* feat(proxy): gzip buffered responses for clients that accept it
Large JSON reads like /user/daily/activity/aggregated shipped tens of MB
uncompressed. Compress single-message bodies of 500B or more when the
client's Accept-Encoding allows gzip (q-values and the wildcard honored).
Streamed and etagged responses pass through untouched, every negotiable
response carries Vary: Accept-Encoding, and bodies of 1MB or more are
compressed in a worker thread
* fix(proxy): skip partial and no-transform responses in gzip and always release the held start
The gzip gate now also skips 206 Partial Content and Cache-Control: no-transform,
since compressing either breaks byte ranges or ignores an explicit ban on transforms.
A response start without a headers key no longer raises, and a start the app never
follows with a body message is forwarded when the app returns instead of being dropped.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* 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>
* ci(circleci): test Redis behavior against local Redis and print short tracebacks
The redis_caching_unit_tests job ran three legacy files against the shared remote Redis. The DualCache and
batch-read logic that never needed a server now lives in tests/unit/caching/test_dual_cache.py with a mocked
RedisCache, and the behavior that does need one (the increment-with-floor Lua script, read-through, deletes,
batch reads) moved to tests/integration, which starts a local Redis. test_returned_settings only read
REDIS_PORT and is replaced by a unit test of Router.get_settings
CircleCI pytest runs now use --tb=short so failure output stays readable in the test results tab
* ci(integration): print short tracebacks from run.py and allow Redis in the sdk shard
Sail now rejects completion_window "flex" on synchronous requests with a
400 saying flex is only for background responses or Batch work. The chat
flex case and the responses flex case have failed on every scheduled
litellm-e2e run in builds 337, 340 and 341. The chat cases keep balanced and
auto, and the responses case sends a caller metadata.completion_window of
balanced, so both still prove the window reaches Sail and the bill uses
that window's distinct rates
* chore(lint): remove the LIT002 mutable-construction rule
Drop LIT002 from scripts/check_type_discipline.py along with its helpers,
its budget entry, its unit tests, and the AGENTS.md and gate docstring
mentions. `# mutable-ok` now only suppresses LIT001, so the markers that
only existed to silence LIT002 became LIT013 stale suppressions and are
removed. The files whose layout depended on those trailing comments are
reformatted with ruff format.
Every other LIT rule count is unchanged and the ASTs of all touched
litellm/ files match main apart from one docstring.
* chore(lint): keep the leftover mutable-ok markers for a follow-up
Restore the ~1.4k `# mutable-ok` markers stripped in the previous commit
so this PR only touches the checker, its tests, the budget, and docs.
Those markers no longer suppress anything, so `# mutable-ok` is exempt
from LIT013 until a follow-up strips them.
* Revert "chore(lint): keep the leftover mutable-ok markers for a follow-up"
This reverts commit c35bc0b84e.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@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
The pytest-postgresql based proxy tests moved to tests/integration on the real
Postgres harness in #43996, so nothing loads the plugin anymore. uv.lock is
edited by hand to drop the package and its now orphaned mirakuru and port-for
deps; uv lock --check passes and a full relock resolves the same package set
* test(proxy): delete the legacy proxy test tree and serve the redirect test from loopback
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): exercise the shard check directly for unit_selection-owned children
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): serve the redirect test from respx instead of a socket
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): credit shard ownership only to unit flags wired in gha
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): implement the wired-flag shard crediting the tests assert
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): split the root proxy test files into their own unit shard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): point the rate-limit skip reason at the usage-based-routing-v2 RPM tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): move proxy_server, _experimental and db tests into tests/unit/proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): keep tuple identity in proxy state restore and fix misc target paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): move utils, agent_endpoints and endpoint tests into tests/unit/proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): package moved unit test directories
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): exclude proxy-db-owned files from the misc target
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): drop the redundant fixture docstrings in the proxy conftest
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* 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(proxy): move auth, hooks, policy_engine and client tests into tests/unit/proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): stub HIBP through respx by disabling the aiohttp transport
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): share the httpx transport fixture across proxy unit tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): restore proxy globals without a missing-value sentinel
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): package moved dirs and stub the login breach check at the HTTP boundary
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): isolate the mcp server manager per test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): move management_endpoints, management_helpers and guardrails tests into tests/unit/proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): reuse the shared httpx transport fixture in moved proxy tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): stub outbound HTTP and package moved test dirs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): restore the config server hostname in the mcp resolution test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): pin the completion tokenizer model in the straiker screening test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.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.
