mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
61 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
mateo-berri
|
b7f4f531b3 | test(router): type the acreate_file fallback test helpers | ||
|
mateo-berri
|
2a1c21b72d |
fix(router): keep acreate_file fallbacks inside the requested model group
A file uploaded through Router.acreate_file lands in the account of the deployment that stored it, so a cross-group fallback silently stores the file with the wrong provider and every later batch or fine-tuning call against the returned id permanently fails. Extend the provider-scoped fallback pin that already covers input_file_id and training_file to file creation, so the original provider error surfaces instead. |
||
|
tin-berri
|
06943b6468
|
feat(router): make routing groups callable as virtual models and list them in /v1/models (#36519)
* feat(router): make routing groups callable as virtual models and list them in /v1/models * fix(router): traffic-scoped cooldown exemption, live model_names on delete, group-info cache invalidation * fix(router): share one recognized-model predicate across proxy gates, resolve aliases in group cooldown, read metadata via the dual-bucket owner * fix(router): close the gate and cache families for callable groups, strip member access_groups from group rows, prove cooldown wiring end to end * refactor(router): cache materialized group rows under the model-group cache owner and drop the redundant wiring test * fix(router): warn-and-shadow on group name collisions, name-level test coverage for group helpers, faithful router doubles in a2a and cursor tests * test(router): pin group cooldown metadata across the retry path |
||
|
Yassin Kortam
|
d8762bf4db
|
fix(router): warn when a deployment's credentials contradict its provider (#36486)
A deployment that carries one provider's credentials while resolving to another is silently broken: litellm ignores the credentials and sends the request to the resolved provider. The common shape is a Bedrock model group where one entry lost its route prefix, so `model: claude-sonnet-5` with aws_region_name set resolves to the first-party Anthropic API and returns "x-api-key header is required". Because the router load balances across the group, only the fraction of requests routed to that entry fails, which reads as an intermittent provider outage rather than a config error, and nothing at startup says otherwise. Warn at deployment registration when provider-scoped credential params (aws_*, vertex_*) sit on a model that resolves elsewhere, naming the params, the resolved provider, and the likely missing prefix. Warn only: an operator may be overriding a route deliberately, so this must not block startup. Deployments litellm cannot classify are left alone. Resolves LIT-5391 |
||
|
Deepanshu Lulla
|
05943b47a3
|
fix(router): cool down failed fallback deployments and correct cooldown TTL after Redis backfill (#35104)
* fix(router): cool down failed fallback deployments and correct cooldown TTL after Redis backfill A deployment that failed partway through a fallback chain (any attempt after the first) was silently exempt from cooldown, because the has_logged_async_failure dedup flag blocks the normal failure callback for every attempt past the first. _trigger_cooldown_for_failed_deployment now explicitly evaluates cooldown for that deployment when the dedup flag is set, using the same deployment-config > response-header > router-default precedence as the primary failure path, and skips advisor-orchestration failures. Deployment-ID resolution prefers the exception's stamped failed_deployment_id, now also set from the generic-API-call fallback path (rerank, embeddings, /v1/messages, etc.), falling back to metadata inspection for call paths that don't stamp it yet. CooldownCache also recomputes the remaining TTL when DualCache promotes a Redis entry into the in-memory layer: before this, a cooldown entry restored from Redis kept the in-memory layer's default 600s TTL regardless of the deployment's real cooldown_time, so a deployment could stay excluded from routing for up to 10 minutes after a much shorter cooldown had already expired. * fix(router): address Greptile review on the fallback-cooldown trigger Two P1 findings on PR #35104: - _trigger_cooldown_for_failed_deployment never incremented the deployment's per-minute failure counter before evaluating cooldown, so a fallback deployment's repeated retryable failures never accumulated toward the default percent-fail-rate threshold that _should_cooldown_deployment checks. - The metadata-bucket fallback (checking "metadata" before "litellm_metadata" for a deployment_model_name marker) could be fooled by a caller with permission to set metadata, since neither bucket's authorship can be determined without knowing the call's function_name. Removed it entirely; cooldown now requires the server-stamped failed_deployment_id, matching what the primary chat-completions path and the generic-API-call path (rerank, embeddings, /v1/messages, etc.) already set unconditionally. * fix(router): freeze the litellm_params fallback mapping to satisfy the type-discipline gate * fix(router): defer f-string interpolation in fallback-cooldown debug logs * fix(router): annotate cooldown-path locals with Final to satisfy the LIT010 budget * fix(router): don't cool down deployments for request-scoped 404s on generic API fallbacks * fix(router): stamp the dynamic client-side-credential deployment id, not the shared static one * fix(router): don't cool down deployments for a caller-supplied x-litellm-timeout * fix(router): stamp dynamic client-side-credential id in completion fallback paths too The generic-API-call helper already stamped the effective (dynamic-if-client-side-credential) deployment id on exceptions, but the regular _completion/_acompletion exception handlers still stamped the static shared deployment's id. A tenant using invalid forwarded credentials could generate repeated failures attributed to, and eventually cooling down, the shared deployment other tenants rely on. Extracted the stamping logic into one shared helper used by all three call sites (generic API, sync completion, async completion) so the fix and future changes to it stay in one place. * test(router): add direct-reference unit tests for the new stamping helper router_code_coverage.py's coverage gate flags _stamp_failed_deployment_id_with_effective_model_info as untested because it only sees the function invoked indirectly through _completion/_acompletion's exception handlers. Added two tests that call it directly, covering both the dynamic-id-present and static-fallback branches. * test(router): cover the timeout stamping branch and async active-cooldown append _acompletion's litellm.Timeout handler and async_get_active_cooldowns' happy path both lacked direct coverage despite their sibling branches (the generic Exception handler, the sync get_active_cooldowns) being tested. * test(router): remove duplicate cooldown-trigger and fallback-helper tests #34416 landed its own TestTriggerCooldownForFailedDeployment/ TestRunAsyncFallbackTriggersCooldown classes and test_ageneric_api_call_with_fallbacks_helper_stamps_failed_deployment_id covering the exact same scenarios as this branch's earlier flat-function tests, once its version of fallback_event_handlers.py was taken as-is during the last merge. Dropping the redundant copies. --------- Co-authored-by: Deepanshu <deepanshu.lulla@alpha-sense.com> |
||
|
Deepanshu Lulla
|
0580465384
|
feat(router): add per-deployment allowed_fails_policy and cooldown_time override support (#34416)
* feat(router): add per-deployment allowed_fails_policy and cooldown_time override support
Three bugs fixed in the router cooldown system: (1) deployment-level allowed_fails and
allowed_fails_policy in model_info now take precedence over router-level settings in
_should_cooldown_deployment; (2) failed fallback deployments now get evaluated for
cooldown via _trigger_cooldown_for_failed_deployment, bypassing the Logging dedup gate;
(3) DualCache promotes Redis cooldown entries using default 600s TTL instead of true
remaining cooldown time -- _corrected_active_cooldown now evicts expired entries and
corrects stale in-memory TTLs on backfill. Adds ServiceUnavailableError, BadGatewayError,
and NotFoundError fields to AllowedFailsPolicy and cooldown_time to LiteLLMParamsTypedDict.
* fix(router): gate fallback cooldown trigger on has_logged_async_failure; use only litellm_metadata for deployment ID
* fix(router): use X | Y union syntax to fix UP007 strict lint gate
* test(router_utils): add coverage for _trigger_cooldown_for_failed_deployment and has_logged_async_failure gate
* test(router_utils): cover deployment cooldown override and exception swallow paths
* fix(router): add InternalServerError/ServiceUnavailableError/BadGatewayError/NotFoundError to router-level get_allowed_fails_from_policy
* fix(router): format router.py and add router-level policy tests
* test(router): add CI-visible coverage for per-deployment cooldown policy
Tests for `_get_deployment_cooldown_policy`, `_resolve_allowed_fails_from_policy`,
and `_should_cooldown_based_on_deployment_policy` (cooldown_handlers.py), the
`_corrected_active_cooldown` branches in CooldownCache, and the four new
exception-type branches in `Router.get_allowed_fails_from_policy` (router.py) --
all in `tests/test_litellm/` which the enterprise-routing CI job runs.
* fix(router): use is not None guard for cooldown_time_override in should_cooldown_based_on_allowed_fails_policy
A cooldown_time_override of 0 was previously treated as falsy and silently
fell through to the router-level cooldown_time value. Switched to an explicit
is not None check so that zero is honored as a valid override.
Added a regression test covering the zero case.
* fix(router): honor has_logged_async_failure and metadata for fallback cooldown; support both model_info and litellm_params locations
Manual verification against a live proxy surfaced that the fallback-cooldown-gap
trigger never actually fired: the has_logged_async_failure check read a plain
attribute that Logging never sets (the real flag lives in model_call_details),
and the deployment_id lookup only trusted litellm_metadata, which regular chat
completions never populate (only batch/thread/file endpoints do). Router
overwrites model_info on whichever key is present before every attempt, so
metadata is equally authoritative there, not caller-controlled as previously
assumed. Also let allowed_fails/allowed_fails_policy/cooldown_time be set under
either model_info or litellm_params, each preferring its own canonical location.
* fix(router): fix ContentPolicyViolationError policy shadowing and partial-policy zero-threshold
Two bugs from Greptile review on PR #34416:
- ContentPolicyViolationError subclasses BadRequestError, so listing
BadRequestError first in _EXCEPTION_POLICY_FIELDS made the isinstance
check always match BadRequestError for content-policy errors, using the
wrong allowed_fails threshold. Reordered so the subclass is checked first.
- A deployment with a partial allowed_fails_policy and no deployment-wide
allowed_fails forced allowed_fails_override=0 for any exception type its
policy didn't cover, cooling the deployment down on the first unrelated
failure. Now defers to router-level behavior for uncovered exception
types instead of forcing an immediate cooldown.
* fix(router): only trust a metadata/litellm_metadata bucket the router itself wrote deployment info into
veria-ai flagged that preferring litellm_metadata whenever present could pick up a
caller-supplied litellm_metadata.model_info.id (preserved via allow_client_pricing_override)
instead of the metadata bucket the router actually populated for a regular completion's
fallback attempt, naming an arbitrary "victim" deployment for cooldown.
Router._update_kwargs_with_deployment() always writes model_info and
deployment_model_name into the same bucket together. Only trust a bucket that
carries deployment_model_name alongside model_info, since that marker is only
ever set by the router itself, not by request-body metadata.
