* fix(otel): emit cache token counts on OTel v2 LLM spans
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): trim comment in LLMUsage adapter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): drop casts in LLMUsage cache token adapter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(deps): bump restrictedpython to 8.3 for GHSA-ffg3-p8fm-mjx2
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 40edeaaecb)
Cherry-pick of #38973 onto rc/1.99.0, same failure mode as #38917:
Wolfi's python3 roll to 3.14 breaks the uvloop 0.21.0 sdist build.
(cherry picked from commit 0f84a7053a)
Cherry-pick of #38917 onto rc/1.99.0 so the release Docker builds stop
picking up Wolfi's python 3.14 roll, which has no uvloop 0.21.0 wheel
and fails the sdist build.
(cherry picked from commit f814945d4c)
Both anchoring tests read the trigger's box before the click and the popup's box the
instant it turns visible. Base UI places the popup asynchronously and opening it can
shift the trigger, so both boxes could be sampled before the layout settled. The run
on 1eedaa3a43 missed by 4.2px (expected >= 446.015, got 441.799) on a tree with no UI
changes at all, having passed on 21092d633b, which differs only in a deleted python
test and a budget json.
Each assertion now re-reads both boxes under expect.poll. The conditions themselves
are unchanged: the popup must sit at or below the trigger's bottom edge in the first
test and must not overlap it in the second. Polling cannot mask a genuinely misplaced
popup, since one that never lands correctly still fails when the poll times out.
(cherry picked from commit d8679508d4)
litellm-e2e-ui 68 failed the test this PR was meant to stabilise: "fallback
never took effect", streak 4 of a required 5, 60s timeout. Requiring a
consecutive streak of 200s after the fallback is set was wrong. It asserts that
the fallback path succeeds five times running, which is a reliability claim the
test never intended to make, and the path is inherently retry-ish because the
broken primary is attempted first on every call. One intermittent non-200
resets the streak, so a mostly-working fallback never converges.
The two directions are not symmetric:
before the write proving NO replica serves it -> needs every replica
after the write proving the fallback serves it -> one success is the claim
So the control keeps a multi-sample window and the success assertion goes back
to polling for a first sighting, on the wider 60s budget rather than the
original 30s that expired on litellm-e2e-ui 63.
Also drops the two local rebinds Greptile flagged against the repo's
no-reassignment convention: the streak counter is gone with the helper it lived
in, and the cache-round loop is now a lazy generator consumed by next().
(cherry picked from commit b95801172c)
Two e2e tests fail on timing rather than on litellm behaviour. Measured over the
last ~35 litellm-e2e / litellm-e2e-ui runs:
routerSettings.spec.ts:254 9/35 runs (7 flaky-on-retry, 2 hard failures)
test_cost_headers_e2e.py 1/29 runs it appeared in
Router fallback control
-----------------------
The e2e stack runs replicaCount 2 with proxy_config_reload_interval_seconds 7,
and every request is routed independently, so an observation of the new config
only proves the replica that served it reloaded. patchRouterSettings returns as
soon as /config/update returns, and clearBrokenFallback never waits at all, so a
retry's one-shot control assertion could be answered by a sibling replica still
holding the previous attempt's fallback. That is exactly the observed pair of
errors: "fallback never took effect" on the first attempt and "broken primary
unexpectedly succeeded on its own" on the retry.
Both assertions now poll for a consecutive streak spanning more than one reload
cycle, mirroring the PROPAGATION_TIMEOUT / settle_propagation doctrine the Python
suite already applies in e2e_config.py.
Cost-header cache read
----------------------
The prime and measure calls fired back to back with no gap, and each retry threw
away the prefix it had just paid to prime in favour of a fresh one. OpenAI
publishes a primed prefix asynchronously and routes cache lookups by
prompt_cache_key, so the test was rerolling the least likely path to a hit.
Each round now pins a prompt_cache_key and re-reads the same primed prefix up to
CACHE_REREADS times before rotating, so a fresh prefix is spent only after the
primed one has genuinely failed to become readable.
No production code changes; prompt_cache_key is added to the e2e ChatBody model,
which serializes exclude_none and so is inert for every other caller.
(cherry picked from commit 84dfc18f6b)
The two vision tests pointed at a Wikipedia-hosted cat photo, so every run
depended on upload.wikimedia.org staying up and unthrottled. It throttled,
and the 429 surfaced as a bedrock APIConnectionError, which reads as a
gateway failure rather than what it was.
