* feat(ui): add a call that posts an OTLP export to the proxy
* feat(ui): build a sample agent run as an OTLP export
* feat(ui): add a pulsing dot for active tracing
* feat(ui): render a crisp sample run preview from real trace components
* chore(ui): remove the pixelated agent traces preview image
* feat(ui): add test trace, tracing key, otel endpoints and more frameworks to tracing setup
* test(ui): cover tracing setup test trace, key masking, endpoints and frameworks
* feat(ui): open the received test trace and mark tracing as active
* test(ui): mock the new tracing setup network calls
* fix(ui): let tracing setup use the full page width
* fix(ui): send OTLP/JSON sample trace ids as hex per the spec
* test(ui): cover the sample trace export shape and hex ids
The usage card hid actual and baseline spend unless every older session
could be rebuilt from SpendLogs within two seconds, which on a real
gateway it never was. Each complexity router's actual spend is now its
rollup spend and its baseline is spend plus recorded savings, for old
and new requests alike, so the benchmarks and session endpoints never
scan SpendLogs. Adaptive and quality routers record no savings baseline
and stay out of the compared totals; savings_estimated_classifier_cost
is kept and covers the same compared requests
* feat(tool-policies): show the user who owns the key that discovered a tool
GET /v1/tool/list and GET /v1/tool/{tool_name} resolve the discovering key's owner from the verification token and user tables at response time and return it as a nullable user field. The Tool Policies page adds a User column that shows alias, then email, then ID, with the same cell the Virtual Keys page uses. Keys without an owner, deleted owners, and rows without a key hash show no user, and a database failure in the owner lookup keeps the tools listed with user null
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(tool-policies): bound the owner lookup with chunked membership queries
The key-by-token and user-by-id lookups behind the tool rows' user field
put every distinct key hash into one IN list. BaseRepository gains
find_many_in, which runs the repository's chunked membership query and
converts the rows like find_many does, and the owner lookup uses it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(tool-policies): cover the owner column across the tool routes and the dashboard
Integration cells for the direct, detail and filtered tool routes, owners without alias or email, deleted owners and keys, keyless and unknown-key historical rows, more keys than one membership chunk, repeated reads, two-worker reads during discovery and a failed owner lookup. A Playwright cell drives the bundled Tool Policies page against the live proxy and follows the owner link
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(ui): bucket model leaderboard usage by day or week
* test(ui): cover daily buckets in model leaderboard series
* feat(ui): add daily/weekly toggle and per-bucket total to model leaderboard chart
* test(ui): cover the daily/weekly toggle on the model leaderboard
* feat(model-insights): add gateway-wide daily totals to the response type
* feat(model-insights): return per-day totals across every model, not just the top ranked ones
* test(model-insights): daily totals include models outside the top ranking
* chore(model-insights): regenerate lazy openapi snapshot for daily totals
* chore(ui): regenerate api types for model insights daily totals
* fix(ui): compute leaderboard bucket totals from gateway-wide daily totals
* fix(ui): show the gateway total, not the top-ten subtotal, in the leaderboard tooltip
* test(ui): cover gateway-wide bucket totals on the model leaderboard
* fix(model-insights): type daily totals as an immutable tuple
* fix(model-insights): build daily totals without new mutable collections
* chore(lens): remove deployment screenshots
* refactor(lens)!: rename internal engine package and API
* fix(lens): pin worker image for renamed API
* test(lens): cover fresh and populated rename migrations
* fix(lens): protect db-push upgrades and restore routing and CI
* fix(lens): resolve migration tables across schemas and include database driver
* feat(s3_v2): add s3_partition_granularity option for hourly S3 folders
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover s3 v2 partition granularity across surfaces, settings and chaos
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover previous_response_id history rebuilt from an hourly cold storage object
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(s3_v2): reuse the cold storage key only when s3_v2 owns cold storage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): cover hour rollover, postgres outage, in-flight switches, key/team vars and real S3 layout
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(liccheck): authorize libfaketime, the GPLv2 dev-only clock the s3 rollover integration test preloads
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): wait for the rejected-request cell's payloads by id, not by line count
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): declare the postgres outage cell's models in config and trip the relay on burst ids
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): drop the libfaketime hour rollover cell and its dev dependency
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): deselect the s3_v2 live e2e on the stage-mirror stack
The stage-mirror config enables no s3_v2 callback, so every test in test_s3_log_e2e.py fails its readiness check there. The file keeps running in the Buildkite e2e lane, which configures s3_v2
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): declare the sink outage burst models in config
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(s3_v2): read cold storage metadata without an empty dict default
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): wait for the proxy to reconnect before the postgres outage recovery request
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mrinal <mrinal@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yucheng <yucheng@berri.ai>
* feat(ui): redesign agent trace run view with chat-style detail pane
Tree with connector lines, typed icon tiles and provider logos, hover
cards with timing, and Input/Output sections rendered as message cards.
* fix(tracing): show text for block-list message content and split normalizers per convention
OpenAI responses-style content (reasoning + text blocks) rendered as raw
JSON in the trace view. Keep the text blocks and drop opaque reasoning.
Move each convention into litellm/tracing/normalizers with an ordered
registry so new frameworks plug in without touching OTLP decoding.
