mirror of
https://github.com/unslothai/unsloth.git
synced 2026-04-28 03:19:57 +00:00
* Studio: make stop button actually stop generation The UI stop button routes through assistant-ui's cancelRun, which aborts the frontend fetch. Four issues combined to let llama-server keep decoding long after the user clicked stop: 1. request.is_disconnected() does not fire reliably behind proxies (e.g. Colab) that don't propagate fetch aborts. 2. llama-server defaults n_predict to n_ctx when max_tokens is not sent, so a cancelled request keeps producing tokens up to 262144. 3. The httpx.Client pool keeps TCP keep-alive, so even a cleanly closed stream reuses the same connection and llama-server's liveness poll never sees a disconnect. 4. No explicit backend route to cancel - every cancel path relied on is_disconnected. Changes: - Add POST /api/inference/cancel keyed by session_id/completion_id, with a registry populated for the lifetime of each streaming response. - Have the frontend (chat-adapter.ts) POST /inference/cancel on AbortController abort, alongside the existing fetch teardown. - Send max_tokens=4096 + t_max_predict_ms=120000 as defaults on every outbound chat completion to llama-server; honoured by user overrides. - Disable httpx keep-alive on the streaming client so connection close reaches llama-server and its 1s liveness check fires. No behaviour changes for non-streaming paths or for existing callers that already pass max_tokens/session_id. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio: harden stop-button cancel path and scope cancel route - Require at least one identifier for /api/inference/cancel so a missing thread id cannot silently cancel every in-flight generation. - Scope /cancel to a dedicated studio_router so it is not exposed under the /v1 OpenAI-compat prefix as a surprise endpoint. - Store a set of cancel events per key in _CANCEL_REGISTRY so concurrent requests on the same session_id do not overwrite each other, and deduplicate in _cancel_by_keys so the cancelled count reflects unique requests. - Always send session_id with chat completions (not only when tools are enabled) so non-tool GGUF streams register under it and are reachable from /cancel. - Register the non-GGUF stream_chunks path in the cancel registry too, so transformers-based stop-button works behind proxies that swallow fetch aborts. - Only apply the 2-minute t_max_predict_ms wall-clock cap when the caller did not pass max_tokens, so legitimate long generations on slow CPU/macOS/Windows supported installs are not silently truncated. - Remove the abort listener on normal stream completion so reused AbortSignals cannot fire a spurious cancel POST after the fact. * studio: close cancel-race and stale-cancel gaps in stop path - Register the cancel tracker before returning StreamingResponse so a stop POST that arrives during prefill / warmup / proxy buffering finds an entry in _CANCEL_REGISTRY. Cleanup now runs via a Starlette BackgroundTask instead of a finally inside the async generator body. - Add a per-run cancel_id on the frontend (crypto.randomUUID) and in ChatCompletionRequest so /api/inference/cancel matches one specific generation. Removes the stale-cancel bug where pressing stop then starting a new run in the same thread would cancel the retry. - Apply t_max_predict_ms unconditionally in all three llama-server payload builders (previously gated on max_tokens=None, which made it dead code for UI callers that always send params.maxTokens). Raise the default to 10 minutes so slow CPU / macOS / Windows installs are not cut off mid-generation. - Make _cancel_by_keys refuse empty input (return 0) so a future internal caller can not accidentally mass-cancel every in-flight request. - Accept cancel_id (primary), session_id, and completion_id on the /api/inference/cancel route. Unify the three streaming sites on the same _cancel_keys / _tracker variable names. - Annotate _CANCEL_REGISTRY as dict[str, set[threading.Event]]. * Add review tests for PR #5069 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio: harden stop-button cancel semantics and wall-clock cap - Make /inference/cancel match cancel_id EXCLUSIVELY when supplied. Previously the handler iterated ('cancel_id','session_id','completion_id') and unioned matches, so a stale cancel POST carrying {cancel_id:old, session_id:thr} would still cancel a later run on the same thread via the shared session_id. cancel_id is now a per-run exclusive key; session_id / completion_id are only used as fallbacks when cancel_id is absent. - Close the early-cancel race. If /inference/cancel lands before the streaming handler reaches _TrackedCancel.__enter__() (stop clicked during prefill / warmup / proxy buffering), the cancel was silently dropped. Stash unmatched cancel_ids in _PENDING_CANCELS with a 30 s TTL; _TrackedCancel.