chat and auto-load surface the dialog.
- Verify trusted-org auto-enable against the Hub with the request token and key
the verdict cache by token; reject local-path and spoofed names.
- Add a consent dialog showing the flagged file, line, and surrounding code.
- Thread hf_token through the scan and load paths for gated repos.
* Address review: token handling, tokenizer/LoRA scan coverage, rollback
- Send the HF token for remote-code scans in the POST body, not the URL, so it
never lands in a log or browser history.
- Collect tokenizer_config.json auto_map files directly instead of relying only
on the repo file listing.
- Resolve a LoRA's base model for the validate flag and the scan endpoint so the
dialog scans the code the workers actually gate.
- Pass the request token to the training YAML trusted-org auto-enable.
- Resend a previously approved fingerprint when rolling back to a custom-code
model after a failed switch.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Consent UX: drop legacy chat toggle, fix decline copy, purge declined downloads
The per-model consent dialog is now the single approval path for custom
(auto_map) code in chat, so three leftovers from before it existed are removed:
- Remove the "Enable custom code" switch from Chat Settings and stop persisting
trust_remote_code, so a previously saved blanket-on cannot linger and load a
model without going through per-version review. The flag stays as an internal
YAML/preset default (e.g. first-party auto-enable); the load path still gates
every custom-code load on a fingerprint only the dialog produces.
- Reword the decline message and the auto-load toast to describe approving the
model's code from the dialog, not a missing settings toggle.
- On decline, purge the repo the scan downloaded so untrusted code is not left
on disk. A new /api/models/discard-remote-code endpoint deletes only a
metadata-only cache entry the scan created; it refuses local paths, loaded
models, and any repo with weight files cached, so a model the user already had
or pre-downloaded is always left untouched. The frontend only calls it when
the scan reported created_by_scan.
Adds discard-endpoint tests (delete metadata-only, refuse on weights/gguf,
refuse local, no-op when not cached) and a created_by_scan payload assertion.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Export: remove the user-facing trust remote code toggle
The Export page kept a "Trust remote code" switch (default on) next to the HF
token field. Like chat, custom (auto_map) code should be approved per model
through the load-time review dialog, not a persistent blanket switch, so the
toggle is removed. The export load path already routes through the same consent
dialog: an HF source now starts with trust_remote_code off and only enables it
when the user approves the scanned code in the dialog (a local checkpoint the
user exported stays trusted by default). With the dialog unreachable and no
approval, an HF source loads with trust_remote_code off, which fails closed
rather than running unreviewed code.
* Block loads of repos with unsafe files using Hugging Face's security scan
The trust_remote_code consent gate covers one load-time RCE vector (a repo's
auto_map Python). It does not cover the other: a malicious pickle inside a weight
file (pytorch_model.bin, *.pkl, *.dat) deserializes during from_pretrained even
with trust_remote_code False, so a repo with a normal config plus a poisoned
pickle slips past the existing gate.
Add a metadata-only malware gate that uses Hugging Face's own scan (picklescan +
ClamAV), read via model_info(securityStatus=True).security_repo_status. It never
downloads, opens, or unpickles the flagged files; it only reads the Hub's verdict
and surfaces the flagged file names. New evaluate_file_security runs
unconditionally (independent of trust_remote_code) in every load path (inference,
training SFT/MLX, export), blocking the load when a file is flagged
unsafe/suspicious/malicious. The /remote-code-scan preflight and the validate
endpoint also report the result so the consent dialog opens as a hard block (no
override) listing the flagged files, even for a repo with no custom code.
Policy: hard block with no user override; fail open when the scan is unavailable
(offline/unscanned) so legitimate loads are not broken; no first-party exemption
(a poisoned pickle in a compromised trusted repo still blocks); local paths and
GGUF are skipped (no Hub scan, non-pickle format). Blocking does not gate on
scansDone, since that is often false for clean repos and a file already flagged
unsafe is unsafe regardless.
Adds test_file_security.py covering the block/allow/fail-open/skip matrix.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: scan list-form tokenizer auto_map, gate unsafe files on all load paths
Fixes from a 10-reviewer pass on the model-fetching hardening:
- The remote-code scanner skipped tokenizer auto_map encoded as a [slow, fast]
list (transformers' standard tokenizer shape, e.g.