The image is now a fixture in the repo, passed as a data URL. That also puts
the two providers on the same bytes: litellm downloads the image itself for
bedrock, while openai is handed the link and fetches it from its own servers,
so the hosted URL quietly meant the two tests were not testing the same thing.
The image was generated for this repo rather than borrowed, so nothing here
carries a third-party license. Also drops a stale comment about openai prompt
caching that sat above the vision helper; no caching test uses it.
(cherry picked from commit ff418ffb9c)
Google withdrew gemini-live-2.5-flash-preview-native-audio-09-2025 from the
Vertex Live API. Every session dies at setup:
received 1007 (invalid frame payload data)
gemini-live-2.5-flash-preview-native-audio-09-2025 is not supported in the live api.
The client sees session.created (the proxy synthesizes it on connect) and then
nothing, so both vertex_ai realtime tests time out waiting for session.updated.
Confirmed by probing the Vertex Live endpoint directly with the e2e stack's own
credentials:
gemini-live-2.5-flash-preview-native-audio-09-2025 -> 1007, not supported
gemini-live-2.5-flash-native-audio -> setupComplete
so this swaps to the non-preview sibling, which is the same native-audio class
and is what the cost map already carries for vertex_ai.
Not a litellm regression. The suspicion fell on #38395 because it removed the
native-audio speechConfig strip, but the setup payload this suite sends is
byte-identical either side of that change: the strip only fires when a client
sends a voice, and the e2e SessionConfig has no voice field. Google's rejection
names the model, not a field.
The gemini (Google AI Studio) provider keeps the -09-2025 id, which still works
there; only the Vertex endpoint dropped it.
(cherry picked from commit a215ecaf3d)
* fix(ui): let the paginated search select keep what the user types
The combobox handed Base UI a freshly built option object for the current
selection every time a page of results came back. Base UI answers a changed
value by rewriting the input with that option's label, so every search response
wiped the query mid-typing and the list never narrowed. Once a user had been
picked in the Usage page filter box, no other user could be reached.
The component now owns the input text. It holds the query while the list is
open, falls back to the selected option's label once the list closes, and
remembers the picked option so its label survives later pages that no longer
carry it, the way the multi-select sibling already does.
* refactor(ui): name the paginated select's search state instead of commenting it
* fix(ui): start a fresh query when typing lands on the selected label
Focusing the filter box without clicking it leaves the caret at the end of the
selected option's label, so the next keystroke extended that label into a query
no server could match. Only a click cleared the box first.
A keystroke that arrives while the box is showing a label is now read as the
start of a new query, wherever in the label it landed.
(cherry picked from commit 3746ba58d7)
The shared SelectContent wrapper defaulted alignItemWithTrigger to true,
which puts Base UI's positioner into item-aligned mode and places the
popup so the active item sits on top of the trigger. In that mode the
side and sideOffset the wrapper passes two lines above are ignored, and
the popup reports data-side="none".
The overlap only becomes visible once the items are tall enough to
matter, which is why the autorouter Template picker shows it clearly:
its options are three-line cards, so the popup covers both the select
box and its own label.
No call site in the dashboard asked for item-aligned mode. 21 of them
across 15 files already passed alignItemWithTrigger={false} by hand to
undo the default, and the remaining 127 inherited the bug. Flipping the
default makes side and sideOffset live, so collision handling works and
a select with no room below now flips above the trigger rather than
covering it. The 21 hand-written opt-outs are deleted as redundant.
(cherry picked from commit 71449b9c55)
The playground message bubble painted its fill, border and avatar circle from
inline hex values, so in dark mode both bubbles stayed near-white while the text
inherited the dark foreground: the message body was unreadable. The MCP-events
placeholder bubble in ChatUI carried the same three fills.
They move onto the tokens the rest of the sweep already uses, so the assistant
surface is bg-card over border-border and the user surface is the info tint at
the same weight the other selected-state surfaces take. Light mode keeps the
same colour family it had.
The regression test asserts the token classes and that no inline style survives
on either surface, which is the exact shape the bug took.
(cherry picked from commit 3fb1009f81)
The tooltip popup is an inline-flex row, so the four sibling blocks passed as a fragment laid out side by side in four columns. Wrap them in a single flex-col container instead.
