Adds resolved_logging_exporters to /team/info and /organization/info, naming every destination whose access scope grants that identity and which actually builds.
Squashed onto the rebased export branch; the previous history conflicted with staging's Final-annotation pass.
Never-rebound names carry Final, deliberate rebinds carry rebind-ok with the reason, and the endpoint suffix check collapses into one endswith call. Two hook parameters and the constructor kwargs move from Any to object, which is both stricter and what the bodies actually rely on.
The remaining constructions keep a mutable-ok naming what needs a concrete dict: pydantic model_copy payloads, the OTel SDK Resource call, and the LRU caches that are mutable by design.
Fans each request's trace out to the destinations its identity resolved, applies per-request credentials only to the exporter their own backend contributed, and caches tracer providers per credential, endpoint and transport.
Squashed onto the current staging tip; the previous history conflicted with staging's Final-annotation pass over the same OTEL v2 modules.
Same ratchet as the credential-model branch: never-rebound names carry Final, the request-state mirror logs at debug instead of swallowing silently, and the empty header and resource fallbacks share one immutable mapping.
Two constructions keep a mutable-ok with a reason: the dedup accumulator consumed on the next line, and the TypedDict rows the resolver returns.
Publishing the destination ContextVar imports the OTel context module, and opentelemetry ships only in the proxy-runtime extra. That call sat outside the resolver's try, so a litellm[proxy] install raised ModuleNotFoundError on every request over a feature it never enabled; the flag being off did not help, since the gate lives inside the resolver and an empty result still fell through.
The helper now returns before publishing when the flag is off, and a missing package with the flag on warns instead of raising, matching what instrument_fastapi_app already did.
The org fallback loads the team, which on a cache miss is a Prisma read on the authentication path. It cannot change which destinations are selected unless some access names an org, so it now runs only then; the logging credentials are also parsed once instead of twice.
The type-discipline refactor inserted _destination_verdict between the
@router.get decorator and get_credentials, so FastAPI registered the helper
as the listing endpoint. It declares a CredentialItem parameter, which FastAPI
reads as a required request body, and every GET /credentials returned 422.
Add the GET routing regression test alongside the existing PATCH one; the
other tests call get_credentials directly and stay green while the route is
dead.
An `arize` credential carrying only `otel_endpoint` is built by the generic passthrough but
resolved under the `arize` name, so the router applied Arize's intrinsic gRPC transport to
the plain HTTP URL the admin typed. The destination delivered nothing while `/team/info`
kept advertising it as active, which is the invariant `resolved_logging_exporter_names`
exists to hold. The passthrough now pins `otlp_http`, which is what it has always meant;
adapter-built Arize destinations keep their gRPC default, covered by its own test.
`GET /credentials` now reports `resolves_to_destination` for logging credentials, computed
by `destination_for_credential` so it cannot drift from the resolver or the disclosure. The
dashboard's Scope column needs this verdict; recomputing the adapter rules there would drift
from them, and that drift is what let a dead destination read as live.
Both regression tests were mutation-checked by reverting their own fix in isolation.
APScheduler anchors an interval job at now + interval, so every scheduled
background job registered in one proxy startup shares a single firing instant
for the life of the process, and every replica a rollout brought up together
shares that instant too. Each tick the spend flushes, budget reset sweep,
config-in-DB reload, credential reload and cost pollers all hit Postgres at the
same moment, on every pod, competing with request-path auth and budget queries.
Shift each eligible job by a deterministic offset derived from
sha256(job_id, identity), where identity covers the pod and the worker process.
The offset lives in the trigger rather than in a one-off next_run_time, because
a cron trigger recomputes each fire from the wall clock and would otherwise snap
straight back onto the shared instant. An interval job is never offset by more
than one of its own periods.
Only schedules LiteLLM chose are shifted: interval jobs always, cron jobs only
when the id is one of the product's own defaults, so an operator-supplied
crontab keeps the instant it asks for. general_settings.scheduled_job_stagger
turns it off, widens the window, replaces the identity, or pins a job. The
applied offsets are logged once at startup and each fire logs its scheduled
instant against its actual start.
Resolves LIT-5433
The outer wrap_sse_stream_with_keepalive_pings layer duplicated the
keepalive engine that PR #34423 already runs inside async_data_generator
for chat completions and responses streams, and it kept pinging
deployments whose operator set keepalive_seconds: 0 as a hard disable.
sse_keepalive_ping_interval_seconds is now the global fallback inside
_resolve_keepalive_seconds, so deployment and request values keep
precedence, an explicit 0 still disables, the [1, 300]s clamp applies,
and router-less proxies arm the wrap when the global default is set.
The Rust messages bridge logs a parsed Anthropic response without an
httpx_response, so the fallback transform dropped the request speed and
billed fast-mode calls at the standard rate. Thread optional_params
speed into transform_parsed_response and add a regression test for the
parsed-response branch.
A stream can terminate with a response.failed event that still reports
consumed tokens; those were rebuilt as None and logged at zero spend.
Parse response.failed alongside completed and incomplete, matching the
buffered path, which prices any terminal response that reports usage.
