* fix(bedrock-invoke): retain clear_tool_uses_20250919 context_management edits and emit context-management-2025-06-27 beta (LIT-3393)
Copy of #29206 by oss-agent-shin, rebased onto litellm_internal_staging so CircleCI can run.
Bedrock InvokeModel supports automatic tool-call clearing (clear_tool_uses_20250919) under the context-management-2025-06-27 beta, but LiteLLM stripped the edit and dropped the beta header, causing a Bedrock 400. This maps bedrock.context-management-2025-06-27 to itself in anthropic_beta_headers_config.json (bedrock_converse stays null) and rewrites _filter_context_management_for_bedrock_invoke around an allowlist of supported edit types that keeps each supported edit and adds its matching beta.
* test(bedrock-invoke): restore beta-headers config cache with a shared fixture in LIT-3393 tests
Greptile flagged that three of the four new tests reloaded the module-level
beta-headers config into local mode without restoring it on teardown, leaking
state into later tests in the same process. Move setup/teardown into a
local_beta_headers_config fixture used by all four tests.
---------
Co-authored-by: oss-agent-shin <ext-agent-shin@berri.ai>
* fix: rust ocr tests finally pass
* fix: move realtime dir
* fix(realtime): normalize azure realtime api_base to host for Foundry endpoints
The azure realtime handler appended the realtime path to api_base verbatim, so a
Foundry base carrying a project path (.../api/projects/<name>) produced an invalid
realtime URL and the websocket handshake hung. Normalize api_base to scheme and host
before building the realtime path so both Azure OpenAI and Foundry bases connect
Point the e2e realtime azure deployment at the GA gpt-realtime model and stop passing
the os.environ refs the realtime path never unwraps, resolving them from the gateway
env by name instead. Drop the local docker-compose scaffolding from the tree
* test(e2e): add Gateway.list_files and list_fine_tuning_jobs for the discovery suite
The discovery endpoints suite calls client.gateway.list_files and
list_fine_tuning_jobs, which did not exist on Gateway, so both tests errored with
AttributeError before reaching the proxy. Add the two GET wrappers using the
existing FileListResponse / FineTuningJobsResponse models
* revert(realtime): drop azure realtime api_base host-normalization
The azure realtime handshake failure was a config issue, not a litellm bug: the
realtime base was set to the Azure AI Foundry project endpoint (.../api/projects/<p>),
but the OpenAI-compatible realtime route lives at the resource root. litellm correctly
appends the realtime path to whatever base it is given, so pointing the realtime
deployment at the resource root is the fix and no core change is needed
* fix(ocr): route azure_ai doc-intelligence to its own endpoint at the source
get_llm_provider inherits AZURE_AI_API_BASE into api_base for every azure_ai/* OCR
model, but Azure Document Intelligence is a separate resource reached via
AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT, so doc-intelligence requests went to the wrong
host. Stop inheriting the azure_ai base for doc-intelligence models so api_base stays
unset and both the rust bridge and the python get_complete_url fall back to the
document-intelligence endpoint. This drops the earlier _rust_bridge_api_base reorder,
which only covered the rust path and let the env silently override an explicit api_base
* refactor(ocr): consolidate azure doc-intelligence detection; keep explicit api_base
Extract is_azure_document_intelligence_model as the single source of truth for the azure_ai doc-intelligence sub-route so the check is no longer duplicated across _prepare_ocr_request and _rust_bridge_api_base, and gate the dynamic_api_base suppression on the caller not supplying an api_base so an explicit endpoint is always honoured. Restore xai to the realtime PROVIDERS as a documented disabled entry instead of dropping it silently, and add a regression test pinning doc-intelligence api_base resolution.
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>
* fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException
The Bedrock-specific GuardrailInterventionNormalStringError predates the
unified guardrails refactor and no proxy code path handles it, so a block
with the flag set surfaced as an uncaught Exception -> HTTP 500 in pre_call
mode and was silently discarded in during_call mode (model call proceeded
in the parallel asyncio.gather; the block hook's data["mock_response"]
mutation happened after route_request had already unpacked kwargs).
