Adds a persistent total_spend column to LiteLLM_VerificationToken and LiteLLM_DeletedVerificationToken, incremented in the same write as spend and left alone by budget resets. Surfaces it on /key/info, /key/list and the Admin UI Virtual Keys table and key detail view
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Chat completions and messages were the only cacheable paths. The suite also
drives /v1/embeddings and /v1/responses through the same OpenAI mount, so both
now cache, each with its own completeness rule: a chat response's `choices`
check would reject a perfectly good embedding, and a Responses run that never
reached `response.completed` must stay out of the cache the same way a
truncated stream does.
Vertex and Gemini stay off the edge. litellm's `_check_custom_proxy` rewrites a
path-prefixed vertex api_base into `{api_base}:{endpoint}`, dropping project,
location and model, so a mount under a path prefix cannot work without a
root-mounted edge on its own port or a change in litellm. Shipping an
unvalidated URL guess would have been worse than saying so in PROVIDER_CACHE.md.
Also finishes the MountPolicy move: a mount now carries its signer and its
unkeyed headers together instead of a bare signer map.
The exact-request cache reused 5% of routed traffic (build 218: 19 hits,
350 misses) because every test salts its prompt with a fresh unique_marker(),
so the same test could never match itself across builds. It also routed only
openai and anthropic, while the week's flakiness was Bedrock.
Key is now HMAC(test id + method + URL + headers + body, with every
unique_marker() token replaced by a placeholder, + FIFO slot index). The slot
index is what keeps two marker-only-different calls in one test on two
recordings and therefore two provider response ids, so spend rows still
reconcile one per invocation. A call outside any test is not cacheable.
Bedrock gets a region-qualified mount and SigV4 re-signing, since the edge
rewrites the Host the proxy signed. Signature headers are excluded from the
key for signing mounts only, because x-amz-date would otherwise make every
Bedrock request a permanent miss; every other mount still keys on its
credentials whole. Only Anthropic-on-Bedrock chat deployments route:
embeddings, image generation, rerank and realtime keep their direct path, and
so do deployments carrying their own aws_role_name or static keys, whose whole
point is to prove the product's assume-role chain rather than the runner's.
The two eventstream actions bypass the cache and go live, still signed.
Counters are now attributed per mount as well as in total, so a build can
report a per-provider hit rate instead of one number.
Key metadata disable_fallbacks only lands on data during add_key_level_controls,
so the local rate-limit fallback retry now rechecks it post pre-call. Also use a
real UserAPIKeyAuth in the skip pre-call test since the path reads router_settings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
A body that serializes litellm_trace_id as null or an empty string carries no identity, so it must not
block the server span fallback. Also mark the nested metadata write as an out-param store
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
UserAPIKeyAuth.parent_otel_span is Any at runtime (opentelemetry is an optional extra), so the OTel
trace-id fallback must only format an int trace id, otherwise an object that merely quacks like a span
turns the whole request into a 500
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Pass user_api_key_dict.parent_otel_span into the outgoing W3C injection so the
legacy otel callback propagates its litellm_request span, falling back to the
otel_v2 request root span and then the ambient span. Extend the mapped unit
tests to assert the propagated trace and span ids over real captured headers
for HTTP and WebSocket passthrough with forwarding on and off.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
When the otel callback is enabled and the client sends no trace or session identity, the request now inherits the W3C trace id of the proxy's server span as litellm_trace_id and metadata.trace_id. The missing_session_id policy and SpendLogs then persist that value as session_id, so a trace in the OTel backend and its row in the Logs UI carry the same id. Explicit x-litellm-trace-id, traceparent, body metadata.trace_id and litellm_trace_id keep priority.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The fallback retry in _pre_call_with_fallbacks re-entered common_processing_pre_call_logic with data already enriched by the first pass, so add_litellm_data_to_request deep-copied a metadata dict holding the live OTel span and the request failed with a 500 (cannot pickle '_thread.RLock') instead of the intended 429 or fallback. Capture the configured fallbacks and a snapshot of the client request before the first pass, look up the fallback chain by the normalized model group after the limiter raises, and run each fallback attempt on a fresh copy of that snapshot. Replaces the mock-heavy tests with a rig that runs the real v3 limiter and a live OTel span through the proxy_logging_obj seam
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The four .parentElement reads in the new lifecycle tests pushed
testing-library/no-node-access to 712 against a 707 budget, failing
frontend-lint. The rows now carry data-testid="lifecycle-row" and the test
picks a row with within(), which keeps the assertion tied to the specific row
rather than the whole panel and takes the count back to 707.
#39050 changed RequestLifecycle from sorting every entry with
(a.start_time ?? 0) to filtering on isTimed, which drops any entry whose
start_time/end_time are null. That was the right call for the not_run entries
the PR introduced, but it also drops entries that DID run and simply carry no
timing, and those are pre-existing: add_standard_logging_guardrail_information_to_request_data
defaults start_time, end_time and duration to None, and the conduct guardrail
passes none of them. One such entry used to draw the whole four-row lifecycle
and now draws nothing, so an admin opening that log sees an empty
Request Lifecycle panel.
An entry now stays on the lifecycle when it is timed OR when it ran, so not_run
keeps the exclusion #39050 wanted and every other shape comes back. Offsets are
number | null and render as an em dash rather than a fabricated T+0ms, which is
what a null minus a null used to produce on the base. Entries without timing
sort after the timed ones and the base time comes from the timed entries, so
real offsets are unchanged.
The two new tests fail on the base component and pass here; #39050's own
not_run tests keep passing untouched, which is what makes this additive rather
than a revert.
tests/integration/conftest.py imported the bare `integration` package. Because
tests/__init__.py and tests/integration/__init__.py both exist, pytest's default
prepend import mode puts only the repo root on sys.path, so that name resolved
only under the PYTHONPATH that tests/integration/run.py injects. Every other
invocation died at conftest import with
ModuleNotFoundError: No module named 'integration' and exit 4, including the
command test_oci_integration.py documents in its own docstring.
The imports now use the tests.integration._support path that pytest actually
resolves, matching the 120 other `from tests.` imports in the suite. run.py's
PYTHONPATH still works because it already puts the repo root on the path.
tests/code_coverage_tests/test_integration_suite_imports.py collects every file
under tests/integration with PYTHONPATH scrubbed and asserts a non-zero
collection count, so an unresolvable import fails the code-quality job instead
of only the developers who run these files by hand. CI runs the three
pre-existing files through the allowlist rather than executing them, which is
why nothing caught this.