* fix(tracing): keep long message histories as valid JSON and parse function_call blocks
* feat(ui): open agent traces in a resizable side drawer with a devtool-style tree
Clicking a run opens it in a drawer over the list instead of a full page.
j/k and the header arrows switch runs, Esc closes. The tree gets dashed
connectors, per-span waterfall bars, mono tool names and real provider
logos. AI messages with reasoning/function_call blocks render as text.
* fix(trace-ui): address review: valid JSON trimming, drawer keys, reduced motion, narrow screens
* feat(tracing): serve span content in a standard LiteLLM UI format
GET /v1/traces/{trace_id}/spans/{span_id} now also returns input_ui and
output_ui, a tagged union of messages, fields or text built server side by
litellm/tracing/ui_format.py. The trace UI renders from those fields and only
falls back to client-side parsing when talking to an older proxy. The raw
input and output strings are unchanged, and so is storage
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(tracing): fall back to an elision marker when shortened messages still exceed the size limit
* fix(tracing): keep both messages when tool_calls are oversized and keep failed-tool styling
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* test(ci): add used_client_oauth_token to the GCS pub/sub spend-log golden
#43063 stamps used_client_oauth_token into spend-log metadata, so
test_async_gcs_pub_sub_v1 failed on main with an extra metadata key
* test(ui): give the auto-router threshold save wait room for the availability debounce
#42625 keeps Save disabled while a 300ms-debounced availability check runs.
This test waits for Save right after the change, so the whole debounce lands
inside waitFor's 1s default and it times out under CI load. It is the
recurring UI Unit Tests failure on main since #42625 landed
* test(e2e): expect no pricing tier on bills for streamed calls OpenAI served at default
#42870 added both the rule that a served default or standard tier bills at
base pricing and records no service_tier, and streamed tests expecting the
row to record 'default'. They have failed on every scheduled litellm-e2e run
since. The tests now map the served tier to the pricing basis the bill must
record and check input is billed at that basis's rate; the messages case
registers custom rates so the rate check has something to compare against
* test(e2e-ui): wait for the call-id search before hovering the logs row
The row the spec hovers is already on the unfiltered first page, so it was
found before the search request returned. The search response then
re-rendered the table under the mouse, and the Base UI tooltip never opened.
Reproduced with Playwright against a local proxy: hovering right after the
fill never shows the tooltip, hovering after the search response shows the
call id every time
* test(e2e): run the Together structured-output case on the hybrid Qwen with reasoning off
The case picked the cheapest Together row flagged supports_response_schema.
DeepSeek-V4-Flash-0731 hit its cost-map deprecation date on 2026-09-29, so the
pick moved to GLM-5.3-Flash, a reasoning-only model that spends the 1024-token
budget thinking and returns content=None. Qwen3.5-9B is the pinned hybrid model
the reasoning_effort=none case already exercises, and Together lists it with
structured output support
* test(integration): read the agent 365 guardrail status by its own name in spend logs
The MCP shard runs under xdist against one database, and a sibling file creates a
default_on pre_mcp_call content filter there. The owned proxy reloads DB guardrails, so
that filter's 'success' entry could land first in guardrail_information and the test
read it instead of the agent 365 verdict
* test(unit): ignore asyncio's leaked-task records in the budget limiter push-failure log check
gc.collect() inside the caplog window can collect a pending task an earlier test left
on a closed loop, and asyncio logs 'Task was destroyed but it is pending' into this
test's records. The check still counts every LiteLLM logger, and unretrieved task
exceptions on this loop still go through the asserted exception handler
* test(e2e-ui): fill the create-tag fields inside the dialog
#42949 added 'Filter by tag name' and 'Filter by description' inputs to the Tag
Management page, so page-wide getByLabel('Tag Name') and getByLabel('Description')
match two elements and Playwright's strict mode fails the create step
* test(integration): run integration proxies with the CI license
Multi-worker proxies start each uvicorn worker in a fresh process, so every
worker reads the license from its environment. Forward LITELLM_LICENSE into the
proxy and test runner environments
* ci: save GitHub Actions caches only from main and bump codecov-action to 5.5.5
Every pull request saved its own uv, maturin, Rust and Prisma caches, about
4.5 GB per PR, so the repository's 10 GB cache budget evicted main's entries
within minutes. Pull request jobs then missed every cache, downloaded all
dependencies from PyPI and hit the install step timeouts. Pull requests now
restore only, and main keeps the caches warm for them. test-linting and
check-ui-api-types run only on pull requests and keep saving
codecov-action 5.5.4 imports its signing key from the deleted codecovsecurity
keybase account, so every upload failed signature verification. 5.5.5 reads it
from codecovsecops; the key ID matches the one signing the current CLI
* test(unit): join the session-minting thread before collecting the handler
asyncio.to_thread resumes the test as soon as the worker sets its result,
while the pool thread can still hold the work item and through it the
handler. gc.collect() then cannot finalize the handler and the session stays
open. A pool that shuts down before the test continues drops that reference
* test(integration): relaunch owned proxies that lose their port, expire idle gateway connections early
owned_proxy_process released its reserved port and the proxy bound it only
after full startup, so another xdist worker or an outgoing connection could
take it first and the proxy exited with 'address already in use'. The launch
now retries on a fresh port when that happens and stops every failed attempt.
