max_budget and reset_at already live on the matching budget_limits entry, so
repeating them (as budget_limit and reset_at) only invited confusion about which
copy is authoritative.
* fix(redis): coerce env var string types and fix param discovery through decorator wrappers
inspect.getfullargspec doesn't work on redis.Redis/redis.RedisCluster because
their __init__ is wrapped by @deprecated_args, which replaces the explicit
signature with *args/**kwargs internally. getfullargspec returns an empty arg
list, so _get_redis_kwargs and _get_redis_cluster_kwargs silently dropped every
real constructor parameter not in their hand-picked include_args set --
cluster_error_retry_attempts and connection_error_retry_attempts among them, so
an operator's configured retry bound never reached the Redis Cluster client and
it fell back to redis-py's own default instead.
Rebased onto litellm_internal_staging, which had independently added
_init_arg_names (MRO-walking, inspect.unwrap-based) for the same class of bug
in _get_redis_url_kwargs. Reused that pattern (as _unwrapped_init_args, without
the MRO walk: redis.Redis/RedisCluster declare every real parameter directly on
their own __init__, and MRO-walking breaks the tests here that mock the class
with autospec=True, since inspect.getmro needs a real __mro__) rather than
introducing a second, differently-shaped fix for the same problem.
_get_redis_cluster_kwargs now also honors its own client argument instead of
ignoring it, so the async cluster client's own extra constructor kwargs
(cluster_error_retry_attempts, connection_error_retry_attempts,
decode_responses, ...) are no longer filtered out by introspecting the sync
class regardless of which client is actually built.
Also fixes environment variables and Helm --set values always arriving as
strings: redis-py 8.x changed health_check_interval's arithmetic to require a
real number, so a stringified value raised TypeError on every Redis operation
instead of connecting. _coerce_redis_kwargs_types coerces to each parameter's
declared type at the end of _get_redis_client_logic, with an explicit type
table for max_connections/socket_timeout/socket_connect_timeout since redis-py
8.x changed the timeout defaults from None to int 5, which would otherwise
make a fractional value fail int() and get dropped.
Co-authored-by: mangabits <1457532+mangabits@users.noreply.github.com>
* ci: verify redis-py client version compatibility across a version matrix
* test(redis): assert an async-only cluster kwarg every matrix version declares
connection_error_retry_attempts is on the async cluster constructor in redis-py
5.x only; 6.0 removed it in favor of retry. The 6.4.0, 7.4.1 and 8.0.1 legs were
failing on that missing parameter name rather than on the behavior under test,
while the allow-list itself was doing the right thing on all four versions.
decode_responses is async-cluster-only on every version the matrix covers, so it
stands in for the same property: the sync cluster class takes it through **kwargs
and never names it in its signature. Reverting _get_redis_cluster_kwargs to ignore
its client argument still fails both tests on 5.3.1 and 8.0.1.
test_async_cluster_passes_async_only_kwargs now builds the real async cluster
client and reads connection_kwargs off it, so it no longer needs a patched class
factory; the constructor does no I/O. The retry-attempts test keeps its patch,
since redis-py >= 6 stores no cluster_error_retry_attempts attribute on the built
client and the constructor call is the only place the forwarded value shows up.
The _get_redis_cluster_kwargs docstring cited the same two parameters as its
examples of async-only kwargs, which is what made the test look reasonable;
cluster_error_retry_attempts is on both classes and connection_error_retry_attempts
is gone from 6.0 on, so it now names decode_responses instead.
* test(redis): drop internal patches from the kwarg coercion tests
The test-quality gate flagged the new patch() calls on litellm internals these
tests added. Three of them faked litellm._redis.inspect.signature with a MagicMock
to hand _coerce_redis_kwargs_types a synthetic parameter; that function already
takes a client argument, so they pass stub functions instead, matching the
_redis_signature_8x idiom the file uses elsewhere. The fourth patched
_redis_kwargs_from_environment to {} to prove _get_redis_client_logic raises
without a host or url, which clearing the real env keys through
_get_redis_env_kwarg_mapping does without pinning the test to that call.