* test(router): add regression coverage for ContentPolicyViolationError policy shadowing
The subclass-ordering fix in commit
|
||
|
mateo-berri
|
933c18b21c |
Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix_batch_group_fallback
# Conflicts: # litellm/router_utils/fallback_event_handlers.py # tests/test_litellm/router_utils/test_fallback_event_handlers.py |
||
|
tin-berri
|
e35ee4e5fa
|
feat(router): independent, default-on deployment affinity for the auto-router (#36146) | ||
|
Yassin Kortam
|
330a09235d
|
fix(router): bound fallback-walk work and error-log volume (#36148) | ||
|
mateo-berri
|
5883aa354d |
fix(router): keep batch fallbacks inside the model group that owns the file
A batch or fine-tuning job is created from a file the caller already uploaded, and that file only exists under the credentials of the deployment that stored it. When the router fell back to a different model group it handed that file id to a provider that has never seen it, so the caller got the second provider's complaint about the file id instead of the error that explains what was actually wrong with their request. run_async_fallback now skips fallback targets outside the original model group whenever the request carries input_file_id or training_file. Order-based fallbacks stay inside the group, so retrying across deployments still works. The same handler also crashed with "'NoneType' object has no attribute 'update'" whenever a fallback fired on a request with metadata set to None, which /v1/batches always does when the caller sends no metadata, turning the provider's 400 into a 500. Record the model group with a merge instead of setdefault, and write it to litellm_metadata on the endpoints that use it so the router's bookkeeping no longer lands in the metadata stored on the provider's batch. |
||
|
Abhimanyu Kapur
|
cc1c7d6101
|
feat(complexity_router): let operators rename the four complexity tiers (#35893)
* feat(complexity_router): let operators rename the four complexity tiers Adds an optional tier_labels map to complexity_router_config so a deployment can put its own vocabulary on the four tiers, e.g. Cheap / Standard / Premium / Deep, instead of reading SIMPLE / MEDIUM / COMPLEX / REASONING in its dashboard, its spend logs, and the rubric the LLM classifier reasons with. Labels are display-only. Every config key stays canonical, so tiers, keyword_tier_rules[].tier, and tier_boundaries are written exactly as they are without labels, and partial maps are fine with unlisted tiers keeping their default name. A validator rejects blank labels, two tiers sharing a label, and a label that is another tier's canonical name, since any of those would make a log row or a rubric line ambiguous. That validator runs on the /model/new and /model/update write path already, so an ambiguous config gets a 400 rather than being stored for the router to refuse later. Under the default heuristic scorer the names are cosmetic: the scorer maps a weighted score to a rung and never reads a tier name, verified by running the eval corpus with and without a rename and getting identical tier and identical score on all 29 cases. Under classifier_type: llm the labels are the names in the rubric and the values the classifier must return, so the response format's enum is now built from the configured labels and a reply is resolved back to its tier against labels first, then canonical names, case-insensitively. An unresolvable reply degrades to the heuristic on the existing fallback path. A test pins the generated schema for an unrenamed deployment as equal to the shipped TierClassification schema, so the wire shape can't drift. Spend logs keep routing_decision.tier canonical so rows from before and after a rename stay comparable, and gain routing_decision.tier_label on the tiers that were renamed. * refactor(complexity_router): drop added comments and the Counter construction Review feedback: the repository guide bans new comments, so the explanatory comments and the appended docstring paragraphs this branch added come back out. One-line docstrings stay in complexity_router.py, matching that file's own convention. The duplicate-label check no longer builds a Counter, which the mutable-collection budget counts, and the error text drops its list() reprs for joined strings. The labels are stripped in tier_label() now rather than by rewriting the field in the validator, so the stored config keeps exactly what the operator wrote. schema.d.ts is regenerated: ComplexityRouterConfig is exposed in the OpenAPI spec, so tier_labels surfaces there. * fix(ui): carry tier_labels through the auto-router preset prefill buildPresetPrefill maps every payload key onto form state, but the tier_labels key added by this branch had no line, so a preset shipping labels would apply its tiers and silently drop its names. |
||
|
tin-berri
|
cb8c734dbe
|
fix(ui): reject an auto-router keyword rule left empty instead of dropping it (#35705)
"Add keyword rule" seeds a row with no keywords, and the only check that a rule carried one lived inside getSemanticConfigError, which returns early when semantic keyword matching is off. Off is the default, so an unfilled row fell through to serializeKeywordTierRules and was discarded on the way to the payload; the create reported success and the rule was gone. The row now reports the gap itself and the submit is withheld while one is outstanding, on the create form and the edit modal alike, both reading emptyKeywordTierRuleIndexes so the row named and the row marked cannot differ. Enter commits a typed keyword: the dropdown is kept closed, which left antd nothing for Enter to select, and submitting was what used to supply the blur that saved the word. The backend already refused such a rule, but only when the router built the deployment, so a caller that sent one anyway got the row written, dropped on reload, and a 500. The management write paths now parse the incoming complexity_router_config with the router's own ComplexityRouterConfig, judged on the config alone so a patch that writes one without naming a model is covered too, and reject it with a 400 having persisted nothing. |
||
|
Yassin Kortam
|
8cf2e2eb43
|
fix(proxy): apply key/team router_settings.model_group_alias (#35486)
Key and team `router_settings.model_group_alias` was accepted, persisted and echoed back by `/key/info`, but never applied at request time, so the request ran on the group the caller asked for. `route_request` forwards only the settings the Router accepts as per-request kwargs, and `model_group_alias` is not one of them: the Router resolves aliases from its own instance attribute, which holds the global config map and is shared across requests. Resolve the alias in the proxy instead, alongside the existing model-alias rewrites and ahead of the pre-call hooks, so per-model limits and guardrails key off the group that actually serves the request. Authorize the alias target before the rewrite; model access was checked against the requested group, so a key whose alias points at a group it cannot call gets the usual 403 rather than being quietly served it. Resolves LIT-4879 |
||
|
Tin Chi Lo
|
1e04aee089 |
fix(proxy): reject model writes that corrupt an auto-router pseudo-model
An auto-router deployment's litellm_params.model (auto_router/...) is the discriminator the router loads it by, but the model management endpoints accepted any client-supplied value verbatim; a doubled or stripped prefix made router init fail on the next load and ignore_invalid_deployments silently dropped the deployment. Validate writes that supply litellm_params.model at all three endpoints against the merged params and reject incoherent values with an actionable 400. Classification is extracted to router_utils/auto_router_model_naming.py so the Router predicates and the validation share one source |
||
|
Tin Chi Lo
|
fc5848174e |
fix(router): take the lowest minimum across a model group, not the highest
The read gate cannot cause a wrong pin. A deployment is only pinned when the cache already holds an entry for the prefix, and async_log_success_event writes entries against the deployment's real model rather than the group alias, so a model that will not cache a prefix never records one and there is nothing to pin it to That makes this gate purely a cheap short-circuit deciding whether the cache lookup is worth doing, so the threshold must be the lowest minimum in the group. Taking the highest skipped the lookup for a prefix a lower-minimum member had genuinely cached, losing a hit it earned, and protected against nothing. It also broke the Fable 5 direction this ticket is meant to fix: its real minimum is 512, so a group gate stuck at a higher value would skip the lookup for a prefix Fable 5 had actually cached |
||
|
Tin Chi Lo
|
25b2f83f97 |
test(router): clear the lru_cache when forcing the local cost map
get_model_info is lru_cached, so swapping litellm.model_cost is not enough on its own. An earlier test that resolved these models against the remote map, which does not carry prompt_cache_min_tokens yet, leaves cached entries without it, and the stale hit resolves to the default. The assertions would then pass for the wrong reason or fail depending on execution order Clear on teardown as well, so entries these tests warm against the local map do not leak into later tests, matching the fixture already used in test_utils.py Also pin that a wildcard route resolves the underlying model's minimum. That works only because pattern_match_deployments substitutes the real model name into litellm_params before the deployment reaches the check; without the assertion that claim is unpinned and the threshold would silently fall back to the default |
||
|
Tin Chi Lo
|
ba70189e32 |
fix(router): resolve prompt cache minimum per model instead of a flat 1024
MINIMUM_PROMPT_CACHE_TOKEN_COUNT was a flat 1024 described as "minimum number of tokens to cache a prompt by Anthropic". Anthropic's minimum cacheable prefix is per-model and ranges from 512 to 4096, and it can differ per platform for the same model, so one constant is wrong in both directions is_prompt_caching_valid_prompt gates PromptCachingDeploymentCheck, which is what optional_pre_call_checks: ["prompt_caching"] turns on. When it believes a prompt is cacheable, async_filter_deployments pins routing to whichever deployment previously served that prefix. For a prompt between 1024 and 4096 tokens on Opus 4.6, Opus 4.5 or Haiku 4.5, litellm judged it cacheable and constrained routing while the provider never cached it, so the pin cost load balancing for nothing. In the other direction Fable 5 caches from 512 tokens, so a 512 to 1024 token prefix was refused a pin it had earned The minimum now resolves from prompt_cache_min_tokens in the model cost map, which keeps it current with new models and lets the Bedrock override for Fable 5 fall out of the existing per-entry keys with no special casing. MINIMUM_PROMPT_CACHE_TOKEN_COUNT stays as a global escape hatch when explicitly set, and as the fallback for models the cost map has no entry for async_filter_deployments only ever receives the model group alias, never a model name, so it resolves the threshold from healthy_deployments instead. A group may mix models with different minimums, so it takes the max: a prompt is only treated as cacheable when it clears every member's minimum, because an unnecessary pin is the defect being fixed while a missed pin only forfeits an optimization Gemini context caching shares this gate and has the same defect; its entries are left unset so they keep today's behavior, tracked separately in LIT-4525 |
||
|
Sameer Kankute
|
5b93ba0ada
|
feat(router): add separate ITPM/OTPM deployment rate limits (#31952)
Some checks are pending
GitHub Actions Security Analysis / zizmor (push) Waiting to run
* feat(router): add separate ITPM/OTPM deployment rate limits Support input/output tokens per minute on deployments via enforce_model_rate_limits, with reservation, reconciliation, refund on failure, and rate-limit headers. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(router): keep ITPM/OTPM diff minimal in router.py Drop unrelated Black reformatting from router.py and types/router.py so the PR only contains functional ITPM/OTPM changes. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(router): make ITPM/OTPM limits separate and atomic Address Greptile review on separate ITPM/OTPM deployment rate limits. - OTPM is now reserved atomically pre-call with rollback, matching the ITPM path, so concurrent requests can no longer overshoot the configured output limit before reconciliation - ITPM counts input tokens only; it no longer accumulates completion tokens, so the input-token limit and x-ratelimit-limit-input-tokens header describe input usage as their names imply - _read_reservation_from_kwargs only falls back to litellm_params.metadata when the top-level metadata channel is absent, so production requests carrying a litellm_params.metadata dict still reconcile and refund their reservation Adds regression tests for OTPM atomicity under concurrency, input-only ITPM enforcement, and reservation lookup when litellm_params.metadata is present. * fix(router): subtract input tokens only from remaining-input-tokens header The in-flight replay for x-ratelimit-remaining-input-tokens subtracted total tokens (input + output) instead of input tokens only, so clients saw remaining input quota understated by the completion token count on every response. Now consistent with the input-only ITPM counter. * fix(router): make itpm/otpm vs tpm/rpm precedence explicit When a deployment configures itpm/otpm alongside tpm/rpm, the io-token path takes over and the tpm/rpm limits are not enforced. Log a warning the first time such a conflicting deployment is seen so the supersession is not silent, and document the mutual exclusivity. Post-call reconciliation now only trues up a counter that was actually reserved against, so the itpm/otpm keys are no longer incremented for deployments that never configured that limit. * fix(router): track actual io-token usage on the reservation-minute key Post-call reconciliation now keys off the exact cache key stashed at pre-call time rather than one recomputed from the response-time minute. This fixes two issues: a request whose pre-call estimate was 0 now still writes its actual billable input to the ITPM counter (previously it was skipped, leaving the limit unenforceable for that request), and a call that finishes in a later minute reconciles against the minute it reserved against instead of pushing a negative delta into the next minute. Counters are only touched when their limit is configured. * fix(router): run io-token reconciliation before the model_id guard async_log_success_event gated IO reconciliation behind the model_id guard that only the TPM tracking path needs. Since reconciliation works entirely from the cache keys stashed in kwargs, a success event whose standard_logging_object lacks model_id would skip reconciliation and leave the reservation on the counter until the TTL expired, wasting quota. Route the IO path first. * fix(router): don't replay in-flight delta for itpm/otpm headers For ITPM/OTPM model groups the counter is incremented at reservation time (pre-call), so the remaining values returned by get_remaining_model_group_usage already account for the current request. Replaying the in-flight delta on top double-counted it and understated x-ratelimit-remaining-input/output-tokens by up to max_tokens on every response. Skip the delta for io-token groups; the legacy TPM/RPM replay path is unchanged. * fix(router): clear io-token reservation after reconcile/refund async_io_token_refund_failure and async_io_token_reconcile_success now clear the stashed reservation keys from the request metadata once done. Otherwise, on a model group mixing IO-limited and non-IO deployments, a failed IO call that retries on a non-IO fallback left the stale sentinel in the shared request metadata; the fallback's success handler would divert into IO reconciliation against the already-refunded key, driving the ITPM counter negative and skipping the non-IO deployment's TPM tracking. * fix(router): tidy reservation channel lookup and header guard Consolidate the reservation channel lookup into a single ordered helper shared by read and clear, so top-level metadata always wins over litellm_params metadata without the tangled per-iteration fallback. Also stop gating the router rate-limit header block on the presence of x-ratelimit-remaining-input/output-tokens. That block only emits those headers for ITPM/OTPM groups; for a non-IO group backed by a provider that natively returns input/output token headers, the extra conditions suppressed the router's own remaining-tokens/requests headers. * fix(router): strip client-supplied io-token reservation keys The reservation sentinels (_litellm_itpm_reserved, _litellm_itpm_cache_key, and the otpm equivalents) are server-only, but metadata is caller-controlled on proxy requests. An authenticated caller could forge these fields with an arbitrary cache key so the post-call reconcile/refund path would decrement any deployment's ITPM/OTPM counter and let it exceed the configured limit. Strip the reserved keys from the request metadata in set_io_token_rate_limit_request_kwargs, which runs before the router stashes its own reservation, so