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>
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>
The org cache entries written by prefetch_auth_objects carry the 5s
DEFAULT_IN_MEMORY_TTL. The first @log_db_metrics getter lazily imports
litellm.proxy.proxy_server, which on a cold CI runner can take longer
than 5s, so the org entry expired before get_org_object read it and the
getter fell through to the MagicMock database. Inject a frozen clock
into InMemoryCache so the test asserts the join, not import latency.
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.
CredentialLiteLLMParams omitted tenant_id, client_id, client_secret,
azure_scope, azure_username and azure_password, so the strict dump used
by credential reuse and Azure client init dropped them and the reused
credential ended with no auth at all
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The e2e harness exists to prove product features end to end against a live
proxy. The prior Hard Rule carved out an exception for "tests that cover the
harness itself" and pointed at coverage_registry/test_collector.py, which in
practice invited unit tests of harness helpers to be staged alongside e2e
work. That is the wrong tool: harness logic that is worth locking down does
not need a mock-driven unit test living under tests/e2e.
Drop the carve-out. The Hard Rule now reads that no unit tests of any kind
belong under tests/e2e, and the passing mention of unmarked harness coverage
in the transport section is removed so the doc no longer contradicts itself.
coverage_registry/test_collector.py still exists on disk and is left in place
for now; whether to relocate or remove it is a separate decision.
Keeps the base's rule that a non-admin id lookup matching no spend-log row answers 403, so the detail route never consults cold storage without an owner row
* fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets
One flush drains up to MAX_LOGS_PER_INTERVAL source transactions or logs, but a
transaction fans out to one LiteLLM_SpendLogToolIndex row per tool and a log
to one LiteLLM_SpendLogGuardrailIndex row per guardrail, so the index
create_many payload was unbounded. Both index writes now go through
spend_log_write_batches(SPEND_LOG_WRITE_BATCH_MAX_BYTES, SPEND_LOG_WRITE_BATCH_MAX_ROWS).
The tool index write moves out of the rollup batch_() so the split reduces
the query-engine payload; replayed index rows are no-ops under
skip_duplicates, and the daily rollup upserts stay in one transaction
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): pin the row budget in the index fan-out tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The bridge probe asked `responses_api_bridge_check` with the summary read straight off
the Responses object, but `litellm.completion` reads it from `optional_params` via
`peek_reasoning_summary_aliases`, which the bridged request never populated. So gpt-5,
gpt-5.1 and azure/gpt-5 answered "bridging" to the probe and "not bridging" for real,
and the object still landed on Chat Completions, which only takes a string
`reasoning_effort` is now always the effort string, and `summary` rides the
`reasoning_summary` alias that main.py already reassembles into `{effort, summary}` on
the bridged path. The alias is emitted only when the probe says the model bridges, so
no chat provider ever sees it, and the probe is now asked with the exact params this
transform emits
The Responses API takes reasoning as an object, {effort, summary}. Chat
Completions takes reasoning_effort as a string enum and has no equivalent of
summary, but the completion bridge forwarded the whole object whenever summary
was set, which agentic clients set on every request.
Bedrock Converse guards its mapping with isinstance(value, str) and has no else
branch, so the object fell through, thinking was never enabled, and the caller
was billed for a non-thinking turn with nothing in the response to explain it.
The object is still forwarded for the one caller that can consume it: a model
whose cost-map mode is responses, which litellm.completion bridges back onto the
Responses API and reassembles {effort, summary} there. That decision is delegated
to responses_api_bridge_check, the same check litellm.completion runs, rather
than a second copy of the rule that could drift from it. An object carrying no
effort now yields no reasoning_effort at all.
Multi-IdP deployments can now set virtual_key_claim_field and
unregistered_jwt_client_behavior on a JWTIssuerConfig entry. Tokens from
that issuer use the issuer-specific claim path and no-match policy for the
virtual key mapping lookup; issuers that omit them keep the global values.
The auth flow now enters the mapping lookup when any issuer configures the
field, not only when the global field is set.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