Both files now sit one TQ008 below the merge base rather than six above it.
* fix(redis): keep the sync client construction inside the basedpyright budget
_get_redis_client_logic now returns dict[str, object] rather than an untyped
dict, which is the honest type for operator-supplied config, but it turns the
33 reportUnknownArgumentType errors at redis.Redis(**redis_kwargs) into 33
reportArgumentType errors plus one reportCallIssue, both over their budget.
No static type fits: redis-py's constructor declares 40-odd differently typed
parameters and the values arrive from config and env, so the allow-list and
coercion above are derived from that same signature and redis-py validates each
value itself at runtime.
The two suppressions name their exact rule and carry that reason. The file ends
up 42 basedpyright errors below the merge base, with reportArgumentType and
reportCallIssue back at the base counts of 3 and 0.
* fix(redis): coerce cluster-only and None-default bool kwargs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mangabits <1457532+mangabits@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>
budget_limits now comes back exactly as stored on /key/info and /v2/key/info.
The per-window usage moves to a sibling budget_limits_usage field keyed by
budget_duration (current_spend, budget_limit, reset_at), mirroring
model_max_budget_usage, so the stored shape that /key/update accepts never
carries a computed field.
Pass window_duration to get_current_spend so /key/info re-checks a stale-low counter against the LiteLLM_BudgetWindowSpend row instead of aggregating LiteLLM_SpendLogs, and reuse _budget_limit_windows for the stored-column coercion. Drop the /v2/key/info batch cap (a new 422 for callers that work today) and the unrelated CI timeout bump and soft_budget test
* feat(ui): auto-router controls for context-window escalation
Adds an Advanced: Context Window Escalation section to the auto-router
form, both create and edit arms, with the toggle for
enable_context_window_escalation and a clamped decimal input for
context_window_escalation_buffer. An untouched control keeps both keys
out of the payload so the router tracks the backend defaults; an
explicit opt-out (false) survives the edit round-trip through the
managed-keys projection and the hydrator, and preset prefill maps both
keys straight through so a preset cannot silently drop them
Resolves LIT-6601
* fix(ui): clearing the context-window buffer removes it from the payload
Both review bots converged on the same defect: an emptied buffer field
early-returned in commitBuffer, the draft was discarded on blur, and the
stale number reappeared and stayed in the saved config, contradicting
the copy that an empty field tracks the backend default. An empty commit
now removes the key, which the managed-keys projection propagates as a
real deletion on edit. Also trims the narrative comments the review
flagged as restating behavior
* fix(proxy): wire team-level logging callbacks into passthrough endpoints
LIT-5152: passthrough routes now wire dynamic team-level callbacks
(success_callback, failure_callback, callback_vars) into Logging constructor,
mirroring the add_litellm_data_to_request behavior. Three hardening fixes:
1. Catch TypeError/AttributeError in _get_validated_callback_metadata when
team logging metadata has wrong shape (e.g., logging list instead of dict),
preventing HTTP 500 on passthrough routes with malformed config.
2. Wrap websocket passthrough logging initialization in try/except, since
the socket is already accepted at that point; errors after accept() yield
abrupt close (1006/1011) rather than clean HTTP error response.
3. Handle malformed deprecated callback_settings gracefully with try/except.
4. Wrap HTTP passthrough callback resolution in try/except to prevent 500 on
malformed team metadata (backward-compatibility fix).
Changes:
- pass_through_endpoints.py: wire dynamic callbacks in HTTP+WS paths, handle
malformed metadata gracefully with try/except fallbacks
- litellm_pre_call_utils.py: expand exception handling in validators
- test file: regression test for happy-path team callback wiring
* refactor(proxy): share passthrough team-callback resolution and cover its fail-open path
Collapse the duplicated callback wiring on the HTTP and websocket passthrough
paths into one helper that returns a frozen wiring value, log resolution
failures at error level so a broken logging config stays visible, and add
regression tests for malformed team metadata and an operational lookup failure.