only a genuine server-side reservation is ever read post-call. * fix(router): track TPM routing load for io-limited deployments deployment_callback_on_success early-returned for any deployment with itpm/otpm set, so its total-token usage never landed in the router's TPM routing counter. TPM-aware routing strategies then saw 0 load for IO deployments and over-routed to them in mixed model groups. Only skip tracking when neither tpm/rpm nor itpm/otpm are configured; itpm/otpm enforcement still runs separately in ModelRateLimitingCheck, so the routing counter and the enforcement counters stay independent. * fix(router): expose standard tpm/rpm headers for io-limited groups get_remaining_model_group_usage returned early for ITPM/OTPM groups, so a group that also set tpm/rpm never emitted x-ratelimit-remaining-tokens / -requests; clients and prometheus gauges reading those saw no data. Build both header sets instead of returning early. Also simplify the in-flight header replay: only the tpm/rpm counters are incremented post-response, so the delta now adjusts just those. The itpm/otpm counters are incremented at reservation time (pre-call), so the input/output token headers already reflect the request and are left untouched - which removes the need for the separate io-group special case. * fix(router): roll back ITPM on any OTPM reservation error; dedup warning per instance Two follow-ups from review. The pre-call OTPM reservation only rolled back the ITPM reservation on a RateLimitError, so a transient cache error while reserving OTPM left the ITPM counter inflated until the TTL expired; catch any exception, release the ITPM reservation, then re-raise. Replace the module-level lru_cache warn-once (caching a logging side effect, which never re-warns in a long-lived process) with an instance-scoped set of already-warned deployment ids on ModelRateLimitingCheck. * fix(router): always clear reservation stash on reconcile; don't collapse id-less warning dedup Clear the reservation in a finally block so a mid-reconciliation cache error still removes the stash and a duplicate success event can't re-process it. Dedup the itpm/otpm-vs-tpm/rpm conflict warning per real deployment id; a deployment with no id no longer collapses every id-less deployment onto the str(None) key (which would suppress all but the first warning). * fix(router): skip io reservation when deployment can't be keyed _get_cache_keys returned a shared 'global_router:None:None:...' key when a deployment was missing model_info.id or litellm_params.model, so misconfigured deployments could share one rate-limit bucket. Return None in that case and skip io reservation for the request. * fix(router): honor explicit max_tokens=0 in io reservation _resolve_max_tokens used 'max_tokens or max_completion_tokens', so an explicit max_tokens=0 fell through to the model default. Only fall back to max_completion_tokens when max_tokens is absent. * fix(ci): satisfy lint budget, router coverage, and dashboard schema sync - Modernize the new itpm/otpm module's type hints to PEP 585 lowercase generics (Dict/Tuple/List -> dict/tuple/list) to clear the added UP006 violations; ratchet ruff-strict-budget.json's UP006 ceiling down to match. - Replace three try/except Exception blocks that must stay broad by design (token_counter and litellm.get_model_info raise untyped exceptions, and an io-token refund failure must never break the logging pipeline) with contextlib.suppress(Exception), matching the codebase's existing resolution for this exact BLE001 pattern. - Add direct unit tests for get_model_group_io_token_usage (multi-deployment aggregation and the empty-model-list case) in test_router_helper_utils.py, satisfying the router function-coverage check. - Regenerate the dashboard's schema.d.ts so the new itpm/otpm fields on GenericLiteLLMParams and ModelGroupInfo are reflected in the OpenAPI types. * fix: enforce io token rate limits consistently * fix: honor zero max tokens in otpm reservation * fix(lint): fix UP007 violation and resync ruff-strict-budget.json to base Convert Union[_Span, Any] to _Span | Any (safe on this repo's Python >=3.10 floor) to clear the new UP007 violation from the TYPE_CHECKING-gated Span alias. The previously committed ruff-strict-budget.json ratcheted UP006 down from a stale base; litellm_internal_staging has since tightened that same ceiling further on its own. Reset the file to the current base's committed values and re-ratchet from there so the budget only ever moves down relative to the actual merge-base, never against a stale snapshot. * fix(router): attach ITPM/OTPM headers on dict responses and harden reservation Strip itpm/otpm from provider kwargs, ensure messages are available for ITPM estimation, honor max_output_tokens on /v1/responses, and propagate rate-limit headers through /v1/messages dict responses via _hidden_params. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(router): attach ITPM/OTPM headers to streaming /v1/messages responses Wrap bare async iterators in HiddenParamsAsyncIteratorWrapper so set_response_headers can attach rate-limit headers to streaming Anthropic messages responses that lack a _hidden_params slot. Co-authored-by: Cursor <cursoragent@cursor.com> * style: ruff format add_retry_fallback_headers.py Fix CI ruff format check failure on get_hidden_params_dict call site. Co-authored-by: Cursor <cursoragent@cursor.com> * refactor(router): extract set_response_headers helpers to fix C901 budget Move header-attachment logic into add_retry_fallback_headers helpers so set_response_headers stays under the strict complexity ceiling. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: keep IO token reservation when response usage is missing Missing usage was reconciled as zero and fully refunded the pre-call reservation, allowing limit bypass on repeated successful calls. Only adjust counters when usage is resolved from the response or standard logging fields; otherwise keep the reservation until TTL expires. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: enforce RPM/TPM alongside IO-token limits on mixed deployments Deployments with both itpm/otpm and tpm/rpm previously returned after the IO reservation and skipped RPM/TPM checks. Run both paths and refund the IO reservation only when RPM/TPM rejects after a successful reservation. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: track TPM usage on success for mixed IO+TPM deployments The early return after IO-token reconciliation in log_success_event and async_log_success_event skipped the TPM counter increment, so the tpm_key the pre-call check reads was never written and tpm_limit was never actually enforced on deployments that also configure itpm/otpm. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: treat total-only usage as unresolved in IO-token reconcile usage/standard_logging_object entries carrying only total_tokens (no prompt/completion or input/output breakdown) were treated as resolved usage, resolving to (0, 0) and refunding the full reservation. Both _usage_is_present and the standard_logging_object fallback now require an actual input/output breakdown before reconciling, keeping the reservation otherwise. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: reserve minimal token when input/output estimation fails _reservation_value(0, limit) reserved the entire limit whenever token estimation failed (empty/unsupported input, tokenizer error), letting one such request claim the whole bucket and 429 every concurrent request to the deployment until it completed. Reserve 1 token instead so estimation failures no longer serialize traffic. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: refund IO reservation synchronously before retry deployment pick On retry, set_io_token_rate_limit_request_kwargs clears reservation sentinels from the shared kwargs dict before a background failure handler can refund them, stranding the counter until TTL. Refund and clear any stale reservation in _update_kwargs_with_deployment before stripping sentinels for the next attempt. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(io_token_rate_limit_check): use model-specific tokenizer for ITPM estimate; document sync-refund Redis ceiling Pass the deployment litellm_params.model to token_counter so it uses the model's native tokenizer instead of the generic fallback, narrowing the reservation over/under-estimate window between pre-call and post-call reconcile. Add a ponytail: comment to refund_stale_reservation_before_retry explaining the known ceiling: the synchronous DualCache.increment_cache issues a blocking Redis INCR when a Redis backend is configured. This only fires on streaming mid-stream retries (non-streaming failures await their failure handler before the retry picks a new deployment, leaving no sentinels to refund). Upgrade path: make _update_kwargs_with_deployment async. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Sameer Kankute
|
133da06aa3
|
chore: litellm oss staging (#31185)
* fix(ui): widen Y-axis gutter on Usage charts so large token/request labels aren't clipped
The Total Tokens Over Time and Total Requests Over Time AreaCharts on the
Usage page used Tremor's default yAxisWidth (~56 px), which is too narrow
once totals pass the hundred-million mark — leading digits of labels like
"100.00M" / "4500.00M" got clipped against the chart edge. The requests
chart was worse: it formatted with toLocaleString(), so billion-scale
request counts produced "1,000,000,000" (13 chars) and overflowed
immediately.
Fix in two places so neither alone has to carry the whole margin:
- activity_metrics.tsx: add yAxisWidth={80} to both AreaCharts, and
switch the requests chart to the shared valueFormatter so it uses the
same compact k/M/B suffixes as the tokens chart.
- value_formatters.tsx: add a >= 1e9 branch to valueFormatter /
valueFormatterSpend that emits a "B" suffix (4.50B, $4.50B), keeping
every formatted label at most 7 chars.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* Update ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* docs(readme): add Deploy on AWS/GCP with Terraform section
Adds a quickstart for the two published Terraform modules on the public
registry (BerriAI/litellm/aws and BerriAI/litellm/google). Copy-paste
main.tf for each cloud, the one-time GCP Artifact Registry remote-repo
command, and pointers to the registry pages for the full input surface.
Sits inside the Get Started section, between the gateway/SDK table and
Run in Developer Mode -- where someone scanning the README for "how do I
deploy this" will land.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(readme): add 1-click deploy buttons for AWS + GCP
GCP gets the real 1-click: Open in Cloud Shell badge that clones the repo
and walks through `terraform apply` via the existing DeployStack
tutorial (already shipped at terraform/litellm/gcp/examples/default/
TUTORIAL.md). User just picks a project.
AWS gets a soft 1-click: a Launch in AWS CloudShell badge that opens an
in-browser, already-authenticated shell. User runs four commands
(clone + cd + cp tfvars + terraform apply) once inside. There's no
native AWS deeplink that pre-clones a repo + runs a tutorial -- CFN
"Launch Stack" + CodeBuild would be needed for that, and that's a
separate piece of work.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(readme): move AWS + GCP deploy buttons next to Render button
* docs(readme): unify deploy button sizes and badge styles
* docs(readme): bump deploy button height to 48 to match Render/Railway
* docs(readme): bump AWS/GCP badge height to compensate for SVG padding
* docs(readme): bump AWS/GCP badge height to 72
* docs(readme): bump AWS/GCP badge height to 84
* fix(readme): make deploy buttons same height (48px)
https://claude.ai/code/session_01MxQRMHSDXbqJh74rF86UBc
* docs(readme): flag GCP project ID substitution in image_registry
* docs(readme): equalize deploy button heights and fix Cloud Shell button font
GitHub rewrites an image's height attribute to "height: auto; max-height: Npx", which only caps and never stretches, so each image renders at its intrinsic height. The AWS/GCP shields badges are intrinsically 28px while the Render/Railway buttons are 40px, leaving the row uneven regardless of the height="48" we set. Replace the two shields badges with committed 40px PNGs so all four header buttons render at the same 40px.
Also swap the Cloud Shell button from open-btn.svg to open-btn.png. The SVG renders its label as live text with font-family "Roboto, Sans" and no generic fallback; since neither font exists in GitHub's render environment, the text fell back to a serif (Times New Roman). The PNG bakes in the correct typeface.
* docs(readme): collapse Railway deploy anchor to a single line
The Railway button wrapped its img across indented lines, so the anchor contained leading and trailing whitespace. GitHub underlines link content, rendering that whitespace as a small blue underline beside the button. Put the anchor on one line like the other three buttons so there is no inner whitespace to underline.
* Add Claude Fable 5 cost map entries as a data-only hotfix
Backports only the model map changes from #30064 so deployments on
released litellm versions pick up Fable 5 pricing, context window, and
the adaptive thinking flag through the hosted cost map fetch without
upgrading. Includes the supports_sampling_params flag on the 28
Fable 5 / Opus 4.7 / Opus 4.8 entries (ignored by released code, read
by the gating that ships with the next release) and the matching
one-line schema declaration so the map validation test passes.
https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm
* fix: correct context window tokens for GPT-5 Pro and GPT-5.4 Mini/Nano
Three bugs in model_prices_and_context_window.json:
1. gpt-5-pro and gpt-5-pro-2025-10-06: max_input_tokens and max_tokens
were SWAPPED. GPT-5 Pro has a 400K context window (input) with 128K
max output, but the values were set as max_input=128000,
max_tokens=272000. This caused token limit errors when sending
prompts over 128K tokens to GPT-5 Pro.
2. gpt-5.4-mini and gpt-5.4-mini-2026-03-17: max_input_tokens was
272000, but GPT-5.4 Mini shares the same 1,050,000 token context
window as GPT-5.4. This was inconsistent with the azure/ variants
which already correctly had 1,050,000.
3. gpt-5.4-nano and gpt-5.4-nano-2026-03-17: same issue as Mini,
max_input_tokens was 272000 instead of 1,050,000.
Source: OpenAI model documentation and contextwindows.dev which
aggregates official context window sizes.
Fixes #30928 (partially — the issue incorrectly claims gpt-5/gpt-5-mini
should be 400K; their 272K values are correct per OpenAI docs)
* fix: also correct max_output_tokens for gpt-5-pro (272000→128000)
Per reviewer feedback, max_output_tokens was left at 272000 while
max_tokens was corrected to 128000, causing an internal inconsistency.
Both should be 128000 per OpenAI docs.
* fix(cost): price gpt-image generated output tokens as image tokens (#31147)
The OpenAI Images endpoints (/v1/images/generations, /v1/images/edits) return
usage with no output token breakdown — litellm's `ImageUsage` has no
`output_tokens_details` field — so generated-image OUTPUT tokens were priced at
the text rate (`output_cost_per_token`) instead of the image rate
(`output_cost_per_image_token`). For gpt-image-2 that is $10/1M vs $30/1M, a ~3x
undercount on the dominant cost component (image output is ~74% of spend). This
also affects azure gpt-image, which shares this calculator.
The OpenAI gpt-image cost calculator re-implemented usage handling instead of
reusing `calculate_image_response_cost_from_usage`, the shared helper that
azure_ai/gemini/vertex_ai already use. That helper classifies generated output
tokens as image tokens when the provider does not itemize output, and splits
text/image when it does.
Fix: route the ImageUsage path through `calculate_image_response_cost_from_usage`
(pre-transformed chat Usage objects are still costed directly). Adds a regression
test for the no-breakdown ImageUsage case (gpt-image-2).
* fix(bedrock): route application-inference-profile ARNs to converse (#18258) (#31098)
A bare application-inference-profile ARN passed as bedrock/arn:... fell
through to the invoke route, which cannot derive a provider from the
opaque profile id and raised 'Unknown provider=None'. The converse route
needs no provider, so detect these ARNs in get_bedrock_route and route
them to converse, matching the behavior of the already-documented
bedrock/converse/arn:... workaround.
Explicit invoke/ prefixes still win, and they remain a dead end for these
ARNs by design (no provider derivable). System-defined inference-profile
ARNs that embed a known model, and other opaque ARN types
(provisioned-model, imported-model, custom-model-deployment) that are
frequently invoke-only, are deliberately left on their current routes;
tests guard both boundaries.
* fix(moonshot): stop mutating caller messages on tool_choice='required' (#31060)
_add_tool_choice_required_message appended the "select a tool" prompt to
the caller's messages list in place, so transform_request corrupted the
caller's conversation history and appended a duplicate prompt on every
retry. Build and return a new list instead so the call stays idempotent.
Adds a regression test asserting the input messages list is unchanged
across repeated transform_request calls.
