v2 accepted generation(id=...). v4 derives the observation id from the OTel
span id, so the isolated tracer provider now carries an id generator that
hands out the id start_generation asked for through a context variable, and
the callback passes the resolved generation_id metadata into it.
The legacy e2e suite patched httpx.Client.post and compared v2 ingestion
batches; it now patches requests.Session.post, decodes the OTLP protobuf
and compares the exported generation against regenerated fixtures. The
local readback test replaces the removed get_generations() with
api.observations.get_many() and polls Langfuse Cloud instead of sleeping.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Replace the v2 trace()/generation()/span() calls with SDK v4 observations exported over OpenTelemetry, with one isolated tracer provider per Langfuse credential set, a discarding exporter for mock mode, and v4 trace and observation id normalization. Keeps the session-header trace provenance logic from main so each call under a session alias still gets its own trace
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Pre-call limiters reject before a deployment is attached to request_data, so
the failure hook could not resolve api_provider for router aliases and emitted
api_provider="None" on litellm_proxy_failed_requests_metric_total and
litellm_proxy_total_requests_metric_total. Fall back to the provider the
limiter already resolved onto RateLimitError.llm_provider, keeping request
data as the first source and ignoring the proxy placeholder.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
_client_async_logging_helper re-submitted logging_obj.success_handler to the
executor after _dispatch_success_logging had already done so, running the same
success pipeline twice per async request and racing on shared logging state.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Peek at the pending session.update instead of popping it, so an eager fallback failure before the bridge starts does not lose the replay for the next attempt. Move the websocket scope keys to constants.py
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Bedrock realtime caught every exception inside both forwarding tasks and
gathered them with return_exceptions=True, so a provider failure surfacing
after the websocket handshake (lazy duplex stream: 503/429/validation only
show up on await_output or the input publisher) made async_realtime return
normally and the router recorded a success instead of running fallbacks and
cooldown accounting. session.updated is now acked only after Bedrock is
ready, provider failures escape as BedrockError with the AWS status code,
a failure after the client disconnected is not reported as a provider
failure, and a fallback attempt on the same websocket replays the pending
session.update instead of emitting a second session.created.
Resolves LIT-6484
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Opt-in allowlist for upload filename extensions, checked before the existing blocked_file_extensions blocklist and mapped through the same upload validation failure path. None keeps today's behaviour, [] rejects every upload, matching is case-insensitive on both sides, and a filename with no extension is rejected when the allowlist is set.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Values loaded after import via proxy config environment_variables or dotenv
were ignored, and a long query string was truncated by the redaction filter
before the path filter could match it. Tests now go through the production
registration on the uvicorn.access logger instead of a hand-built filter.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
An org admin listing their own teams on GET /team/list and GET /v2/team/list
only saw teams in the orgs they administer. Teams they belong to in other
orgs were dropped because the org scope and the membership scope were ANDed.
A self query now unions the two, while a query for another user keeps the
org boundary intersection.
Resolves LIT-3723
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
RouterRateLimitError now carries the model group's deployment ids so it
can tell when every deployment is cooled down, and exposes that as
type=all_deployments_in_cooldown with an explicit message. A partial
cooldown keeps type=rate_limit_error. Either way the proxy no longer
reports type=internal_server_error next to code 429
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
CodeQL flagged two module-level cyclic imports introduced by defining
CachedTokensDetails in litellm.types.llms.openai and importing it from
litellm.types.utils and litellm.cost_calculator. The class now lives in
litellm.types.llms.base, which imports nothing from litellm, and every
user imports it from there.
Also pins that combining realtime usages where only one response.done
carries cached_tokens_details keeps the earlier modality split in both
orders, and commits the regenerated dashboard API types.