Convert the block to ModifyResponseException at the raise site inside
make_bedrock_api_request. That exception is the industry-standard proxy
contract already caught in proxy_server, anthropic_endpoints, response_api
_endpoints, and pass_through_endpoints; it turns into a 200 response with
finish_reason=content_filter and the block message as content, which is
exactly what the flag was documented to yield. Post-call blocks attach
the LLM response to original_response so the synthetic reply reports the
upstream call's real token usage instead of zero.
Deletes the now-orphaned GuardrailInterventionNormalStringError class and
the dead create_guardrail_blocked_response / mock_response plumbing in the
Bedrock hooks; updates the existing tests that had locked in the buggy
contract.
Resolves LIT-4186
* chore(guardrails/bedrock): drop dead str branch in _update_messages_with_updated_bedrock_guardrail_response
Follow-up to the disable_exception_on_block fix. That method used to
receive either a BedrockGuardrailResponse or a plain string (the block
message, when the flag was set). Now that a block always raises
ModifyResponseException before this method runs, the string branch is
unreachable; tighten the type to BedrockGuardrailResponse and delete
the guard.
* fix(guardrails/bedrock): streaming post_call block yields synthetic stream instead of surfacing as SSE 500
Regression from the LIT-4186 refactor: pre-refactor, the streaming
post_call iterator caught GuardrailInterventionNormalStringError locally
and replaced the assembled response with a synthetic content-filter
message, then re-emitted it as chunks via MockResponseIterator. After
the refactor the exception was re-raised as ModifyResponseException,
which async_streaming_data_generator serializes as a proxy 500 error
frame because the SSE response headers are already flushed by the time
the block fires.
Non-streaming paths still let ModifyResponseException propagate to the
endpoint handler (which converts it into a 200). Streaming can't do
that, so keep the local synthesis: on the exception, rebind the
assembled response to a ModelResponse whose single choice carries the
block message as content and finish_reason=content_filter, and let the
downstream MockResponseIterator emit it as chunks. Same shape a
non-streaming block produces.
Adds a mapped-file regression test that mutation-kills the raise
behavior and locks in the synthetic-stream contract.
* fix(guardrails/bedrock): preserve upstream usage on streaming post_call block
Non-streaming post_call blocks report the upstream LLM call's real
token usage via ModifyResponseException.original_response, which the
endpoint handler unwraps through _blocked_response_usage. Streaming
post_call synthesizes its own ModelResponse locally (the exception
can't escape the SSE generator), and previously left .usage unset,
so the client saw accurate billing on non-streaming blocks and zero
on streaming blocks -- silent revenue leak.
Copy the assembled response's .usage onto the synthetic block
response before yielding. Pre-refactor code had the same gap
(create_guardrail_blocked_response never set usage); this is a net
improvement, not a regression fix.
* fix(proxy): capture logging_obj before post_call_failure_hook pops it in ModifyResponseException streaming path
post_call_failure_hook removes litellm_logging_obj from request_data before
iterating callbacks (it's not serialisable). The streaming branch of the
ModifyResponseException handler read it from _data after that call, so it
always received None and CustomStreamWrapper.__init__ crashed with
AttributeError: NoneType has no attribute model_call_details.
Capture it before the hook runs so the streaming path gets a valid object.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* test(proxy): add regression for streaming ModifyResponseException logging_obj capture
Covers the bug where logging_obj was read from request_data after
post_call_failure_hook had already popped it, causing CustomStreamWrapper
to crash with AttributeError.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* test(proxy): drive real chat_completion in ModifyResponseException streaming logging_obj regression
The original test inlined the fix pattern (capture before pop) in its
own body rather than calling the actual chat_completion handler in
proxy_server.py, so a revert of the fix left the test passing.
Confirmed via mutation check: reverting the two-line source fix and
re-running left the test green.
Rewrite the test to drive chat_completion directly:
- patch _read_request_body so chat_completion sees the seeded dict
- patch ProxyBaseLLMRequestProcessing.base_process_llm_request to
raise ModifyResponseException with the same request_data
- patch proxy_logging_obj so post_call_failure_hook mutates the dict
the way production does (pops litellm_logging_obj)
- intercept CustomStreamWrapper.__init__ and assert logging_obj is
the non-None object seeded in request_data
Mutation-verified: reverting the source fix now surfaces the exact
production crash inside CustomStreamWrapper's __init__
(AttributeError: NoneType has no attribute model_call_details) rather
than a silently-passing test.
