Cue grouping previously assumed space-separated Latin-style text. Chinese
and Japanese audio fused entire utterances into one unbreakable word (and
therefore one giant cue) because CJK scripts carry no spaces, and Arabic,
Urdu, Hindi and Armenian sentence terminators never triggered a cue break.
Words now also split at CJK character boundaries with basic kinsoku
handling so punctuation stays attached, the sentence-end set covers
script-specific terminators, and the cue length budget counts East Asian
wide characters as double width so CJK cues match the same two-line
subtitle footprint as Latin text.
The previous cue grouping broke every 15 subword tokens or 5s, which
produced uniform ~3s cues that split mid-word and bridged silence gaps,
so subtitles did not track the actual speech. Cues are now built from
whole words and break on sentence-final punctuation, speaker changes,
silence gaps >= 700ms, a 84-char budget, or a 7s duration cap, with
timestamps taken directly from token timings. Untimestamped translation
tokens are excluded from cues so translated text is never mixed into
original-language subtitles.
The comment restated what the gate does and carried incident detail that would drift,
including a claim about downstream callbacks that the evidence does not support. The
rationale belongs in the regression test, which fails if the copy is ever reintroduced
ahead of the gate, rather than in prose that can rot silently
Also corrects that test's docstring for the same overclaim: the raise aborts the handler
body at the redaction call, and what that costs a given deployment was not established
perform_redaction deepcopies the result before inspecting it, but every shape it does not
recognize falls through to the placeholder return at the end of that block, so the copy is
built and then discarded. Binary and HTTP response bodies land in exactly that case: batch
output, file content and audio responses hold an unpicklable `_thread.lock`, so
copy.deepcopy raises TypeError
The raise lands inside the try in Logging.success_handler that also wraps the callback
loop, so the handler body aborts at the redaction call and everything after it is skipped.
It surfaces only as "[Non-Blocking] Exception occurred while success logging cannot pickle
'_thread.lock' object", which is why it can run unnoticed. The async handler body reaches
perform_redaction the same way. Only deployments with message redaction enabled are
affected, since perform_redaction runs only when turn_off_message_logging resolves true
Deciding redactability before copying fixes the crash as a consequence rather than catching
it, and keeps the deepcopy off large batch bodies it was never going to help. Behaviour for
every recognized shape is unchanged: the copy still shields the caller's object from
in-place redaction
Observed on a live gateway with turn_off_message_logging enabled, where every managed-batch
output download logged that error; after this change the error no longer appears
/v1/messages and other litellm_metadata endpoints store proxy metadata,
including x-litellm-tags header tags, under litellm_metadata instead of
metadata. The pre-routing hook read request tags with a hardcoded
metadata bucket, so it never saw the tags that selected the marker and
cleared the consumed-tags stamp, and tag filtering then 401'd the routed
tier. Resolve the bucket from the request kwargs instead, matching how
the stamp write and the tag-filter read already resolve it.
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
LiteLLMCompletionStreamingIterator overrides __init__ without calling
super().__init__(), so completed_response was only set once the stream
reached RESPONSE_COMPLETED. On a mid-stream provider error the router's
_extract_partial_responses_usage read source_iterator.completed_response
during fallback recovery and raised AttributeError, masking the real
provider error (e.g. Anthropic 529) and bypassing configured retries and
fallbacks. Initialize the attribute to None so recovery degrades to no
partial usage instead of crashing.
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
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.
Register remote MCP servers without awaiting OAuth metadata, warm discovery in the background, and share bounded request-time retries with per-server cooldowns.
Preserve the existing discovered-tool boundary for explicit server calls.
Co-Authored-By: Codex
AWS no longer serves `anthropic.claude-3-sonnet-20240229-v1:0`. The streaming
path returns a plain 404, "Model with the provided id
anthropic.claude-3-sonnet-20240229-v1:0 is not found", and the non-streaming
path answers 500 for the same reason. Our own cost map has carried a
2026-07-30 deprecation date for it since #36538
That accounts for 20 failures across local_testing_part1, local_testing_part2
and llm_translation_testing. litellm maps both statuses correctly, so the
tests are what went stale, not the client
Replacement is `us.anthropic.claude-sonnet-4-5-20250929-v1:0`: a like-for-like
Sonnet, and the newest Bedrock Sonnet this repo exercises against the real API
in tests/e2e. Newer ids exist in the cost map, but nothing in the repo calls
them live, so picking one would be an unverified guess about model access on
the CI account
Scope is limited to the tests that actually issue a request. The occurrences
that assert on the model string itself, or that feed mocked transformations,
keep the old id so their assertions stay meaningful
* 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.