uvicorn closes idle keep-alive connections after 5 seconds and httpx expired
them at the same 5 seconds, so a request sent right at that mark could reuse a
socket the server was closing and get 'Connection reset by peer'. Gateway
clients now drop idle connections after 2 seconds
* ci(circleci): give the base SDK wheel build the same 30 minute no-output window as the Windows build
The release profile builds with fat LTO and one codegen unit, so the final
link of litellm-cache-s3 runs silently for minutes. Successful builds take
711 to 749 seconds, right at the default 10 minute no-output limit, and about
30% of recent runs were killed there
* test(integration): model the budget-reset database outage as 10 seconds instead of 5 refused connections
The proxy retries the database about every 30 seconds and each retry opens
roughly one connection, so a 5-connection outage took 3 to 4 retries to clear
and recovery landed between 60 and 90 seconds, straddling the test's 80 second
reset window. A fixed 10 second outage still refuses the immediate reconnect
and recovers on the next retry
* ci: move the unit-test uv cache split into a composite action
check_workflow_startup_safety sums every setup step's timeout, so the save and
restore variants each counted 5 minutes although only one runs. One composite
step keeps the setup ceiling at 35 minutes
* test(unit): point tiktoken at the bundled cache for every unit test
The rust_bridge tokenizer tests loaded o200k_base before any test in their
xdist worker had imported default_encoding, so tiktoken fell back to the
temp cache and tried to download under pytest-socket. Move the session
fixture from litellm_core_utils/conftest.py to the root unit conftest.
* test(integration): answer model discovery probes in the hosted_vllm wire tests
The router's periodic upstream model info refresh sends GET /v1/models to
hosted_vllm deployments, so a wire server that is live during a refresh
sees an extra request. Answer the probe with an empty model list and leave
it out of the provider-call assertions, matching the responses bridge
tests.
* feat(proxy): record in spend logs whether a request used a client-forwarded Anthropic OAuth token
Stamp metadata.used_client_oauth_token where the proxy decides to forward a
client's Anthropic OAuth token, carry it through StandardLoggingMetadata into
the spend log row, add a used_client_oauth_token filter to /spend/logs/ui, and
surface it on the Logs page as a Credential filter and drawer field. The token
itself never reaches the log
* fix(proxy): carry used_client_oauth_token onto failure spend rows for litellm_metadata routes
* fix(proxy): resolve used_client_oauth_token against the provider the call was sent to
* fix(proxy): keep the proxy's used_client_oauth_token stamp on failure rows and move the resolver under llms/anthropic
* fix(logging): read used_client_oauth_token from the proxy-stamped metadata slot
On routes that carry proxy metadata in litellm_metadata, metadata is the
caller's own body field, and merge_litellm_metadata lets it win. Resolve the
flag from litellm_metadata when the proxy stamped it there so a caller cannot
set it in the standard logging payload
* fix(spend-logs): read used_client_oauth_token from the bucket the route stamped
A guardrail on the unified path adds litellm_metadata to a chat request after
the proxy stamped metadata, so both spend row writers read the new bucket and
stored null. The success row now resolves the flag the same way the callback
payload does, and the failure row picks the bucket from the request route.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* feat(tracing): bring current ingestion prerequisite onto main
Port the prerequisite implementation from BerriAI/litellm#43915 at 5aacd57455 so Lens does not depend on the retired tracing stack.
* feat(lens): add trace analysis and standalone worker
* fix(lens): clarify review limits and finalize main integration
* fix(lens): simplify worker setup and show the next check
* fix(lens): simplify analyzer setup and resolve integration failures
* fix(lens): preserve durations and evidence from later trace reads
* fix(lens): trust server context for internal analysis exclusion
* fix(lens): pin reviewed analyzer image and verify request inclusion
* test(lens): select time units before entering custom duration
* test(lens): allow the standalone analyzer lifetime HTTP client
* test(lens): run analyzer tests in active proxy coverage shard
* feat(ui): adopt the new LiteLLM logo and monogram
Swap the bundled admin UI logos for the new brand assets: the primary
logo in blue for light mode and white for dark mode, and the monogram for
the collapsed sidebar, favicons, and the built-in guardrail cards.
/get_image gains a variant=monogram query parameter so the collapsed
sidebar can request the monogram while admin-configured UI_LOGO_PATH /
UI_LOGO_PATH_DARK logos still take precedence. The bundled light logo
moves from JPEG to a transparent PNG.
* test(ui): query collapsed sidebar logos by role to stay within the lint budget
* fix: point remaining logo consumers at the new bundled assets
The Rust gateway UI served /get_image from the removed litellm_logo.jpg,
the non-root get_image tests pinned logo.jpg, and a cookbook script read
litellm/proxy/logo.jpg. Point them at the monogram and logo.png.
* fix(mcp): serve the BYOK OAuth page logo from /get_image
The page pointed at /ui/assets/logos/litellm_logo.jpg, which the rebrand
removes from the dashboard sources, so the next UI build would drop it.
