* fix(pricing): add unversioned vertex_ai/claude-haiku-4-5 entry
Missing unversioned entry causes cost tracking to return $0.00 for
all requests using vertex_ai/claude-haiku-4-5. All other Vertex AI
Claude models have both versioned and unversioned entries.
* fix(router): skip misleading tags error when no candidates (e.g. cooldown)
Return early from get_deployments_for_tag when healthy_deployments is empty so
tag-based routing does not raise no_deployments_with_tag_routing after cooldown
filters all deployments. Adds regression test.
Made-with: Cursor
* feat(oci): add embedding support and update model catalog
- Add OCIEmbeddingConfig for OCI GenAI embedding models
- Add 16 new chat models (Cohere, Meta Llama, xAI Grok, Google Gemini)
- Add 8 embedding models (Cohere embed v3.0, v4.0)
- Update documentation with embedding examples
- Update pricing for all new models
* test(oci): add unit tests for OCI embedding support
- 17 unit tests covering OCIEmbeddingConfig
- Tests for URL generation, param mapping, request/response transform
- Tests for model pricing JSON completeness
* style(oci): format with black and ruff
* fix(oci): correct embedding request body format
OCI embedText API expects inputs, truncate, and inputType at the
top level of the request body, not nested under embedTextDetails.
Fixed transformation and updated tests accordingly.
Verified with real OCI API: 3/3 embedding models working.
* docs: clarify tag routing early return and test intent
Made-with: Cursor
* fix(oci): address code review findings from Greptile
- P1: Fix signing URL mismatch with custom api_base by accepting
api_base parameter in transform_embedding_request
- P2: Remove encoding_format from supported params (OCI does not
support it, was silently dropped)
- P2: Raise ValueError for token-array inputs instead of silently
converting to string representation
- Add test for token-list rejection
* fix(mcp): add STS AssumeRole support for MCP SigV4 authentication
MCPSigV4Auth only supported static AWS credentials or the boto3 default
credential chain. Production Kubernetes environments typically authenticate
via IAM role assumption (sts:AssumeRole), which was not possible.
Add aws_role_name and aws_session_name parameters to the MCP SigV4 auth
stack. When aws_role_name is provided, MCPSigV4Auth calls sts:AssumeRole
to obtain temporary credentials before signing requests. Explicit keys,
if also provided, are used as the source identity for the STS call;
otherwise ambient credentials (pod role, instance profile) are used.
* fix: stop logging credential values and add missing redaction patterns
Replaces raw credential values in debug/error log messages with
boolean presence checks or type names. Adds PEM block, GCP token,
JWT, SAS token, and service-account blob patterns to the redaction
filter. Fixes private_key pattern to capture full PEM blocks instead
of stopping at the first whitespace.
Addresses: Vertex AI credential JSON (including RSA private key)
being logged to stderr on health check failures.
* fix: log only field names for UserAPIKeyAuth, not full object
* style: apply black formatting to experimental_mcp_client/client.py
* style: fix black/isort formatting and mypy error in proxy_server.py
- Fix black formatting in experimental_mcp_client/client.py (done in prev commit)
- Fix black/isort formatting in key_management_endpoints.py, proxy_server.py, transformation.py
- Fix mypy: iterate over optional list safely (access_group_ids or []) in proxy_server.py
* fix(test): patch check_migration.verbose_logger directly to fix xdist ordering issue
When test_proxy_cli.py tests run before test_check_migration.py in the same
xdist worker, litellm.proxy.db.check_migration is already in sys.modules.
Patching litellm._logging.verbose_logger has no effect on the already-bound
reference. Patch the correct target (check_migration.verbose_logger) and
import the module before patching so the order doesn't matter.
* fix(mypy): make api_base Optional in PydanticAIProviderConfig to match base class signature
---------
Co-authored-by: Ihsan Soydemir <soydemir.ihsan@gmail.com>
Co-authored-by: Milan <milan@berri.ai>
Co-authored-by: Daniel Gandolfi <danielgandolfi@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
Co-authored-by: user <70670632+stuxf@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
Tests cover: matching deployments, wrong team_id filtering, string-encoded
model_info, empty results, invalid model_info, and mixed deployment filtering.
