* test(e2e): cover ollama and ollama_chat on chat completions, responses and messages
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): declare Subject metadata and check streamed tool call ids in the ollama suite
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Mubashir Osmani <mubashir@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata
* docs(e2e): name every markerless harness test file that carries no Subject
* test(e2e): keep the step discovery comprehensions to one for clause
* feat(mcp): advertise the SDK's latest spec revision and validate the RFC 9207 iss
MCPSpecVersion stopped at 2025-06-18 while the pinned SDK negotiates 2025-11-25, and the version LiteLLM puts on its own outbound initialize was a hardcoded historical member. Add the missing revision, name the highest revision we speak once, and pin it to the SDK's LATEST_PROTOCOL_VERSION with a test so the two cannot drift apart silently.
/authorize now seals the issuer it sent the user to into the OAuth state, and /callback holds the authorization response's RFC 9207 iss against it, refusing to forward a code that came back from an authorization server we never sent the user to. An absent iss, an unanchored server row and a state minted before the seal all keep their current behavior.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): keep params, query and fragment significant in issuer comparison
The shared canonicalizer drops all three, so two issuers differing only outside the path compared equal and a response from another tenant's authorization server would have continued through the flow.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): refresh generated API snapshots
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(mcp): cover OAuth client isolation and lint checks
* fix(mcp): preserve registered clients in the existing save payload
* test(mcp): cover optional OAuth registration metadata
* fix(mcp): preserve compatible OAuth registrations across edits
* fix(mcp): retain OAuth state through pending authorization
* fix(mcp): guard pending OAuth at form submission
* fix(mcp): discard canceled OAuth edit snapshots
* test(mcp): preserve complete OAuth registration assertions
* refactor(mcp): construct OAuth credential updates without mutation
* fix(mcp): simplify issuer binding and reject unverifiable callbacks
* fix(mcp): preserve replacement clients and pending redirect bindings
* fix(mcp): retain clients with replacement authentication methods
* fix(mcp): preserve cached clients and pin manual OAuth issuers
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(caching): count tool_call cache_control marks in the injection census
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): remove cache census casts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): only skip injection on message or content marks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): skip injection on messages whose tool calls carry marks
Reverts 9f08d8aef8. A default 5m mark injected on assistant text lands
before the client's 1h tool_use mark, which Anthropic rejects with a 400
because a 1h breakpoint must not follow a 5m one. Keeping the full census
in the skip check leaves the client's tool_call breakpoint as the only
one on that message.
* fix(caching): count every client tool_call cache mark in the breakpoint census
The census gated tool_call marks on type function and dict shape, so a client mark on a call without a type or with a string cache_control slipped past the count and injection overflowed the 4 breakpoint cap. Count any non-None tool_call mark, keep the server tool exclusion, and add integration cells for the capped surfaces, the yaml stand-down, Bedrock and Gemini, and router affinity
* test(integration): hold the upstream so the worker kill lands mid-burst
* refactor(caching): reuse the transform's server tool lookup in the breakpoint census
The census now calls the same helper the Anthropic transform uses to decide
whether a marked tool call becomes a server tool block, so the two cannot
drift apart. The owned-proxy burst test waits up to 90 seconds for the burst
to reach the wire before it kills a worker
* refactor(anthropic): move the server tool rebuild check under llms/anthropic
* test(integration): audit the tool call mark census across chat, messages, responses, and chaos
Adds the /audit cells for the breakpoint census on assistant tool_calls marks: the
Responses stream bridge, the OpenAI and Anthropic SDK clients, in-process Pydantic
messages, response cache twins, request-level points, a provider 401 on a capped request,
malformed provider_specific_fields and tool_call ids, null or empty points, a points
update mid-burst, a proxy restart mid-burst, and a worker SIGKILL that picks the worker
holding the burst's upstream connections
* test(integration): close the SDK clients the cache census cells open
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(e2e): jwt auto_register map-existing-key repro
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(jwt): auto_register_map_existing_key maps JWT to the user's existing virtual key
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(jwt): exclude blocked keys from auto_register_map_existing_key reuse
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(jwt): route existing-key lookup through VerificationTokenRepository
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): stop requiring LITELLM_SALT_KEY for the owned JWT gateway
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): gate the owned JWT gateway tests behind E2E_OWNED_GATEWAY
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(jwt): only reuse keys that can call LLM routes in auto_register_map_existing_key
Skip Admin UI session keys and keys whose allowed_routes restrict them to
anything other than llm_api_routes (management, read_only, password-reset
sessions). Mapping a JWT to one of those left the user with 401s or 403s on
every LLM call, since the mapping persists.