/get_image?variant=monogram is always served by the proxy and follows any
admin-configured logo.
* fix(ui): invert the LiteLLM monogram on dark guardrail cards
The blue monogram has a transparent train cut-out, so on a dark card it
read as a muddy blue block. Inverting it yields the brand's white mark,
which the logo guidelines prescribe for dark backgrounds.
* fix(gateway-ui): serve theme and variant aware logos from the dashboard export
The Rust gateway served one monogram for every /get_image request, and the
committed export lacked it, so /get_image returned 404 until the next UI
release build. Pick the full or monogram logo in light or dark from the
query, ship those assets in the dashboard's public dir and the committed
export, and drop two comments that restated asserted paths.
* feat(ui): add agent trace api calls
* feat(ui): add agent trace types
* feat(ui): add span tree row types
* feat(ui): build span tree rows, grouped per agent
* test(ui): cover span tree rows, grouping and previews
* test(ui): add research trace fixture
* test(ui): add swarm trace fixture
* test(ui): add deep agent trace fixture
* test(ui): add trace list fixture
* feat(ui): fetch agent traces with a rolling live window
* feat(ui): look up a span's request log at its own time
* test(ui): cover rolling trace window and span log lookup
* feat(ui): add status mark for spans
* feat(ui): add duration bar for span timeline
* feat(ui): add copy button
* feat(ui): render span content as messages
* feat(ui): open a span's request log in place
* feat(ui): show raw span attributes
* feat(ui): add span detail pane
* test(ui): cover span detail pane
* feat(ui): span tree with timeline and keyboard nav
* feat(ui): run view with back out of load errors
* test(ui): cover the run view and initial selection
* feat(ui): add runs table toolbar
* feat(ui): add runs table
* feat(ui): add runs timeline with drag to zoom
* test(ui): cover runs timeline bucketing and drag
* feat(ui): add time range and live controls
* feat(ui): agent traces section with timeline and range
* test(ui): cover agent traces section
* feat(ui): add agent traces page
* feat(ui): otel setup guide for agent traces
* test(ui): cover agent traces setup guide
* feat(ui): add agent traces preview image
* feat(ui): add langgraph logo
* feat(ui): add langchain logo
* feat(ui): add openai agents logo
* feat(ui): add crewai logo
* feat(ui): add pydantic ai logo
* feat(ui): add llamaindex logo
* feat(ui): add opentelemetry logo
* feat(ui): add agent traces tab to logs
* test(ui): cover agent traces tab on logs
* feat(ui): collapse sidebar on logs for a full screen view
* test(ui): cover sidebar collapse on logs
* fix(ui): render access group MCP and agent selections as wrapping chips
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(ui): cover 20 selected MCP servers rendering as separate chips
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(ui): cover MCP and agent chip selection in access group create dialog
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: ryan-crabbe-berri <ryan@berri.ai>
* fix(ui): right-align money and count columns across tables
Make numeric the one alignment token for the three shared table
wrappers (DataTable, MemberTable, SimpleTable) via NUMERIC_CELL_CLASS,
and flag every money, cost, and bare-count column that was still
left-aligned. Raw ui/table usages that render spend or budgets get the
same class on their header and cell.
* test(ui): render the organizations alignment test with providers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(ui): query alignment cells by role instead of DOM traversal
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(ui): keep MCP permissions visible after key, team and MCP server saves
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): type the object_permission include as a prisma TypedDict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): do not block key save confirmation on cache refetch
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): surface x-litellm-call-id in Logs search, table and drawer
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(ui): regenerate api types for spend logs search description
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): drop redundant comments from the call id logs helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(e2e): format logs call id helper and spec
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): keep one id per Logs row, move x-litellm-call-id to hover and drawer
The Request ID cell shows only request_id again. When the row's litellm_call_id
differs, the cell tooltip lists it as x-litellm-call-id with its own copy button,
and the drawer header labels the second line x-litellm-call-id: instead of the
call id caption. Stacking two ids in every row made the column noisy for the
common case where the viewer only needs the row they searched for.
* test(e2e): cover the Request ID tooltip hover and copy path
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: poll the clipboard after the tooltip copy and drop a jsdom aside
The e2e read navigator.clipboard right after the click, so a slow async write
could fail the check even though copy works. The unit test's fireEvent choice
(jsdom has no layout, so a real pointer move off the trigger closes the tooltip
before the click lands) is documented here instead of inline.
