Read strict from the caller's output_format/output_config.format instead
of hardcoding true, defaulting to false to match OpenAI's API default.
Explicit true/false values are preserved and output_format still takes
precedence over output_config.format.
* fix(http_handler): dispose aiohttp session when finalized without a running loop
AsyncHTTPHandler.__del__ can only schedule an async close when a running
event loop exists at finalization time; in any other context (worker
threads whose loop has closed, sync contexts, interpreter shutdown) the
RuntimeError from get_running_loop() is swallowed and the underlying
aiohttp ClientSession is abandoned to GC, emitting 'Unclosed client
session' / 'Unclosed connector' warnings.
This is the disposal gap left after the recycle-time fix: clients created
for short-lived event loops (the loop-id-keyed LLM client cache mints one
handler per loop) are never recycled - they live and die with their loop,
and their finalization is precisely the loop-less case.
Fix:
- no running loop: fall back to the connector's synchronous teardown via
LiteLLMAiohttpTransport._mark_connector_closed - the same finalizer-safe
path used for dead-loop recycles - honoring _owns_session so a shared
session is never closed.
- running loop: keep the async close, but hold a strong reference to the
scheduled task until it completes (a bare create_task() result may be
collected before running), mirroring _background_close_tasks.
Tests: loop-less finalization closes a dead-loop session; running-loop
finalization registers and drains the close task; the sync fallback
respects session ownership. All three fail without the fix.
* lint: conform new finalizer code to the type-discipline budget
Final on the five never-rebound locals (LIT010); the class-level task
registry keeps its mutable set with the sanctioned mutable-ok reason,
mirroring the aiohttp transport's registry (LIT001).
* lint: reasoned pyright ignore on the cross-class teardown call
The handler deliberately reuses the transport's finalizer-safe connector
teardown; no public seam exists and an async close can never run at
loop-less finalization. Clears the net-new reportPrivateUsage the
basedpyright budget gate flagged once the LIT stage passed.
* fix(http_handler): retrieve exceptions from finalizer close tasks
A bare discard done-callback dropped the task without consuming its
exception, so a failing aclose() emitted "Task exception was never
retrieved" at GC, the same noise class this path exists to remove.
Mirror the transport's _on_close_task_done: discard, early-return on
cancellation, retrieve and debug-log the exception.
* fix(http_handler): dispose foreign-loop sessions instead of scheduling aclose on the live loop
GC on a live loop (e.g. the app's) of a handler whose session belongs to
another, possibly dead, loop scheduled aclose() on the current loop, the
cross-loop path the transport refuses. Route both that case and the
loop-less case through the transport's lifecycle-aware
_close_recycled_session, which picks async close on the session's own
loop, threadsafe handoff, or the synchronous connector teardown.
Regression test: a dead-loop session collected while another loop runs
is disposed without scheduling anything on that loop.
* chore: retrigger CI (test_mcp_logging payload-order flake, also failed on litellm_spendlogs_fallback_metadata minutes earlier)
* test(mcp): select the MCP tool-call payload instead of the last-delivered one
TestMCPLogger kept a single last-writer slot; an async success event from
another call (a mocked acompletion whose log task lands late) races the
MCP event for it, so the cost assertions intermittently read the wrong
payload. This PR's finalizer change shifts task interleaving on the loop
and tips that latent race over (also seen on an unrelated PR minutes
earlier). Collect call_type=call_mcp_tool payloads in their own list and
assert on those.
* test(mcp): MCPLoggerHook inherits the order-independent payload capture
It duplicated TestMCPLogger's init and success handler verbatim; the
hook test reads the same MCP payload selection, so subclass instead.
The LLM classifier capped every prior turn at 200 characters independently, so a
785 character turn was cut even when the whole block it belonged to was 353
characters. A character budget now bounds the block: turns are taken newest first
and quoted whole while they fit, older turns are dropped whole once it runs out,
and only the turn straddling the boundary is cut. The per-turn cap stays as an
optional clamp for operators who set it deliberately, defaulting to unset.
Adds a scheduled GitHub Actions lane on top of the merged record/replay
transport. A Saturday cron records the `replayable` e2e tests against the
real providers and publishes the fixture bundle as a private
`e2e-fixtures-bundle` artifact with a SHA-256 sidecar. Weekday crons pull
that artifact by its pinned digest, verify the checksum before extracting,
and replay it with provider credentials set to bogus values, so a run that
ever reached a real provider fails instead of passing.
