temp_budget_increase was only applied on the DB-fetch path of _user_api_key_auth_builder, so a key served from the auth cache reverted to its original max_budget and was wrongly blocked with BudgetExceededError once spend crossed the original budget while staying under the effective budget.
Move _update_key_budget_with_temp_budget_increase out of the DB-only branch so it runs for every resolved token regardless of source. The cache stores the original budget and each cache hit returns a fresh model_copy(), so this never double-applies.
Fixes#25760
Co-authored-by: shivam <shivam@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The JWT first-login upsert in get_user_object creates the user row by
merging default_internal_user_params straight into table.create, so a
configured budget_duration landed with budget_reset_at NULL. The reset
sweep now heals such rows (PR #33623), but until the next sweep the row
shows a null reset time and its first window starts at the sweep instead
of one full duration after creation. Compute budget_reset_at at creation
like every other write path (/user/new, UI SSO, /key/generate, /team/new)
already does
Continues #29762. Response models (Message, Choices, Usage) delete unset
optional fields in __init__ so model_dump matches the OpenAI spec. Each delete
routed through pydantic's BaseModel.__delattr__, whose per-call
ModelMetaclass.__getattr__ lookup and _check_frozen dominate construction. When
the target is a declared field already present in __dict__ on a non-frozen
model, delete it with object.__delattr__ directly; that is exactly what pydantic
2.13 does for that case, minus the metaclass getattr and the frozen check. It
falls back to the previous super().__delattr__ path for extras, private
attributes, cached properties and missing names, so behavior is unchanged.
Co-authored-by: Jay Gowdy <jgowdy@godaddy.com>
Internal users seeded from default_internal_user_params (SSO/JWT first-login
upsert, or /user/new without an explicit budget_reset_at) get budget_duration
set but budget_reset_at = NULL. The ResetBudgetJob user/team queries filter on
{"budget_reset_at": {"lt": now}}, which never matches NULL, so these rows are
never reset: their spend accumulates for the lifetime of the row and silently
exceeds max_budget with no periodic reset.
The budget-table query already handles this by OR-ing in a
{budget_reset_at IS NULL AND budget_duration IS NOT NULL} branch. Apply the
same pattern to the user and team reset queries in PrismaClient.get_data.
Adds a regression test asserting both the user and team reset queries select
NULL-budget_reset_at rows that have a budget_duration.
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Ran the before/after proof live against Vertex Claude (global endpoint,
project vertex-check-481318): base transform 400s an unflagged model
(claude-opus-4-7) on a mid-conversation role:system reminder, the fix
hoists it to a 200, and a flagged model (claude-opus-4-8) keeps the
reminder in messages with cache_read held at 15615 across the reminder
turn. Flip both vertex.mid_conversation_system rows to fail_before_fix:
proven.
Azure AI Foundry and Vertex AI serve Claude on the first-party Anthropic
Messages contract, which was verified live to be byte-identical to
api.anthropic.com: a leading role:"system" entry in messages is rejected on
every model ("messages.0: use the top-level 'system' parameter"), and a
mid-conversation role:"system" reminder is accepted in place on Claude 4.8+/5
but 400s on Claude 4.7 and older ("role 'system' is not supported on this
model"). This is the same contract Bedrock Invoke already handles model-aware
(PRs #32578/#32831/#32882); Vertex and Azure did no hoisting at all, so a Claude
Code session on an older Vertex/Azure Claude model hard-400s on its reminder
turns, and the only thing sparing 4.8+/5 was that nothing was hoisted
Extract Bedrock's model-gated normalization into the shared
AnthropicMessagesConfig base as _normalize_system_role_messages and call it from
the Vertex and Azure messages configs. Flagged models (4.8+/5) hoist only the
leading run of system entries and keep mid-conversation reminders in place so
the top-level system prefix stays byte-identical and the prompt cache is
preserved; unflagged models hoist every system entry so the request returns a
completion instead of a 400
Add supports_mid_conversation_system to the azure_ai and vertex_ai Claude 4.8+/5
cost-map entries. Exact cost-map hits win over the claude-mid-conversation-system
fallback rule, so without the explicit flag those models would be treated as
unsupported and hoist every reminder, collapsing the prompt cache (the exact
customer regression). A per-provider test guards this so future 4.8+/5 entries
cannot silently miss the flag
Closes the Vertex/Azure gap from the customer RCA
Continues #29761. Delta.__init__ set roughly ten attributes through pydantic's
__setattr__ and then deleted the five OpenAI omits on every chunk. Those keys
are extra fields (extra='allow'), so this builds __pydantic_extra__ and
__pydantic_fields_set__ directly after the parent init instead of round-tripping
each field through __setattr__/__delattr__. The resulting __dict__,
__pydantic_extra__, __pydantic_fields_set__ and model_dump output (including
exclude_unset, which the streaming path relies on) are byte-identical to the
previous behavior; a serialization-contract test locks that. A TYPE_CHECKING
block re-declares the extra attributes with their concrete types so type
checkers still see delta.content and friends.