Co-authored-by: Wassbdr <wassim.badraoui07@gmail.com>
* fix(transcription): accept fractional usage.seconds in diarized_json responses (#30996)
gpt-4o-transcribe and compatible ASR backends return a diarized_json
response with usage={"type": "duration", "seconds": <float>}, e.g. 295.8.
TranscriptionUsageDurationObject typed seconds as int, so parsing the
response raised a pydantic ValidationError (int_from_float). That error
surfaces as an APIConnectionError which the router treats as retryable, so
it keeps re-calling the upstream (200 every time) until the upstream
rate-limits and returns 429 to the caller.
OpenAI specs this field as a float (see openai SDK UsageDuration.seconds),
so widen seconds to float. With the parse succeeding there is no exception
left to retry, which removes the loop.
Co-authored-by: Neimar Avila <19142978+neimaravila@users.noreply.github.com>
* fix(deepseek): drop non-function tools before chat completions call (#30910)
* fix(deepseek): drop non-function tools before chat completions call
DeepSeek's /chat/completions only accepts tools of type "function".
Requests bridged from /v1/responses can carry responses-API-native tool
types, for example a Codex CLI tool typed "namespace", which DeepSeek
rejects with "unknown variant 'namespace', expected 'function'" so the
whole request fails (issue #30722).
Filter unsupported tool types in the DeepSeek request transform so the
function tools still go through; when nothing callable remains, also drop
the now-dangling tool_choice and parallel_tool_calls
Fixes #30722
* test(deepseek): cover async tool filtering and document tool_choice assumption
Add an async_transform_request regression test so the sync and async tool
filtering paths cannot silently diverge, and document in _drop_unsupported_tools
that only non-function tools are dropped, so a function-named tool_choice always
references a surviving tool
* feat(catalog): add zai/glm-5.1, zai/glm-4.7-flash, openrouter/z-ai/glm-5.1 (#29840)
* feat(ui): surface team budget on key overview when key has no own budget (#30801)
* feat(ui): surface team budget on key overview when key has no own budget
* fix(ui): replace IIFE with derived variable and use find() for team budget display
* fix(anthropic): emit replayable streaming thinking blocks (#31022)
* feat(proxy): read cold-storage prompts back in the logs detail view (#30364)
* feat(proxy): read cold-storage prompts back in the logs detail view
When a deployment offloads prompts and responses to cold storage instead of
Postgres, the spend-log row holds only "{}" placeholders plus a
metadata.cold_storage_object_key pointer, so the UI logs detail drawer showed
nothing. The detail endpoint only read the placeholder columns and never
fetched the object back.
Resolve the payload per row based on actual content, not a config flag: if
Postgres has content, return it; otherwise read the exact stored object key and
fetch from the configured cold storage backend through ColdStorageHandler.
Reading the persisted key is a single GET. The key embeds a microsecond
timestamp that cannot be reconstructed from the millisecond-precision startTime
column, and listing the day's prefix to match on request_id would be too
expensive for this per-open path.
Also teach the detail drawer's pretty-view parser to accept a bare messages
array. The cold storage payload carries the prompt as a top-level messages list
with no proxy_server_request, so without this the output rendered while the
input stayed blank.
ColdStorageHandler gains an optional injected logger so the resolver can be unit
tested without monkeypatching. Postgres-stored prompts are unaffected: the fast
path returns the existing columns and the request-body object still renders the
same way.
* Update litellm/proxy/spend_tracking/spend_management_endpoints.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* test(proxy): cover ColdStorageHandler resolution paths and cold-storage fetch failure
Add unit tests for ColdStorageHandler (injected logger, graceful None when no
logger is configured, and resolution of a configured logger from the callback
registry) and a regression test asserting a cold storage backend exception
degrades to the Postgres values instead of surfacing a 500.
---------
Co-authored-by: Bytechoreographer <Bytechoreographer@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(mavvrik): advance metricsMarker after upload; fix scheduler startup (#31068)
* fix(mavvrik): advance metricsMarker after upload + fix scheduler startup
Two bugs fixed:
1. deliver() never called PATCH /metrics/agent/ai/{connectionId} after a
successful GCS upload, so metricsMarker stayed at 0 and every daily run
re-exported the same dates in an infinite catch-up loop.
Fix: add _update_metrics_marker(date_epoch) called at the end of deliver()
after _upload_to_gcs() succeeds. A 4xx warns but does not raise (the GCS
file is already committed). A 410 raises consistent with the rest of the
destination.
2. init_mavvrik_focus_background_job runs at proxy startup before any LLM call
has triggered lazy instantiation of MavvrikFocusLogger, so it found no
logger instance and silently skipped registering the daily export job.
Fix: if no instance is found but "mavvrik" is in litellm.callbacks, call
_init_custom_logger_compatible_class to force instantiation before
the APScheduler job is registered.
* fix(mavvrik): catch up from earliest window when metricsMarker=0
When the connector is freshly registered, metricsMarker=0 parses to None.
The catch-up block was guarded by `if last_ingested and ...` which skipped
it entirely for None, so only yesterday was exported instead of the full
_MAX_CATCHUP_DAYS window.
Fix: treat None as being _MAX_CATCHUP_DAYS behind (start from earliest_catchup).
The existing > 7 day warning only fires for non-None markers that are old.
* fix(mavvrik): use now as end_time for yesterday's export window
LiteLLM_DailyUserSpend rows for a given date get their updated_at
bumped by the spend flush job throughout the next morning. The core
database query filters on updated_at, so capping end_time at midnight
(yesterday + 1 day) missed any spend rows flushed after midnight.
Fix: pass now (cron fire time) as end_time for the daily "yesterday"
window so all fully-settled rows are captured regardless of when the
flush job ran.
Verified: claude-3-5-sonnet BilledCost went from 0.0 to ~$2.40 per
row in the exported FOCUS CSV.
* fix(mavvrik): also use now as end_time for catch-up windows
* fix(mavvrik_focus): pass required args to _init_custom_logger_compatible_class
Calling it with only logging_integration raised TypeError at proxy startup
because internal_usage_cache and llm_router have no defaults. Also fix test
name to reflect the actual status code (5xx not 4xx) used in the mock.
* ci: retrigger CI run
* feat: pass through optional `instruction` field in the rerank API (vLLM/Qwen3-Reranker) (#30757)
* Add optional `instruction` passthrough to the rerank API
vLLM's /v1/rerank and /v1/score accept an optional top-level `instruction`
field (folded into the model's chat_template_kwargs and consumed by the
chat template — e.g. Qwen3-Reranker). LiteLLM's managed rerank route silently
dropped it: RerankRequest / OptionalRerankParams had no such field, so the
outgoing body was rebuilt without it.
Thread an opt-in `instruction: Optional[str]` through rerank()/arerank(),
get_optional_rerank_params, and the hosted_vllm transformation into the
request body, only when non-None. When callers omit it, model_dump(exclude_none)
drops the field and the outgoing request is byte-for-byte unchanged — fully
backward-compatible. (DeepInfra already forwards `instruction` via
non_default_params; this formalizes the field in the shared types.)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Address review: thread `instruction` as a typed param + cover rerank_utils
Per PR review (greptile P2 + codecov):
- Make `instruction` a typed, named argument on the rerank provider interface
instead of recovering it from the opaque `non_default_params` blob. Adds
`instruction: Optional[str] = None` to `BaseRerankConfig.map_cohere_rerank_params`
and every provider override, and forwards it explicitly from
`get_optional_rerank_params`. hosted_vllm now reads the named param directly.
It is still also surfaced in `non_default_params` so providers that read it
there (e.g. DeepInfra) keep working now that `rerank()` consumes `instruction`
as a named param rather than leaving it in **kwargs.
- Add get_optional_rerank_params unit tests (present + absent) to cover the
previously-uncovered threading line flagged by codecov.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: scan rerank `instruction` through request guardrails
The rerank guardrail translation (CohereRerankHandler.process_input_messages)
only scanned `query`, so the newly added `instruction` field reached the
backend model unscanned. Since instruction-aware rerankers (hosted vLLM /
Qwen3-Reranker) fold `instruction` into the prompt, an authenticated caller
could place content there to bypass configured rerank request guardrails.
Generalize the handler to scan every user-controlled text field (`query` and
`instruction`) in one apply_guardrail call and write each sanitized value back
by index. Query-only requests are unchanged (single-element list at index 0);
non-string fields are left untouched. Adds tests covering instruction
scanning, PII masking write-back, and the non-string case.
Addresses the Veria AI security review on PR #30757.
* test: narrow Optional results before len() to satisfy basedpyright budget
The lint gate (basedpyright delta-vs-base budget) flagged one new
reportArgumentType: len(result.results) where results is
List[RerankResponseResult] | None. Assert results is not None first to
narrow the type before len()/indexing.
* fix: read rerank `instruction` from kwargs to satisfy basedpyright budget
The basedpyright delta-vs-base gate flagged one new reportArgumentType: the
Router forwards rerank calls via an untyped `**kwargs` unpack
(`litellm.arerank(**{**data, **kwargs})`), and declaring `instruction` as a
typed named param on the public `rerank`/`arerank` entrypoints made pyright
check that key against `str | None`, adding an error at router.py with no real
safety gain. Read `instruction` from kwargs in `rerank` instead.
It remains fully typed where it matters - threaded as a typed argument through
`get_optional_rerank_params` and each provider's `map_cohere_rerank_params`
(the original Greptile P2 ask). Whole-repo reportArgumentType is back to the
base count (net 0); rerank hosted_vllm + cohere guardrail suites pass; ruff clean.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(github_copilot): synthesize empty choices at the provider seam (#30929)
Newer Copilot Claude models (opus-4.7, opus-4.8) return responses with
choices=[], either carrying Anthropic-native content blocks or, for the
max_tokens=1 probe Claude Code sends, no content at all. github_copilot
is dispatched through the OpenAI SDK handler, which calls
convert_to_model_response_object directly and never invokes
GithubCopilotConfig.transform_response, so the empty-choices guard there
surfaced as a 500
Instead of synthesizing choices inside the shared
convert_to_model_response_object (which would silently turn empty choices
into a fabricated success for every provider), add a no-op
transform_parsed_response_dict hook on BaseConfig. GithubCopilotConfig
overrides it to synthesize choices from Anthropic-native content, reusing
its existing parsing, and the OpenAI SDK handler routes its parsed
response through the hook before generic conversion. The core utility
keeps treating empty choices as an error for all other providers
Fixes: https://github.com/BerriAI/litellm/issues/30927
Signed-off-by: David J. M. Karlsen <david@davidkarlsen.com>
* fix(router): stop fallback lookups from mutating the router fallbacks config (#30624)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens (#29693)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens
* test: scope local cost map env var with monkeypatch to avoid test pollution
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold (#30764)
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold
_mask_value did partial reveal by showing the first visible_prefix and last
visible_suffix characters, but for a value whose length was at or below
visible_prefix + visible_suffix (8 by default) it returned the value verbatim.
A value of exactly 8 chars fell through the length guard and computed
masked_length == 0, reconstructing the original string with no mask characters;
anything shorter hit the early return. Either way short credentials were emitted
in plaintext.
mask_dict routes real secrets through this path, so an 8-char-or-shorter redis
password, api key, or token could be written to logs and the UI unmasked. The
sibling helper mask_sensitive_keys already guards this case; _mask_value now does
the same by fully masking any value at or below the threshold.
* fix(sensitive_data_masker): add mask_short_values opt-out for truncation callers
Fully masking short values is the right default for secret masking, but
CooldownCache reuses the masker purely to truncate exception messages to the
first 50 characters, and it relies on short messages being returned readable.
Masking those blanked out short exception text and broke its tests.
Add a mask_short_values flag (default True, secure) and have CooldownCache pass
False so it keeps the truncation behavior, while every secret-masking caller
still gets short values fully masked.
* fix(mcp_debug): opt out of short-value masking to keep diagnostic token preview
MCPDebug uses the masker to preview auth tokens in debug headers and documents
that values of 10 chars or fewer are shown unchanged so token types stay
distinguishable. Pass mask_short_values=False so that diagnostic behavior is
preserved while secret maskers keep masking short values.
* fix(mcp_debug): mask short auth values in debug headers instead of echoing them
Earlier this masker opted out of short-value masking to keep a token preview, but
that echoes short authorization and token values verbatim in debug response
headers, which is the same leak this change is meant to close. Auth material
should never be emitted in full, so mask short values here too; the first/last
character preview still applies to longer tokens. Only CooldownCache keeps the
opt-out, since it truncates exception text rather than masking secrets.
* test(mcp_debug): assert masked short value preserves length
* refactor(fireworks_ai): remove deprecated audio transcriptions endpoint (#30917)
Fireworks AI deprecated audio inference on 2026-06-10
(https://docs.fireworks.ai/updates/changelog#audio-inference-and-image-generation-deprecation).
Live API testing confirms the endpoint is already non-functional: a valid
Fireworks API key receives HTTP 401 "Unauthorized" from
api.fireworks.ai/inference/v1/audio/transcriptions for every request,
regardless of payload. The audio-prod.api.fireworks.ai host referenced in
the test suite returns 401 for every path; the entire host is decommissioned.