__enter__() now replays any matching pending cancel by set()-ing the event immediately after registration. - Make t_max_predict_ms = _DEFAULT_T_MAX_PREDICT_MS conditional on max_tokens is None at all three llama-server payload sites. The cap is a safety net for callers who leave max_tokens unset (otherwise llama-server defaults n_predict to n_ctx, up to 262144). Callers who set an explicit max_tokens are already self-limiting and must not be silently truncated at 10 minutes on slow CPU / macOS / Windows legitimate long generations. - Guard each StreamingResponse return with try/except BaseException so _tracker.__exit__ runs even if StreamingResponse construction or any preceding statement raises between _tracker.__enter__() and the BackgroundTask attachment. Prevents a registry leak on that narrow window. * studio: close TOCTOU race and restore wall-clock backstop on UI path - Close TOCTOU race in the pending-cancel mechanism. The previous fix split cancel_inference's (cancel_by_keys + remember_pending_cancel) and _TrackedCancel.__enter__'s (register + consume_pending) into four separate lock acquisitions. Under contention a cancel POST could acquire-then-release the lock, find the registry empty, and stash ONLY AFTER __enter__ had already registered and consumed an empty pending map -- silently dropping the cancel. Both call sites now do their work inside a single _CANCEL_LOCK critical section, via the new atomic helper _cancel_by_cancel_id_or_stash() and an inlined consume-pending step in __enter__. Reproduced the race under forced interleaving pre-fix; 0/2000 drops post-fix under parallel stress. - Apply t_max_predict_ms UNCONDITIONALLY at all three llama-server payload sites. The previous iteration gated the cap on `max_tokens is None`, which turned out to be dead code on the primary Studio UI path: chat-adapter.ts sets maxTokens=loadResp.context_length after every model load, so every chat request carries an explicit max_tokens and the wall-clock safety net never fired. The cap's original purpose is to bound stuck decodes regardless of the token budget; it must always apply. - Raise _DEFAULT_T_MAX_PREDICT_MS from 10 minutes to 1 hour. 10 minutes was too aggressive for legitimate slow-CPU chat responses (a 4096-token reply at 2 tok/s takes ~34 min); 1 hour accommodates that and still catches genuine zombie decodes. - Prune _PENDING_CANCELS inside _cancel_by_keys as well, so stashed entries expire proportionally to overall cancel traffic rather than only to cancel_id-specific POSTs. * studio: trim verbose comments and docstrings in cancel path * studio/llama_cpp: drop upstream PR hashes from benchmark comment * Add review tests for Studio stop button * Consolidate review tests for Studio stop button * Align cancel-route test with exclusive cancel_id semantics * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio: move cancel cleanup to generator finally; drop dead helper - Move _tracker.__exit__ from Starlette BackgroundTask into each streaming generator's finally block. Starlette skips the background callback when stream_response raises (OSError / ClientDisconnect), which leaked _CANCEL_REGISTRY entries on abrupt disconnect. - Check cancel_event.is_set() at the top of each GGUF while loop so a pending-replay cancel falls through to final_chunk + [DONE] instead of propagating GeneratorExit out of _stream_with_retry. - Remove unused _remember_pending_cancel; _cancel_by_cancel_id_or_stash superseded it. * Add review tests for Studio stop-button * studio: wire audio-input stream into cancel registry - Register cancel_event with _TrackedCancel on the audio-input streaming path so POST /api/inference/cancel can stop whisper / audio-input GGUF runs. Previously the registry stayed empty on this branch, so the stop button returned {"cancelled":0} and the decode ran to completion. - Apply the same finally-based cleanup and pre-iteration cancel-event check used on the other three streaming paths. - Update the _CANCEL_REGISTRY block comment to list cancel_id as the primary key (was stale "session_id preferred"). * Consolidate review tests for Studio stop-button cancel flow - Merge the 6 behavioral tests from test_stream_cleanup_on_disconnect.py (finally cleanup on normal/exception/aclose, pre-set cancel_event pattern, and its regressions) into test_stream_cancel_registration_timing.py, which is the PR's existing file covering the same area. - Extend structural invariants to include audio_input_stream alongside the three GGUF / Unsloth streaming generators: no _tracker.