* fix(jwt): scope auto_register_map_existing_key reuse to the JWT-resolved team
Only reuse a key whose team_id matches the team auth_builder resolved for
the JWT (no team matches no team), so a personal key can no longer bypass
the resolved team's model and budget limits.
With the flag on, the first JWT request now falls through to the same
virtual-key checks later mapped requests get, instead of returning early,
so a reused key's own limits apply from request one rather than 200 then
403. Flag off keeps the early return unchanged.
* fix(jwt): keep the early return when no master key is set
Without a master key the generic virtual-key path returns a bare
INTERNAL_USER object, so falling through on the first auto-registered
request dropped the key's team, models and budgets. Only fall through when
a master key is configured.
Tests now assert the reused key per team rather than the query shape, and
cover the flag-off early return and the no-master-key case.
* test(jwt): assert on race-loser's returned key, not only mocks (TQ002)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(jwt): close the auto_register_map_existing_key race, shared-claim and expiry holes
A key auto_register just minted is never adopted by a concurrent request, so the race loser's cleanup can no longer delete a key another request mapped and cascade its mapping away (503, user left with no key)
Reuse only happens when the claim value is the JWT-resolved user_id. A shared claim such as azp or client_id falls back to minting, so one user can no longer land on another user's personal key and budget
Only keys that never expire are reused, so an expiring key can no longer pin the claim to a permanent 401
Integration tests on a real proxy and Postgres cover all three. The race test holds the first mapping insert in a Postgres relay, so the interleaving is forced rather than timed. The where-clause shape unit tests are replaced by these, since only a real database proves the filter
* test(e2e): create the reused key in the team the JWT resolves to
The flag only reuses a key in the JWT-resolved team, and this identity's groups claim resolves to its team, so a teamless key was never eligible and the test could not pass
* test(integration): match the held statement across TCP reads
The relay looked for the trigger inside one read, so an insert split across two reads was never held and the race test would fail waiting for it. It now matches one exact trigger over a window that keeps the end of the previous read
* fix(jwt): gate key reuse on the claim field, not on the claim value
Requiring the claim value to equal the resolved user_id skipped reuse for users matched through the sso_user_id or case-insensitive email fallback, whose stored user_id differs from the JWT sub. That is the lookup LIT-5378 asks for. Reuse is now allowed when the virtual key claim is the user_id or user_email JWT field, globally or for the token's issuer, which still keeps shared claims such as azp or client_id on the mint path
* fix(jwt): let an issuer's own user field replace the global one when gating key reuse
An issuer that identifies users by uid no longer treats the global sub field as a user identity claim, so a shared sub under that issuer mints instead of reusing a personal key
* test(jwt): make the flag-off test fail when the flag no longer gates key reuse
The flag-off test used a config where sub was not a user identity claim, so deleting the flag check still passed. Configure user_id_jwt_field=sub so only the flag keeps the lookup off, and drop test docstrings
* chore(lint): drop mutable-ok suppressions that LIT013 flags as no-ops
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mrinal <mrinal@berri.ai>
Co-authored-by: Mrinal Chanshetty <mchanshetty@Mrinals-MacBook-Pro.local>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* test(e2e): move live-provider legacy tests into tests/e2e
Port legacy tests that exercise real providers into the tests/e2e suites that own them, using the harness (/model/new plus deferred cleanup) and asserting on what the caller receives. Delete legacy tests already covered at equal or stronger strength by e2e, integration or unit tests, and drop the now empty ocr_testing CircleCI job