Remove the dead FireworksAIAudioTranscriptionConfig class and every
reference to it across the codebase:
- Delete litellm/llms/fireworks_ai/audio_transcription/ directory (17-line
config class that inherited from OpenAIWhisperAudioTranscriptionConfig)
- Remove the Fireworks branch from
ProviderConfigManager.get_provider_audio_transcription_config() in
litellm/utils.py; update the stale comment in
get_optional_params_transcription that referenced fireworks ai
- Remove the FireworksAIAudioTranscriptionConfig entries from
LLM_CONFIG_NAMES and _LLM_CONFIGS_IMPORT_MAP in
litellm/_lazy_imports_registry.py
- Remove the TYPE_CHECKING re-export in litellm/__init__.py
- Remove the transcription branch in the fireworks_ai case of
get_supported_openai_params() in
litellm/litellm_core_utils/get_supported_openai_params.py
- Remove the whisper-v3 and whisper-v3-turbo entries from
model_prices_and_context_window.json and
litellm/model_prices_and_context_window_backup.json (both had
mode: audio_transcription and zero-cost pricing)
- Remove the TestFireworksAIAudioTranscription test class and its
imports from tests/llm_translation/test_fireworks_ai_translation.py
No other provider is affected. The openai_compatible_providers list,
FireworksAIMixin, and the OpenAI Whisper transcription handler all stay
because they are shared with other Fireworks endpoints and other
providers. The provider_endpoints_support.json registry already had
audio_transcriptions set to false for fireworks_ai.
* feat: add darkbloom provider (#30876)
* feat: add darkbloom provider
* fix: document darkbloom provider endpoints
* fix: address darkbloom review feedback
* fix: update darkbloom tool metadata
* fix: fail fast for non-Postgres database URLs (#30883)
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URL instead of hanging on startup
LiteLLM's Prisma datasource is pinned to provider = 'postgresql', so a sqlite:// or mysql:// DATABASE_URL can never connect.
Today that surfaces as an opaque startup stall where the port never binds, and a separate 'DB not connected' 500 on /key/generate when no DATABASE_URL is set at all leaves operators guessing what to configure.
Validate the DATABASE_URL / DIRECT_URL scheme in run_server before any Prisma call and exit with an actionable message naming the unsupported scheme.
Also reword CommonProxyErrors.db_not_connected_error to tell the operator to set DATABASE_URL to a postgresql:// connection string.
Add regression tests covering postgres acceptance and sqlite/mysql/mssql rejection.
* fix: resolve CI failures and proxy DB URL typing issue
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URLs with clear startup errors instead of hanging
* Validate DIRECT_URL alongside DATABASE_URL startup guards
* fix(bedrock): surface modeled HTTP status for mid-stream error events so 5xx is retryable (#24608) (#30946)
* fix(bedrock): surface modeled HTTP status for mid-stream error events (#24608)
* test(bedrock): mid-stream server errors trigger streaming fallback (#24608)
* style(bedrock): black-format stream-error helper (#24608)
* fix(mcp): re-land native tool preservation with typed annotations (#30645)
* fix(mcp): preserve native tools in semantic filter hook with typed annotations
* fix(mcp): tighten _is_mcp_tool Chat Completions shape check
* fix(sambanova): return embeddings supported params instead of dropping them (#30937)
* fix(router): send fallback metadata when streaming (#30914)
When a streaming request triggers a fallback, there was previously no way to
know it happened. This commit addresses this in a few ways:
1. The response now correctly populates the fallback headers
(`x-litellm-attempted-fallbacks`) so callers know a fallback happened.
2. The correct model ID is passed in the streaming chunks.
3. A streaming chunk with the fallback error can be optionally sent back
to the client (opt-in) by passing `include_fallback_errors: true` in
the request.
The format of the fallback errors while streaming is intentionally OpenAI
compatible to not break existing libraries that parse these events. It was
tested with Vercel's AI SDK (ai-sdk.dev). It is also opt-in, so it is not
delieved unexpectedly to callers by default.
* fix(mistral): drop output-only reasoning fields from input messages (#30884)
LiteLLM attaches reasoning_content and thinking_blocks to assistant
responses. Replaying those assistant turns verbatim forwarded the fields
back to Mistral, whose input schema forbids unknown keys, so the whole
request failed with a 422 extra_forbidden and reasoning models became
unusable across multiple turns.
Strip both fields from assistant messages before the request is built, in
a spot that runs ahead of the image/file branch so it applies on every
path. Fixes #30835
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(perplexity): bill search queries at the per-request price, not 1/1000 of it (#30652)
* fix(perplexity): bill search queries at the per-request price, not 1/1000
The fallback cost calculator divided search_context_cost_per_query by
1000, but that field stores the per-request price in USD: sonar is
{low: 0.005, medium: 0.008, high: 0.012}, matching Perplexity's published
$5/$8/$12 per 1,000 requests expressed per request. The gemini cost
calculator reads the same field per request with no division (its
docstring calls it "the per-request cost").
The division understated search cost by 1000x on every Perplexity call
that falls back to manual calculation (i.e. when the API does not return
a pre-computed usage.cost). Use the value directly.
Update the tests that had encoded the /1000 factor in their expectations,
and drop an unused import flagged by ruff in the touched test file.
* test(perplexity): update integration test search-cost expectations to per-request
The integration tests still encoded the old /1000 search-cost factor, so
they failed once the fallback calculator was corrected to bill
search_context_cost_per_query per request. Update the four expected-cost
computations (and the high-volume dollar-value comments) to match.
* test(perplexity): drop unused mock imports flagged by ruff
* fix: include model_access_groups when expanding all-team-models in get_team_models (#30622)
* fix(fireworks_ai): return None for transcription in get_supported_openai_params
Fireworks AI deprecated audio inference on 2026-06-10; the endpoint is
decommissioned. Without an explicit transcription branch, requests with
request_type='transcription' fell through to the else and returned
FireworksAIConfig chat-completion params. Return None instead to signal
the provider does not support transcription.
* fix(proxy): gate include_fallback_errors behind expose_fallback_errors_to_caller setting
Without an operator gate, any authenticated caller could set include_fallback_errors=True,
trigger a fallback, and read raw upstream exception messages from the
x-litellm-fallback-errors header and the litellm-fallback-metadata SSE event.
Strip include_fallback_errors from request data in common_processing_pre_call_logic
when expose_fallback_errors_to_caller is not set, so the router never builds the
error list. Also gate _should_include_fallback_errors on the same setting as a
secondary check for the streaming SSE injection path.
* test(proxy): opt in to expose_fallback_errors_to_caller in streaming SSE test
The operator gate added in
|
||
|
Sameer Kankute
|
80c5a84871
|
chore: litellm oss staging (#30968)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens (#29693)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens
* test: scope local cost map env var with monkeypatch to avoid test pollution
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold (#30764)
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold
_mask_value did partial reveal by showing the first visible_prefix and last
visible_suffix characters, but for a value whose length was at or below
visible_prefix + visible_suffix (8 by default) it returned the value verbatim.
A value of exactly 8 chars fell through the length guard and computed
masked_length == 0, reconstructing the original string with no mask characters;
anything shorter hit the early return. Either way short credentials were emitted
in plaintext.
mask_dict routes real secrets through this path, so an 8-char-or-shorter redis
password, api key, or token could be written to logs and the UI unmasked. The
sibling helper mask_sensitive_keys already guards this case; _mask_value now does
the same by fully masking any value at or below the threshold.
* fix(sensitive_data_masker): add mask_short_values opt-out for truncation callers
Fully masking short values is the right default for secret masking, but
CooldownCache reuses the masker purely to truncate exception messages to the
first 50 characters, and it relies on short messages being returned readable.
Masking those blanked out short exception text and broke its tests.
Add a mask_short_values flag (default True, secure) and have CooldownCache pass
False so it keeps the truncation behavior, while every secret-masking caller
still gets short values fully masked.
* fix(mcp_debug): opt out of short-value masking to keep diagnostic token preview
MCPDebug uses the masker to preview auth tokens in debug headers and documents
that values of 10 chars or fewer are shown unchanged so token types stay
distinguishable. Pass mask_short_values=False so that diagnostic behavior is
preserved while secret maskers keep masking short values.
* fix(mcp_debug): mask short auth values in debug headers instead of echoing them
Earlier this masker opted out of short-value masking to keep a token preview, but
that echoes short authorization and token values verbatim in debug response
headers, which is the same leak this change is meant to close. Auth material
should never be emitted in full, so mask short values here too; the first/last
character preview still applies to longer tokens. Only CooldownCache keeps the
opt-out, since it truncates exception text rather than masking secrets.
* test(mcp_debug): assert masked short value preserves length
* refactor(fireworks_ai): remove deprecated audio transcriptions endpoint (#30917)
Fireworks AI deprecated audio inference on 2026-06-10
(https://docs.fireworks.ai/updates/changelog#audio-inference-and-image-generation-deprecation).
Live API testing confirms the endpoint is already non-functional: a valid
Fireworks API key receives HTTP 401 "Unauthorized" from
api.fireworks.ai/inference/v1/audio/transcriptions for every request,
regardless of payload. The audio-prod.api.fireworks.ai host referenced in
the test suite returns 401 for every path; the entire host is decommissioned.
Remove the dead FireworksAIAudioTranscriptionConfig class and every
reference to it across the codebase:
- Delete litellm/llms/fireworks_ai/audio_transcription/ directory (17-line
config class that inherited from OpenAIWhisperAudioTranscriptionConfig)
- Remove the Fireworks branch from
ProviderConfigManager.get_provider_audio_transcription_config() in
litellm/utils.py; update the stale comment in
get_optional_params_transcription that referenced fireworks ai
- Remove the FireworksAIAudioTranscriptionConfig entries from
LLM_CONFIG_NAMES and _LLM_CONFIGS_IMPORT_MAP in
litellm/_lazy_imports_registry.py
- Remove the TYPE_CHECKING re-export in litellm/__init__.py
- Remove the transcription branch in the fireworks_ai case of
get_supported_openai_params() in
litellm/litellm_core_utils/get_supported_openai_params.py
- Remove the whisper-v3 and whisper-v3-turbo entries from
model_prices_and_context_window.json and
litellm/model_prices_and_context_window_backup.json (both had
mode: audio_transcription and zero-cost pricing)
- Remove the TestFireworksAIAudioTranscription test class and its
imports from tests/llm_translation/test_fireworks_ai_translation.py
No other provider is affected. The openai_compatible_providers list,
FireworksAIMixin, and the OpenAI Whisper transcription handler all stay
because they are shared with other Fireworks endpoints and other
providers. The provider_endpoints_support.json registry already had
audio_transcriptions set to false for fireworks_ai.
* feat: add darkbloom provider (#30876)
* feat: add darkbloom provider
* fix: document darkbloom provider endpoints
* fix: address darkbloom review feedback
* fix: update darkbloom tool metadata
* fix: fail fast for non-Postgres database URLs (#30883)
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URL instead of hanging on startup
LiteLLM's Prisma datasource is pinned to provider = 'postgresql', so a sqlite:// or mysql:// DATABASE_URL can never connect.
Today that surfaces as an opaque startup stall where the port never binds, and a separate 'DB not connected' 500 on /key/generate when no DATABASE_URL is set at all leaves operators guessing what to configure.
Validate the DATABASE_URL / DIRECT_URL scheme in run_server before any Prisma call and exit with an actionable message naming the unsupported scheme.
Also reword CommonProxyErrors.db_not_connected_error to tell the operator to set DATABASE_URL to a postgresql:// connection string.
Add regression tests covering postgres acceptance and sqlite/mysql/mssql rejection.
* fix: resolve CI failures and proxy DB URL typing issue
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URLs with clear startup errors instead of hanging
* Validate DIRECT_URL alongside DATABASE_URL startup guards
* fix(bedrock): surface modeled HTTP status for mid-stream error events so 5xx is retryable (#24608) (#30946)
* fix(bedrock): surface modeled HTTP status for mid-stream error events (#24608)
* test(bedrock): mid-stream server errors trigger streaming fallback (#24608)
* style(bedrock): black-format stream-error helper (#24608)
* fix(mcp): re-land native tool preservation with typed annotations (#30645)
* fix(mcp): preserve native tools in semantic filter hook with typed annotations
* fix(mcp): tighten _is_mcp_tool Chat Completions shape check
* fix(sambanova): return embeddings supported params instead of dropping them (#30937)
* fix(router): send fallback metadata when streaming (#30914)
When a streaming request triggers a fallback, there was previously no way to
know it happened. This commit addresses this in a few ways:
1. The response now correctly populates the fallback headers
(`x-litellm-attempted-fallbacks`) so callers know a fallback happened.
2. The correct model ID is passed in the streaming chunks.
3. A streaming chunk with the fallback error can be optionally sent back
to the client (opt-in) by passing `include_fallback_errors: true` in
the request.
The format of the fallback errors while streaming is intentionally OpenAI
compatible to not break existing libraries that parse these events. It was
tested with Vercel's AI SDK (ai-sdk.dev). It is also opt-in, so it is not
delieved unexpectedly to callers by default.
* fix(mistral): drop output-only reasoning fields from input messages (#30884)
LiteLLM attaches reasoning_content and thinking_blocks to assistant
responses. Replaying those assistant turns verbatim forwarded the fields
back to Mistral, whose input schema forbids unknown keys, so the whole
request failed with a 422 extra_forbidden and reasoning models became
unusable across multiple turns.