__enter__ inside the async gen body, cleanup via try/finally, no background= on StreamingResponse. - Delete test_stream_cleanup_on_disconnect.py (now empty). * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio: make cancel-via-POST interrupt Unsloth and audio-input streams Close two remaining gaps in the stop-button cancellation wiring: - stream_chunks (Unsloth path): add a top-of-loop cancel_event check and call backend.reset_generation_state() so cancel POSTs flush GPU state and close the SSE cleanly instead of relying on request.is_disconnected (which does not fire through proxies like Colab's). - audio_input_stream: run the synchronous audio_input_generate() via asyncio.to_thread so blocking whisper chunks do not freeze the event loop, matching the pattern already used by the GGUF streaming paths. * Add review tests for Studio stop-button cancel flow * Consolidate review tests for Studio stop-button cancel flow - Delete standalone test_cancel_registry.py at repo root: tests duplicated test_cancel_atomicity.py / test_cancel_id_wiring.py and re-implemented registry primitives inline (scaffolding). - Extend tests/studio/test_stream_cancel_registration_timing.py with regression guards for the iter-1 cancel-loop fixes: structural: each streaming generator checks cancel_event in its loop; audio_input_stream offloads next() via asyncio.to_thread; stream_chunks cancel branch calls reset_generation_state(). runtime: Unsloth loop breaks on external cancel and resets state; audio loop stays responsive under blocking next(); both loops emit zero tokens on pre-set cancel (replay path). * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio: extend stop-path to passthrough streams; tighten wall-clock cap - Lower _DEFAULT_T_MAX_PREDICT_MS from 1 hour to 10 minutes so the wall-clock backstop actually bounds runaway decodes when cancel signaling fails. - Wire _TrackedCancel and cancel_event.is_set() into _openai_passthrough_stream and _anthropic_passthrough_stream and disable httpx keepalive so stop requests from /v1 and /v1/messages tool-calling clients reach llama-server. - Apply t_max_predict_ms to the tool-passthrough request body so the backstop covers passthrough paths as well. - Symmetric pre-registration stash for session_id/completion_id cancels (_cancel_by_keys_or_stash) so early cancels by those keys replay on later registration like cancel_id. - Drop dead except BaseException guards around StreamingResponse() at four streaming sites; cleanup lives in the generator's finally. * studio: harden cancel registry against ghost-cancel and leak paths - Revert the session_id/completion_id stash in the fallback cancel helper. session_id is thread-scoped and reused across runs, so stashing it on an unmatched POST would fire cancel_event for the user's next unrelated request via _TrackedCancel.__enter__. cancel_id remains the only per-run unique key that gets stashed. - Default max_tokens to _DEFAULT_MAX_TOKENS in the tool-passthrough body. Mirror the direct GGUF path so OpenAI/Anthropic passthrough callers who omit max_tokens get the same zombie-decode cap instead of relying on the wall-clock backstop alone. - Wrap _openai_passthrough_stream setup with an outer try/except BaseException. The inner except httpx.RequestError does not catch asyncio.CancelledError at await client.send, which would otherwise leave _tracker registered in _CANCEL_REGISTRY indefinitely. - Frontend stop POST uses plain fetch + manual Authorization header instead of authFetch. A 401 on the cancel POST no longer refreshes tokens or redirects the user to the login page mid-stop. * Add review tests for Studio stop-button cancel flow * studio: trim comments on stop-button review changes Collapse multi-paragraph rationale blocks on the cancel registry, _openai_passthrough_stream, and the frontend onAbortCancel handler into one-line explanations of why the non-obvious behaviour exists. Drop authFetch import that became unused when the cancel POST switched to plain fetch. * Consolidate review tests for Studio stop-button cancel flow Move review-added tests out of test_cancel_dispatch_edges.py into the existing PR test files that already cover the same areas: - backend registry fan-out / exclusivity / idempotency / falsy-keys edge cases moved into tests/studio/test_cancel_atomicity.py - frontend plain-fetch (not authFetch) + manual Authorization header moved into tests/studio/test_cancel_id_wiring.py Delete the now-empty test_cancel_dispatch_edges.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: stop default-capping responses at 4096 tokens (follow-up to #5069) (#5174) * Studio: stop default-capping responses at 4096 tokens Follow-up to #5069. The 4096 default introduced for runaway-decode defense silently truncates any caller that omits max_tokens. The Studio chat UI sets params.maxTokens = loadResp.context_length after a GGUF load, so it's fine, but every other consumer is not: - OpenAI-API direct callers (/v1/chat/completions, /v1/responses, /v1/messages, /v1/completions) where the OpenAI default is effectively unlimited per response. langchain, llama-index, raw curl, and the openai SDK all rely on that. - Reasoning models. Qwen3 / gpt-oss reasoning traces routinely exceed 4096 tokens before the model emits a single visible content token. The user sees the trace cut off mid-thought. - Long-form generation ("write a chapter", "produce a full SVG"). Reproduced on this branch: gemma-4-E2B-it-GGUF Q8_0, prompt asking for a 10000-word story, no max_tokens in the request: finish_reason: stop (misleading -- should be 'length') content_chars: 19772 content_tail: ...'a comforting, yet immense, pressure.