The inline code samples also used bg-muted, which is defined against the page surface, not the inverted tooltip surface, so they rendered as near-white chips carrying near-white text. Tint them from the popup's own token instead.
(cherry picked from commit 6db5a5d660)
The virtual key shown after creating a key sits in a div with a
hardcoded #f8f8f8 inline background, so in dark mode the box keeps
the light background while the key text inherits the light foreground
color, leaving the key nearly unreadable. Swap the inline styles for
the bg-muted and text-foreground tokens, which resolve per theme.
(cherry picked from commit 5f56be3294)
* test: add regression coverage for twelve closed issues
Adds targeted regression tests for behavior that was fixed but left ungated,
so the fixes cannot silently regress:
- #33772 openai cache_write_tokens cost
- #34309 Responses API cache cost_breakdown
- #35363 /v1/responses batch spend
- #36619 auto-router api_base/api_key leak on a shared model name
- #35359 batch fallbacks within the owning model group
- #36523 passthrough streamed Responses spend log
- #36646 passthrough embeddings spend log
- #37147 non-object metadata on create_batch is a 400
- #35362 unscoped list files reads the managed-file store
- #33221 gpt-5.6 bridges to Responses on function tools alone
- #34487 LLM complexity classifier runs for every caller metadata shape
- #35124 streamed /v1/messages emits success logging on both bridges
Cost assertions read rates from litellm.model_cost rather than hardcoding
dollar amounts, so they do not drift on repricing.
* fix: stop the new regression tests polluting and tripping over shared global state
Two shard failures, both from global state the new tests share with their
neighbours rather than from the behaviour under test.
test_main.py's local_cost_map pinned litellm.model_cost but left the
get_model_info lru_cache warm, so completion_cost billed at whatever prices
were cached earlier in the process while the assertions read the pinned map.
Clear the cache on both sides of the fixture, matching the local_model_cost_map
fixture in tests/test_litellm/conftest.py.
The anthropic messages streaming tests called GLOBAL_LOGGING_WORKER.flush()
on whatever queue happened to be around. A queue left non-empty by an earlier
test is still bound to that test's loop, so join() either hangs or raises
"bound to a different event loop". Rebind to the running loop before the call
and wait for the captured payload instead of a fixed sleep.
An empty content list, or one holding only opaque blocks, still lets the
provider-bound branch replay the summary text. The inspection path treated
any non-None content as final, so that replayed text stayed invisible to
guardrails and token counting.
The field is declared optional on OpenAIFileObject and its own docstring says it
is absent on every upload guardrails did not touch, but the /v1/files routes have
no response_model, so FastAPI falls through to jsonable_encoder with exclude_none
off and serialises the unset default as an explicit null. Every create and
retrieve response on a proxy with no guardrails configured at all picked up a
litellm_batch_guardrail: null it never had before, and so did every row of a file
list, since those rows are the same object.
A wrap serializer drops the key only when nothing set it, so the populated report
still reaches the wire intact, including a record whose guardrail is null. The
managed-files list route spreads a stored file_object blob rather than the model,
so rows persisted before this lands keep their null until it is dropped there too.
* test(e2e): send no-cache on every cacheable request body, opt in only where a hit is the assertion
The e2e proxy runs with the response cache on, so any test that re-sends an
identical chat, messages, responses, completions, embeddings or rerank body
reads back a redis copy of an earlier call instead of reaching the provider.
Five tests in the last week failed that way. Default cache: {"no-cache": true}
on those request models and pass cache=None only in the two tests whose
assertion is the cache hit itself.
* test(e2e): give image edits and OCR a 180s client timeout
Both routes wait on providers that can legitimately take longer than the
60s transport-wide request timeout (gpt-image edits, Azure Document
Intelligence), and a client-side read timeout there fails a green request.
post/upload now accept a per-call timeout like get already does; only those
two call sites use it.
* test(e2e): rerun once on network errors and upstream 5xx only
Assertion failures still fail on the first attempt; only an outcome whose
error string carries the e2e_http network kind or a 5xx status gets one
more try. Test Engine records every attempt, so the flake rate stays
visible while a single provider blip no longer reds the rc run.