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
pyjwt 2.13.0 -> 2.14.0 (uv.lock only, pyproject floor unchanged), moment
2.30.1 -> 2.31.0 and the brace-expansion override 5.0.9 -> 5.0.12 in the
dashboard. oauthlib's only fixed release (4.0.0, 2026-09-28) is still inside
the 3-day uv exclude-newer cooldown, so its two findings are ignored until
2026-10-02
* fix(proxy): recover daily spend key owners
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): simplify daily spend owner recovery
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): format daily activity metadata
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): cover recovered owner metadata merge
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): bound the daily spend owner lookup with the statement timeout
* test(integration): audit the daily activity key owner fallback on every usage route
Thirty five integration cells under tests/integration/spend cover the daily
spend owner fallback on all nine daily activity routes and /usage/ai/chat:
the happy path per route, the unanimity rules (two users, blank and null
rows, an owner the user table lacks, live and deleted keys with and without
their own user, a spend log alias), a non admin reader, an invalid key, a 5 KB
key, a locked LiteLLM_DailyUserSpend, 300 keys of one team, repeated reads, a
second user landing between reads, a concurrent burst across the unified
endpoints, a killed worker, and a proxy restart
The traffic cells ignore the GET /v1/models call the proxy's five minute token
limit refresh makes to every registered OpenAI compatible deployment, since it
lands on a test's provider wire whenever the refresh instant falls inside the
test
---------
Co-authored-by: jesus <jesus@berri.ai>
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>
* feat(cost_calculator): add cost_per_second for chat per-second pricing
Keep legacy input_cost_per_second and output_cost_per_second as aliases for chat, completion, embedding and responses. When both legacy fields are set, input_cost_per_second wins
Move Bedrock commitment rows to cost_per_second so they bill once
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost_calculator): drop legacy per-second fields from chat paths
Keep Azure chat token pricing generic and update inert Voxtral rates and SageMaker examples
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost_calculator): recognize output-only per-second rates
Include output_cost_per_second when checking whether a deployment cost entry has pricing so output-only legacy aliases remain attached to the deployment during cost selection
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(pricing): cover cost_per_second and legacy per-second aliases through the proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost_calculator): drop output_cost_per_second as a chat per-second alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(cost_calculator): restore output_cost_per_second as a chat per-second fallback
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost-map): keep input_cost_per_second on bedrock commitment rows for older clients
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): send a configured gateway_name from noma_v2 to Noma
The noma_v2 guardrail accepts a gateway_name param, falling back to the
NOMA_GATEWAY_NAME env var. The value is stripped, and when it is non-empty
it goes out as a top-level gateway_name field on /litellm/guardrail. The
param works for both guardrail: noma_v2 and guardrail: noma with use_v2,
and it is appended after the existing constructor params so positional
callers keep their meaning
* chore(ui): regenerate OpenAPI snapshot and dashboard types for gateway_name
The new noma_v2 gateway_name param shows up in the proxy OpenAPI spec, so
the lazy snapshot and the generated dashboard types need regenerating
* Update litellm/proxy/guardrails/guardrail_hooks/noma/noma_v2.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat(proxy): add model leaderboard analytics
* feat: add model insights task and range constants
* feat: record task type from task tags in model usage rollup
* feat: serve 365 days of model insights by UTC date
* test: cover task tag resolution in model usage rollup
* test: update model insights range limit test to 365 days
* chore: regenerate dashboard api types for model insights
* feat: add model insights aggregation helpers
* test: cover model insights aggregation helpers
* feat: redesign model leaderboard with stacked bars, treemap and ranking
* test: update model leaderboard view test
* feat: mark model leaderboard as beta in sidebar
* chore: sync schema.prisma copies from root
* fix: only treat task: prefixed tags as model insight tasks
* feat: add metric type for model insights ranking
* fix: rank model insights by selected metric and scope detail queries to ranked deployments
* test: plain tags are not model insight tasks
* test: cover metric ranking, deployment scoping and rollup round trip
* fix: build model insights weeks and halves from the requested date range
* test: cover empty weeks and range-based change comparison
* fix: refetch by metric, show load errors and ignore stale responses
* test: cover metric refetch and error state
* feat: define model insight tasks in a JSON file
* feat: return task labels and categories from model insights
* feat: load model insight tasks from JSON
* refactor: validate rollup task tags against the JSON task list
* feat: serve the task list with model insights
* refactor: drop hardcoded task list from constants
* build: ship model insight tasks JSON in the wheel
* test: cover model insight task JSON
* refactor: take task labels and categories from the API
* test: pass task info to task tile builder
* refactor: color treemap by API-provided category
* test: include tasks in model leaderboard fixture
* fix: make daily model usage migration idempotent
* feat: bound the model insights task query size
* fix: compute task breakdown independent of the chart metric
* test: task breakdown is stable across chart metrics
* chore: regenerate lazy openapi snapshot for model insights
* chore: regenerate dashboard api types for model insights
* fix: keep previous ranking dimmed while a new metric loads
* test: cover stale metric state in model leaderboard
* refactor: drop task row cap constant
* fix: return the full task breakdown instead of a truncated one
* test: task query is not truncated
* feat: add task summary types for model insights
* feat: summarise tasks server-side on a separate model insights endpoint
* test: cover the model insights tasks endpoint
* chore: regenerate lazy openapi snapshot for model insights tasks
* chore: regenerate dashboard api types for model insights tasks
* refactor: drop client-side task aggregation
* test: remove client-side task aggregation tests
* feat: load task breakdown separately from the chart metric
* test: task breakdown is not refetched on chart metric change
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* feat(mcp): scan and pin upstream tool descriptions
Run every discovered MCP tool's description and input schema through the
pre_mcp_call guardrails before a listing reaches the client, drop the tools
a guardrail blocks, and serve the guardrail's masked text otherwise. Add
POST and DELETE /v1/mcp/server/{server_id}/pin so an admin can freeze a
server's tool names and descriptions; the gateway serves the pinned catalog
and raises a Slack alert with the diff when the upstream drifts.