Strip both fields from assistant messages before the request is built, in
a spot that runs ahead of the image/file branch so it applies on every
path. Fixes #30835
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(perplexity): bill search queries at the per-request price, not 1/1000 of it (#30652)
* fix(perplexity): bill search queries at the per-request price, not 1/1000
The fallback cost calculator divided search_context_cost_per_query by
1000, but that field stores the per-request price in USD: sonar is
{low: 0.005, medium: 0.008, high: 0.012}, matching Perplexity's published
$5/$8/$12 per 1,000 requests expressed per request. The gemini cost
calculator reads the same field per request with no division (its
docstring calls it "the per-request cost").
The division understated search cost by 1000x on every Perplexity call
that falls back to manual calculation (i.e. when the API does not return
a pre-computed usage.cost). Use the value directly.
Update the tests that had encoded the /1000 factor in their expectations,
and drop an unused import flagged by ruff in the touched test file.
* test(perplexity): update integration test search-cost expectations to per-request
The integration tests still encoded the old /1000 search-cost factor, so
they failed once the fallback calculator was corrected to bill
search_context_cost_per_query per request. Update the four expected-cost
computations (and the high-volume dollar-value comments) to match.
* test(perplexity): drop unused mock imports flagged by ruff
* fix: include model_access_groups when expanding all-team-models in get_team_models (#30622)
* fix(fireworks_ai): return None for transcription in get_supported_openai_params
Fireworks AI deprecated audio inference on 2026-06-10; the endpoint is
decommissioned. Without an explicit transcription branch, requests with
request_type='transcription' fell through to the else and returned
FireworksAIConfig chat-completion params. Return None instead to signal
the provider does not support transcription.
* fix(proxy): gate include_fallback_errors behind expose_fallback_errors_to_caller setting
Without an operator gate, any authenticated caller could set include_fallback_errors=True,
trigger a fallback, and read raw upstream exception messages from the
x-litellm-fallback-errors header and the litellm-fallback-metadata SSE event.
Strip include_fallback_errors from request data in common_processing_pre_call_logic
when expose_fallback_errors_to_caller is not set, so the router never builds the
error list. Also gate _should_include_fallback_errors on the same setting as a
secondary check for the streaming SSE injection path.
* test(proxy): opt in to expose_fallback_errors_to_caller in streaming SSE test
The operator gate added in
|
||
|
Sameer Kankute
|
3b40ac987f
|
Litellm oss 090626 (#30021)
* fix(mcp): report scoped server name during initialize (#29865) * fix mcp scoped server name * Update litellm/proxy/_experimental/mcp_server/mcp_context.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * test(mcp): cover scoped server name in the SSE initialize handler --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(ui): show all session logs in the drawer, not just the first 50 (#29795) * fix(ui): show newest session logs first * test(ui): keep session log pagination coverage * fix(ui): show all session logs in the drawer, not just the first page The session detail drawer fetched session logs via sessionSpendLogsCall without page/page_size, so it only ever received the backend default of one page (50 rows). Sessions with more than 50 calls had the rest unreachable in the UI (#29153). sessionSpendLogsCall now takes page/page_size, and the drawer fetches the first page, reads total_pages, then fetches the remaining pages and accumulates them before the existing client-side sort. This keeps the single continuous list (and the selected-log lookup and keyboard navigation, which all assume the full session) correct. Fetching is bounded by a page cap, and the sidebar shows a "showing most recent N" note if a session exceeds it. The rows are lightweight metadata (the endpoint excludes messages/response), so the full set is small; request/response bodies are still loaded per log on demand. * fix(ui): default session drawer to most recent log, newest first Open a session with its most recent log selected, and order the sidebar newest-first to match the all-sessions logs overview. MCP calls stay grouped last. The latest log by time is computed explicitly, since the MCP grouping means it is not always the first row. * Apply fetching pages in batches suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(ui): derive session total from accumulated rows when backend omits it Compute the session total after all pages are fetched, falling back to the accumulated row count rather than the first page's. Guards the truncation note against a backend response that omits total but spans multiple pages. --------- Co-authored-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(proxy): handle Mistral multipart passthrough (#29927) * fix(proxy): handle Mistral multipart passthrough * chore: satisfy passthrough ci formatting * test(proxy): cover Mistral passthrough in CI shard * fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573) Context caching built the cachedContents URL as https://{location}-aiplatform.googleapis.com, which is an invalid host for the eu/us multi-region endpoints and returns 404. The inference path already resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com) via get_vertex_base_url(); reuse that helper in _get_token_and_url_context_caching so caching uses the same host as inference. Adds tests covering the eu/us multi-region cachedContents URLs (v1 and v1beta1). Fixes #29571 * Support per-model encrypted content affinity config (#29760) Co-authored-by: shin-berri <shin-laptop@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> * fix: propagate upstream status code in proxy API exception handler (#29402) * fix: propagate upstream status code in proxy API exception handler When Google GenAI / Vertex returns a 404 for deprecated or missing models via streamGenerateContent, the exception was falling through to a generic handler that defaulted to 500. Now provider exceptions carrying a valid HTTP status_code correctly propagate it through to the ProxyException. * fix: apply black formatting to common_request_processing.py * fix: tighten status code range to 400-599 and deduplicate ProxyException raise * fix(tests): use valid vertex_location in context caching tests Replace "test_location" (contains underscore) with "us-central1" so tests pass the regex validation added in get_vertex_base_url(). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(sdk): add xAI OAuth provider (#29866) * Add xAI OAuth provider * Update oauth.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Fix xAI OAuth CI failures * Add xAI OAuth coverage tests * Move xAI OAuth coverage tests to core utils * Address xAI OAuth review comments * Prevent xAI OAuth api_base token exfiltration * Treat blank xAI OAuth api keys as absent * Wrap invalid xAI OAuth JSON responses * Use xAI OAuth behind explicit flag --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751) * fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update Fixes #27734 Sending null for budget_duration, team_member_budget, team_member_budget_duration, team_member_rpm_limit, or team_member_tpm_limit via /key/update or /team/update returned 200 OK but silently ignored the null value. The fields remained unchanged in the database. Root causes: - /key/update: prepare_key_update_data() popped budget_duration from the update dict but never re-added it (or budget_reset_at) when the value was None. - /team/update: _set_budget_reset_at() only acted when budget_duration was non-None, leaving a stale budget_reset_at in the DB. - /team/update: team_member_* null values bypassed the budget table update entirely because should_create_budget() requires at least one non-None field. * test(proxy): cover no-budget-row path in clear_team_member_budget_fields * fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028) * fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes When output_parse_pii=true on the Anthropic native path (anthropic/claude-*), response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with the original values before reaching the caller. Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta / text_delta events, and apply _unmask_pii_text before re-encoding. Wire it into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist. * fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks don't bypass it and silently swallow a JSONDecodeError. Add ensure_ascii=False to json.dumps so non-ASCII replacement values like accented names are preserved as UTF-8 on the wire rather than being \uXXXX-escaped. Add regression tests for both cases. * feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925) * feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) Bedrock Mantle serves the Responses API on two upstream paths: - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses; any model declared mode=responses (price-map entry or user model_info) -> /v1/responses; everything else returns None and keeps the existing chat-completions emulation. Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests. * feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path Addresses the Greptile review point that frontier detection should be a price-map field rather than a hardcoded name match. The gate now routes a model to /openai/v1/responses when its price-map entry declares use_openai_responses_path, so a frontier model whose name does not follow the openai.gpt- convention can be onboarded by JSON alone. The name-convention check is kept as a fallback that needs no price-map entry, which preserves zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4 get the flag in both price maps. Adds tests for the data-driven flag path and for the flag presence on the gpt-5.x entries; both branches are mutation-tested. * test(model_prices): allow use_openai_responses_path in price-map schema The model_prices_and_context_window.json schema validator (test_aaamodel_prices_and_context_window_json_is_valid) enforces additionalProperties: false, so the new use_openai_responses_path flag on the gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean, alongside the other supports_* / capability flags. * Add Tensormesh serverless models to the model cost map (#30037) * Add Tensormesh serverless models to the model cost map * Flag reasoning support on the Tensormesh models that expose thinking mode * fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001) * fix(proxy): reconcile stale key spend counter after budget reset * fix(proxy): invalidate stale key spend counter after budget reset or manual spend update * fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass * revert: undo unrelated formatting changes in enterprise directory * test(proxy): add unit test for key spend update invalidating counter * test(proxy): fix mocked update_data and hash token expectations in unit test * fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728) The `elif is_responses:` branch of `openai_passthrough_handler` was calling the chat-completions `transform_response` on a Responses API payload. The chat-completions transformer expects `choices: [...]` in the raw response; the Responses API uses `output: [...]` and `usage.input_tokens` / `usage.output_tokens` (not `prompt_tokens` / `completion_tokens`). The result was a KeyError 'choices' deep inside `convert_to_model_response_object`, swallowed by the surrounding `except Exception` in the handler, and the SpendLogs row was written by the fallback path with zeroed-out tokens, spend, and model. This bug silently undercounts cost for every successful pass-through call to either OpenAI's `/v1/responses` or Azure's `/openai/v1/responses` (deployments configured for the Responses API). Reproduced 2026-06-04 against a real Azure OpenAI Responses API deployment proxied through LiteLLM v1.88.0. Fix: use the dedicated `OpenAIResponsesAPIConfig.transform_response_api_response` for the Responses branch. This transformer already exists in LiteLLM (`litellm/llms/openai/responses/transformation.py`) and knows the Responses-API on-the-wire shape. `litellm.completion_cost` already handles `ResponsesAPIResponse` natively with `call_type="responses"`, so no downstream changes are needed. Tests: test_responses_api_uses_responses_transformer_not_chat_completions NEW. Real regression test — exercises the openai_passthrough_handler with a real-shaped Responses payload (no `choices`, has `output` and Responses-API `usage` keys) and NO mocked `get_provider_config`. Pre-fix: raises KeyError 'choices' inside the chat-completions transformer (the bug). Post-fix: returns a ResponsesAPIResponse, completion_cost is called with call_type="responses" and a ResponsesAPIResponse instance (asserted). Verified to fail on un-fixed handler + pass on fixed handler before commit. test_responses_api_cost_tracking UPDATED. Old test mocked `get_provider_config` (no longer called in the responses branch post-fix). Now mocks the Responses transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`) to test the downstream cost-calc contract. Out of scope for this PR (separate followup): - Recognizing *.cognitiveservices.azure.com (the newer Azure OpenAI hostname) in the is_openai_*_route checks. Separate PR. Co-authored-by: shin-berri <shin-laptop@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> * fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116) Skill IDs are generated as litellm_skill_<uuid> and the model-facing tool name is the sanitized skill ID, but the post-call execution gates in SkillsInjectionHook only ran tools whose name starts with "skill_", so DB skills were silently returned to the client as raw tool calls. Fixes #28122. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115) * fix(team): reserve team budget raises for proxy admins on /team/update (#30030) The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a team's spend ceiling has nothing to do with the admin's own key budget. That comparison was an unintended side effect of reusing _check_user_team_limits() (which exists for the /team/new path) and broke the UI, which re-sends the unchanged budget on every save. New behavior on /team/update for standalone teams: - A team admin (already authorized via _verify_team_access) may freely KEEP or LOWER the team budget, and change models/tpm/rpm, without being gated by their personal limits. - GROWING a team's spend ceiling is a budget-authority action reserved for proxy admins -> 403 for team admins. "Growing" covers both raising max_budget above the team's current finite value and removing the cap entirely (max_budget=null, detected via model_fields_set so an explicit null is distinguished from an omitted field). For a team that currently has no cap, setting a finite value is a restriction and is allowed. - Org-scoped teams remain governed by _check_org_team_limits() (capped by the org budget). Also reverts the #29525 existing_team_max_budget workaround in _check_user_team_limits() back to the create-only form; /team/new still enforces the creator's personal caps. docs(access_control): resolve the contradiction in the team-admin section — team admins can keep/lower the budget and manage rate limits/models, but cannot raise the team budget (proxy-admin only). tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed, keep/lower/resend allowed, and unchanged create-path guards. Co-authored-by: Cursor <cursoragent@cursor.com> * test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974) * test(ui): add a data-driven App Router migration E2E smoke Add a growing Playwright smoke for migrated pages: for each segment it deep-links to the path route, asserts the URL and that the dashboard shell rendered, then clicks off to a legacy page and asserts navigation still works. Driven by e2e_tests/fixtures/migratedPages.ts, so adding a page is one line. Runs in two situations against the same proxy: the default mount (npm run e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root). globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage state is valid under a prefix. Seeded with api-reference; append the rest as their migrations merge. * test(ui): support headed slow-motion + watch pauses in the migration smoke Honor SLOWMO in the server-root-path config (the default config already did), and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state. Both are no-ops by default, so CI behavior is unchanged. * test(ui): make the migration smoke a sidebar-click user journey Rework the smoke from deep-linking to a real navigation journey: start at the landing page, click the migrated page in the sidebar (expanding submenus for nested items), assert the path route rendered, reload it (the check a wrong server_root_path breaks), bounce to a legacy page and back, and — once two pages are migrated — navigate directly between two migrated pages. Verifies via URL + shell render, driven by the same fixture list. * test(ui): address review on the migration smoke Escape ROOT and segment before interpolating them into RegExp URL matchers so a future segment containing regex metacharacters can't silently widen the match. Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead of silently re-running the default mount and passing without exercising the prefix. * test(ui): drop unused watch helper and fix stale smoke README * test(ui): run the migration smoke under a server root path in CI * test(ui): harden + instrument the server-root-path proxy reboot in CI * test(ui): run the server-root-path migration smoke as its own CI job Replace the in-place proxy reboot in e2e_ui_testing with a dedicated e2e_ui_testing_server_root_path job that boots the proxy once with SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the config gets its own job rather than killing and relaunching the live proxy. The reboot was failing deterministically: after pkill -9 and relaunch the prefixed proxy never came back up on :4000 (connection refused), so the smoke never ran. The readiness step that was supposed to surface the cause could never reach its boot-log tail because CircleCI runs steps under bash -eo pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's exit 7. Booting the proxy as the job's own background step lets any boot crash land in that step's log instead of being swallowed. The default e2e_ui_testing job is unchanged aside from dropping the reboot, prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at the root mount there via the default Playwright config. * fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232) * fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through * test: mock post_call_response_headers_hook in audio speech route tests * chore(ui): remove dead App Router route stubs under (dashboard) (#30045) models-and-endpoints, organizations, and virtual-keys each had a page.tsx route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and deep links never resolve to it and the route is unreachable. Each was a thin wrapper that handed the shared view empty or no-op props (empty modelData with a no-op setModelData, hardcoded empty organizations, no-op setUserRole/setUserEmail), so reaching one would render a degraded page in any case. The real wrapper belongs in the PR that flips each page into MIGRATED_PAGES, written with eyes on it and a test This continues the dead-scaffolding cleanup from #28891. The shared components these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay, since the legacy ?page= switch in app/page.tsx and src/components still import them * fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000) * fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session * fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss * fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041) * fix(mcp): honor team access-group grants in OAuth authorize/token access check * test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation * docs(security): require a reproduction video for vulnerability reports (#30048) (#30063) With AI models capable of automated vulnerability discovery now publicly available, we expect a large increase in report volume, much of it unverified. Requiring a video of the exploit running against a live instance raises the bar for submissions and keeps triage focused on reproducible issues. Reports without a video will be closed and reopened if one is added later. Co-authored-by: stuxf <70670632+stuxf@users.noreply.github.com> * feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796) * feat(ui): add admin flag to disable in-product UI nudges for everyone Admins can now suppress the survey and Claude Code feedback popups for all users via a single disable_ui_nudges UI setting, instead of relying on each user dismissing them individually. * fix(ui): suppress nudges while ui settings are loading Gate nudgesDisabled on the ui-settings loading state so an admin with disable_ui_nudges on doesn't see the survey prompt flash, and the getInProductNudgesCall fetch doesn't fire, on a cold page load before the flag resolves. Falls back to showing nudges if the fetch errors. * test(ui): wrap CreateKeyPage test in QueryClientProvider page.tsx now calls useUISettings (react-query), which needs a QueryClient that layout.tsx supplies in production but the test did not. Add the provider and mock getUiSettings so the query resolves. * chore(ui): remove dead dashboard files and unused dependencies (#30047) * chore(ui): remove dead dashboard files and unused dependencies knip flagged seven orphaned source/config files with no importers and five declared dependencies that nothing in the tree uses. Removing them shrinks the dashboard bundle's source surface and keeps the manifest honest; vite stays installed transitively via vitest, so test tooling is unaffected. * fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec (tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml workflow step still depend on it, so the redirect e2e job failed to load a config that no longer existed. * fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009) * fix(proxy): authorize batch files using upload target_model_names (LIT-3593) After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593) Restores the reverse-lookup for the JSONL body.model fallback path so that legacy/pre-target_model_names managed files still map stripped provider IDs back to proxy aliases before auth. Also cleans up redundant `or None`. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)" This reverts commit |
||
|
Sameer Kankute
|
e59e34bed3
|
Gemini managed agents support (#28270)
Some checks are pending
Unit Tests: Proxy DB Operations / assert-shard-coverage (push) Waiting to run
Unit Tests: Proxy DB Operations / auth-checks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / budgets (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / custom-logging (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / db-and-spend (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / endpoints-and-responses (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / guardrails-hooks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / jwt-and-keys (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / key-generation (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / logging-misc (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-runtime (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-server-core (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / schema-migration (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-utils (push) Blocked by required conditions
Unit Tests: Security / security (push) Waiting to run
* Add support for environment variable in interactions api * Add sdk support for gemini create agent * Add agents endpoint support via proxy * Add outputs of each api * Add routing for model and agents param * Remove redundant condition in get_provider_agents_api_config LlmProviders.GEMINI.value is literally the string "gemini", so the second clause of the or was checking the exact same thing as the first. Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com> * fix: forward query-param credentials to list/get/delete/versions Gemini agent endpoints The list_gemini_agents, get_gemini_agent, delete_gemini_agent, and list_gemini_agent_versions endpoints previously constructed a hardcoded data dict with no mechanism to pass provider credentials. Unlike create_gemini_agent (POST, reads litellm_params_template from body), these GET/DELETE endpoints gave no way for multi-tenant callers to supply a per-request api_key or other LiteLLM params. Fix: - Add _merge_query_params_into_data() helper that reads query parameters from the request and merges them into the data dict without overwriting already-set keys (e.g. path params like 'name'). - Support a JSON-encoded litellm_params_template query parameter (matching the POST body pattern) as well as flat key=value pairs (e.g. api_key=AIza...). - Apply the helper in all four affected endpoints. - Add 13 unit tests covering the helper and each endpoint. Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com> * fix: pass model=None for managed agent proxy endpoints to prevent agent name polluting data["model"] Endpoints acreate_agent, aget_agent, adelete_agent, and alist_agent_versions were passing model=<agent_name> to base_process_llm_request. This caused common_processing_pre_call_logic to write the agent name into self.data["model"], which then triggered spurious model-alias mapping, rate-limiting lookups, and logging tied to a non-existent model deployment. The agent name is already carried in data["name"] and is passed correctly to the SDK functions (litellm.interactions.agents.*). There is no reason to also set model=<agent_name>; the correct value is model=None for all five managed-agent management routes. Adds tests/test_litellm/proxy/google_endpoints/test_managed_agents_model_param.py to verify all five managed-agent endpoints pass model=None. Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com> * fix: address greptile P1/P2 review comments P1 (router.py): Restore fallback/retry support for acreate_interaction and create_interaction. Both were silently moved to _init_interactions_api_endpoints (direct call, no fallbacks). Moved them back to _ageneric_api_call_with_fallbacks so users with configured fallback models keep retry behaviour. P1 security (agents_endpoints.py): Remove flat query-param credential path (e.g. ?api_key=AIza...) from _merge_query_params_into_data. Credentials in URL query strings appear verbatim in server access logs, CDN edge logs, and browser history. Only the JSON-encoded litellm_params_template query param (matching the POST body pattern) is retained. P2 (interactions/http_handler.py): Extract _BaseHTTPHandler with shared _handle_error, _sync_client, and _async_client helpers. InteractionsHTTPHandler now extends _BaseHTTPHandler. The _async_client reads the provider from litellm_params instead of hardcoding GEMINI. P2 (interactions/agents/http_handler.py): AgentsHTTPHandler now extends InteractionsHTTPHandler (which inherits _BaseHTTPHandler) so all shared HTTP infrastructure is reused rather than duplicated. Removes the hardcoded LlmProviders.GEMINI from the async client path. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: address CI failures from greptile review fixes - black: format interactions/agents/main.py and utils.py - tests: update test_gemini_agents_endpoints.py to match new _merge_query_params_into_data behaviour (flat credential params are rejected; only JSON-encoded litellm_params_template is accepted) - ci: add test_gemini_agents_endpoints.py to endpoints-and-responses shard in test-unit-proxy-db.yml so assert-shard-coverage passes - tests: add _initialize_managed_agents_endpoints and _init_managed_agents_api_endpoints test coverage so router_code_coverage passes; also fix TestRouterCreateInteractionRouting to reflect that acreate_interaction now correctly routes through _ageneric_api_call_with_fallbacks (restoring fallback support) Co-authored-by: Cursor <cursoragent@cursor.com> * fix: remove InteractionsHTTPHandler._handle_error override to fix type errors AgentsHTTPHandler extends InteractionsHTTPHandler and calls self._handle_error(provider_config=agents_api_config) where agents_api_config is BaseAgentsAPIConfig. Python MRO resolved _handle_error to InteractionsHTTPHandler._handle_error which expected BaseInteractionsAPIConfig, causing 10 mypy arg-type errors in interactions/agents/http_handler.py. Removing the redundant override lets both classes inherit _BaseHTTPHandler._handle_error (provider_config: Any) which is structurally correct for both config types. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: agent-only interactions and managed agents provider routing Resolve None custom_llm_provider in agents HTTP client lookup and set custom_llm_provider on GenericLiteLLMParams for all agent CRUD paths. Stop mapping agent names to proxy model routing; route interactions through _init_interactions_api_endpoints with fallbacks only when model is set. Consolidate duplicate router elif branches for interaction APIs. Co-authored-by: Cursor <cursoragent@cursor.com> * Fix greptile review * test(agents): add unit tests for managed agents SDK and HTTP handler Adds coverage for the new `litellm.interactions.agents` surface area: - main.py: sync/async entry points (create/list/get/delete/list_versions), provider config lookup, logging-obj helper, async error wrapping - http_handler.py: every CRUD method (sync + async paths), `_is_async` dispatch branches, and provider error mapping through GeminiAgentsConfig - utils.py: get_provider_agents_api_config for supported / unsupported providers Brings patch coverage on these files from <25% to ~100% so codecov/patch is satisfied. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * docs(gemini-agents): fix misleading credential-passing examples in GET/DELETE docstrings (#28293) The four GET/DELETE endpoint docstrings (list_gemini_agents, get_gemini_agent, delete_gemini_agent, list_gemini_agent_versions) documented passing per-request credentials as flat query parameters (e.g. ?api_key=AIza...). However, _merge_query_params_into_data only reads the JSON-encoded litellm_params_template query parameter and intentionally ignores flat params (URL query strings appear verbatim in access logs, browser history, and Referer headers). Callers following the documented curl examples would have their credentials silently dropped and hit auth failures against Gemini. Update the examples to use the supported JSON-encoded litellm_params_template query parameter, matching _merge_query_params_into_data's own docstring. Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * refactor(agents): rename provider-agnostic agent response types Move GeminiAgent{ListResponse,DeleteResult,VersionsResponse} to provider-neutral names (AgentListResponse, AgentDeleteResult, AgentVersionsResponse) so the BaseAgentsAPIConfig interface no longer references Gemini-specific type names. * fix(gemini-agents): close veria-flagged credential-escalation gaps Two high-severity findings from the veria-ai PR review are addressed: 1. **api_base override could leak the shared Gemini key** GeminiAgentsConfig.validate_environment falls back to GOOGLE_API_KEY / GEMINI_API_KEY when no api_key is supplied. Combined with caller-controlled api_base on the proxy CRUD endpoints, an authenticated user could redirect the outbound request to an attacker-controlled host and capture the operator's shared Gemini key from the x-goog-api-key header. The config now refuses env-fallback whenever api_base is explicitly overridden. 2. **Managed-agent CRUD exposed to ordinary LLM keys** The new /v1beta/agents routes live in google_routes (i.e. llm_api_routes), so any non-admin LLM key can reach them. Unlike /v1beta/models/...: generateContent these endpoints are NOT model-routed and have no model_list-supplied credentials, so env-fallback would let any LLM key list / create / delete agents inside the operator's Gemini project. Each endpoint now calls _enforce_caller_supplied_provider_key, which requires non-admin callers to supply their own Gemini api_key via litellm_params_template. Proxy admins keep the env-fallback convenience. Tests cover non-admin rejection, admin allow-through, the api_base override guard, and SDK env-fallback when api_base is not overridden. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * test(router): restore strict assert_called_once_with on interactions default-provider test --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> |
||
|
Mateo Wang
|
2e5ebf826f
|
fix(responses): register cooldowns on failure + fail fast on stale encrypted_content (#27820) | ||
|
Cursor Agent
|
40db114a23
|
fix(router): accept Pydantic LiteLLM_Params in encryption-boundary key lookup
Greptile flagged that the strict isinstance(dict) guard in
_encryption_boundary_key would silently return None for any non-dict input,
including a LiteLLM_Params Pydantic instance, which exposes a custom .get()
method and is intended to be used dict-style in some router paths. If such
an instance ever flowed into healthy_deployments, the guard would drop every
candidate from boundary matching and fall through to the full deployment
pool, i.e. trigger the exact invalid_encrypted_content failure this check
exists to prevent.
Loosen the guard to accept any object exposing a callable .get(): plain
dicts (the common case) and LiteLLM_Params-style Pydantic instances. The
function still returns None for non-dict-like values (None, lists, strings,
ints, bare objects).