{"AutoTokenizer": ["owner/repo--tokenization_x.Slow", null]}). External
tokenizer code in that form was never fetched, scanned, or fingerprinted, so an
AutoTokenizer(trust_remote_code=True) load could run it. _auto_map_refs now
flattens string, list, and nested values. Adds a regression test.
- Compare-mode chat loads and background auto-load only gated on
requires_trust_remote_code, so a repo flagged unsafe by the Hub scan but with no
custom code skipped the hard-block dialog. Both now also gate on
requires_security_review, matching the main chat path.
- The /remote-code-scan and /validate routes collapsed a LoRA adapter to its base
before the malware scan, so unsafe files in the adapter repo itself were missed
in the pre-load review (the workers already scan both). Both routes now run the
file-security scan over the adapter and the base.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Require approval for all HIGH remote code, fail closed when unscannable
Tighten the load-time security gates based on review:
Consent gate
- HIGH-severity auto_map code now requires explicit, per-version approval for
every repo, including first-party unsloth/nvidia. The org is no longer a
blanket bypass: a compromised first-party repo with HIGH code still warrants
review. CRITICAL stays a hard block; clean code still loads after the consent
prompt.
- Fail closed when auto_map code is present but cannot be fully fetched or
listed to scan (gated, offline, transient, or a repo-listing failure that
could hide an imported helper). We cannot fingerprint code we cannot see, so
this is a non-approvable block, retryable once the repo is reachable.
- Scan auto_map from every config that can carry one (model, tokenizer, image
and feature processor, processor, video processor), not just config.json and
tokenizer_config.json, so a custom-processor model is not missed. The file
list is the single source of truth in remote_code_scan and is pinned to the
transformers filename constants by a guard test.
- Distinguish a genuine 404 (config truly absent) from a transient error: only
the latter forces a scan, so a repo with no config is correctly a no-op.
Malware gate
- Scan a remote repo even when its name ends in .gguf; only local paths skip the
Hub scan, so a repo cannot dodge the scan by naming itself "*.gguf".
- Correct the docstring: a file already flagged unsafe blocks regardless of
scansDone; the only fail-open path is an unavailable scan.
Coverage
- Resolve a remote LoRA adapter's base model (not just local directories) so the
base, where the code and weights actually execute, is scanned in validate,
the scan route, and the training and export workers.
- Gate the embedding training path (FastSentenceTransformer) with the malware
and consent checks, matching the other load paths.
Tests updated and added for each change.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Scope malware gate to the load-path vector; stop false-blocking first-party models
Follow-up hardening from a second review pass + a broad live model matrix
(unsloth/* , nvidia/* , third-party, and the eicar malware repo).
Malware / unsafe-file gate
- Scope the block to the actual RCE vector: a root-level file in a code-executing
format. from_pretrained deserializes weight files at the repo ROOT, so a flag is
only a load-path pickle vector there. Two exclusions, because neither is loaded:
inert formats (safetensors is tensor-only, gguf is non-pickle, configs/text/
images) and files in subdirectories. This keeps eicar blocked (its *.pkl/*.dat/
eicar_test_file sit at the repo root) while no longer false-blocking legitimate
first-party repos: nvidia/Nemotron-H-8B-Base-8K ships root safetensors plus NeMo
pickle checkpoints under nemo/ that the loader never touches, and the Hub flags
both; the gate previously hard-blocked it.
- Unknown / future non-"safe" levels now fail closed (block) instead of being
silently allowed, so Hub schema drift cannot introduce a bypass; in-progress
("pending"/"scanning"/"error") levels stay non-blocking to avoid false blocks.
Consent gate
- Ignore a STALE own-repo auto_map target that is absent from the repo listing (an
older config pointing at a file the repo no longer ships) instead of failing the
whole repo closed as unscannable. The present .py are still fully scanned, which
is the stronger coverage, and a file that is not there cannot execute. This
unblocks first-party models like unsloth/PaddleOCR-VL (its tokenizer_config.json
names processing_ppocrvl.py while the repo ships processing_paddleocr_vl.py). A
referenced .py that IS present but cannot be fetched, and a repo-listing failure,
still fail closed.