\n\n*"' Body ended mid-sentence on a stray opening quote, right at the 4096 token mark. After this patch the same request returns 38357 chars ending with '...held in a perfect, dynamic equilibrium.' -- a natural stop, not a truncation. Implementation: rename the constant to _DEFAULT_MAX_TOKENS_FLOOR and set it to 32768. Each call site now uses the model's effective context length when known, falling back to the floor: default_cap = self._effective_context_length or _DEFAULT_MAX_TOKENS_FLOOR The 10-minute t_max_predict_ms wall-clock backstop from #5069 is preserved as the second line of defense. Plumbed _build_passthrough_payload + _build_openai_passthrough_body through the routes layer so the Anthropic and OpenAI passthrough paths also respect the model's context length. * [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: cancel passthrough streams during llama-server prefill + route through apiUrl for Tauri Three reviewer-flagged correctness gaps in the stop-button mechanism. 1) `_openai_passthrough_stream` could not honor cancel during prefill. The cancel check ran inside the `async for raw_line in lines_iter` body, so a cancel POST that arrived before llama-server emitted the first SSE line was unobservable until prefill completed. With a long prompt under proxy/Colab conditions -- the exact target scenario for this PR -- that left the model decoding for a long time after the user clicked Stop. Add an asyncio watcher task that closes `resp` as soon as `cancel_event` is set, raising in `aiter_lines` so the generator can exit. The watcher polls a threading.Event because the cancel registry is keyed by threading.Event for the synchronous /cancel handler. 2) `_anthropic_passthrough_stream` had the same blocking-prefill pattern. Same fix. 3) The frontend's stop-button cancel POST used a bare relative `fetch("/api/inference/cancel", ...)`, which targets the webview origin in Tauri production builds (where the backend is at `http://127.0.0.1:8888`). Route through the existing `apiUrl()` helper from `lib/api-base.ts` to match every other Studio call. Browser/dev builds get the empty base, so behavior is unchanged there. Verified via temp/pr_simulation/sim_5069_prefill_cancel.py: cancel during prefill terminates within ~250ms on both passthrough paths (was 145s+ on the Anthropic path before this change), and the standard non-passthrough chat path still cancels with no regression. * Studio: log cancel-body parse errors instead of silently swallowing Reviewer-flagged defensive logging gap. The bare `except Exception: pass` in `cancel_inference` would mask malformed payloads that hint at a buggy client or a transport issue. Log at debug so future investigation isn't left guessing whether `body={}` came from a missing body or a parse failure. Behavior is unchanged: an unparseable body still falls through to the empty-dict path and the cancel call returns `{"cancelled": 0}`. * Studio: Anthropic passthrough cancel parity with OpenAI passthrough Two reviewer-flagged consistency gaps in the cancel surface for /v1/messages. 1) Anthropic passthrough did not register cancel_id, so a per-run cancel POST (the cleanest Studio-style cancel path) silently missed when the route hit `_anthropic_passthrough_stream`. The OpenAI passthrough has registered (cancel_id, session_id, completion_id) since this PR was first opened; mirror that here. Also add `cancel_id` to `AnthropicMessagesRequest` so the route handler can plumb it through. 2) The cancel handler's fallback key list checked only completion_id and session_id, never message_id. Anthropic clients that send their native `id` (returned in the SSE message_start event) for cancel had no way to hit the registry. Add message_id to the fallback list. Verified via temp/pr_simulation/sim_5069_prefill_cancel.py: P2 now cancels by cancel_id in 137ms (was hanging pre-fix), and the new P2b case cancels by message_id in 77ms. P1 (OpenAI) and P3 (standard chat) still pass with no regression. --------- Co-authored-by: danielhanchen <michaelhan2050@gmail.com> 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: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
169 lines
6.4 KiB
Python
169 lines
6.4 KiB
Python
"""
|
|
Wiring tests for the per-run cancel_id field.