* test(proxy): move auth, hooks, policy_engine and client tests into tests/unit/proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): stub HIBP through respx by disabling the aiohttp transport
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): share the httpx transport fixture across proxy unit tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): restore proxy globals without a missing-value sentinel
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): package moved dirs and stub the login breach check at the HTTP boundary
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): isolate the mcp server manager per test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): migrate DB and Redis backed proxy tests into tests/integration
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): drop a type suppression comment from the key metadata integration test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): scope integration test cleanup to owned rows and wait for backend stats flush
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): seed NULL cache_hit and bound recovery reads from below
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): group /v1/messages contracts under tests/integration/messages
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): make ci coverage census collect nested test dirs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): nest /v1/messages contracts under messages_endpoint/providers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): replay a real Claude Code /v1/messages request through the native wire
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drop legacy covers marker from claude code wire test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): inline the Claude Code request instead of a json fixture
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drop the legacy covers marker from the new contract
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): add Claude Code /v1/messages customer-journey matrix (native + responses bridge) (#43386)
* test(anthropic): add Claude Code /v1/messages customer-journey matrix (native + responses bridge)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): strengthen bot-flagged assertions in the Claude Code matrix
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): type the usage mapping parameter in the shared builders
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>
* test(anthropic): drop low-priority Claude Code error and count_tokens tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): send the full 24-tool Claude Code request and pin upstream headers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drop responses bridge Claude Code tests to keep this PR Anthropic direct only
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): fix duplicate WebSearch tool, drop mutation in stream builders, ignore pings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): assert upstream request order in multi-turn Claude Code tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): name Claude Code wire tests by behavior and move provider-agnostic ones to routing and streaming
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): sort imports after moving the Claude Code fixture into _support
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): group anthropic messages tests into feature subfolders
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the pre-move anthropic test paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): cover native reasoning translation, response and pricing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): narrow PR to new reasoning tests, restore moved files and drop non-reasoning tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): scope reasoning tests to reasoning and cover betas, thinking usage and streamed pricing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): write reasoning cases as literal sent and received fields
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): require stopped stream blocks and check upstream model on switch
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>
* test(proxy): inject the HIBP client into the breached-password update test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(mcp): drive optional-discovery deadlines with an injected loop clock
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: bound MCP deadline checks, support Python 3.10, pin HIBP URL
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(guardrails): scan Responses API input in Azure Text Moderation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): log Azure Text Moderation prompts at debug and cover streamed Responses blocking
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): scan Responses API input in Azure Prompt Shield and Text Moderation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): tolerate unmodeled Responses input items in Azure prompt extraction
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): pick Azure prompt source by call type so a messages stub cannot hide Responses input
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): tighten Azure Content Safety endpoint test types
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): suppress Azure cast lint violations with cast-ok reasons
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): audit Azure content safety across endpoints
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): isolate worker-kill audit rig and cover during_call on chat
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(guardrails): shorten Azure cast-ok reasons to fit the line limit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): inline spend row count in the concurrency audit cell
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): assert caller-observed outcomes in Azure call type unit tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): reuse the existing text moderation response helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): assert no duplicate rows instead of exact row count after worker kill
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): poll worker-kill spend rows to settle before the duplicate check
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): keep Azure Text Moderation on messages only so this PR stays Prompt Shield scoped
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: shivam <shivam@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yucheng <yucheng@berri.ai>
* fix(proxy): restore pre-config-wins handling of pass-through endpoints
Config-wins (#41779) made general_settings.pass_through_endpoints a config-owned key. The DB reader then got the config list back as if it were DB rows, re-registered each entry without forward_headers on every DB sync, and the stripped copy won the route lookup, so a config pass-through with forward_headers: true stopped forwarding Authorization. UI create, update and delete of pass-throughs were also rejected while the config declared any.
This puts pass-throughs back on their pre-#41779 path: the settings store no longer lets the config own the key, the config list is captured env-resolved at load_config, each DB sync merges DB entries with config entries on paths the DB does not declare, and /config/field/info reads the stored rows only. A UI pass-through write re-applies that merge immediately so the config entries stay served until the next sync.