Addresses Greptile P1 on PR #32665.
---------
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
create_model now waits until the new deployment is servable on the data plane
(polls /v1/models) before returning, instead of assuming /model/new makes it
instantly callable. On a split control/data-plane proxy the gateway only sees a
model after its next DB reload, so an immediate call raced the reload and 400'd
with "Invalid model name passed" (embeddings, responses, messages, ocr, ...).
It also stops pinning model_info.id to the model_name, letting the proxy assign a
unique model_id. Re-registering a fixed-name deployment (the batch suite's
openai-batch et al.) after a failed teardown no longer collides on the model_id
unique constraint (prisma UniqueViolationError surfaced as the generic 500
"Failed to add model to db", erroring every batch_lifecycle case at setup)
* fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException
The Bedrock-specific GuardrailInterventionNormalStringError predates the
unified guardrails refactor and no proxy code path handles it, so a block
with the flag set surfaced as an uncaught Exception -> HTTP 500 in pre_call
mode and was silently discarded in during_call mode (model call proceeded
in the parallel asyncio.gather; the block hook's data["mock_response"]
mutation happened after route_request had already unpacked kwargs).
Convert the block to ModifyResponseException at the raise site inside
make_bedrock_api_request. That exception is the industry-standard proxy
contract already caught in proxy_server, anthropic_endpoints, response_api
_endpoints, and pass_through_endpoints; it turns into a 200 response with
finish_reason=content_filter and the block message as content, which is
exactly what the flag was documented to yield. Post-call blocks attach
the LLM response to original_response so the synthetic reply reports the
upstream call's real token usage instead of zero.
Deletes the now-orphaned GuardrailInterventionNormalStringError class and
the dead create_guardrail_blocked_response / mock_response plumbing in the
Bedrock hooks; updates the existing tests that had locked in the buggy
contract.
Resolves LIT-4186
* chore(guardrails/bedrock): drop dead str branch in _update_messages_with_updated_bedrock_guardrail_response
Follow-up to the disable_exception_on_block fix. That method used to
receive either a BedrockGuardrailResponse or a plain string (the block
message, when the flag was set). Now that a block always raises
ModifyResponseException before this method runs, the string branch is
unreachable; tighten the type to BedrockGuardrailResponse and delete
the guard.
* fix(guardrails/bedrock): streaming post_call block yields synthetic stream instead of surfacing as SSE 500
Regression from the LIT-4186 refactor: pre-refactor, the streaming
post_call iterator caught GuardrailInterventionNormalStringError locally
and replaced the assembled response with a synthetic content-filter
message, then re-emitted it as chunks via MockResponseIterator. After
the refactor the exception was re-raised as ModifyResponseException,
which async_streaming_data_generator serializes as a proxy 500 error
frame because the SSE response headers are already flushed by the time
the block fires.
Non-streaming paths still let ModifyResponseException propagate to the
endpoint handler (which converts it into a 200). Streaming can't do
that, so keep the local synthesis: on the exception, rebind the
assembled response to a ModelResponse whose single choice carries the
block message as content and finish_reason=content_filter, and let the
downstream MockResponseIterator emit it as chunks. Same shape a
non-streaming block produces.
Adds a mapped-file regression test that mutation-kills the raise
behavior and locks in the synthetic-stream contract.
* fix(guardrails/bedrock): preserve upstream usage on streaming post_call block
Non-streaming post_call blocks report the upstream LLM call's real
token usage via ModifyResponseException.original_response, which the
endpoint handler unwraps through _blocked_response_usage. Streaming
post_call synthesizes its own ModelResponse locally (the exception
can't escape the SSE generator), and previously left .usage unset,
so the client saw accurate billing on non-streaming blocks and zero
on streaming blocks -- silent revenue leak.
Copy the assembled response's .usage onto the synthetic block
response before yielding. Pre-refactor code had the same gap
(create_guardrail_blocked_response never set usage); this is a net
improvement, not a regression fix.
The App Router migration is complete: every page is a path route and the
legacy `?page=` switch is gone from the index. This closes it out.