* test(e2e): address review on the live-provider test move
Assert the SSE error frame a client actually receives when a post_call guardrail blocks a stream, and require a tool call for every requested city before checking the answer. Restore the OCR matrix and its CircleCI job, the Claude Agent SDK streaming test, and test_async_create_batch, since their SDK-level and callback assertions have no equivalent in tests/e2e
* test(e2e): accept both guardrail block shapes on a blocked stream
A post_call block before the first chunk reaches the client as HTTP 400 with either a JSON error body or a single SSE error frame, depending on whether the block surfaced as an exception or an error chunk. Assert the policy message is present and the blocked output is absent in both
* test(realtime): restore direct SDK realtime tests against OpenAI
The e2e realtime tests go through the proxy and the remaining SDK tests either mock the upstream or assert less, so keep the direct litellm._arealtime tests with and without intent, and TestOpenAIRealtime::test_realtime_connection, in place
* test: make realtime and Nova stream checks deterministic
The direct SDK realtime tests now fail on a refused connection instead of skipping. The with-intent test asserts OpenAI rejects the exact intent value sent, which only happens when the intent is forwarded. The Nova /v1/messages stream test asserts stream structure, stop reason and usage instead of model wording
* test(realtime): own intent forwarding with a unit test instead of a live rejection
Assert litellm._arealtime passes the intent query param into the OpenAI realtime websocket URL, which is the behavior LiteLLM owns, and drop the live test that depended on OpenAI's rejection wording
* feat(e2e): record each e2e test's steps, starting with ProxyClient
@step on a harness method records a plain-English line for every call, in
order, as repeated JUnit step properties. Labels are templates filled from the
call's parameters, like "Generate a virtual key with models: claude-haiku-4-5
and rpm limit: 3", and secret request fields are marked Field(repr=False) so
they never print. ProxyClient and the rate-limit QuotaClient carry steps first;
the other harnesses follow one area at a time. The recorder and JUnit tests run
in the Code Quality workflow's test_e2e_metadata step.
* docs(e2e): rewrite the recorded test steps guide in plain language
* fix(e2e): keep logging callback credentials out of recorded steps
* fix(e2e): mask the run's credentials in every recorded step
* fix(e2e): attach steps before the oauth failure snapshot
The failed setup or call report of an mcp_oauth_live test copied user_properties before the steps were attached, so it carried no steps. Every setup and call report now takes its properties after the steps attach
* fix(e2e): name the saved credential in its recorded step
The create_credential label read credential_info, which defaults to {} and is never set by the live callers, so the step printed nothing after 'for'. It now reads the required credential_name, and a guard fails on any label that reads a field with a default
* fix(proxy): delete large teams without per-member transaction fan-out
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): evict email-only member caches and reset team members metric on delete
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep new delete-team literals within the LIT002 ceiling
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): resolve deleted-team member ids before the locked delete
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): resolve email-only deleted-team members with one case-insensitive lookup
`_deleted_team_member_user_ids` looked each email-only roster entry up with its own
`find_users_by_email` call inside an unbounded `asyncio.gather`: one exact-match query
per email, so a large roster fanned out against the pool again and a roster email that
differed in case from its user row was missed. Add `UserRepository.find_by_emails`, a
single case-insensitive `in` query, and call it once before the locked delete.
`management_helpers/utils.py` goes back to its main-branch shape since the single-email
helper no longer needs exporting.