* chore: sync schema.prisma copies from root
* fix(mcp): pin input schemas, scan before pinning, admin-only pin writes
* fix(mcp): apply overrides and the pin before the discovery scan, dedupe alerts before sending
The guardrail scan now runs on the text the client is about to see: description overrides are applied first, the pinned catalog next, and the scan last, so a masked pinned or override description is served masked and a pinned tool keeps serving its pinned text while the upstream's text is poisoned. The alert signature is recorded before the send and dropped only when that send fails, so a recovery during a slow send is never undone. A tool whose scan payload cannot be built is hidden alone instead of failing the listing. apply_tool_overrides shrinks to apply_display_name_overrides and the MagicMock servers in the MCP tests carry pinned_tools=None.
* fix(mcp): snapshot the pin through the REST module's unpinned catalog helper
* fix(mcp): pin the raw upstream catalog so an override never hides upstream description drift
* refactor(mcp): trim the tool catalog guard docstrings to one line
* test(mcp): cover guarded discovery boundaries and response definitions
* fix(mcp): bound discovery guardrail concurrency per catalog
* fix(mcp): scan tool catalogs in bounded parallel batches
* fix(mcp): hide pinned catalogs from restricted management views
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(ui): rename All Models tab to Deployed Models and view filter to All Proxy Models
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): use All Proxy Models label for the public model name filter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): rename ALL_MODELS_VIEW constant to ALL_PROXY_MODELS_VIEW
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): fail open by default when Agent 365 cannot evaluate and count it in Prometheus
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(tests): ruff format the Prometheus fail-open registry test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): add Agent 365 authority host override, fail-open integration test and per-guardrail YAML default
Add `authority_host` to the Agent 365 config (also read from AGENT365_AUTHORITY_HOST, then AZURE_AUTHORITY_HOST) so sovereign clouds and the integration test can point the OBO exchange at a different Entra host.
Add tests/integration/mcp/test_mcp_agent_365_guardrail.py, a real proxy test with Postgres, Redis, a scripted MCP upstream and local Entra and Agent 365 doubles covering the default fail-open, explicit fail-closed and fail-open, Defender Skipped, policy denial, persisted status and Prometheus counter.
Use PrometheusLogger.get_instance for the fail-open metric lookup instead of a hand-rolled callback scan. Clarify the config description: gateway credential failures fail open, caller token failures block.
Extract the dashboard YAML preview into teamGuardrailConfigYaml.ts so the effective per-guardrail default is unit tested and the "default" hint only shows when nothing was set explicitly.
Regenerate the lazy OpenAPI snapshot and schema.d.ts for the new field.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): default a scheme-less Agent 365 authority host to https and treat a null fallback as unset in the YAML preview
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): audit cells for the Agent 365 fail-open default across entry points, Entra faults, throttling and two workers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): prove both Agent 365 workers serve and that a killed worker is replaced
Each fresh connection reports its worker pid from /debug/memory/summary and its MCP catalog on the same
connection, so the two-worker readiness wait covers both workers by identity. The kill test now kills a
pid the proxy reported as a worker and waits for a replacement pid, instead of the first psutil child
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): drop the prometheus fail-open counter from the agent 365 guardrail
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): keep agent 365 fail closed by default and make fail_open an explicit opt-in
Restores the shared unreachable_fallback default and the sibling guardrail initializers, drops the Admin UI YAML preview that only existed for the per-guardrail default, and reworks the unit and integration tests so the default blocks with HTTP 503 while unreachable_fallback: fail_open lets availability failures through as Unscanned
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): append authority_host after the existing Agent365Guardrail parameters
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): agent 365 fails open by default and hides the production overrides from the UI form
Agent 365 sits in the runtime path of every MCP tool call, so an Entra or
Agent 365 outage now lets the call through unscanned (logged at error level,
recorded as Unscanned with guardrail_failed_to_respond) instead of blocking it.