Remote LoRA base resolution
- Distinguish a genuine 404 (not a LoRA / repo absent -> None) from a transient
error: the transient case is retried once, then logged as a WARNING (a missed
base is scanned by neither gate) rather than silently skipped.
Discard endpoint
- Treat .onnx and .ckpt as weights so a repo whose only heavy artifact is one of
those is never eligible for the declined-download purge.
Tests added for each: load-path scoping (safetensors/subdir/Nemotron-H shapes,
unknown-level fail-closed, pending non-block), stale own-repo auto_map ref, remote
LoRA transient retry, and the empty-config-list (all-404 -> []) semantics.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Make LoRA-base transient-warning test robust to logging backend
Assert on the logger object directly instead of capsys, so the test does not
depend on whether the real structlog logger or the module-stub logger is active
(which varies with test collection order).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Allow a repo with auto_map but no executable code (e.g. GGUF) instead of blocking
A config can declare an auto_map yet the repo ship NO executable .py -- most
commonly a GGUF repo whose config.json carries an auto_map copied from the original
model (e.g. unsloth/Llama-3_1-Nemotron-Ultra-253B-v1-GGUF references
modeling_decilm.py, which the GGUF-only repo does not contain). A GGUF model loads
through llama.cpp, which never executes auto_map, and transformers cannot run a file
that is not present, so there is nothing to scan and trust_remote_code is a no-op.
The fail-closed change treated this empty result the same as "code is present but we
could not fetch it" and hard-blocked the load. Distinguish the two: repo_remote_code_files
now RAISES RemoteCodeUnscannable when code is present but cannot be fully fetched or
listed (offline / gated / transient / a present .py that 404s / a listing failure),
and returns an empty dict only when the listing succeeded and the repo genuinely ships
no executable .py. The consent gate blocks on the exception (fail closed) and allows the
empty case as a no-op. Real unscannable code still hard-blocks; eicar and CRITICAL/HIGH
custom code are unaffected.
Verified against all 37 unsloth/*Nemotron* models (two GGUF repos were false-blocked,
now load) and the existing matrix (eicar still blocks; DeepSeek-OCR / NVLM-D-72B still
prompt approvable consent). Tests updated to expect the raise for unscannable cases and
added for the no-executable-code no-op.
* Ignore vestigial auto_map in GGUF repos (llama.cpp never runs it)
A GGUF repo's config.json is often copied verbatim from the original
transformers model, auto_map and all, but a GGUF load goes through
llama.cpp which never executes auto_map, so the config is inert. Treat
a direct .gguf reference, and a repo that ships .gguf weights with no
.safetensors, as having no remote code so the consent flow is never
triggered. A mixed repo with both .gguf and .safetensors is still gated,
since the safetensors variant would load through transformers where
auto_map does run. The check sits behind the existing auto_map-present
gate so normal models pay no extra repo listing.
* Add scanner-result copy to the remote-code consent dialog
Make the consent dialog state the scan outcome in plain language for
every model. When the static scan finds nothing, reassure the user with
'Our automatic scanner did not flag any worrying files, but please
double check.' (shown only for the clean, approvable case). When the
scan flags custom code or unsafe files, label the list with 'Our
automatic scanner flagged issues including:'. The Hugging Face
attribution for unsafe files stays in the dialog description.
* Close GGUF-suffix consent bypass for repo ids ending in .gguf
The .gguf short-circuit in _config_has_auto_map skipped the scan for any
model name ending in .gguf, including a bare two-segment repo id like
'evil/model.gguf'. Such a repo can still ship safetensors plus auto_map
Python that transformers would execute, so skipping the scan was an
asymmetric bypass (file_security already scans those repos). Restrict the
short-circuit to genuine direct GGUF file references via
_is_direct_gguf_file_ref: a local .gguf path, or a remote repo_id plus
filename (three or more segments). A two-segment repo id named *.gguf now
falls through to the config scan and _is_gguf_repo file inspection, so it
only skips consent when it actually ships .gguf weights and no safetensors.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Align consent dialog body with the title and fix narrow-width overflow
The scan results (the 'Our automatic scanner...' label, finding/unsafe
cards, and the clean-scan reassurance) sat at the dialog's left padding
while the title and description were indented past the status icon, so
the body did not line up under the description. Move the title,
description and results into one column to the right of the icon so they
share a left edge, and let that column fill its width so the description
no longer wraps early.