* fix(repositories): slice find_by_emails into bounded IN statements
The unbounded-IN lint flagged the case-insensitive email lookup added for
/team/delete cache eviction. chunked_in.find_many_in cannot carry Prisma's
insensitive mode, so the repository slices the deduplicated list into
IN_LIST_CHUNK_SIZE statements itself and concatenates the pages. Empty input
still returns () without a query.
* fix(proxy): delete a team once when /team/delete repeats its id
The audit sent {"team_ids": [T, T]}: main answered 400 "User not found in
team" after deleting the keys and memberships and writing two tombstones,
leaving the team row behind; this branch answered 200 but still wrote the
tombstone, audit row and eviction twice. DeleteTeamRequest now collapses
repeated ids in order, so every later step sees each team once and the
response lists each deleted team once.
* test(integration): audit cells for /team/delete on large, legacy and concurrent teams
Thirty-eight deterministic cells in tests/integration/management/ (the CircleCI
integration-management group) covering the /team/delete happy, sad, edge and chaos rows:
250 members against a pool limit of five on two workers, the advisory-lock wait, email-only
legacy roster entries in every casing, member and team cache eviction on both proxies for
every client and endpoint, the Prometheus gauge, audit rows, malformed and duplicate input,
the route gate, and a worker kill, a Redis outage and a proxy restart mid-burst.
Every cell runs against the real proxy, Postgres and Redis with the scripted upstream; no
component is mocked. On the merge base the rows this fix changes are red (P2028 on the
250-member team, two lock waiters, case-mismatched email lookups, duplicate ids, orphaned
LiteLLM_UserTable.teams references under a concurrent burst); on the tip every cell is green
twice with identical selections.
Two pre-existing behaviours are pinned as observed rather than fixed here: a roster entry with
neither user_id nor user_email answers 500, and the LiteLLM_DeletedTeamTable row is committed
before the locked transaction, so a delete that dies in between leaves a tombstone for a live
team and the retry adds a second.
* test(integration): pin each chaos outage to a live /team/delete
The three chaos cells applied the outage once three deletes had answered, which on a fast
run let the whole burst finish before the worker kill, Redis stop or SIGTERM landed, so the
cells passed without exercising the failure. Each cell now holds the first team's advisory
lock from a test-owned transaction, waits until that team's delete is queued behind it in
Postgres with its request unanswered, applies the outage, and only then releases the lock,
so an in-flight delete meets the failure on every run and both legs. The pinned team's
outcome and the number of deletes answered before the outage are recorded as junit
properties (pinned_delete, answered_before_outage).
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
* fix(streaming): keep the provider's served service_tier on streamed chunks and spend rows
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): satisfy type-discipline and strict ruff budgets
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): stamp the served service_tier on every Responses bridge chunk
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-adapter): expose streamed chunks so disconnects bill partial spend
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(service-tier): cover anthropic and responses served-tier billing paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-adapter): return a chunks-exposing stream so disconnects bill partial spend
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(service-tier): bill disconnects through the router's anthropic stream wrapper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: apply ruff format to the anthropic stream changes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(coverage): ignore delegating properties the ast scan cannot see
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: keep the cast-ok reasons on the cast call line
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover served service_tier billing for streamed chat and messages, complete and disconnected
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-cache): delegate chunks/messages/model through the messages stream cache writer
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): keep service_tier on OpenAI-compatible parsed chunks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(streaming): parameterize delegated chunks and messages types
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(tests): follow the anthropic pass_through rename after merging main
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drain the logging worker between response cache tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): cover azure, databricks, responses bridge and gemini served tiers in the stream billing integration test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(databricks): keep the served service_tier on streamed chunks and bill it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(databricks): type the served service_tier chunk without a loose kwargs dict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost): bill the served service_tier over the requested one
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost): drop explanatory comment from the tier resolution
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: kerry <kerry@berri.ai>
Register Sail (providers.json, LlmProviders.SAIL, OpenAI-compatible lists,
ProviderConfigManager) for chat, Responses and /v1/messages, and add its 12
models to both cost maps with asap, balanced and flex price columns.