An egress sentinel pins the provider hostnames to a local sink for the whole
replay job and counts every connection that reaches them; the job asserts
that count is zero, so hermeticity is proven by measurement. A red Saturday
publishes no bundle, so the next weekday finds nothing fresh and fails loudly
rather than replaying a week-old recording, and the transport's seven-day
freshness gate hard-fails any bundle that has drifted too far. The lane also
runs on demand from the Actions tab with a record/replay `mode` input.
Tests join the lane with `@pytest.mark.replayable`. The streaming Anthropic
test now counts to twenty so its recorded response banks several content
deltas, matching the assertion that the stream arrives incrementally.
A request carrying a session/trace header fans the header value into
litellm metadata as both trace_id and session_id. LangSmith then rejected
the whole ingest batch: a root run's trace_id must equal the run id
embedded in dotted_order (400), and a run-body session_id must reference
an existing tracer session (404/422). Override caller trace_id on runs
that post as roots and drop session_id only when it mirrors trace_id,
so deliberate child-run and valid tracer-session fields still pass through.
The drilldown now self-dismisses when refetched activity has no failures
for its call_type, instead of holding a selection the chart no longer
shows. groupErrorBuckets is rewritten as pure filter/map/sort over the
already-grouped SQL rows.
A quoted routine call qualified by a schema and sitting inside a CREATE INDEX
expression, ON "Foo" (public."f"(col)), walked its qualifier read-through back
across the opening paren to the ON that introduces the indexed table, so the call
was misread as a relation and dropped from the call set, leaving a rewrite in that
routine unscanned. A word now only introduces the name when nothing but whitespace
and qualifier dots lies between them, so a paren in that gap keeps ON (and any
relation-introducing keyword) from reaching across it and the call stays a call.
The Responses-API to /chat/completions bridge yields ModelResponseStream
chunks that carry choices followed by a trailing event object that has no
choices key. stream_chunk_builder assumed every chunk was subscriptable at
"choices", so assembling those chunks raised KeyError('choices') and was
re-wrapped as a 500 APIError building the streaming usage.
Guard each choices access with .get("choices") so choices-less chunks are
skipped instead of crashing. Behavior is unchanged for chunks that do carry
choices, since .get("choices") is truthy only for a non-empty choices list.
Adds a regression test that assembles content across chunks followed by a
trailing chunk with no choices key.
Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com>
/global/activity/cache_hits now returns an error_breakdown: failed spend
logs bucketed per call_type by error code and error class, read from
metadata->error_information. Clicking a red failed-requests segment on
the cache activity chart opens a per-code bar chart; hovering a bar
lists the error classes behind that code.
The video edit endpoint parsed the multipart body but dropped the uploaded
source video, only normalizing it to an id. When a raw file is uploaded it now
flows through videos.main -> the http handler -> the provider transform, which
emits multipart/form-data with the source video as a file part, matching the
official OpenAI SDK's videos.edit wire format. Edit-by-id still egresses JSON.
The LLM classifier's conversation context cut each prior turn head-only, so a turn
opening with an incident report and closing with the actual request reached the
classifier as the incident report alone. Keeping head and tail costs the same
budget and is what the truncation literature measures as best for classifying
long text.
On mapped pass-through routes, of which /vertex_ai is one,
user_api_key_auth accepts the caller key from a header literally named
litellm_user_api_key and applies it last, so it overrides every other source.
The credential-less filter neither dropped it nor resolved the caller key from
it, so a virtual key there reached Google past a real x-goog-api-key, and a
bring-your-own Authorization could be stripped when auth actually came from that
header. Drop it by name and resolve it at highest precedence.
* refactor(ui): install the shadcn field primitive
`components/shared/form/field.tsx` was the upstream base-vega `field` source
living outside `components/ui/`. It exported the same ten symbols as upstream,
so `npx shadcn add` could never update it and it had already drifted: its
`FieldLabel` was missing the hover and focus-visible ring utilities upstream
now ships for labels that wrap a nested field.
Install the primitive and point the 77 importers at it. The copy is deleted
rather than kept as a wrapper because it added nothing beyond `forwardRef`,
which React 19 makes unnecessary since `ref` arrives as an ordinary prop.
`field.test.tsx` moves next to the primitive with no edits to its contents,
and its nineteen tests, ref assertions included, pass against the generated
file. That is the evidence the swap is behaviour-preserving.
Two nested-field call sites pick up the upstream hover and focus-visible
styling that the stale copy had been missing.