* fix(proxy): keep config pass-throughs in every reload of the merged list
get_config now returns DB pass-throughs plus config ones on other paths,
each DB sync republishes that merged list, and /config/field/info reads
pass_through_endpoints from the DB row so a UI write never drops stored
entries when models are not stored in the DB
* fix(proxy): keep serving pass-throughs while the config file reloads
load_yaml cleared the runtime pass-through list, so auth: false routes
answered 401 while get_config awaited the database
* fix(proxy): read stored pass-throughs from the writer before a UI write
A lagging read replica could return an older list, and the UI create and
edit flows write the whole field back
* fix(proxy): apply config file pass-through auth changes on reload
The kept runtime list was merged as if it were DB entries, so an edited
config entry on the same path was dropped. Merge the stored DB row with
the fresh config instead, and give the field-info test mock a writer
* fix(proxy): keep pass-throughs served while a DB sync reads the database
get_config resets the stored DB rows before reading them again, which
cleared the served pass-through list and made auth: false routes answer
401 for the length of the read
* refactor(proxy): move the settings store reload out of the loop
basedpyright rejects a Final variable assigned inside a loop
* feat(guardrails): honor litellm_params.timeout in every HTTP guardrail
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): accept timeout kwarg in presidio and responses-handler post stubs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): bound hiddenlayer startup jwt call by configured timeout, drop akto from timeout coverage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): narrow hiddenlayer startup auth timeout without cast
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): bound hiddenlayer jwt refresh by configured timeout
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): keep provider timeout defaults when unset and bound only rubrik moderation calls
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): cover model_armor and run timeout probes concurrently
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): match sink calls to the exact guardrail name
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(e2e): give e2e tests typed metadata for what they drive
@meta(Subject(domain, route, providers, models, capabilities, mode)) declares
what a test is about with closed enums, and each field lands in the JUnit report
as a property. The quota_management suites are the first to declare it.
* docs(e2e): say e2e_metadata avoids litellm, not that it is stdlib-only
It already imports pydantic and pytest, both of which the suite needs to collect. The rule that matters is no litellm import
* test(e2e): declare models through the constant each test drives
43 @meta declarations in quota_management typed the model name out again, so changing the call would leave the coverage report naming the old model. Each file now has one constant used by both, and a guard fails on any model written as a string literal in @meta
* refactor(e2e): set route only when the endpoint is what the test checks
A budget or rate-limit test whose chat call only triggers the block now leaves route unset, since its steps already name the call. Tests of an endpoint keep it: budget CRUD, key creation, spend reporting reads, and the per-endpoint spend tests for chat, messages, embeddings, batches and health. The two /spend/logs tests tagged chat_completions are now spend_reporting
* refactor(e2e): build the declared properties without mutating a list
subject_properties seeded a list and grew it with append and extend. It now flattens one tuple per field, and the plural-name table is a read-only mapping
* fix(e2e): tag each spend-route probe with the endpoint it checks
The breadth test gave all 33 probes spend_reporting, so /key/list, /user/list, /team/list, /organization/list and /customer/list counted as spend reporting. Each case now carries its own route, with organization and customer management added to Route
* fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch
The post-call Redis batch only goes out after every success callback finishes or the 1s deadline, so an
identical request sent right after the first response missed the cache and went to the provider again.
Response-cache writes go straight to Redis again, the counters, rate limits, TPM and slot releases keep
riding the post-call batch
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): re-export DualCache explicitly instead of through a noqa
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): keep the DualCache re-export as a reasoned noqa for the strict ruff gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(e2e): record each e2e test's steps, starting with ProxyClient
@step on a harness method records a plain-English line for every call, in
order, as repeated JUnit step properties. Labels are templates filled from the
call's parameters, like "Generate a virtual key with models: claude-haiku-4-5
and rpm limit: 3", and secret request fields are marked Field(repr=False) so
they never print. ProxyClient and the rate-limit QuotaClient carry steps first;
the other harnesses follow one area at a time. The recorder and JUnit tests run
in the Code Quality workflow's test_e2e_metadata step.