Sail picks speed and price with metadata.completion_window and rejects
service_tier, so the Sail chat and Responses configs translate the tier:
default and priority to asap, flex to flex, balanced to balanced, auto to no
window. Billing prices the window that was sent. A tier Sail has no window
for, or a window or tier set where billing cannot see it (request metadata,
extra_body), is a 400 unless drop_params is set.
Add balanced to ServiceTier and its _balanced price columns to the model
info types, the Rust catalog and the dashboard schema. A transform_extra_body
hook on the chat and Responses base configs, which returns extra_body
unchanged by default, lets Sail keep the window when a caller also sends
extra_body.metadata. Sail is listed in the Add Model form and model picker.
Co-authored-by: shrey kharbanda <shrey@berri.ai>
* fix(proxy): send a real error event when a /v1/messages stream fails
When a stream failed halfway through, the proxy wrote the error as a plain
`data: {"error": ...}` line with no `event:` in front of it. Anthropic clients
pick stream events by that name, so they skip the line and the request looks
like it simply stopped with nothing in it.
Write the failure as an `event: error` frame with Anthropic's own payload, and
take the error type from the status code
* fix(proxy): use the shared Anthropic error mapping for the stream error frame
The first pass added a third copy of the status to error-type table, and it
disagreed with the documented one: 529 came out as `api_error` rather than
`overloaded_error`, and 413 as `invalid_request_error` rather than
`request_too_large`, which hides the two failures a client can actually act on.
Drop that copy and put the frame builder next to the table litellm already
keeps in anthropic_interface/exceptions. The bridged adapter path was building
the same frame inline, so it uses the shared one now too
* fix(proxy): seal a torn SSE frame before the /v1/messages error event
An upstream that drops mid-frame leaves the client inside an open event,
so the error frame that follows is glued onto the torn data line and the
Anthropic SDK raises a JSON decode error instead of an APIStatusError.
Close the open frame with a ping event the SDK skips before writing the
error event, and add the e2e stream-cut edge with Bedrock, Anthropic
boundary, and Anthropic mid-frame legs.
* fix(proxy): keep the SSE tail unchanged on a chunk that is not text
A serializer that hands a dict or model object through as-is has no bytes
the frame tail can learn from, so advance_sse_tail leaves it alone instead
of slicing it.
* fix(proxy): answer a /v1/messages stream that fails before its first byte as a JSON error carrying its status
* test: move the Anthropic error frame tests into tests/unit
* test(e2e): cut the upstream stream only after content has been relayed
* test(e2e): carry split SSE lines across chunks and always tear a data line mid-frame
* test(e2e): find the next data line across a chunk boundary before tearing it
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(proxy): list key and team model aliases in GET /v1/models
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep alias listing helpers within the type discipline budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): cover alias rows on GET /v1/models and /v1/models/{id}
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply team then key aliases like chat completions and keep the alias as the retrieved id
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply key aliases twice like chat completions and skip only malformed alias entries
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply the global model_alias_map between the key alias passes like chat completions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): list only the caller's own aliases and never rewrite a listed model id on retrieval
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): ruff format model_info alias lookup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): hide undiscoverable names from model retrieval so an alias named like one resolves to its target
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep undiscoverable models retrievable by id while excluding them from the alias guard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): pass an immutable name sequence into the model_info alias guard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): type the model list alias test helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): annotate the new alias listing test fixtures and helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): attribute provider and model info on pre-call rejected requests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep pre-call rejections out of deployment cooldown and prometheus deployment state
Stamp model_info only into the logging metadata so the router's failure callbacks do not
count a key-level 429 or guardrail 403 against the deployment, treat a resolved plus an
unresolved deployment as ambiguous provider attribution, and stop the prometheus deployment
counters and deployment_state from treating a proxy-side reject as a selected deployment
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): skip deployment attribution when the rejected body's model is not a string
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(prometheus): bucket non-string request models as other instead of raising in failure hook
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): resolve team deployments and treat guardrail rejects as proxy-side in failure attribution
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(prometheus): flag pre-routing rejects instead of matching exception names
Post-call GuardrailRaisedException failures kept their deployment labels on main but lost them
on this branch because every GuardrailRaisedException was treated as a pre-routing reject.