(cherry picked from commit 947f7fa674c83bfc57f43ad8bfc89c894da947a2)
* test(ui): cover the nested-field interaction cues FieldLabel had lost
The stale copy of `field` was missing the hover, focus-visible and disabled
selectors upstream applies to a label that wraps a nested field, so installing
the primitive restored them with nothing asserting they stay.
Assert the class contract rather than the rendered effect. jsdom evaluates
neither `:has()` nor `:focus-visible`, and Tailwind is not compiled under
vitest, so a test that clicked or tabbed would pass on an element with no
styling at all. Checking the utilities are present is the assertion that
actually fails when they go missing, which is the way they were lost before.
Verified by stripping the four selectors from the primitive: both tests fail,
and both pass once it is restored.
(cherry picked from commit 5a5dbf64270d9d1285dbc4a7af76bb3d927778a8)
The recursive_detector code-quality gate fails on litellm_internal_staging
because _flatten_form_field and _flatten_form_data_field in
llm_request_utils.py are recursive but absent from IGNORE_FUNCTIONS. Both are
bounded structural recursion over an already-parsed JSON-shaped request body
(a finite tree, no cycles possible), matching the existing ignored walkers, so
add them to the ignore list with a justification comment.
Follow-up to #38130. The function has no callers in the repo or the docs and is
not exported from `litellm/__init__.py`, and `token_counter` already does the same
job better, so keeping a second entry point only preserves a trap.
That trap is real: Greptile flagged on #38130 that `token_counter` picks the claude
tokenizer only for bare ids. `claude-sonnet-4-5` resolves to huggingface_tokenizer,
while `claude-3-opus-20240229` and `anthropic/claude-sonnet-4-5` fall back to the
OpenAI one, 24 tokens against 27 on the same string. Deleting the wrapper removes
the surface rather than papering over it; the selection gap in `token_counter`
itself is worth its own fix.
BREAKING CHANGE: `from litellm.utils import prompt_token_calculator` no longer
resolves. Use `litellm.token_counter(model=..., text=...)`.
The dashboard used `cva@1.0.0-beta.4` with the object-argument API behind
`@/lib/cva.config`, while shadcn emits `class-variance-authority` with the
positional API. Every `shadcn add` of a cva-based primitive therefore needed a
hand fix-up before it compiled, which meant `components/ui/` could never match
a fresh CLI run and `shadcn add <name> --diff` reported the whole file as
changed instead of showing real upstream drift.
Swap the dependency, and regenerate `badge`, `button`, `button-group`,
`input-group` and `tabs` straight from the base-vega registry so they are now
byte-identical to the CLI output plus prettier.
Two primitives could not be regenerated because they are local code rather
than registry items, so they move out of `components/ui/`: `sidebar` (203
lines against upstream's 730, and only `leftnav` consumes it) and `meter`
(no registry entry at all, it wraps Base UI's Meter).
The customisations that were baked into the regenerated files move to
wrappers, following the rule that `components/ui/` holds CLI output and
anything on top of it lives outside:
- badge carried info, success and warning variants that duplicated the
existing `StatusBadge` tone map, so its five call sites now use
`StatusBadge`, which gains an optional `className`
- input-group's addon focuses `[data-slot=input-group-control]` rather than
upstream's `input`, which matters because the chat composer puts a textarea
there. That handler now sits at the one call site that needs it
`cx` keeps its previous twMerge behaviour. It came from the old
`defineConfig({hooks: {onComplete: twMerge}})`, and CVA's own `cx` is plain
clsx, so pointing it at `cn` avoids silently dropping conflict resolution in
the six files that use it.
`Sidebar.test.tsx` covers the failure mode this migration can hide: passing
the object form to the positional API is accepted by clsx and renders the
literal class string "base variants defaultVariants", so the component loses
every style while the type checker and the existing suite stay green.
A quoted routine call with a SQL comment between its name and parenthesis,
`"backfill" /* reason */ ()`, is a real call that rewrites rows at boot, but the
call-site check read the raw SQL and stopped at the comment, so the routine was
read as uncalled and its rewrite slipped through. Read the call test from the
masked text instead, where every comment is already blanked to spaces, so a
comment between the name and its parenthesis is skipped exactly as whitespace is,
line, block and nested block comments alike, while a like-named non-call
identifier still opens no call and stays masked
The resolver placed both operator-configured key headers at the top of its
precedence, but user_api_key_auth only overrides with litellm_key_header_name;
a pass_through_endpoints litellm_user_api_key is checked last. So a request that
authenticated via Authorization while also sending a pass-through header could
have the wrong value chosen, leaving the authenticated Authorization key
forwarded. Order the resolver exactly like get_api_key: override first, built-in
headers next, pass-through header last.