The `/ui/` index (page.tsx) kept its own duplicate copy of teams state, a
teams fetch, and keys/addKey plumbing solely to feed a second `UserDashboard`
render for the `invitation_id` case. That was redundant: `ApiKeysDashboard`
already renders `UserDashboard` sourcing its own data, so the index is thinned
to just render `<ApiKeysDashboard />`. The login redirect, the legacy `?page=`
deep-link redirect for old bookmarks, and the post-login return-URL handling
stay on the index.
The invitation entry point now resolves in one place. Modern invitation links
already point at the dedicated `/onboarding` route; the dashboard layout now
redirects legacy `/ui/?invitation_id=` links there too (via `migratedHref`,
the same base-aware redirect the index uses for `?page=`), instead of
re-rendering that route's page component inline. This removes an import of one
route's `page.tsx` into another module, and lets the now-unreachable
`if (invitation_id) return <Onboarding/>` branch in the shared
`user_dashboard.tsx` be deleted along with its dead `Onboarding` import and
`searchParams` read. A layout test asserts the redirect and fails if it
regresses.
`legacyPageHref` and the sidebar's migrated-vs-legacy href fallback are left
in place; they are still live for the parent-category nav nodes (agentic,
tools, experimental, settings) that are not page routes.
eslint-metrics.json is resynced: -2 no-explicit-any from the removed `any`
casts, plus pre-existing drift the gate requires the snapshot to match.
* fix(ui): forward refs through ui primitives and fail tests on swallowed refs
Under React 18 a ref passed to a plain function component is dropped
with only a dev console warning, so Base UI render-prop triggers
composed over our shadcn-style primitives silently stop working (the
tooltip just never opens; ui/badge.tsx hit exactly this on the shared
DataTable branch). Label, Separator, Skeleton, UiLoadingSpinner and the
Table family now use React.forwardRef like Button and Input already
did, a contract test pins ref delivery for each, and setupTests turns
React's ref warning into a test failure so the next primitive that
swallows a ref fails CI instead of shipping a dead tooltip
* fix(ui): include captured ref warnings in the tripwire error
The afterEach tripwire threw a fixed message and discarded the collected
React warnings, so a failure never said which component swallowed the ref.
Append the captured warnings (component name + stack) to the thrown error.
The expanded reasoning block did not constrain its width or break long unbreakable tokens, so its inline-block bubble grew past its max width and pushed the whole page wider (#32481). Mirror the message body handling by capping the container width and breaking long words/code.
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
When an IdP denies SSO access it redirects back to /sso/callback with
error and error_description query params and no code param. The callback
previously fell through to the provider token exchange, which failed
with a generic "'code' parameter was not found in callback request"
400 that hides the real denial reason. Raise a 401 that surfaces the
IdP's error and description instead.
Ported from #26640 with conflicts resolved against current staging
The v2 OTel integration stamped litellm-specific error details as
error.code, error.stack_trace, and error.llm_provider, squatting on the
semconv-owned error.* namespace. They now live at
litellm.provider.error.code, litellm.provider.error.stack_trace, and
litellm.provider.error.llm_provider alongside the other vendor-extension
keys. error.type and error.message stay on the semconv keys.
* fix(guardrails): walk Responses-API text taxonomy in shared content helpers
Every guardrail sharing litellm/proxy/guardrails/_content_utils.py silently
drops all text on the /v1/responses path. AIM turns it into a loud 422 (
{"error":"No messages in the request"}); every other guardrail (Lakera v2,
Cato, Lasso, Repello, IBM, Azure Content Safety, enterprise secret
detection) scans an empty payload and lets the request through unscanned.
Three defects, all in _content_utils.py:
1. _iter_text_parts_in_content recognised only part.type == "text", but the
Responses API uses input_text (request) and output_text (assistant).
2. _coerce_input_to_messages gated on "every item has a role key"; any
Responses input list containing a function_call or function_call_output
item failed the check and was wrapped as one opaque blob.
3. build_inspection_messages forwarded any role through, including a bare
tool role missing tool_call_id, which validators like AIM's /fw/v1/analyze
reject with a schema error.