Co-authored-by: Jay Gowdy <jgowdy@godaddy.com>
Staging now contains #33153, whose final rounds made _extract_upstream_auth_failure a thin delegate
to upstream_auth_challenge and introduced the response-level iterator this branch predates. The
resolution completes the consolidation both branches were converging on: iter_exception_tree
(faults/traversal.py) is the one tree walk, _iter_upstream_responses is rebuilt on top of it instead
of carrying a second copy of the traversal, the manager keeps the delegate, and the semantic filter
port from this branch stands. Test conflicts were append-append and both sides are kept
* test(e2e): cover passthrough headers, batch assume-role, gemini, vllm, bedrock guardrails, batch rate-limit mapping
Add parent-package e2e suites for the six feature gaps: pass-through header forwarding via /config/pass_through_endpoint, Bedrock batch STS assume-role, Gemini chat + files, hosted_vllm batch/files, Bedrock guardrail pre_call blocks (plus restored content-filter team opt-out), and OpenAI batch RPM 429 body mapping. Registry cells and LiteLLMParamsBody/TeamMetadata fields updated so markers collect cleanly.
* test(e2e): cover LIT-4587 gaps for redis, responses, tpm cache, apply_guardrail, langfuse
Adds customer-shaped live e2e for apply_guardrail, responses store+metadata TTL,
TPM excluding cached tokens, redis-backed RPM, redis circuit-breaker path,
Langfuse spend, Cohere chat, virtual-key auth, file content download, hosted_vllm
chat, and Nova Sonic realtime. Registry cells updated for the new markers.
* test(e2e): drive LIT-4587 gap suites on Anthropic to avoid Gemini quota flakes
Redis RPM, circuit-breaker path, virtual-key auth, responses metadata, and
Langfuse driver models now use Anthropic haiku so local runs stay green when
Gemini daily quota is exhausted.
* test(e2e): drop Langfuse spend suite; feature is being deprecated
Remove test_langfuse_e2e.py, logging.langfuse registry cells, and the
langfuse-only conftest driver/credentials fixtures.
* test(e2e): fold provider/batch feature tests into their endpoint suites
Keep the e2e layout endpoint- and suite-scoped instead of one file per
provider or feature
Move the virtual-key auth case into access_control/test_access_control_e2e.py
as TestVirtualKeyAuth (replacing an incomplete stub) and drop the standalone
test_virtual_key_auth_e2e.py
Fold the five per-file batch suites (file content, RPM 429 mapping, Bedrock
assume-role, Gemini files, hosted_vllm batch) into batches/test_batches_e2e.py.
The hosted_vllm batch case is skipped for now since it needs a live vLLM server
(HOSTED_VLLM_API_BASE) the e2e environment does not provision; it and the
gemini-files and RPM-mapping cases reference LIT-3382 / LIT-3266 where relevant
Merge the cohere, gemini and hosted_vllm chat cases into
llm_translation/test_chat_completions_regression_e2e.py so /chat/completions
coverage lives in one endpoint file, and repoint the coverage_registry source
fields to the new homes
Move the shared CacheControl / TextBlock / RichMessage request blocks into the
root models.py (re-exported from endpoints_client) so quota_management can use
them without a cross-suite import, which also clears the basedpyright errors in
test_tpm_excludes_cached_tokens_e2e.py; type the httpbin echo body in
test_passthrough_headers_e2e.py with a pydantic model to drop the Any-typed
json.loads path
* test(e2e): address review feedback and re-home virtual-key coverage
Replace the tautological Bedrock assume-role batch id assertion (`startswith(...)
or batch.id`, always true) with a managed-id shape check, since the unified
target_model_names path re-encodes the id rather than returning a raw ARN
Raise the batch RPM-mapping test's rpm_limit above one so the file upload can no
longer consume the key's sole request unit before batch create runs; the batch
create then clears the generic per-request limiter and the batch limiter is what
returns the "Batch rate limit exceeded" body the assertions check
Set exercised_on to [] on the pass-through header test; it drives a pass-through
endpoint, not /chat/completions
Move the virtual-key valid_allows / invalid_denied cells from other.yaml to
mgmt.yaml as mgmt.virtual_key.* so TestVirtualKeyAuth rolls up under Management,
and point its covers marker at the new ids
* test(e2e): add reliability suite covering fallback, timeout, and cache behavior
* test(e2e): move reliability suite under router and drive it with real deployments
* test(e2e): make the router complexity fixture opt-in so reliability tests can coexist
* fix(cache): make in-memory and disk increments atomic
* refactor(cache): narrow in-memory increment lock scope
* fix(cache): address follow-up review on increment tests/types
* fix(cache): refresh atomic increment coverage
* test(cache): widen increment race window with non-zero _SlowInt seed
The zero seed was falsy, so InMemoryCache.increment_cache's `get_cache(...) or 0`
and DiskCache.get_cache's truthiness guard both discarded the _SlowInt before
__add__ could run, leaving the sleep-based window-widening inert. Seed a non-zero
value and return _SlowInt from __add__ so the sleep fires on every read-modify-write
in both backends, making the concurrency regression deterministic.