Also stop a wide code snippet from pushing the dialog off-screen on
narrow viewports: AlertDialogHeader is a grid with place-items-center,
which sized the content row to its content; give the row w-full so it
fills the track, and add min-w-0 down the results chain so the snippet
scrolls inside its card instead of widening the dialog. Verified aligned
and contained from mobile portrait through ultrawide.
* Treat a repo as GGUF-only only when it ships no transformers weights
_is_gguf_repo excluded only .safetensors, so a repo with a .gguf and a
pytorch_model.bin (or .pt/.pth/.h5/.msgpack/.onnx/.ckpt) and no
safetensors was treated as GGUF-only and skipped the consent scan, even
though transformers can load that weight set and execute the repo's
auto_map code. Require the absence of ANY transformers-loadable weight
before treating the repo as a llama.cpp-only GGUF load. A genuine
GGUF-only repo (only .gguf) is still inert; a mixed repo with any pickle
or safetensors weight is gated. Adds a regression test across all the
non-safetensors weight formats.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Block flagged subdir weight shards referenced by a root index
The malware gate treated every subdirectory file as non-loadable, but
from_pretrained deserializes a subdir shard a root index references
(pytorch_model.bin.index.json -> shards/...-00001-of-00002.bin). Read the
root weight indexes and block a flagged subdir pickle the weight_map
points at; a flagged subdir pickle no index lists (NeMo nemo/*.distcp)
stays non-blocking, and an inconclusive index lookup fails closed.
* Pass hf_token to the export checkpoint load
ExportBackend.load_checkpoint scanned with hf_token in the worker but
loaded the weights unauthenticated, so a gated/private checkpoint passed
preflight then 401'd at from_pretrained. Add hf_token to load_checkpoint
and forward token to every from_pretrained branch; the worker passes the
command's hf_token.
* Scope created_by_scan to every HF cache the discard searches
created_by_scan used get_cache_path (active HF_HUB_CACHE only) while
/discard-remote-code deletes across active, legacy, and default caches. A
repo the user already had in a legacy/default cache was marked
scan-created and deleted on decline. Check all three caches for the repo
dir before declaring the scan created it.
* Scan the full .py closure of external auto_map repos
An auto_map cross-repo ref (owner/name--module.Class) only had its entry
file downloaded, but transformers also fetches that file's relative
imports from the same repo, so a dangerous helper.py was left outside the
scanned fingerprint. List each external repo's .py and scan the whole set
(plus the referenced entry files); fail closed if the repo cannot be
listed or fetched.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fail closed when a weight index cannot be fully read
_indexed_shard_paths treated a partial result as definitive: if one weight
index read cleanly but another failed transiently, it returned the shard
paths it did see. A flagged subdirectory pickle listed only by the index we
could not read would then be classed as "not a load input" and skipped,
re-opening the very fail-open this guard was added to close.
Return None whenever any index read is inconclusive, even if another read
cleanly, so the caller blocks the already-flagged subdir pickle. A repo that
ships no index files raises EntryNotFoundError for each (never inconclusive)
and still returns an empty set.
* Match cached repos case-insensitively in the created_by_scan guard
_repo_in_any_hf_cache resolved casing only against the active cache and then
probed every cache with an exact directory name. A case-variant already
present in a legacy or default cache (models--Unsloth--Foo for a scan of
unsloth/foo) was missed, so the repo was marked created_by_scan and deleted
on decline -- but discard_remote_code_download deletes case-insensitively,
so that delete would hit the user's pre-existing cache entry. Detect
case-insensitively too, mirroring the deletion path.