Also updates MockPrismaClient.find_many to support the new startswith query.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add brave/search to model_prices_and_context_window.json (#25042)
Brave Search is supported by litellm as a search provider (documented at
docs.litellm.ai/docs/search/brave and listed in provider_endpoints_support.json)
but was missing from model_prices_and_context_window.json, making it invisible
to any code that discovers search providers from litellm.model_cost.
Cost: $0.005/query ($5 per 1,000 requests) per https://brave.com/search/api/
* feat(models): add NVIDIA Nemotron 3 Super 120B on Bedrock (#24588)
* feat(models): add NVIDIA Nemotron 3 Super 120B on Bedrock
Add model definition for nvidia.nemotron-3-super-120b-a12b-v1 via
Bedrock Converse API with pricing, context window (256k/32k), and
capability flags (function calling, tool choice, system messages).
* fix model ID to nvidia.nemotron-super-3-120b + add tests
Correct the Bedrock model ID from nvidia.nemotron-3-super-120b-a12b-v1
(NVIDIA's internal name) to nvidia.nemotron-super-3-120b (the actual
AWS Bedrock programmatic model ID). Add unit tests verifying model
resolution, pricing, and context window.
* fix(proxy): allow JWT auth for /v1/mcp/server sub-paths (#24698)
mcp_routes only contained "/v1/mcp/server" (exact match). Starlette's
compile_path produces an end-anchored regex, so sub-paths like
/register, /health, /submissions, /oauth/* all failed the JWT
allowed_routes_check. Add a {path:path} wildcard entry so all
sub-paths are covered.
---------
Co-authored-by: Daniel Yudelevich <4537920+yudelevi@users.noreply.github.com>
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
Adds tenant_id, client_id, and client_secret to the Azure provider entry
in provider_create_fields.json so the credential add/edit modals and the
add-model form surface Service Principal auth as an alternative to api_key.
The Azure handler already reads these fields from litellm_params at request
time via get_azure_ad_token(); this change makes them inputtable from the
UI without code changes to the React components (the form is driven by
GET /public/providers/fields).
Replace per-ID _resolve_access_group_resources loop with a single
find_many call that deduplicates IDs across all teams. Removes the
N+1 query pattern on cold cache for the team list endpoint.
Three tests were patching the non-existent `get_access_object` instead
of `_get_access_object` (the lazy-import wrapper), causing AttributeError.
Also added missing `prisma_client` mock so tests get past the early-exit
guard and actually exercise the resolution logic.
* Litellm ishaan april1 (#25103)
* fix(proxy): enforce upperbound key params on key/update and add custom_key_update hook
The /key/update endpoint did not enforce upperbound_key_generate_params,
allowing users to bypass configured limits (tpm_limit, rpm_limit,
max_budget, duration, budget_duration) by updating an existing key
instead of generating a new one.
Extract the upperbound enforcement logic from _common_key_generation_helper()
into a standalone _enforce_upperbound_key_params() function and call it from
both the generate and update paths. For updates, None values are skipped
(not filled with defaults) since they mean "don't change this field".
Also adds a custom_key_update config option and user_custom_key_update global,
mirroring the existing custom_key_generate pattern, so custom key validation
logic can fire during key updates as well.
* fix(proxy): invoke custom_key_update hook in bulk update path
The user_custom_key_update hook was only called in update_key_fn
(single key update) but not in _process_single_key_update (bulk
update path), allowing custom validation to be bypassed via the
/key/update/bulk endpoint. Mirror the hook invocation in both paths.
* fix(proxy): pass UpdateKeyRequest to hook in bulk path, not BulkUpdateKeyRequestItem
Move the custom_key_update hook invocation to after UpdateKeyRequest
is constructed so the hook receives the same type in both single and
bulk update paths. Previously the bulk path passed
BulkUpdateKeyRequestItem (5 fields only), which would cause
AttributeError for hooks accessing fields like tpm_limit or models.