|
|
|
|
A chat-thread-scoped session_id is not safe as a cancel key because a
|
|
late stop POST can match a subsequent run on the same thread. The fix
|
|
adds cancel_id (a fresh UUID per generation) that is sent both in the
|
|
completion payload and in the /api/inference/cancel body.
|
|
|
|
Verifies:
|
|
- ChatCompletionRequest exposes an Optional[str] `cancel_id` field.
|
|
- /api/inference/cancel accepts `cancel_id` as the first-preferred key.
|
|
- OpenAIChatCompletionsRequest (frontend type) includes cancel_id.
|
|
- chat-adapter.ts generates a per-run cancelId (crypto.randomUUID
|
|
with a Math.random fallback), sends it in the completion payload,
|
|
and includes it in the /inference/cancel body on abort.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import ast
|
|
import re
|
|
from pathlib import Path
|
|
|
|
|
|
WORKSPACE = Path(__file__).resolve().parents[2]
|
|
MODELS_SRC = (WORKSPACE / "studio/backend/models/inference.py").read_text()
|
|
ROUTES_SRC = (WORKSPACE / "studio/backend/routes/inference.py").read_text()
|
|
ADAPTER_SRC = (
|
|
WORKSPACE / "studio/frontend/src/features/chat/api/chat-adapter.ts"
|
|
).read_text()
|
|
API_TYPES_SRC = (
|
|
WORKSPACE / "studio/frontend/src/features/chat/types/api.ts"
|
|
).read_text()
|
|
|
|
|
|
def _find_class(tree: ast.AST, name: str) -> ast.ClassDef | None:
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.ClassDef) and node.name == name:
|
|
return node
|
|
return None
|
|
|
|
|
|
def test_chat_completion_request_has_cancel_id_field():
|
|
tree = ast.parse(MODELS_SRC)
|
|
cls = _find_class(tree, "ChatCompletionRequest")
|
|
assert cls is not None
|
|
fields = {
|
|
n.target.id
|
|
for n in cls.body
|
|
if isinstance(n, ast.AnnAssign) and isinstance(n.target, ast.Name)
|
|
}
|
|
assert "cancel_id" in fields, (
|
|
"ChatCompletionRequest must expose a cancel_id field for per-run "
|
|
"cancellation routing"
|
|
)
|
|
|
|
|
|
def test_cancel_route_matches_cancel_id_exclusively_when_present():