Fix walks the actual Responses item taxonomy (message, function_call,
function_call_output, bare content parts and strings), recognises
{text, input_text, output_text} everywhere, and coerces any role outside
{system, user, assistant} to user in the outbound inspection payload.
* style: ruff-format changed guardrail files
* test(guardrails): cover function_call_output string form; drop em-dash in new docstring
* fix(guardrails): map function_call_output straight to user role
Avoids ever materialising a schema-invalid bare tool message. The
downstream role-safety coercion in build_inspection_messages still
guards genuinely caller-supplied non-standard roles (developer,
function, custom values); add a regression test covering that path
so the coercion has real coverage after this simplification.
* test(guardrails): pin chat-completions tool-role coercion in build_inspection_messages
* docs(test): soften AIM-specific claims in LIT-4294 test docstrings
Ryan's review flagged that several test docstrings assert AIM's
/fw/v1/analyze validates + rejects specific schema violations. That
behavior is customer-reported in the LIT-4294 writeup, not directly
verified by us. Rephrase to attribute the AIM 422 to the customer's
writeup and describe the underlying constraint as the OpenAI chat
schema; any downstream API that validates against that schema rejects
the same shape.
* refactor(guardrails): move unsupported-role coercion into AIM only
The generic coercion in build_inspection_messages collapsed any role
outside {system, user, assistant} to user for every caller of the
helper. Combined with the pre-existing apply_redacted_messages_back
write-back behavior in Lakera/AIM/Cato, that turned a loud OpenAI 400
on chat-completions tool-message masking into a silent semantic
corruption of the outbound request (role tool with tool_call_id got
rewritten to bare role user, dropping the assistant + tool_calls
sibling).
AIM specifically requires the coercion because its /fw/v1/analyze
validates the payload against the OpenAI chat schema; other guardrails
either do not validate roles or do their own reconstruction. Move the
coercion to AimGuardrail._build_aim_inspection_messages so the shared
helper keeps caller roles intact and no new cross-guardrail role
corruption is introduced. The pre-existing apply_redacted_messages_back
structural flatten remains as separate follow-up work.
function_call_output items still synthesise role user in the shared
helper because they have no natural role field, which is a different
concern from coercing a caller-supplied role.
* refactor(guardrails): preserve role fidelity in shared _content_utils
Shared inspection helpers should extract text and preserve semantic
role signals; role coercion for third-party schema safety stays inside
the guardrail that needs it (AIM).
Three shared-helper changes:
- Bare content-part dicts (input_text/output_text) with an explicit role
keep it; only role-less parts default to user.
- Responses message items already had their role preserved; the
behavior is now covered by an explicit test.
- function_call_output items default to role tool (semantic equivalent
of the chat-completions tool message shape) instead of role user, so
Responses and chat completions produce symmetric inspection payloads.
A caller-supplied role on the item is still preserved.
AIM's schema-safe coercion in _build_aim_inspection_messages already
handles the resulting role tool: it collapses to user before the POST
to /fw/v1/analyze so AIM's OpenAI-schema validator does not reject the
bare tool message (no tool_call_id can survive the flatten). Added a
regression test in test_aim.py covering that path.
The in-workflow regex list was hard to maintain and, because it runs on pull_request, could be modified by the same PR it inspects. Path gating for the OSS daily branches now lives in repository branch protection settings, so this workflow keeps only the OSS-safe checks: the hardcoded-secret test and ruff
Bedrock Converse supports cachePoint ttl (1h GA for Claude 4.5+), and
_get_cache_point_block maps cache_control.ttl -> cachePoint.ttl, but the
model parameter its allow-list gate requires was only threaded through
the system-message path. Every message-level path either called
_get_cache_point_block without model= (8 call sites in
_bedrock_converse_messages_pt / _pt_async) or hardcoded
CachePointBlock(type="default") (tool-result blocks and
_convert_to_bedrock_tool_call_invoke), so a requested 1h ttl silently
degraded to the 5-minute default - exactly on the conversation-tail
breakpoint that long-running agents need to survive tool calls longer
than 5 minutes.