A migration that defines an uncalled row-rewriting routine and elsewhere
references a quoted column, table, index, or constraint sharing the routine's
name was wrongly flagged: the guard restored every double-quoted identifier
before the name search, so a like-named identifier read as a call. Restore only
quoted names that open a call, followed by "(", so a routine invoked through a
quoted identifier is still caught while a like-named non-call identifier stays
masked and no rewrite-free migration is rejected
user_api_key_auth also accepts the caller key from a pass_through_endpoints
entry's headers.litellm_user_api_key, not just litellm_key_header_name. Drop
every operator-configured caller-key header by name and treat them as
top-precedence caller-key sources, so a virtual key sent through one is never
forwarded to Google.
LoggingWorker._ensure_queue nulled self._queue on a loop change, discarding every
pending LoggingTask (each an un-awaited spend-logging coroutine) with no counter and
only a debug log. SDK callers using asyncio.run() per request and mixed sync/async
processes rebind the queue's loop and silently lose spend rows and observability events.
Drain the stale queue and move the pending tasks onto a fresh queue bound to the new
loop, warn with the carried-over count, and keep flush()/join() honest since the queue
is no longer thrown away. Adds a regression test that fills the queue before the loop
change and asserts every task survives and still executes.
The LIT-4761 streaming-classification tests passed only the bring-your-own
Google OAuth token in Authorization and mocked get_litellm_virtual_key, a shape
that cannot authenticate in production. The credential-less filter now resolves
the caller key by auth precedence, so a lone Authorization value reads as the
key and is stripped. Send the virtual key in x-litellm-api-key, matching a real
request, so Authorization is preserved and the classification assertions run.
A migration that defines a row-rewriting routine and calls it as
"backfill"() at the top level slipped past the checker, since masking
blanks double-quoted identifiers before the routine-call search runs, so
the call could not be found by name and the body read as uncalled. mask()
now returns those identifier spans and outside_definition puts them back,
so a call written through a quoted identifier reads as the call it is and
the routine's body gets scanned the same as a bare call
the x-litellm-model upload path returns ids wrapped with
encode_file_id_with_model (litellm:<raw>;model,<m> base64'd). chat
completions + /v1/responses forwarded the wrapped id straight to the
provider, breaking openai (file not found / >64 chars), gemini
(unknown mime), etc. wire up the existing get_original_file_id +
is_model_embedded_id helpers in update_messages_with_model_file_ids
and update_responses_input_with_model_file_ids — falls through after
the managed-files path so existing flows are unchanged. 3 new
regression tests + dem proof len 71 -> 26.
Adds the `gemini_family` bundled template to the auto-router tab, a
heuristic-classifier preset alongside the existing Anthropic and OpenAI
family presets.
Tiers ascend in cost across the Gemini lineup:
SIMPLE gemini-2.5-flash-lite $0.10 / $0.40
MEDIUM gemini-3.1-flash-lite $0.25 / $1.50
COMPLEX gemini-3.7-flash $0.75 / $3.75
REASONING gemini-3.1-pro-preview $2.00 / $12.00
Uses concrete model ids rather than Google's `gemini-*-latest` aliases.
Those aliases hot-swap to the newest release of their variation (stable,
preview or experimental) with only a two-week notice, while their rows in
model_prices_and_context_window.json are pinned at 2.5-generation rates,
so a swap onto a 3.x model would bill at the stale price and silently
undercount auto-router spend. A pin test asserts no tier resolves to a
`-latest` alias and that all four rungs are distinct.
A downstream disconnect mid-relay was recording the chunk whose write never
landed, so replay would hand back a byte the record run never delivered. Append
each chunk after its yield returns, and label the truncation from the generator
close, so the recording holds exactly what the proxy received.
The caching-local, proxy-extras and enterprise-package shards each budget
pytest 20m but cap the whole job at 55m. Setup can consume up to 35m, and
the runner adds 5m of overhead, so the job deadline can preempt pytest
inside its own advertised budget and the shard dies without a test report.
check_workflow_startup_safety enforces that invariant and is currently
failing on litellm_internal_staging, which reds the code-quality job for
every open PR. Raising the three caps to 60m satisfies 20 + 35 + 5.