Reverts the _get_validated_callback_metadata except widening: it changed
behavior for normal LLM routes, which is outside this ticket's scope.
* fix(proxy): keep passthrough alive when team callback vars hold env references
The deprecated team_metadata.callback_settings branch builds
TeamCallbackMetadata directly, skipping the AddTeamCallback validation
that strips os.environ/ references from the newer logging list. Stamping
those vars onto the Logging object made its constructor raise, so a team
on the legacy shape got HTTP 500 on every passthrough call. Validate the
resolved vars inside the fail-open boundary instead, so the request goes
through with dynamic callbacks skipped and the reason logged.
* fix(proxy): lint violations in team callback wiring helper
* style: format lint
mgmt.cache_settings.update.happy_path and
mgmt.config_override.hashicorp_vault.happy_path were the last two uncovered
Management/UI cells, and neither can be covered against the shared proxy the
e2e suites run on. Both routes reconfigure the whole process rather than a
resource the test owns.
/cache/settings persists whatever it receives into a row that outranks the YAML
cache_params and is re-applied on a timer, so a partial write downgrades a TLS
cluster to a plaintext standalone node and every later Redis call hangs. That is
what took out 60 of 72 tests on 2026-07-25 and got the original test removed in
PR #34664.
/config_overrides/hashicorp_vault has the same shape: a POST sets the HCP_VAULT_*
env vars, swaps litellm.secret_manager_client process-wide, and writes a row the
config-reload poll re-applies, so every os.environ/ lookup on the pod resolves
against the test's Vault until the DELETE lands. Its constructor also never
dials Vault, so a POST to a bogus address still returns 200 and a smoke test
built on it would pass for the wrong reason.
Keeping rows we have decided not to cover only inflates the denominator, so drop
them and record the reasoning where someone would go to write the test. Filing
the isolated-proxy harness they both need separately; the cells come back with
it.
Management/UI goes 75/77 to 75/75, headline 402/544 to 402/542.
* fix(auth): quiet malformed virtual key rejections to stdout
Reduce noisy invalid-api-key error logs by classifying malformed virtual
keys and routing their rejections to stdout as WARNING instead of stderr
as ERROR. Suppressible via LITELLM_LOG=ERROR or log_client_error_tracebacks=true.
Changes:
- auth_utils: is_invalid_virtual_key_error() classifier and marker functions
- auth_exception_handler: log invalid keys as WARNING to child logger before
identity seeding and callbacks, escalate non-401 transforms to ERROR
- user_api_key_auth: websocket early-raise WebSocketException(1008) to avoid
double-logging at HTTP layer
- _logging: child logger verbose_proxy_stdout_logger with no handler/level;
LevelRoutingStreamHandler routes its WARNING records to stdout; handler
setLevel in _turn_on_json() closes JSON config handler level leak
- test_auth_exception_handler: new test case verifying malformed-key logs
at WARNING with marker retention through transformations
Fixes LIT-5362
* fix(auth): classify malformed-key 401 by raise-site marker, not message text
Review round 1 (Greptile P2, veria Low):
- Move the marker attribute name to litellm/constants.py per the shared
sentinel convention
- Stamp the marker on the malformed-key 401 where it is raised and classify
only by it. Message text is caller-influenceable on other 401s (vector
store ids, organization ids are interpolated into their messages), so a
phrase match would let a request body demote an authorization failure to
the quiet log path
- Regression test: a 401 carrying the phrase but not the marker stays at
ERROR on stderr
Replace table tbody and data-slot locators with getByRole, restore prior
public MCP hub entries instead of clearing the whitelist on cleanup, seed
the public agent via the append-semantics per-agent route, and rework
mutable cleanup state into const-scoped try/finally blocks
* fix(ui): keep litellm_credential_name from LiteLLM Params JSON when no credential is selected
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(ui): drop null litellm_credential_name from AddModelPanel payload fixture
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>
ProxyExtrasDBManager.spend_logs_is_partitioned() (#38452) silently returns
False when psycopg can't be imported, and psycopg was never added to the
extra_proxy install, so every production image lacks it. Schema
reconciliation then generates the unfiltered primary-key rewrite against a
genuinely partitioned LiteLLM_SpendLogs and Postgres rejects it, exactly the
failure the fix was meant to prevent. Ships psycopg via extra_proxy and logs
a warning when it's still missing instead of failing silently.