- pass model= at the 8 _get_cache_point_block call sites
- tool-result blocks: capture the cache_control dict (was a boolean)
and route through _get_cache_point_block so ttl survives
- _convert_to_bedrock_tool_call_invoke: accept optional model and route
per-tool-call cache_control through _get_cache_point_block
Completes the ttl support added for system messages (#19848, #20326):
message-level cache_control now behaves identically.
Note: message-level cache_control on a content-less assistant message
emits no cachePoint at all today; that pre-existing gap is orthogonal
to ttl and left out of scope (per-tool-call placement covers it).
Co-authored-by: Arash <arashne@glia-ai.com>
* refactor(ui): point invitation links at the dedicated /onboarding route
Invitation and reset-password links were built as /ui?invitation_id=..., which lands on the dashboard index and renders the onboarding form inline. They now point at the standalone /ui/onboarding route, so the index no longer has to special-case invitations. Old links keep working unchanged; the index still renders onboarding inline for ?invitation_id until the migration closeout removes that branch.
Updates the three generators (the enterprise email builder, bulk user create, and the invitation/reset-password modal) and extracts the modal's URL building into a pure, unit-tested buildOnboardingUrl
Refs LIT-3687
* refactor(ui): guard buildOnboardingUrl against a missing invitation id
Return "" instead of emitting an invitation_id=undefined link when the id is not yet available, matching the existing empty-baseUrl guard. Placed after the SSO branch so the SSO link, which does not use the id, is unaffected
Refs LIT-3687
* fix(rerank): log optional_rerank_params at debug not info to avoid leaking request content
* test(rerank): exercise sync rerank path so coverage counts the log line
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(vertex): forward realtime health check params
* refactor(vertex): resolve realtime health check params via VertexBase helpers
Address review feedback on the vertex param forwarding: pass model_params
through to _realtime_health_check and resolve vertex credentials, project,
and location inside the vertex_ai branch using the existing
VertexBase.safe_get_vertex_ai_* helpers, so provider-specific key extraction
no longer lives in litellm_core_utils and dict-typed vertex_credentials are
supported
* test(vertex): move realtime health check test to mapped unit test path
codecov/patch reported the vertex branch of _realtime_health_check as
uncovered because tests/litellm_utils_tests is not part of the unit test
groups that upload coverage. Move the test into
tests/test_litellm/litellm_core_utils/test_health_check_helpers.py, which
the core-utils group runs, keeping the same end-to-end assertions through
litellm.ahealth_check
---------
Co-authored-by: Aleksandr Liadov <72351793+AleksandrLiadov@users.noreply.github.com>
The connect gate resolved x-mcp-{alias}-authorization by matching the raw
lowercased alias/server_name/name only, but dashboard clients send
x-mcp-{sanitize_mcp_alias_for_header(alias)}-authorization, and egress resolves
those through lookup_mcp_server_auth_in_headers, which also tries the sanitized
alias. So a per-server token bound with a sanitized alias (e.g. alias 'pt-server'
arriving as header key 'pt_server') was forwarded at egress but still triggered a
preemptive 401 at connect. _client_has_per_server_auth_header now resolves through
the same lookup_mcp_server_auth_in_headers egress uses, so connect and egress
agree on which header names match.
The listing fan-out withholds the request-wide Authorization from a
true_passthrough / oauth_delegate server when another server in scope also
consumes it, so one bearer is not replayed across upstreams. The later
server.extra_headers copy loop did not honor that decision: a server listing
Authorization in extra_headers would re-copy the withheld bearer from
raw_headers. The withhold decision is now computed once and applied to both
the forwarding branch and the extra_headers loop.
The preemptive 401 for true_passthrough and oauth_delegate only inspected the
request-wide Authorization, so a caller who bound the upstream token via the
per-server x-mcp-{alias}-authorization header (the required shape in a
multi-server aggregate, where the request-wide Authorization is withheld) was
spuriously 401'd at initialize even though egress already honors that header.
The gate now recognizes the per-server header for both modes via a shared
helper, mode-correctly: true_passthrough treats any Authorization or the
per-server header as the upstream token, oauth_delegate keeps requiring a
distinct x-litellm-api-key so a lone Authorization consumed for admission is
never mistaken for an upstream token. The preemptive raise is also gated to
single-server scopes so a multi-server aggregate degrades gracefully instead
of one missing token 401-ing the whole connect.