|
|
# A stale cancel POST carrying cancel_id AND session_id must not
|
|
# cancel a later run on the same thread via the shared session_id.
|
|
# Enforce this by requiring the handler to early-return through an
|
|
# exclusive-cancel_id path -- either an atomic helper or a keys
|
|
# list containing ONLY cancel_id (never session_id).
|
|
for node in ast.walk(ast.parse(ROUTES_SRC)):
|
|
if isinstance(node, ast.AsyncFunctionDef) and node.name == "cancel_inference":
|
|
break
|
|
else:
|
|
raise AssertionError("cancel_inference handler missing")
|
|
|
|
cancel_id_exclusive_branch = False
|
|
for sub in ast.walk(node):
|
|
if not isinstance(sub, ast.If):
|
|
continue
|
|
test_src = ast.unparse(sub.test)
|
|
if "cancel_id" not in test_src or "isinstance" not in test_src:
|
|
continue
|
|
branch_src = "\n".join(ast.unparse(s) for s in sub.body)
|
|
before_return = branch_src.split("return", 1)[0]
|
|
matches_cancel_id_only = (
|
|
"_cancel_by_cancel_id_or_stash(cancel_id)" in branch_src
|
|
or "_cancel_by_keys([cancel_id])" in branch_src
|
|
)
|
|
if matches_cancel_id_only and "session_id" not in before_return:
|
|
cancel_id_exclusive_branch = True
|
|
break
|
|
assert cancel_id_exclusive_branch, (
|
|
"cancel_inference must early-return with an exclusive cancel_id "
|
|
"match when a cancel_id is supplied, so a stale stop POST "
|
|
"cannot cancel a later run on the same thread via session_id"
|
|
)
|
|
|
|
|
|
def test_cancel_route_falls_back_to_session_or_completion_when_no_cancel_id():
|
|
for node in ast.walk(ast.parse(ROUTES_SRC)):
|
|
if isinstance(node, ast.AsyncFunctionDef) and node.name == "cancel_inference":
|
|
break
|
|
else:
|
|
raise AssertionError("cancel_inference handler missing")
|
|
|
|
src = ast.unparse(node)
|
|
assert "session_id" in src and "completion_id" in src, (
|
|
"cancel_inference must still accept session_id / completion_id as "
|
|
"fallback keys when cancel_id is absent"
|
|
)
|
|
|
|
|
|
def test_frontend_request_type_has_cancel_id():
|
|
assert re.search(
|
|
r"cancel_id\?\s*:\s*string\s*;", API_TYPES_SRC
|
|
), "OpenAIChatCompletionsRequest must expose an optional cancel_id"
|
|
|
|
|
|
def test_chat_adapter_generates_cancel_id_per_run():
|
|
m = re.search(
|
|
r"const\s+cancelId\s*=\s*([^;]+);",
|
|
ADAPTER_SRC,
|
|
)
|
|
assert m, "chat-adapter.ts must declare a per-run `cancelId` constant"
|
|
rhs = m.group(1)
|
|
assert (
|
|
"randomUUID" in rhs
|
|
), "cancelId should prefer crypto.randomUUID() for uniqueness"
|
|
|
|
|
|
def test_chat_adapter_sends_cancel_id_in_completion_payload():
|
|
assert "cancel_id: cancelId" in ADAPTER_SRC, (
|
|
"chat-adapter.ts must include cancel_id in the streamChatCompletions "
|
|
"request payload so the backend registers under that key"
|
|
)
|
|
|
|
|
|
def test_chat_adapter_sends_cancel_id_in_abort_cancel_post():
|
|
m = re.search(
|
|
r"const\s+onAbortCancel\s*=\s*\(\)\s*=>\s*\{(.*?)\};",
|
|
ADAPTER_SRC,
|
|
flags = re.DOTALL,
|
|
)
|
|
assert m, "onAbortCancel arrow function missing"
|
|
body = m.group(1)
|
|
assert re.search(r"cancel_id\s*:\s*cancelId", body), (
|
|
"onAbortCancel must include cancel_id in the /inference/cancel body "
|
|
"so a stop POST matches the specific run, not the whole thread"
|
|
)
|
|
|
|
|
|
def test_abort_cancel_post_uses_plain_fetch_with_manual_auth_header():
|
|
# authFetch redirects to login on 401, which would kick the user to
|
|
# the login page mid-stop if the access token expired during a long
|
|
# stream. Use plain fetch + manual Authorization header for a
|
|
# best-effort cancel that never triggers the refresh/redirect flow.
|
|
start = ADAPTER_SRC.find("const onAbortCancel")
|
|
assert start >= 0, "onAbortCancel handler missing"
|
|
rest = ADAPTER_SRC[start:]
|
|
end = rest.find("\n try {")
|
|
body = rest if end < 0 else rest[:end]
|
|
assert "/api/inference/cancel" in body
|
|
assert "authFetch(" not in body, (
|
|
"onAbortCancel must NOT call authFetch; a 401 from it would "
|
|
"redirect the user to the login page during a stop click"
|
|
)
|
|
assert "fetch(" in body, "onAbortCancel must use plain fetch(...)"
|
|
assert "getAuthToken" in body, (
|
|
"onAbortCancel must read the bearer token via getAuthToken() "
|
|
"rather than relying on authFetch's 401 flow"
|
|
)
|
|
assert "Authorization" in body
|
|
assert (
|
|
"keepalive: true" in body
|
|
), "keepalive is required so the fetch survives page unload during stop"
|