The proxy failure path now flags litellm_params with proxy_rejected_before_routing only when
it adds deployment attribution itself, and the Prometheus logger keys deployment selection
off that flag
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): key pre-routing reject flag off provider handoff, not caller metadata
Caller-supplied metadata.model_info (kept for keys allowed to override pricing) no longer
suppresses proxy_rejected_before_routing. The hook now checks the logging object's
first_api_call_start_time, which only the provider handoff sets, so Prometheus never
records a deployment failure for a request that was rejected before routing.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): poll for both served and rejected spend rows before asserting attribution
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yucheng <yucheng@berri.ai>
* feat(proxy): opt-in include_guardrail_response returns guardrail_information in the response
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): read include_guardrail_response from the request metadata bucket the router did not reseed
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): format common request processing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): redact matched content in guardrail_information and stop mutating cached responses
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): traverse guardrail diagnostics iteratively
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): annotate guardrail traversal cast
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): reuse core redaction helper for guardrail_information
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(proxy): justify response rebind when attaching guardrail information
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>
* fix(websearch_interception): propagate parent session/trace ids into intercepted searches
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(websearch_interception): let parent correlation win over configured search params and type test params
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): bill an intercepted web search under the parent request session
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): drop unrelated reformatting from the websearch session harness change
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(e2e): keep the websearch interception session suite out of the stage-mirror gate
The stage-mirror stack runs no websearch_interception callback or search tool, so the suite is deselected there and the changed-tests gate fails on a file that executed nothing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(e2e): run the websearch interception session suite on the stage-mirror stack
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs(e2e): leave CONTRIBUTING.md untouched
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: shivam <shivam@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): write key deleted audit logs for cascade and alias key deletions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): assert persisted key deleted audit rows for cascade paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): route /audit and /v2/login to the control plane in split transport
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>
* fix(otel v2): map rerank and search output and the OCR, image edit and search input onto the Langfuse generation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel v2): summarize OCR data URIs by media type and size and log an empty document URL as empty
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel v2): keep URL-less search results, name OCR file streams and skip non-str query parts when logging
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(otel v2): drop the unused typing imports and the decorative section divider
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>
* fix(guardrails): store the masked output in spend logs when a post_call guardrail rewrites the response
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): record served output without re-narrowing the logging object
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): overlay the served output before message redaction so turn_off_message_logging still wins
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): type the monkeypatch fixture in the redaction ordering regression
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): poll through raw card output until the guardrail reaches the serving worker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): keep blanked, multi-choice and disconnected served output out of raw spend logs
Served text keeps empty strings and tracks unavailable choices as None so a guardrail that blanks
the output still overrides the raw provider text. Stream choices are sized from the highest choice
index, served chunks are recorded before a client disconnect or stream failure propagates, and
message-logging redaction drops the served text from callback kwargs
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>
* fix(otel v2): map completions, images, speech, transcription and moderation output onto the generation output
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(redaction): redact text completion choices in the standard logging payload
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): compare decoded generation output text and follow the live moderation verdict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel v2): compare logged byte counts with the received media and move e2e schemas into models.py
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(e2e): keep the otel_v2 Langfuse output e2e file out of the stage-mirror gate it cannot run in
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>
/v1/videos dispatches call_type avideo_generation, which CallTypes did not
know and no guardrail translation handler covered, so the unified guardrail
hook returned the request unscanned. Add the video call types and an OpenAI
video guardrail translation package that scans the prompt for create, remix,
edit and extension requests
Resolves LIT-6685
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Register s3_access_key_id, s3_secret_access_key and s3_encryption_key_id as
LiteLLM-owned batch params so they are no longer forwarded to Bedrock as
additionalModelRequestFields (which 400s ordinary chat on a batch-configured
deployment), keep them on CredentialLiteLLMParams so the batch/file paths
still receive them, and redact the S3 credential key names in debug logs.