* Skip remote-code and security review for selected GGUF variants
validate_model ran the trust_remote_code and Hugging Face security-scan
preflight against the repo even when the selected artifact is a .gguf. A
GGUF loads through llama.cpp, which never executes the repo's auto_map
Python and never deserializes root pickle weights, so repo-level Transformers
artifacts (a config.json with auto_map, or an unsafe pytorch_model.bin next
to the .gguf in a mixed repo) are inert for that load. Gating the GGUF on
them is a false positive. Run both preflights only for non-GGUF loads.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Scope the malware gate to actual load roots and serialized files
Two fixes to evaluate_file_security so it neither misses a load-path pickle nor
false-blocks an inert file:
- Honor subdirectory load roots. Spark-TTS / BiCodec call from_pretrained on the
snapshot's LLM subdirectory, so a flagged pickle directly under it is a
root-level load artifact there. A new load_subdirs parameter (set from the
model's audio type via security_load_subdirs) reclassifies those files relative
to the load root and looks for weight indexes under it, so a flagged shard in
that subdir is no longer skipped as "not root-level".
- Exempt source files. A root .py is never deserialized by from_pretrained;
executable repo code runs only through auto_map, which the remote-code consent
gate scans. Flagging a Python helper here would false-block a repo that merely
ships a build or train script.
* Scan a LoRA adapter and base as one consent unit, and gate MEDIUM code
A LoRA load runs both the adapter's and the base's repo code. The consent gate
scanned them separately and pinned one fingerprint per repo, so an adapter that
shipped its own auto_map code was either never shown in the dialog (which only
saw the base) or impossible to approve with the base's fingerprint.
evaluate_remote_code_consent_for_targets now scans all of a load's repos as a
single combined unit and pins ONE fingerprint over the union of their code, so
approving the load approves every repo's code together. evaluate_remote_code_consent
becomes a thin single-target wrapper, and an unscannable target fails the whole
load closed.
Also gate MEDIUM findings: like HIGH they now block pending pinned approval, so a
direct API caller cannot run flagged code by setting trust_remote_code=True
without consenting. Only a clean scan loads without a fingerprint.
* Preflight a LoRA load's adapter and base as one combined consent scan
scan_model_remote_code rewrote a LoRA adapter to its base and scanned only the
base for remote code, so the dialog never surfaced an adapter's own auto_map
code. Scan the adapter and base together through
preflight_remote_code_consent_for_targets, which pins one combined fingerprint
the worker gate accepts. The malware preflight is also scoped to each target's
load subdirectories.
* Apply combined consent and subdir-aware malware scan in load workers
Each load worker (inference, export, training) evaluated remote-code consent
once per target with a single shared fingerprint, so a LoRA adapter that ships
its own auto_map code could not be approved by the base's fingerprint. They now
scan the adapter and base together via evaluate_remote_code_consent_for_targets,
which pins one combined fingerprint over the union of their code. The malware
scan in each worker is also scoped to the model's load subdirectories so a
flagged pickle under a from_pretrained load subdir is not missed.
* Report a consistent trust_remote_code requirement after a model loads
validate_model reports requires_trust_remote_code from the YAML default OR the
raw auto_map, but the load, already-loaded, and status responses reported only
the YAML default. A custom-code model approved and loaded via auto_map was then
reported as not requiring trust_remote_code, so the frontend stored false and a
later retry or rollback sent trust_remote_code=false and failed.
A shared resolver reports the same requirement for a loaded model (a value
stored at load time, else the trust_remote_code the load used, else the YAML
default, else the raw auto_map check), and the load response persists it so the
status and already-loaded paths stay consistent. The selected-GGUF security
review is also scoped to the model's load subdirectories.
* Run the consent gate on training resume and for YAML-only trust_remote_code
Three frontend gaps left a model loading without the trust_remote_code it needs:
- The shared consent helper returned early when the scan found no auto_map and no
unsafe files, dropping a requirement that comes from a model's Studio YAML
default (e.g. GLM-4.7-Flash). It now grants the caller's requirement with an
empty pin instead of sending trust_remote_code=false.
- Resume-from-history called startTraining directly with no consent gate, so a
resumed run whose model needs custom code (or an old run with no approved
fingerprint) hit the worker block with no dialog. It now runs the same gate as
a fresh start.