* docs(e2e): rewrite the recorded test steps guide in plain language
* fix(e2e): keep logging callback credentials out of recorded steps
* fix(e2e): mask the run's credentials in every recorded step
* fix(e2e): attach steps before the oauth failure snapshot
The failed setup or call report of an mcp_oauth_live test copied user_properties before the steps were attached, so it carried no steps. Every setup and call report now takes its properties after the steps attach
* fix(e2e): name the saved credential in its recorded step
The create_credential label read credential_info, which defaults to {} and is never set by the live callers, so the step printed nothing after 'for'. It now reads the required credential_name, and a guard fails on any label that reads a field with a default
* test(ci): repair stale request fakes, spend-log golden, auto-router labels, and Interactions spec lookups
Request fakes now carry the scope a real Starlette request has, the GCS pub/sub
spend-log golden gains the agent identity keys from #43722, the auto-router
session tests follow the baseline_models contract from #43348, and the
Interactions spec checks resolve the create body and resource paths from the
live spec instead of hardcoded names
* test(ci): move retired OpenAI text-completion fixtures to live vehicles
OpenAI still serves native /v1/completions on the gpt-5.4 family, so the
single-prompt cases move to text-completion-openai/gpt-5.4-nano. Multi-prompt
batches and echo with logprobs now 500 on every OpenAI model, so those cases
keep the same text-completion-openai transport pointed at Fireworks, which
documents both. The optional-params test asserts the request body actually
sent instead of a success callback whose assertions were swallowed
* test(ci): use a serverless Fireworks model for the text-completion batch and echo cases
gpt-oss-20b is on-demand only on Fireworks, so the CI key got 404 model not
deployed; glm-5p3-flash is listed as serverless
* test(ci): skip the ROI calculator repository listing in the security route sweep
GET /roi-calculator/repositories (#43669) lists repositories from the configured
GitHub API, api.github.com by default, so the S2 sweep's GET of every route made
the owned proxy reach an external host and failed the egress check in 31
integration-security tests. It joins /get/latest_release_info in the deny list
* 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>
* fix(azure_storage): keep the DataLakeServiceClient alive until its TTL elapses
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci: rerun integrations shard after unrelated gitlab prompt manager timeout
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): audit azure_storage client reuse against a local Data Lake sink
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(azure_storage): cover the exact TTL expiry boundary
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(azure_storage): wait for a rejected write before flipping the sink back
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): add azure_storage log delivery cells behind an opt-in lane
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(azure_storage): restart the proxy mid burst and bound the loss to the unflushed queue
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(azure_storage): drop the redundant stop after the owned proxy exits
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): read azure_storage objects at the auth-mode-dependent layout
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): install the datalake sdk in the e2e lint environment
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(azure_storage): drop the opt-in real Azure e2e cells and their e2e-dev dependency
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>
* fix(guardrails): treat an unknown straiker api_version as unset instead of skipping the guardrail
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): patch the shared proxy logger directly in the straiker api_version test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): keep the straiker stray-version block marker separate from the shared block marker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): drop redundant comments on the straiker api_version integration tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(grayswan): send request conversation and tool calls to post-call monitor
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(grayswan): tighten post-call context typing and wire test helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(grayswan): resolve post-call surface from request route before call_type
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(grayswan): omit tools from post-call monitor when request context is empty
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(grayswan): apply ruff format to post-call context changes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(grayswan): merge response text and tool calls into one assistant monitor message
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(grayswan): only merge tool calls into the response text for single-choice responses
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): audit post-call context across endpoints, modes and outages
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): share the upstream model probe reply across audit responders
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): assert the full generic guardrail body and kill a real serving worker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): normalize the client user agent in the generic body assert
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): normalize accept-encoding in generic body assertion
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): keep volatile header placeholders only when the header is present
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): capture monitor calls immutably in the unit test client
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(grayswan): type the test helper parameters
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>
TestPriceDataReloadAPI, TestPriceDataReloadIntegration and TestInvitationEndpoints set
app.dependency_overrides[user_api_key_auth] and never removed it. Under xdist the shared
proxy app kept the override, disabling auth for later tests on the same worker and failing
test_harness_smoke.py::test_auth_as_cleans_up_on_exit. Set it through monkeypatch.setitem
so it is undone at teardown
A per-test leak check over every tests/test_litellm/proxy file that touches
dependency_overrides found these 20 tests as the only leakers; it reports none after this change
Map dangerous-tool-use-2026-09-03 for azure_ai in the beta header config so the
Claude Code auto mode beta reaches Foundry instead of being stripped, matching
the anthropic, bedrock, and vertex_ai entries
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(router): inherit catalog service-tier rates for custom-priced deployments
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost): apply tier-suffixed long-context rates when only tier thresholds are set
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(router): cover canonical cost-map backend model resolution
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(router): use descriptive names for service-tier pricing fixtures
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(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
* test(bedrock): restore the AWS env after a failed live call in the auth tests
* test(bedrock): assert the regression test's failing call actually ran
* test(bedrock): drop the test that tests the auth tests
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* refactor(proxy): route every team-admin decision through auth/team_access.py
Move the six team-admin helpers out of common_utils, team_endpoints and
key_management_endpoints into litellm/proxy/auth/team_access.py under public
names, and point every management route and helper at them. The key routes
keep checking team admin before org admin, so a team admin whose user row is
gone still passes as before. Status codes and bodies are unchanged, which the
223-case team-admin matrix confirms at the merge base and at the tip
common_utils keeps `_is_user_team_admin` as an alias because the published
litellm-enterprise 0.1.71 wheel still imports it from there
* refactor(proxy): answer every team access check with TeamAccess.allows
Replace the six helpers in auth/team_access.py with one resolver in
litellm/proxy/management/teams/access.py. Each route passes the roles it
accepts (TEAM_OR_ORG_ADMIN or TEAM_ADMIN_ONLY), and /team/update and
/team/info rank roles through strongest_role so org admin still outranks
team admin there
The org lookup moves behind an OrgRoles protocol, implemented by
PrismaOrgRoles in management/users/service.py, and get_team_access in
management/teams/dependencies.py is the only place that reads proxy_server
globals. _check_key_admin_access keeps its name and body from main
Routes that checked org admin first now read the roster first, so a team
admin whose org lookup errors now passes on /team/delete, /team/block,
/team/unblock, member reset_spend and reset_budget, and the team callback
routes. No allowed caller is denied
* fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python
pip install litellm fails on Microsoft Store Python because its user
site-packages is already 134 chars plus the profile name, and the content
filter guardrail ships YAML five directories deep under
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/. The
existing wheel guard assumed a 100-char install prefix, so it never saw it.