The Anthropic batch create never persisted the creating key's hashed token or its
request tags on the managed object, so when CheckBatchCost billed the batch hours
later there was nothing to attribute it to. Key spend, key budgets and tag spend
never moved for batch usage.
Persist both from the create, the way the Vertex passthrough already does, and
register the batch only from the collection route. An id-scoped route cannot
rebuild the unified object id, because it embeds the model and the model comes
from the create's request body, so it could only claim a row it did not create or
fail the model_object_id unique constraint.
The shared metadata helpers, the route predicate and the registration-result
logging now live in batch_attribution instead of being copied per provider. The
Anthropic write previously logged success unconditionally, before the
fire-and-forget task had run.
Resolves LIT-5288
Streams that terminate with response.incomplete (e.g. max_output_tokens
reached) carry real usage in the terminal event but were rebuilt as None
and logged at zero spend, letting callers bypass budget enforcement.
Parse response.incomplete alongside response.completed when
reconstructing the streamed response.
Addresses review feedback: the ResponseCompletedEvent SSE parsing now lives
in OpenAIResponsesAPIConfig next to the other Responses stream event handling,
and the proxy logging handler calls it. Adds coverage for streams that end
without a response.completed event.
* feat(router): make routing groups callable as virtual models and list them in /v1/models
* fix(router): traffic-scoped cooldown exemption, live model_names on delete, group-info cache invalidation
* fix(router): share one recognized-model predicate across proxy gates, resolve aliases in group cooldown, read metadata via the dual-bucket owner
* fix(router): close the gate and cache families for callable groups, strip member access_groups from group rows, prove cooldown wiring end to end
* refactor(router): cache materialized group rows under the model-group cache owner and drop the redundant wiring test
* fix(router): warn-and-shadow on group name collisions, name-level test coverage for group helpers, faithful router doubles in a2a and cursor tests
* test(router): pin group cooldown metadata across the retry path
Gemini image usage carries prompt_tokens and friends as extra fields on
ResponseAPIUsage, which collided with the bridge's explicit kwargs and
raised TypeError. Exclude keys the bridge already sets explicitly.
Every TypedDict field must carry a ReadOnly[...] qualifier (PEP 705),
nesting freely with Required/NotRequired/Annotated. Detection covers the
class form (including same-module transitive subclasses) and the
functional form. The 4519 existing violations across litellm/ are
grandfathered via type-discipline-budget.json; suppress deliberate
writable keys with # writable-ok: <reason>.
Drop the transform overrides that swapped response.usage to the chat
shape, which broke the /v1/responses client contract. Provider extras
like server_side_tool_usage_details already survive validation via
ResponseAPIUsage extra fields, so the shared usage bridge now carries
them onto the bridged chat Usage generically. The web_search_call
output gate also reads dict output items, since items that fail SDK
validation stay plain dicts, and the chat path gains billing tests.
* fix(alerting): dedupe scheduled Slack spend reports across pods
Every pod ran its own weekly/monthly spend report jobs, prometheus
fallback stats cron, and daily report loop, so deployments with
multiple replicas or uvicorn workers received one copy per pod.
Gate each scheduled send behind the shared PodLockManager redis lock.
The lock is never released: its TTL (the full reporting window for the
weekly interval job, whose per-pod anchors drift by boot time and
jitter) doubles as a sent-this-window marker. acquire_lock returning
None (no redis wired) proceeds, preserving single-pod behavior.
Also generalize the pod lock could-not-acquire log line, which claimed
to be about spend tracking for every consumer.
Fixes#14809
* fix(alerting): harden spend report locks after adversarial review
Weekly lock TTL gets an hour haircut: with ttl equal to the interval,
the winner re-fires just before its own key expires, reacquires without
a TTL refresh, and the key then lapses in time for a trailing pod to
re-send. Job/lock ids move to litellm/constants.py per convention, and
spend_report_frequency now rejects non-positive day counts, which
previously coerced to an every-second schedule and would now compute a
negative lock TTL that silently never sends.
Adds the missing test coverage the review flagged: startup_event's
pod_lock_manager wiring (identity-asserted), the prometheus closure's
positive path, and the ungated immediate prometheus send pinned to
exactly one await.
* test(alerting): consolidate spend_report_frequency validator coverage
Drops a duplicate non-positive-days test and parametrizes the survivor
over the suffix half of the validator too
* fix(alerting): route the startup prometheus fallback send through the pod lock
Greptile caught that the boot-time send still ran once per pod when
PROMETHEUS_URL is set, the same duplication class this PR removes
* fix(alerting): make report lock acquisition non-reentrant
Greptile caught that a pod booting within an hour of the fallback stats
cron sent twice: the startup send takes the lock, then the cron fire
hits acquire_lock's reacquire branch, which returns True for the
holder. Window-marker gates now pass allow_reentrant=False so a live
lock blocks everyone including its holder; leader-election consumers
keep the reentrant default
* test(proxy): give spec'd ProxyLogging mocks a db_spend_update_writer
_initialize_slack_alerting_jobs now reads it for the pod lock manager,
and spec=ProxyLogging blocks instance-only attributes