* fix(bedrock): promote cache usage to message_delta for Claude Code (#24850)
Ensure Bedrock/Anthropic-compatible streaming exposes cache usage where Claude Code reads it by promoting message_stop usage onto message_delta and preserving usage fields in fake-streamed message_delta events.
Made-with: Cursor
* fix(search): Support self-hosted Firecrawl response format in search transform (#24866)
The `transform_search_response` method only handled Firecrawl Cloud (v2)
response format where `data` is a dict with `web`/`news` keys. Self-hosted
Firecrawl (v1) returns `data` as a flat list of result objects, causing an
`AttributeError: 'list' object has no attribute 'get'`.
Detect the response format by checking if `data` is a list (self-hosted)
or dict (cloud) and handle both cases.
Cloud format: {"data": {"web": [...], "news": [...]}}
Self-hosted: {"success": true, "data": [{"url": "...", "title": "...", ...}]}
Co-authored-by: Synergy <synergyoclaw@gmail.com>
* feat: add environment and user tracking to prompt management (#24855)
* feat: add environment and user tracking to prompt management
- Add environment (development/staging/production) and created_by columns to LiteLLM_PromptTable
- Update unique constraint to [prompt_id, version, environment]
- All CRUD endpoints support environment filtering and user tracking
- Redesigned prompt detail page with environment tabs and version history
- UI: environment filter on list page, environment selector in editor
- 8 new tests for environment and user tracking
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: Black formatting and add environments to PromptInfoResponse TypeScript type
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address Greptile review findings
- P1: delete_prompt scopes in-memory cleanup to environment when provided
- P2: dotprompt_content parsed directly regardless of environment flag
- P2: use distinct for environments query
- P2: fix double-fetch on initial mount in prompt_info.tsx
- fix: remove unsupported select kwarg from find_many
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address remaining Greptile review comments
- Remove unused useCallback import (index.tsx)
- Remove unused ENV_COLORS variable (prompt_info.tsx)
- P1: in-memory fallback in get_prompt_versions now respects environment filter
- P1: reset selectedEnv when promptId changes to avoid stale state
- Cyclic imports are pre-existing pattern, not introduced by this PR
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: scope patch_prompt to environment using primary key
- Add environment query param to patch_prompt endpoint
- Look up target row by composite key (prompt_id + version + environment)
- Update by primary key (id) to target exactly one row
- Fixes Greptile finding: patch with multiple environments no longer ambiguous
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use actual start_time for failed request spend logs (#24906)
async_post_call_failure_hook set both start_time and end_time to
datetime.now(), making all failed requests show duration=0. Use the
actual start_time from litellm_logging_obj instead, so spend logs
reflect the real request duration on timeout and other failures.
Fixes#24888
* feat(bedrock): add nova canvas image edit support (#24869)
* feat(bedrock): add nova canvas image edit support
* fix(bedrock): support PathLike inputs for nova image edit
* chore: sync schema.prisma copies from root
* fix(mypy): correct type-ignore code for delta_usage arg-type
* fix(mypy): cast status_code to str, suppress intentional str yield
* fix(lint): extract _create_content_block_chunks to fix PLR0915
* fix(lint): extract helpers to fix PLR0915 in prompt endpoints
---------
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: redhelix <amin.lalji@gmail.com>
Co-authored-by: Synergy <synergyoclaw@gmail.com>
Co-authored-by: Talha Anwar <37379131+talhaanwarch@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: madhu19991 <madhu@thunkai.com>
Co-authored-by: Srikanth @adobe <devarakondasrikanth@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(test): update model armor streaming test to handle string or int error code
---------
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: redhelix <amin.lalji@gmail.com>
Co-authored-by: Synergy <synergyoclaw@gmail.com>
Co-authored-by: Talha Anwar <37379131+talhaanwarch@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: madhu19991 <madhu@thunkai.com>
Co-authored-by: Srikanth @adobe <devarakondasrikanth@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
When Model Armor blocks a streaming response, it correctly raises
HTTPException(status_code=400) but create_response() catches it with a
bare except Exception and hardcodes a 500 response, discarding the
original status code.