* test(e2e): let the reseed burst survive one upstream failure and print why
The burst is the precondition, not the property: one 5xx among six
concurrent calls still leaves five workers racing the cold counter, which
is what the reseed assertion measures. Two or more failures still abort,
and the failing bodies are now in the message instead of only the status
codes.
* test(e2e): keep polling Jaeger through a transient query failure
poll_traces_for_call already waits up to POLL_TIMEOUT for spans to land,
but a single refused connection to the query API failed the test on the
spot. Jaeger restarted twice during today's gate runs (19:05 and 19:41
UTC, each under a minute) and took ten and three otel tests with it while
the same tests passed on the rc build minutes later. A network failure
now counts as not-yet inside the same deadline; if Jaeger is still
unreachable when the deadline passes the test fails with that error, and
any non-network failure still fails immediately.
A reasoning input item that carries only summary text is replayed to the
provider as reasoning_content, so inspection-only callers must see that
text too. They used to fall through to the generic content branch, which
reads content and drops a summary-only item, leaving guardrails and token
counters blind to text the model still receives.
litellm_request_total_latency_metric's start_time is set inside
common_processing_pre_call_logic, which only runs after user_api_key_auth
has already succeeded, so the metric silently excluded authentication and
pre-call setup time despite being documented as total request latency. The
sibling litellm_request_queue_time_seconds metric had the same problem:
its arrival_time was captured after auth too, despite its own comment
claiming to track when the request arrived at the proxy.
request.state.litellm_received_at is now stamped unconditionally at the
very first line of user_api_key_auth (previously only when OTEL was
configured), giving a timestamp that precedes all auth work. Both metrics
now derive from it: queue_time_seconds genuinely spans arrival through the
start of pre-call processing, and the total-latency metric adds that
queue time on top of its existing start/end window so it becomes true
end-to-end latency.
queue_time_seconds ends exactly at start_time rather than a separately
captured timestamp, so its window and the total-latency window share a
boundary instead of overlapping and double-counting a few lines of setup
work on every request.
When get_team_object fails, the centralized auth gate rebuilds the team
from the token's own fields. A token whose team row was missing when the
key was read carries team_models=[] and team_blocked=False, and the
model-access check reads an empty model list as every model, so the
rebuilt team grants more than the real team ever did.
get_team_object reported a deleted team and a database that would not
answer as the same 404, so the fallback could not tell a definitive
answer from a degraded read. Raise a TeamNotFoundError subclass, still a
404 with the same detail so every other caller is unaffected, only when
the database answers and the row is absent.
A team that is provably gone now refuses, and no setting overrides that.
Otherwise the grant is merely unknown: a token carrying one may vouch,
since replaying a recorded grant cannot widen it, and a token carrying
none may not. allow_requests_on_db_unavailable still opts back out there,
and is only consulted once the failure is known to be a degraded read.
The Admin UI mints every session key against the UI_TEAM_ID sentinel,
which by design never has a team row, so every UI request hit the new
refusal with no override. Exempt UI_TEAM_ID explicitly so it keeps
reconstructing from the token unconditionally, matching how the MCP
handler and agent_permission_handler already special-case it.
Resolves LIT-5522
* fix(auth): resolve team object_permission independently in the unresolvable-team fallback
When get_team_object fails for a token's team_id, _user_api_key_auth_builder
reconstructs a LiteLLM_TeamTableCachedObj from the token's own cached fields,
carrying team_object_permission_id but leaving object_permission unset. That
silently dropped any vector-store or MCP restriction the team carried,
granting more access than the token's own object_permission_id vouches for.
Resolve the object permission by its id directly via get_object_permission,
independent of the unreadable team row, matching how every other consumer of
a team's object_permission (vector store access checks, MCP tool/server
resolvers) already treats an unresolvable team as "no restriction at this
level" and re-resolves on its own.
* fix(auth): trim ticket references and narrative docstrings per Greptile review
Drop the LIT-5539 ticket id from test names and fixture strings, and shorten
both the new helper's docstring and the regression test docstrings to their
contracts rather than restating the fix's history.
The team roster update, the user.teams update, the team membership
delete, and the team-scoped verification token delete ran as four
sequential writes with no transaction around them, so a failure
between any two left the removal half applied. Thread a single
prisma transaction through all four writes, following the same
tx.<table> pattern /team/member_add and /team/member_update already
use, so either all four land or none do.