For the client-forwarded token modes the gateway relays the caller's
Authorization to the upstream, so a request carrying more than one
Authorization header would make which token is forwarded ambiguous (the
ASGI header list collapses to last-wins) and could diverge from what
admission inspected. Multiple Authorization headers is malformed for
bearer auth anyway (RFC 9110: not a comma-combinable field), so the
ingress header converter now fails closed with a 400 instead of silently
keeping one. Applies to every MCP request, not just passthrough.
* feat(ui): add shared table_cells kit and convert logs columns
DateCell, MoneyCell, IdCell and StatusBadge consolidate the duplicated
per-table cell implementations behind one component each. The logs page
columns are the reference conversion; the dead auditLogColumns export
(superseded by audit_logs.tsx) is removed with it
* refactor(ui): consolidate table cells onto the shared table_cells kit
106 cell sites across 44 table files converge onto DateCell, MoneyCell,
IdCell and StatusBadge, replacing 8 date formats, 6 spend formats, 7 id
truncation strategies and 6 status badge styles with one implementation
each. Badge now forwards refs so Base UI tooltip triggers composed over
it can attach (they previously never opened under React 18). TimeCell
is deleted; its two consumers now render DateCell
* fix(ui): suppress cost tooltip for zero spend and drop dead getStatusBadge param
The logs Cost tooltip showed the raw $0 over a "-" cell for zero or
null spend (pre-existing, surfaced by review); the tooltip now only
renders when there is a real amount. healthCheckColumns no longer takes
the unused getStatusBadge callback and its dead definition is removed
* fix(ui): restyle StatusBadge as tinted pill matching the prior antd Tag look
* fix(ui): keep StatusBadge fully rounded like the other kit pills
Staging recently added the local eslint rules no-large-inline-object-arg and
no-long-condition-chain and tightened no-nested-ternary to an error. After
merging staging, the license-banner code tripped them: the banner's tiered
description was a nested ternary (now an error), and two option objects were
passed inline (adding budget debt). Extract the description into an
early-return helper, and hoist the useQuery options and the date-format options
into named constants. No behavior change; keeps the inline-object-arg count at
the committed baseline rather than bumping it
* fix(guardrails): forward grayswan scan id header
* test(guardrails): cover grayswan scan id forwarding
* fix(guardrails): prevent overwriting existing metadata headers when extracting scan id
* test(guardrails): cover header merging logic
* chore(guardrails): fix formatting
* test(guardrails): enforce case preservation
* chore(guardrails): corrected grayswan type annotations
* fix(guardrails): sanitized grayswan header metadata
* test(guardrails): covered grayswan logging headers
* fix(guardrails): guard grayswan header lookup against None and drop dead comment
- Fall back to {} when proxy_server_request is explicitly None so
request_data.get(...).get('headers') never raises AttributeError.
- Remove the commented-out user_api_key_auth pop; it was inert and
greptile called it out as ambiguous.
---------
Co-authored-by: Theodore Drzewinski <93957989+tediferJones@users.noreply.github.com>
The layout test renders DashboardShell without a QueryClientProvider and mocks
DebugWarningBanner to null for exactly that reason. The new LicenseExpiryBanner
also uses a React Query hook, so it needs the same treatment; without it the
test threw "No QueryClient set". Runtime is unaffected: the app mounts a
QueryClientProvider above the layout (DebugWarningBanner already relies on it)
* feat(ui): add eslint rules for nested ternaries, large inline object args, and long condition chains
Adds three dashboard lint rules to keep new code readable. Nested ternaries
are banned outright via the built-in no-nested-ternary, with the 265 existing
occurrences grandfathered in eslint-suppressions.json so only new ones fail.
Two custom rules ship as a small local plugin under scripts/eslint-rules:
no-large-inline-object-arg flags object literals with 4+ properties passed
straight into a call, nudging toward a named variable, and no-long-condition-chain
flags boolean expressions that combine 4+ conditions, nudging toward a named
boolean. Both are warnings tracked on the existing budget ratchet
(eslint-budgets.json + eslint-metrics.json) with headroom above the current
counts, so they ratchet down over time rather than freezing a baseline. Both
thresholds are configurable rule options and covered by RuleTester unit tests.