* test(cache): cover InMemoryCache.async_increment delegation
Add a focused async test asserting async_increment accumulates through the
locked sync path, exercising the previously uncovered delegation line.
---------
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
It is a non-binary latency SLO threshold rather than a deterministic pass/fail
behavior a single e2e test can assert, so it does not fit the coverage registry's
one-test-per-cell contract. The registry README already flagged the perf cells for
a support-check or prune, and throughput SLO under load is covered structurally by
the Locust load suite. Removing it keeps the denominator to behaviors an e2e test
can deterministically prove.
Caller-supplied bedrock_tags land as AWS resource tags under the proxy's
AWS identity, letting an authenticated caller forge ownership or
cost-allocation labels. Add bedrock_tags to _BANNED_REQUEST_BODY_PARAMS
so per-request tags need general_settings.allow_client_side_credentials
or configurable_clientside_auth_params on the deployment, matching the
aws_bedrock_project_id precedent. Deployment-level bedrock_tags in
litellm_params are unaffected.
Also stop an explicit empty bedrock_tags list in litellm_params from
falling through to optional_params
The model_info / get_model_info_with_id endpoint tests drove refactored
endpoints with bare, unspec'd MagicMock routers and models. Because the
mocks were unspec'd, any attribute or method the (refactored) endpoints
newly read auto-materialized a child MagicMock, and whether that child
was reached depended on process-global state (premium_user, and the real
get_available_models_for_user chain reading litellm globals) that sibling
tests in the same xdist worker mutate. When reached, the MagicMock either
unpacked to empty (a, b = mock.method() -> 'not enough values to unpack
(expected 2, got 0)') or leaked into RouterModelInfo(**model_info) and
failed Pydantic str validation. Pass in isolation, fail under xdist.
The original TestModelInfoEndpoint failure (#33807 CI) was the same class
surfaced by merge skew: #33721 added a get_configured_token_limits unpack
to create_model_info_response, and CI's merge commit ran that against the
un-updated bare-mock test before the #33742 band-aid landed.
Fix (test-only, no product change):
- TestModelInfoEndpoint: mock the real seam (get_available_models_for_user),
configure the router methods the endpoint actually calls, return a real
Deployment, and drop the dead proxy_server.get_key_models/get_team_models/
get_complete_model_list patches the refactor had stranded.
- TestGetModelInfoWithIdBlocked: spec the model mock so unset enterprise
columns read as None instead of child MagicMocks.
- test_ProxyConfig_get_model_info_with_id_missing_model_id_raises: pin
premium_user so the asserted AttributeError no longer flips with the
ambient license global.
_resolve_v2_auth dropped the resolved client_credentials auth when extra_headers
already carried Authorization (MCPJWTSigner, static_headers), so the upstream got
the injected header instead of the minted token and the one-shot 401 refetch was
lost. M2M now joins token_exchange and authorization_code in the authoritative
set; the conflicting header is dropped
The auth object is the httpx client's auth for the whole MCP session; after a
401 recovery it kept sending the rejected token first, burning a 401 round trip
and the single retry on every subsequent call
An expires_in of zero or below computes a ttl of 0; the entry could never be
served but still occupied a slot in the bounded backend, where it could evict
a live token. The mint still serves the current request and the next get
re-fetches under the per-server lock
Greptile P2s: the per-server lock dict now evicts its oldest entry past
max_locks so ephemeral server ids (REST tools preview) cannot grow it
unbounded, and the min-cache floor is capped at the token's actual lifetime so
an expires_in below the skew is never served past expiry
The graft test pinned the pre-migration contract (M2M defers to v1). Replaced
with two tests pinning the new one: a complete-config M2M server resolves via
the v2 arm into ClientCredentialsBearerAuth, and an incomplete-config server
fails closed with a 500 misconfigured naming the missing grant fields
Replaces the not_implemented stub with a live arm: ClientCredentialsTokenSource
mints and caches the M2M token (rotation-aware identity key, expires_in-driven
TTL, audience and token_endpoint_auth_method support) and
ClientCredentialsBearerAuth retries an upstream 401 exactly once with a freshly
minted token. to_server_spec owns oauth2_flow=client_credentials servers and
fails closed on incomplete grant config instead of connecting unauthenticated