- HF export passed requiresTrustRemoteCode=false for every HF source, so a
YAML-only model could not flip the flag before export. It now signals the
requirement for HF sources.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Cover both LoRA repos in validate, report GGUF as inert, purge all declined repos
Three follow-on gaps from the combined adapter+base consent work:
- validate_model resolved requires_trust_remote_code from the base alone, so a
LoRA adapter that ships its OWN auto_map code (with a plain base) was reported
as not needing trust_remote_code and the consent dialog never opened. It now
checks the [adapter, base] target set, matching the scan route and the workers
(which already gate both) and the security review already running over both.
- The already-loaded, loaded, and status responses for a selected GGUF reported
requires_trust_remote_code from the model's YAML default. A GGUF loads through
llama.cpp, which never executes the repo's auto_map Python, so the requirement
is inert for that load. They now report False, matching validate_model (which
already skips both gates for GGUF) so a status refresh cannot flip the flag
back on.
- The remote-code scan downloads both the adapter's and the base's config, but
created_by_scan tracked only the primary, so a base the scan was first to pull
into the cache was left on disk when the user declined. The scan now reports
scan_created_repos (every repo it newly cached) and the decline cleanup purges
each; created_by_scan stays for older clients. The frontend falls back to the
primary flag when the list is absent.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Scan the repo the load fetches, purge external code on decline, harden consent pins
Six follow-on hardening fixes from a fresh review pass over the gate:
- The malware gate scanned the literal "Spark-TTS-0.5B/LLM" alias, but the trainer
downloads it as unsloth/Spark-TTS-0.5B and loads LLM/, so the alias 404'd and
failed open, missing a flagged LLM/ pickle. evaluate_file_security now resolves
the alias to the repo the loader fetches and scans LLM/ as a load root.
- security_load_subdirs relied only on tokenizer detection, which fails on an
unresolved alias or offline; it now also honors the Studio YAML audio_type
default, so a BiCodec LLM/ load root is not missed.
- The remote-code scan downloads external auto_map repos (owner/name--module.Class),
but the decline cleanup tracked only the model/adapter/base, leaving the external
untrusted code cached. The scan now enumerates external auto_map repos and reports
the ones it created in scan_created_repos, so a decline purges them too.
- External auto_map refs failed the whole load closed on a stale or mis-derived
dotted ref (sub.mod.py vs the real sub/mod.py) even though the actual file was
present and scanned. They now drop such refs when the repo listing is real, exactly
like the own-repo path; an empty/incomplete listing still fetches and fails closed.
- The combined consent fingerprint keyed code by the raw target string, so the scan
endpoint's canonicalized casing and a worker's raw user input produced different
pins for identical code, rejecting a valid approval. Hub repo ids are now folded to
lowercase in the key (local paths stay case-sensitive), so the pin tracks the code.
- Export threaded hf_token into the weight load but not into detect_audio_type /
is_vision_model, so a gated multimodal base 404'd in detection and fell through to
the text loader. Both probes now use the same token.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Thread the token through check-vision and guard the gate's parallel sites
The /check-vision endpoint classified a model without the hf_token, so a gated or
private vision model 404'd in the probe and was reported as a plain text model --
the same dropped-token shape as the export probes, at a sibling site. It now passes
the token like the neighboring /check-embedding endpoint.
Add deterministic consistency guards (tests/test_security_gate_consistency.py) that
enumerate the gate's parallel sites mechanically instead of relying on a review to
spot a missed sibling: every is_vision_model / is_embedding_model / detect_audio_type
caller under routes/ and core/ must thread the token, every GGUF response must report
trust_remote_code via the resolver or False (never the raw YAML default), and every
load worker that runs the malware or consent gate must resolve the LoRA base. A new
site that drops the token or mis-reports the requirement now fails CI directly.
* Narrow the LLM alias rewrite and make audio detection token-aware
Three fixes from the confirmatory review, one a regression from the previous round:
- _load_scan_target rewrote EVERY remote repo ending in "/LLM" to unsloth/<parent>,
so a real third-party repo named "<owner>/LLM" was scanned as unsloth/<owner>
while the loader still fetched the real repo -- a fail-open hole introduced when
the Spark-TTS alias handling was added. It now rewrites only a registry-known
bicodec alias; every other "/LLM" repo is scanned as itself.