* fix(ui): scope no-long-condition-chain to boolean operators, not nullish
Greptile flagged that the rule counted nullish-coalescing chains the same as
&&/|| chains, so a 4-part `a ?? b ?? c ?? d` fallback surfaced "Boolean
expression combines 4 conditions", which is inaccurate since a `??` fallback
is value defaulting, not a condition. Restrict the visitor to && / || nodes so
`??` chains are treated as leaves, while a boolean chain nested inside a `??`
is still caught. Drops 6 miscounted occurrences (240 -> 234).
* chore(ui): sync lint metrics and suppressions with staging
Merge advanced the base branch, adding one no-large-inline-object-arg
occurrence (508 -> 509) and making one grandfathered react-hooks suppression
stale. Regenerate eslint-metrics.json and prune the suppression so the
budget/drift gate passes.
* chore(ui): sync lint metrics with staging
Merge advanced the base, adding four no-large-inline-object-arg occurrences
(509 -> 513). Regenerate eslint-metrics.json so the drift gate passes.
UsageIndicator was fetching /health/license through its own useEffect while
the new expiry banner fetches the same endpoint via useLicenseInfo, so an admin
with the usage widget open made two identical calls per page load. Point
UsageIndicator at useLicenseInfo too; both callers now share one React Query
cache entry, collapsing it back to a single request. The null/error semantics
are preserved (data ?? null matches the previous catch-to-null), and license
errors never fed the widget's error state before either
* test(ui): characterize DataTable behavior before shadcn reskin
Pins the shared view_logs DataTable contract with library-agnostic
queries ahead of the tremor-to-shadcn table migration: loading and
empty states, TanStack column defs with custom cell renderers,
onRowClick payload, both expansion render paths (colspan sub-component
and sibling child rows), the getRowCanExpand gate, and client-side
sorting on and off. These must pass unchanged after the reskin.
* refactor(ui): reskin shared DataTable from tremor onto shadcn table primitives
Swaps the view_logs DataTable's presentational layer from @tremor/react
to the in-repo components/ui/table primitives and hardens the seam that
every later table migration copies:
- getRowId is injected instead of hardcoded to request_id through an
any cast; identity defaults to the row index and the logs page now
passes request_id explicitly, keeping expansion state attached to the
right row across refetch reorders
- one expansion render path: renderChildRows had zero consumers and is
removed; renderSubComponent (colspan cell) is the single path
- the four consumers passing dead no-op renderSubComponent and
getRowCanExpand boilerplate drop it
- loading and empty defaults become generic (Loading... / No results)
instead of log-specific
The characterization tests from the previous commit pass unchanged
except the dead child-rows path test, replaced by a reorder-stability
test for injected getRowId plus coverage of the new generic defaults.
First tremor removal of the tables track; view_logs/table.tsx no longer
imports @tremor/react.
* test(ui): assert child rows hidden before expansion in DataTable test
* fix(ui): suppress row hover on DataTable placeholder rows
* feat(ui): polish DataTable with skeleton loading, header band, and numeric column alignment
* feat(ui): shape DataTable skeletons per column and keep stale rows during refetch
* revert(ui): drop DataTable skeleton loading, restore text loading row
* fix(ui): clip DataTable to its rounded wrapper and right-align Duration/TTFT values
The v2 emitter has never stamped error.message / error.code /
error.stack_trace / error.llm_provider as span attributes; only error.type
reached the wire. Backends that flatten span attributes into label
indexes (Elastic APM labels.error_*, Datadog span tags) lost these
four fields when v2 became the active integration on v1.90+ for
otel_v2-flagged deployments. The pre-existing exception span event
carrying the full message (LIT-3758) is unchanged; the message now
rides both places at once, matching v1s shape.
SpanError grows three optional detail fields; _parse_error threads
them from StandardLoggingPayloadErrorInformation; the emitters error
branch stamps them via a new module-level helper, guarded per field so
guardrail-shape errors are not polluted with empty attributes. New
semconv constants mirror open_inference.ErrorAttributes byte-for-byte,
so v1 and v2 consumers read the same keys.
Regression tests extend the mapped test files under
tests/test_litellm/integrations/otel/. pytest reports 243 passed.