unreachable_fallback: fail_closed stays as the opt-in strict mode. Policy
blocks, throttling, 4xx rejections and a rejected caller token still block
The shared unreachable_fallback field becomes nullable so each guardrail owns
its default; every sibling still resolves None to fail_closed and typesafe
keeps failing open
api_base, resource_app_id and agent_id have production defaults and leave the
dashboard form (ui_hidden); they stay available in config.yaml and env. The
authority_host override and its env keys are gone, the OBO exchange always
uses login.microsoftonline.com. The integration suite keeps only the cells
that need no Entra double, the evaluation paths live in unit tests with an
injected handler
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(ui): regenerate openapi snapshot and schema.d.ts for the nullable unreachable_fallback
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): fix agent 365 to the production endpoint and keep fail_closed as the default
Remove api_base, resource_app_id and agent_id from the Agent 365 config model, their AGENT365_* env fallbacks and the _is_ui_hidden helper: the evaluation URL and the Agent Tools app id are fixed production constants and the agent identity is always the caller's key alias. Revert the fail_open default; unreachable_fallback: fail_open stays an explicit opt-in. Restore the shared unreachable_fallback field, the sibling guardrail initializers and typesafe to main. Move the Entra dependent cells from the subprocess integration suite to unit tests with an injected HTTP handler.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): warn when agent 365 yaml still carries the removed override keys
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): inject the http handler into the agent 365 initializer instead of assigning it after construction
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>
* feat(otel): add SigNoz preset for OpenTelemetry v2
Adds the signoz callback (OTLP/HTTP exporter, GenAI vocabulary, key and team level dynamic ingestion endpoint and key) as an OpenTelemetry v2 preset, with the preset factory accepting the allow_missing_credentials kwarg the V2 registry always passes so construction no longer falls back silently to legacy OpenTelemetry. Ships the deterministic tests/integration/observability/test_signoz_delivery.py audit suite
Absorbs the work from https://github.com/BerriAI/litellm/pull/38206
Co-authored-by: Nagesh Bansal <nageshbansal59@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(otel): drop explanatory comments from the SigNoz preset
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(types): keep signoz dynamic param lines within ruff format width
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(signoz): assert the missing-endpoint boot path directly instead of in an except block
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(ui): regenerate schema.d.ts for the signoz health service
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): allowlist SigNoz key/team endpoints and route keyless collectors without the operator key
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel): terminate the SigNoz shutdown cell before the flush and drop test docstrings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(otel): keep the shared tenant routing untouched and require an ingestion key for SigNoz key/team endpoints
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): warn about a keyless SigNoz team endpoint from the header resolver so the shared cache actually reaches it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Nagesh Bansal <nageshbansal59@gmail.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(proxy): add maximum_daily_tag_spend_retention_period cleanup setting
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(ui): regenerate schema.d.ts for new retention setting
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(proxy): rebase daily tag spend retention onto the run-budgeted cleanup job
Reworks the cleanup on top of the refactored SpendLogCleanup: the daily tag spend table is pruned through the shared batched delete with a text cutoff on the indexed ISO date column, the setting is picked up by /config/update and the scheduler registration, and an integration test proves rows older than the period are pruned while the cutoff day and unset retention are left alone
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): schedule the cleanup job when a retention db row lands before the side effects run
A config reload applies the db row to the SettingsStore before _update_general_settings snapshots the previous retention values, so the before/after compare saw no change and a retention period first set through /config/update never scheduled the cleanup job. Also reschedule when the job is missing but a retention period is set
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): accept list-valued top-level keys in the base integration proxy config
The shared tests/integration/proxy_config.yaml now carries list-valued top-level keys, so the retention config helper validates only the mapping it merges into. Also drops a SQL-shape assertion from the unit test in favor of the behavioral cutoff-day check
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover runtime update, invalid value, independent horizons and worker loss for daily tag spend retention
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): restore the shared retention setting, capture seeded days once and kill a listening worker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): retry a failed cleanup schedule only when its settings change
_apply_retention_settings rescheduled whenever retention was set and no job existed, so an unparseable cleanup cron was retried on every config reload. Remember the last attempted retention, cron and interval tuple and retry only when it differs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): give daily tag spend retention tests a 240s timeout
Each node boots a proxy and waits for a whole-minute cleanup cron tick, so the global 90s pytest-timeout can expire during teardown on a slow runner, as integration-accounting did on pipeline 90302
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): reschedule cleanup when only the cron or interval changes at runtime
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): reschedule cleanup when the first db sync changes only the cron or interval
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(ui): add text input for String general settings so retention periods can be set from the Admin UI
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): record a cleanup schedule attempt only after it did not raise
Records _last_cleanup_schedule_attempt after _reschedule_spend_log_cleanup_job returns, so a transient add_job error is retried on the next config sync while an invalid cron, which is caught and logged inside the reschedule, is still attempted once per settings value
Also adds --num_workers 2 to the dev proxy command in AGENTS.md as requested on the PR
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs: revert unrelated AGENTS.md dev command change
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* Revert "docs: revert unrelated AGENTS.md dev command change"
This reverts commit 047706a623.
* Revert "fix(proxy): record a cleanup schedule attempt only after it did not raise"
This reverts commit 678f7c72b4.
* Revert "feat(ui): add text input for String general settings so retention periods can be set from the Admin UI"
This reverts commit 24e49d71d7.
* fix(proxy): record a cleanup schedule attempt only after it did not raise
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): validate the cleanup schedule before swapping the job and leave startup registration to the startup block
_reschedule_spend_log_cleanup_job builds the new trigger first and only touches the live job once it parsed, so an invalid cron or interval (including a non string value) keeps the previous schedule running instead of removing it. An error raised while rescheduling is logged and retried on the next sync, so it no longer stops the rest of the general settings sync. _apply_retention_settings skips the job-missing path while the scheduler is still stopped, so the startup block is the only registration before start and the cross-replica stagger it applies to pending jobs survives
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): skip cleanup rescheduling while the scheduler is stopped and retry a failed replacement
The stopped-scheduler guard only covered the missing-job path, so the first DB sync (which runs before the startup block) still registered the cleanup job whenever the DB schedule differed from yaml, and startup then replaced it. Every runtime path now defers to the startup block while the scheduler is stopped.