Resolves LIT-8290
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Register s3_access_key_id, s3_secret_access_key and s3_encryption_key_id as
LiteLLM-owned batch params so they are no longer forwarded to Bedrock as
additionalModelRequestFields (which 400s ordinary chat on a batch-configured
deployment), keep them on CredentialLiteLLMParams so the batch/file paths
still receive them, and redact the S3 credential key names in debug logs.
Resolves LIT-8290
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Live proxy with cancel_on_disconnect, two-deployment group, generic allowed_fails=0, red at the pre-fix handler and green with the bare raise
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Resolves the six conflicts main accumulated against the SDK migration.
endpoints_client.py stays deleted (main only added the safety_identifier
kwarg to it), and its two new importers move onto the SDK clients: the
Bedrock safety_identifier forwarding test in test_responses_e2e.py now
sends its /v1/responses leg through the OpenAI SDK and its chat leg
through ProxyClient.chat, and test_messages_azure_foundry_e2e.py drops
the x-litellm-rust header check together with EXPECT_RUST, which main
removed from e2e_config in a84f68b6e3. proxy_client.py keeps both the
rerank and router-settings model imports. uv.lock is main's lock plus
the anthropic e2e-dev entry, and the pricing JSONs are taken verbatim
from main since this PR never meant to change them.
/key/info now serves a deleted key from the archive with status deleted
instead of answering 404, so the delete test's convergence predicate never
settled and the read timed out against a 200 it kept discarding.
The predicate now waits for status deleted through the same
_key_info_everywhere helper the rest of the file uses, and KeyInfo carries
the status field. The chat-rejection assertion after it is unchanged, so
the test still proves the key stops serving.
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.
Re-migrates the e2e tests that main extended through endpoints_client
since this branch was opened (Azure Foundry, mid-conversation system
messages, Bedrock web search, google native streaming) onto the
provider SDK clients, so no endpoints_client reference remains
The sequential version sent one request at a time, so a Redis outage never
reached the concurrency where the failed-tracking alert body actually grows.
This drives the proxy with locust against one model group of three mock
deployments, two failing at order 1 and one serving at order 2, so every
request spends its retries on the failing pair and lands on the serving
deployment through the order-based fallback. Two phases, a healthy baseline
and a CLIENT PAUSE WRITE window, and every request must succeed in both.
Latency, RSS and CPU are reported as p50/p90/p99 per phase rather than
asserted on: RSS and CPU come from psutil on the proxy's process tree, since
a multi-worker proxy serves /metrics from the prometheus multiprocess
collector and that drops the process collector's series. Thresholds stay open
until weekly runs give real baselines.
Co-Authored-By: Claude Code <noreply@anthropic.com>
On the release gate the e2e tests only see the nginx router, and the chart's
ingress sent /debug/memory/summary to the backend catch-all, so the RSS check
measured the backend pod instead of the gateway workers that serve the failing
requests. Render it as an Exact gateway path next to /test, name the host in the
summary response so workers behind one origin never collide on pid alone, and
key the harness readings by (origin, hostname, pid)
Add an embeddings case with its own closed-port primary and mock backup (the fallback map in
the gateway config gains the pair; LiteLLMParamsBody.mock_response accepts the list an embedding
mock needs). Assert from /metrics that the proxy's resident memory grows by no more than 200 MB
across each case where the process collector reports it (Linux), that the router counted a
successful fallback for every request, and that every spend row is a success.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014ZDULyJPp17ZFiJenRxs2T