Adds regression tests covering:
- LiteLLM_Params Pydantic instance resolves to the same boundary tuple as
an equivalent plain dict
- non-dict-like values and dicts missing required fields still return None
|
||
|
mateo-berri
|
f3b8aad883
|
fix(router): pin Responses API affinity to Azure resource on model-group switch
When a Responses API follow-up switches model_name (e.g. gpt-5.3-codex -> gpt-5.4, or to a LiteLLM-side alias of the same Azure deployment), the router has already filtered healthy_deployments to the new group, so the originating model_id is no longer present. The encrypted_content_affinity check would log "decoded deployment not found" and fall back to the full deployment pool, where simple-shuffle could land on a different Azure resource and trip a 400 invalid_encrypted_content. Fall back to pinning by the originating deployment's encryption boundary (api_base + api_key) when the model_id miss is across model groups. The encrypted_content travels with the Azure resource, not the model_name, so any deployment on the same resource accepts it. LIT-2531 |
||
|
mateo-berri
|
860f6b526e
|
Merge branch 'litellm_internal_staging' into litellm_access-group-routing-fix | ||
|
shivam
|
e72eac9176
|
Fix add_model_file_id_mappings when router returns single deployment dict
When model_info.id equals model_name (common for batch models), the router resolves via has_model_id and returns one deployment dict instead of a list. The dict branch incorrectly iterated deployment keys (model_name, litellm_params, model_info), producing non-string values that broke LiteLLM_ManagedFileTable validation on managed file upload. Normalize list vs dict by wrapping single deployments and extracting model_info.id for each response pair. Add regression tests including the batch model id == model_name case. Made-with: Cursor |
||
|
Sameer Kankute
|
a3da4721ca
|
test(router): add coverage for access-group deployment filter
Add a router utils unit test that directly exercises _filter_deployments_by_model_access_groups for access-group-only key permissions. Made-with: Cursor |
||
|
Ishaan Jaffer
|
e8461b5b97
|
style: run black formatter on files from main merge | ||
|
Sameer Kankute
|
3a4ed48f54
|
fix(router): don't create litellm_metadata for non-Responses API calls in encrypted_content_affinity_check (#25347)
Using setdefault('litellm_metadata', {}) unconditionally created an empty
litellm_metadata key for chat completions and embeddings. This caused
_get_metadata_variable_name_from_kwargs to return 'litellm_metadata' instead
of 'metadata', so tag-based routing looked for tags in the wrong dict and
ignored all tag filters.
Fix: only set the encrypted_content_affinity_enabled flag when litellm_metadata
already exists (Responses API path). Chat completions and embeddings never have
this key, so nothing is created and tag routing works correctly.
|
||
|
ishaan-berri
|
51876292a0
|
Litellm ishaan april4 2 (#25150)
* feat(router): integrate allowed_fails_policy into health check failures (#24988) * feat(router): integrate allowed_fails_policy into health check failures Health check failures now increment the same per-deployment failure counters used by allowed_fails_policy, so users can control how many health check failures of each error type are required before a deployment enters cooldown. - ahealth_check() preserves the original exception in its return dict - run_with_timeout() returns a litellm.Timeout on health check timeout - _perform_health_check() propagates exceptions to unhealthy endpoints - _write_health_state_to_router_cache() calls _set_cooldown_deployments for each unhealthy endpoint that has an exception - When allowed_fails_policy is set, the binary health check filter is bypassed so cooldown is the sole routing exclusion mechanism - Safety net: if all deployments are in cooldown with enable_health_check_routing=True, the cooldown filter is bypassed Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(router): add health_check_ignore_transient_errors flag When enabled, health check failures with 429 (rate limit) or 408 (timeout) status codes are skipped from the cooldown pipeline. These are transient load issues, not broken deployments. Auth errors (401), 404, and 5xx errors still increment counters and trigger cooldown as before. Config (general_settings): health_check_ignore_transient_errors: true Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(router): also exclude 429/408 from health state cache when ignore_transient_errors set The previous fix only skipped cooldown counter increments. The health state cache was still marking 429/408 endpoints as is_healthy=False, causing the binary health check filter to exclude them from routing. Now, when health_check_ignore_transient_errors=True, 429/408 endpoints are also excluded from the unhealthy list passed to build_deployment_health_states(), so the binary filter treats them as unaffected (not unhealthy). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs(router): add health check driven routing guide New standalone page covering the full health check routing feature: allowed_fails_policy integration, health_check_ignore_transient_errors, architecture SVG, step-by-step setup, and gotchas (TTL, AllowedFails semantics). Replaces the inline section in health.md with a link to the new page. Added to the Routing & Load Balancing sidebar. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(health-check-routing): fix three CI failures - Add "exception" to ILLEGAL_DISPLAY_PARAMS in health_check.py so the exception object is stripped before the health endpoint serializes results to JSON (fixes TypeError: 'URL' object is not iterable) - Add allowed_fails_policy = None to FakeRouter stubs in test_router_health_check_routing.py (fixes AttributeError) - Add health_check_ignore_transient_errors to config_settings.md router settings reference table (fixes documentation test) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Fix litellm/tests/proxy_unit_tests/test_proxy_server.py * fix(router): address greptile review comments - Narrow cooldown safety-net bypass: only fires when allowed_fails_policy is set (cooldown is health-check driven). Without a policy, cooldowns are from real request failures and must not be bypassed. - Restore cooldown deployments DEBUG log that was accidentally removed. - Fix test_health TypeError: move exception extraction to a separate exceptions_by_model_id dict returned alongside endpoints, so exception objects never appear in the endpoint dicts that get JSON-serialized by the /health response. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(health-check-routing): properly isolate exceptions from health response Return exceptions_by_model_id as a separate third value from _perform_health_check / perform_health_check so exception objects (which contain non-JSON-serializable httpx URL types) never appear in the endpoint dicts that get serialized by the /health response. Callers updated: _health_endpoints.py, shared_health_check_manager.py, proxy_server.py background loop. All use the exceptions dict only for cooldown integration, not for display. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(shared-health-check): fix remaining 2-value return sites and update type annotation * fix(health-check-routing): fix P0 cooldown integration never firing The cooldown loop was reading endpoint.get("exception") which is always None because exceptions are now returned via exceptions_by_model_id, not stored in endpoint dicts. Fixed to use _exceptions.get(model_id). Also fixes the transient-error filter to use _exceptions instead of endpoint.get("exception"), and fixes all remaining 2-value return sites in shared_health_check_manager.py. Tests updated to pass exceptions via exceptions_by_model_id parameter instead of endpoint dicts. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(health-check-routing): fix P1 transient-error filter broken on cache hits When SharedHealthCheckManager returns cached results, exceptions_by_model_id is always {} so the transient-error filter defaulted to status 500 for all endpoints, incorrectly marking 429/408 endpoints as unhealthy. Fix: store integer exception_status on each unhealthy endpoint dict in _perform_health_check. _get_endpoint_exception_status() uses the live exception object when available (direct path) and falls back to the stored integer (cache-hit path). The integer is JSON-serializable and survives the shared cache round-trip. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(health-check-routing): gate cooldown loop behind allowed_fails_policy Without the policy, cooldown is not the routing exclusion mechanism. Firing _set_cooldown_deployments for all enable_health_check_routing users was a backwards-incompatible change — 401s would immediately cooldown deployments that the binary filter would have recovered on the next cycle. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * revert: undo allowed_fails_policy gate on cooldown loop Cooldown integration via health checks is intentional for all enable_health_check_routing users, not just those with allowed_fails_policy. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(docs+tests): fix health_check_ignore_transient_errors doc section and test coverage - Move health_check_ignore_transient_errors from router_settings to general_settings in config_settings.md (code reads it from general_settings) - Remove duplicate enable_health_check_routing / health_check_staleness_threshold entries that were incorrectly listed under router_settings - Replace TestHealthCheckEndpointExceptionPropagation tests with ones that exercise the real _perform_health_check code path via mocked ahealth_check, verifying exceptions appear in exceptions_by_model_id and NOT in endpoint dicts Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(tests+docs): fix tuple unpacking and docs test failures - Update test mocks that return (healthy, unhealthy) to return (healthy, unhealthy, {}) to match the new 3-value signature - Update test unpackings of perform_shared_health_check to use healthy, unhealthy, _ = ... - Add health_check_ignore_transient_errors to router_settings section in config_settings.md (it is a Router constructor param, so the doc test requires it there; it also lives in general_settings for proxy use) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Fix CodeQL errors * fix(tests): fix 2-value unpackings of _perform_health_check in test_health_check.py * fix(tests): fix mock _perform_health_check returning 2-tuple instead of 3 * fix team routing --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: add distributed lock for key rotation job (#23364) * fix: add distributed lock for key rotation job * fix: address Greptile review feedback on key rotation lock (#23834) * fix: address Greptile review feedback on key rotation lock * fix req changes greptile * feat(proxy): Optional on_error for guardrail pipeline (API / technical failures) (#24831) * guardrails fallback * docs * docs: add LITELLM_KEY_ROTATION_LOCK_TTL_SECONDS to environment variables reference * fix(mypy): accept Union[Dict, Any] in _get_deployment_order and use typed list to fix min() type error * fix(mypy): use Optional[str] for api_base in PydanticAI provider to match superclass signature --------- Co-authored-by: Sameer Kankute <sameer@berri.ai> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Harshit Jain <48647625+Harshit28j@users.noreply.github.com> Co-authored-by: Shivam Rawat <shivam@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> |
||
|
Yuneng Jiang
|
fc32f91ffd
|
[Fix] Rename test file so router code coverage check detects it
The router_code_coverage.py script only scans test files with "router" in the filename. test_health_check_routing.py was invisible to this check, causing _async_filter_health_check_unhealthy_deployments and _filter_health_check_unhealthy_deployments to appear untested. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Sameer Kankute
|
7675488640
|
feat(router): add health-check-driven routing behind opt-in flag
Background health checks now feed deployment health state into the router candidate-filtering pipeline. Unhealthy deployments are excluded proactively instead of waiting for request failures to trigger cooldown. Gated by `enable_health_check_routing: true` in general_settings. Off by default — zero behavior change for existing users. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
Sameer Kankute
|
528daa8cf4 |
feat(router): add per-model-group deployment affinity configuration
Enable deployment_affinity, responses_api_deployment_check, and session_affinity to be configured per model group via router_settings.model_group_affinity_config, falling back to global settings for unconfigured groups. - Add model_group_affinity_config parameter to Router and DeploymentAffinityCheck - Add _get_effective_flags helper to resolve flags per model group - Update async_filter_deployments and async_pre_call_deployment_hook to use per-group config - Add 4 comprehensive tests covering per-group config, fallback, and override scenarios This allows fine-grained control of affinity behavior across model groups, e.g., enabling stickiness only for cross-provider deployments while leaving other groups free to load-balance. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com> |
||
|
yuneng-jiang
|
1092c17468 |
Fix flaky encrypted_content_affinity tests: mock at handler level
The 4 integration tests were flaky in CI because the AsyncHTTPHandler.post mock was bypassed when aiohttp transport is used. Mock at the higher BaseLLMHTTPHandler.async_response_api_handler level instead, which bypasses the HTTP layer entirely while still exercising router deployment selection, pre-call checks, and response post-processing (item ID rewriting). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
yuneng-jiang
|
67e905f0d0 |
Fix flaky encrypted_content_affinity tests: clear HTTP client cache, disable retries
Tests failed intermittently in CI (-n 8 workers) because cached AsyncHTTPHandler instances from other tests bypassed the class-level mock on AsyncHTTPHandler.post, causing real requests to OpenAI with mock API keys. Router retries (default 2) masked the root cause. - Add autouse fixture to flush litellm.in_memory_llm_clients_cache before/after each test so mocks always apply to fresh clients - Set num_retries=0 on all Router instances to surface mock failures immediately instead of silently retrying Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
Sameer Kankute
|
521f804350 | Fix encrypted content streaming affinity issue | ||
|
Sameer Kankute
|
2bc4da76ce | Update the tests | ||
|
Sameer Kankute
|
18bf3f2df6 | Fix mock github test | ||
|
Sameer Kankute
|
a88a17796b | Fix logging and encrypted content extraction | ||
|
Sameer Kankute
|
9f627c67d8 | Add tests for encrypted_content_affinity | ||
|
Sameer Kankute
|
394c49d303 | Add tests for encrypted_content_affinity | ||
|
Sameer Kankute
|
7cda0e4edd | Fix code qa | ||
|
Harshit Jain
|
456d8f5524 | feat: add session_id to have better routing | ||
|
Emerson Gomes
|
3dd55a7b61 | Merge main into affinity_callback and address deployment affinity review feedback | ||
|
Emerson Gomes
|
f7726c8950 | Fix wrong keys being used for model sticky entry | ||
|
Emerson Gomes
|
059e75ad88 |
fix(router): scope deployment affinity by model_map_key
- Key affinity by (user_api_key_hash, model_map_key) -> model_id - Ignore OpenAI 'user' param for affinity - Avoid double hashing user_api_key_hash - Add unit tests + docs clarifications |
||
|
Emerson Gomes
|
e23bd21a28 | Add deployment affinity routing | ||
|
Ishaan Jaff
|
539f629eff
|
[Feat] New Logging Integration - Azure Sentinel Logger (#18146)
* add AzureSentinelLogger * logging: AzureSentinelLogger * test_azure_sentinel_signature_and_send_batch * docs azure sentinel * fix AzureSentinelLogger * test fix * docs fix * fix: AzureSentinelLogger * docs sentintel * feat: add example SLP * docs sentinel * docs fix * docs fix * docs fix * fix code qa * QA fix * fix test * TestInitializeInteractionsEndpoints |
||
|
Cesar Garcia
|
7c2e2111c0
|
fix(router): handle tools=None in filter_web_search_deployments (#17684)
Fixes #17672 Changed `request_kwargs.get("tools", [])` to `request_kwargs.get("tools") or []` to handle the case where tools is explicitly set to None. |