A raised add_job that was replacing a live job was never retried because the live job kept wants_job == has_job; the sync now remembers the failure and retries on the next sync until the schedule is applied.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): drop redundant docstring on _spend_log_cleanup_trigger
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): schedule DB-only retention at boot and log overflowing cleanup intervals once
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): drop explanatory comment from startup cleanup block
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): reject a non-string cleanup cron at startup and drop legacy covers markers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): reschedule spend log cleanup when the reload path already applied a DB cron or interval edit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): assert cleanup scheduling on a real paused scheduler instead of mock call counts
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>
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>
* feat(proxy): add fail_closed_rate_limit_enforcement to reject requests with 503 while Redis rate limit counters are unreachable
* fix(proxy): reject fail-closed rate limit checks before logging the in-memory fallback and pin the boot warning in the lifespan
* fix(proxy): coerce the fail-closed flag, fail closed on read-only checks, and refund partial cluster increments
* fix(proxy): window-guard rate limit refunds and catch the fail-closed rejection by type
* fix(proxy): read the compaction rate-limit gate's limiter from the proxy hook registry
* fix(proxy): count the pending request in read-only rate-limit checks and keep the compaction gate off the caller's parallel slot
The compaction polyfill's summary-model gate, once it ran against the real v3 limiter, showed two behaviors nobody had chosen. The read-only check compared the stored counter with the same `>` the increment path uses, but a read-only check decides a request that has not been counted yet, so a summary model exactly at its rpm limit still went out. The read-only path now adds the pending increment of 1 before comparing; the increment path is unchanged.
The gate also passed the key's max_parallel_requests gauge through, and the read-only gauge count includes the caller's own in-flight slot, so a key with max_parallel_requests: 1 never compacted. The gate now drops that gauge from its descriptors, since the summary call runs inside a request the limiter already admitted.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* feat(proxy): email alerts at configured percentages of a team member budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(alerting): label team member budget crossings as team member budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(auth): cover the team member alert dispatch from _check_team_member_budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(email): drop the emoji from the team member budget alert template
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): ignore team member alert thresholds outside 1 to 100 on both the backend and the dashboard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): bound team member alert threshold key length before int parsing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the legacy covers marker from the team member alert test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(team): reject malformed team_member_max_budget_alert_emails on team writes
Thresholds outside 1-100, non-list recipients, and invalid emails now return 422 on
/team/new, /team/update and PATCH /team/{id} instead of being stored and silently
ignored. The value is stored canonically. Read-side LiteLLM_TeamTable is unchanged,
and the PATCH body stays a raw merge patch so a null threshold still deletes it.
* fix(auth): enforce and alert on team member budgets only in common_checks
The builder re-checked the team member budget inline before common_checks ran the same
check, so one request that crossed a team_member_max_budget_alert_emails threshold
dispatched two alerts. Drop the inline check; common_checks is the single authorization
point and already covers per-member rows, the team default member budget, zero-cost
skips and the cross-pod spend counter. Its 422 message now uses the TeamMember=user:team
form the builder and budget reservation already returned.
* Revert "fix(team): reject malformed team_member_max_budget_alert_emails on team writes"
This reverts commit 703e754b46.
* fix(alerting): keep BaseBudgetAlertType.get_event_message zero-arg
Requiring user_info broke existing callers and out-of-tree subclasses. The team member
label now comes from SlackAlerting.budget_alerts, so the interface and its Readme are
unchanged from main.
* fix(mcp): keep team member budget enforcement on the MCP OAuth auth dependency
The MCP OAuth dependency stops at _user_api_key_auth_builder and never reaches common_checks, so removing the builder's inline member budget check would have let over-budget members through there. Enforce it explicitly for that caller.
* fix(auth): keep main's team member budget enforcement, alert once per request
Restore the builder's team member budget check and 422 message exactly as on main and drop the MCP-only gate. The builder sends the member alert only on the request it rejects; common_checks sends it for requests that get past the builder, so no request alerts twice.
* test(integration): read team member alert deliveries without a shared accumulator
* test(integration): match team member alert deliveries by subject so other alerts cannot race the count
* refactor(proxy): build the team member alert threshold config without mutable collections
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): collapse the alert recipient isinstance checks into one call
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): read the SMTP sink through lock-guarded snapshots and assert the exact deliveries
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(xai): add native xAI batches and files support
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(xai): tighten batch handler typing and avoid Final redeclaration on star import
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(xai): walk batch result pages iteratively
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(xai): stop paging on empty pagination token and honor litellm.xai_key
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(xai): import NotRequired and TypedDict from typing_extensions for Python 3.10
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(batches): accept image and video endpoints on batch create
* test(xai): lock batch endpoint, auth, and result contracts
The batches test package collided with litellm/batches under pytest prepend, so the All Other Providers shard could not collect the new tests.
* fix(xai): price grok batch usage at xAI's 20 percent batch discount
* fix(xai): map not-found file reads to 404, bill batch reasoning tokens, and add 200k batch tier rates
* refactor(xai): drop routine prose and move tests under tests/unit
* fix(health): hand the resolved provider to list_batches in batch-mode health checks
* test(xai): make tests/unit/llms/xai/batches a package
* fix(xai): walk every page of the files list by pagination_token
---------
Co-authored-by: Mubashir Osmani <mubashir@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