Move categories/ and policy_templates/ to
litellm/proxy/guardrails/content_filter_data/ and drop the benchmark
fixtures from the wheel. Old category_file paths keep resolving because
the resolver only keys on the trailing categories/<file> or
policy_templates/<file> suffix.
Derive the guard's worst-case prefix from the Store Python site-packages
path with a 15-char profile name (149), fail files at 260 and directories
at 248 (CreateDirectoryW), and fix the off-by-one that let a 260-char
path through.
Fixes#43851
* ci: run the Windows wheel install guard on pull requests
The two Windows jobs live in CircleCI, which never runs on pull requests,
so nothing installs the wheel on Windows before merge. Add a GitHub Actions
job on windows-latest that builds the wheel and runs the guard.
Two things make the run deterministic instead of image dependent. The job
turns the LongPathsEnabled registry key off first, because runner images
ship with it on and python.exe is long-path aware, so a 300-char path would
install fine. The guard installs with pip instead of uv, because uv writes
files from Rust, which switches to extended-length paths on its own and can
never hit MAX_PATH.
* fix(guardrails): keep the old content filter package dir as a category search root
Deployments that copied their own category YAML into
guardrail_hooks/litellm_content_filter/ before the data move would have had
that file rejected by the new directory jail and missing from by-name loads,
inherit_from lookups, the UI category listing and the category YAML endpoint.
Every lookup now searches the bundled data dir first and the old package dir
second, with the bundled copy winning on a name clash.
* fix(guardrails): resolve category files through safe_join
By-name category lookups and the suffix search in the category_file resolver now go through safe_join, so a name or suffix that would escape its data root never reaches the filesystem. The LITELLM_CONTENT_FILTER_ALLOW_EXTERNAL_PATHS opt-out keeps its unjailed search. Clears the two CodeQL path-injection findings on the new lookup code.
* fix(guardrails): keep symlinked category files loadable by name
By-name category lookups resolved symlinks through safe_join, so a category file symlinked into the categories folder from elsewhere stopped loading. Those lookups now only reject names that leave the folder lexically and return the link untouched, matching how by-name loads behaved before the data move. The category_file resolver keeps its realpath jail as before.
* fix(guardrails): keep the category viewer inside the category folders
GET /guardrails/ui/category_yaml/{name} hands raw file contents to any valid key, and on main it refused a symlink whose target left the categories folder. The previous commit let by-name lookups follow symlinks again, which also let the viewer read whatever a symlink in a legacy categories folder pointed at. The viewer now checks the found file's real path against every categories folder it searches and answers 400 as before, while the guardrail's own by-name loads keep following symlinks
The roots come in through a FastAPI dependency so the check is testable against a temp folder, and the content filter's realpath containment moves to path_utils.is_within so both surfaces share it. The test that patched os.path.commonpath covered a branch that no longer exists and goes with it
* ci: drop the Windows wheel install job from pull requests
The job took about 13 minutes on every PR to guard an edge case. The
guard still runs its path-length check on Linux in base_sdk_install and
on Windows in the CircleCI windows_release_wheel job.
* fix(transcription): honor base_url alias for Groq Whisper and report it as the api base
transcription() and speech() only accepted api_base, so a deployment configured with base_url leaked the alias into the provider params, which Groq rejected as an unknown param, and the request never reached the internal gateway. get_api_base() now reads the same alias so response headers and logs show the configured endpoint instead of the provider default
Resolves LIT-9071
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(speech): keep base_url after existing audio params, route Vertex speech to it, skip empty alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