At end of drain the pump enqueued the sentinel first and picked the
billing mode from client_detached afterward, so a client that consumed
the sentinel and tore the relay down before the pump resumed (possible
whenever the sentinel enqueue hit a full queue) had its fully delivered
response billed through the teardown path, skipping the proxy's
post-response hook. Bill or park before the sentinel goes out, and let
an unconsumed sentinel fall back to dispatching the parked billing.
Shadow eval jobs previously targeted only virtual keys, so deployments on
pure JWT auth (which present no key at all) could never sample their
traffic. Jobs now carry a typed (target_type, target_id) pair covering
keys, teams, and users; sampling matches the identity every request
resolves to at auth time, so team and user jobs cover JWT traffic with
no client changes.
Resolves LIT-6578
* feat(complexity_router): escalate oversized prompts to a tier that fits before dispatch
The classifier scores complexity and never prompt size, so a long agentic
session whose newest ask is trivial classifies SIMPLE onto a small-window
tier and the provider rejects it with a context-window 400 that nothing
retries. The gate runs after classification on every decision path
(classify tail and session-affinity pin), estimates prompt tokens
including the out-of-band carriers (top-level system, tools,
instructions), and when the decided tier provably cannot hold the prompt
moves the request to the lowest configured tier with a model whose
declared window fits, restricting the pick to fitting models when the
decided tier can keep it. Models with no resolvable window are never
escalated away from or onto, escalated decisions are never written as
session pins, and the decision records context_escalated plus the
original tier in spend logs.
Resolves LIT-6503
* fix(complexity_router): judge groups by smallest window, bound skips by bytes, filter adaptive picks
Review-round rework, one mechanism per finding. A group is judged by its
smallest resolvable deployment window, since the core router picks within
a group with no fit check. The counting skip is gated on UTF-8 byte
length, which BPE token counts can never exceed, so token-dense scripts
cannot slip past it; only a real tokenizer count ever moves a request and
a failed count leaves the placement alone. The fit facts now filter every
adaptive phase including cold start and the tier fallbacks. Window
questions adopt the declared provider and never resolve authenticating
providers, and a router instance without get_model_list degrades the gate
to a no-op. Tests rebuilt on real Router instances resolving deployment
model_info end to end, plus a full-path test through
async_get_available_deployment
A guardrail modify_response verdict on a streaming request only produced a
proper replacement on /v1/messages: the chat completions and Responses API
translations had no build_block_sse_chunks, so the ModifyResponseException
re-raised and surfaced as an in-stream 500 error frame (or a whole-request
500 in buffered mode) instead of the documented 200 replacement.
Implement build_block_sse_chunks for both OpenAI translations: chat emits a
content delta plus a finish_reason content_filter chunk with real usage;
Responses emits the typed event sequence (standalone via
build_synthetic_response_events pre-stream, or an output-item continuation
under the in-progress response id mid-stream) ending in response.completed.
UsersTable overrides DataTable's default noDataMessage with its own
EmptyState, so the row reads "No users found" rather than "No results".
Assert that, and pair it with the seeded user being absent so the check
cannot pass while the filter silently does nothing.