- detect_audio_type cached results under the bare model name, so an unauthenticated
probe of a gated/private repo cached None and poisoned a later authenticated call
with the token. The cache is now keyed by (normalized_name, token_fingerprint),
matching the vision cache.
- The training fallback /check-vision call dropped the hf_token, misclassifying a
gated/private VLM when the config endpoint failed. It now passes the token, like
the getModelConfig call it falls back from; checkEmbeddingModel takes the token too.
Extend the consistency guards: every capability cache must be keyed by a tuple
including the token, so a cache re-declared as Dict[str, ...] fails CI.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Document the broad .py scan as deliberate and enforce it with a test
The remote-code scanner scans every .py in a repo once an auto_map exists, not
just the auto_map entry's static import closure. This is intentional: the entry
module can reach a sibling via an absolute import, importlib, or exec, none of
which a static relative-import closure follows, so closure-only scanning would be
a real bypass of a load-time RCE gate. The broad scan never under-scans; the cost
is that an unrelated benign script can over-block, which is the safe failure
direction (HIGH stays approvable; only CRITICAL hard-blocks).
Spell this out at both the local and remote scan sites so the choice reads as
deliberate, and add a test asserting an unrelated, never-imported .py is still
scanned -- so a future narrowing to the static closure fails CI.
* Purge a declined remote LoRA adapter the scan downloaded
scan_model_remote_code probed the created-by-scan state AFTER resolving the base,
but get_base_model_from_lora_identifier downloads a remote adapter's own
adapter_config.json, so the adapter looked already-cached and was dropped from
scan_created_repos. On decline the adapter -- including the auto_map .py the
preflight fetched -- was left on disk, defeating the "untrusted code is not left
on disk" guarantee for the adapter itself.
Snapshot the primary's cache state BEFORE base resolution and use it when marking
the adapter scan-created; on any probe error treat it as pre-existing so a decline
never deletes it. The base and external repos are unaffected (their configs are not
downloaded before their own probe). Add a test that models the mid-scan download
side effect, which the prior static-stub tests did not.
* Clear remote-code approval when the training model changes
Switching the training model from an approved custom-code model to a clean one
kept the previous model's trust_remote_code=true and approved fingerprint in the
store: setSelectedModel reset visionImageSize on a true switch but not the
remote-code approval. The clean model then trained with trust_remote_code=true,
which bypasses the compiler and disables fused cross-entropy.
Reset trustRemoteCode and approvedRemoteCodeFingerprint on a true model switch.
The new model's own YAML default is re-applied by loadAndApplyModelDefaults, and a
custom-code model still re-opens the consent dialog before training starts, so the
only change is that a clean model no longer inherits a stale approval.
* Trim verbose comments across the model-fetching hardening changes
Condense the explanatory comments and docstrings introduced across the
trust_remote_code consent gate, the malware/unsafe-file gate, the remote-code
scanner, the load workers, the model routes, and the security frontend into
fewer, tighter lines while preserving every security rationale (fail-open vs
fail-closed direction, the deliberate broad-scan anti-bypass note, the
empty-vs-unscannable distinction, stale-ref handling, and the alias-rewrite
spoof guard).
Comments and docstrings only. No code, logic, identifiers, or test behaviour
changed; verified comment-only via the AST/TypeScript checker (40/40), with the
backend test suite and frontend tsc green.
* Do not cache transient audio-detection failures
detect_audio_type cached _detect_audio_from_tokenizer's result
unconditionally, so a transient read failure (network error or 5xx,
returned as None) poisoned the cache and the later successful probe never
ran. Mirror the vision cache: _detect_audio_from_tokenizer now returns
(audio_type, definitive) and the caller caches only definitive results.
A read that succeeds with no audio tokens, or clean 404s for every
tokenizer path, stays a cacheable None; only a genuine transient failure
(connection error, timeout, 5xx, malformed body) skips the cache so the
next call retries.
---------
Co-authored-by: danielhanchen <michaelhan2050@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Michael Han