Fix create_response() to preserve status_code from HTTPException instead
of hardcoding 500. Also update Model Armor's streaming hook to yield an
SSE error event instead of raising (matching the Prisma Airs pattern),
and fix make_model_armor_request() to return 400 for upstream API
failures instead of passing through the upstream status code.
* fix(proxy): enforce key-level model allowlist for custom auth
custom_auth_run_common_checks only runs common_checks (team/user/project model checks).
Custom auth now also enforces key-level model restrictions via can_key_call_model.
Move the custom-auth key-access regression tests to test_user_api_key_auth.py and keep test_custom_auth_end_user_budget.py focused on end-user budget behavior.
Made-with: Cursor
* fix(proxy): gate custom-auth key model checks behind opt-in
Keep key-level model allowlist enforcement in custom auth behind `custom_auth_run_common_checks` to preserve backwards compatibility, and update tests to verify default non-enforcement and opt-in enforcement behavior.
Made-with: Cursor
* test(proxy): isolate custom auth default check from shared settings state
Patch `proxy_server.general_settings` to an empty dict in the default custom-auth key-access test so it remains deterministic under shared module state.
Made-with: Cursor
* test(proxy): strengthen custom auth post-check assertions
Tighten custom auth regression tests by asserting exact can_key_call_model args and remove an unused common_checks mock from the default behavior path.
Made-with: Cursor
* fix(agentcore): parse A2A JSON-RPC responses in AgentCore provider
* fix(prompt-templates): ensure_alternating_roles handles tool-call chains
* feat(auth): add JWT claim routing overrides for OAuth2 validation
Made-with: Cursor
* docs(auth): document JWT-to-OAuth2 routing overrides
Add generic docs for running JWT and OAuth2 together, including routing_overrides YAML examples and list-based selector behavior for iss/client_id/aud.
Made-with: Cursor
---------
Co-authored-by: Milan <milan@berri.ai>
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
- Fetch each access group object once and extract all 3 resource fields
in a single pass instead of 3 separate calls (3N → N lookups)
- Use asyncio.gather to resolve access groups across teams concurrently
in list_team_v2 instead of sequential awaits
- Add 5 unit tests for _resolve_access_group_resources
* update bedrock models in tests
* updated more tests and model_prices_and_context_window
* fix model id and pricing
* replace more sonnet models
* update tests
* git push
* update pricing
* flaky total cost
* monkey patch
* relax the cost change
* fix and revert some changes
* revert the pricing
* chore: move cost/pricing changes to bedrock-cost-fixes branch
* chore: split Bedrock file-api beta stripping to separate branch
Removes strip_unsupported_file_api_betas_for_bedrock_invoke from this branch;
see litellm_bedrock_invoke_strip_file_api_betas for that fix.
Made-with: Cursor
Resolve conflicts between pinned versions and main's caret ranges,
keeping exact pins. Add pytest-cov==5.0.0 from main. Regenerate
poetry.lock.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
pytest-asyncio 1.x no longer provides an implicit event loop in sync
fixtures/tests. Make async-dependent fixtures and tests async, and
replace deprecated asyncio.get_event_loop() in tests. Switch
Dockerfile.build_from_pip from Alpine to Debian slim since
pyroscope-io 0.8.x has no musl wheels.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
asyncio.create_task in CSW.__anext__ scheduled the deferred logging
callback as an independent task that raced with unified_guardrail's
end-of-stream block. For short-stream providers (Vertex AI, Azure,
Anthropic), the logging fired before guardrail_information was written,
causing post_call guardrail entries to be missing from
StandardLoggingPayload.
Move the deferred callback trigger from CSW.__anext__ to
ProxyLogging.async_post_call_streaming_iterator_hook (after the full
streaming pipeline completes). CSW now stores the assembled response
args; the outer consumer fires the callback after all guardrail
end-of-stream blocks finish. Also skip apply_guardrail guardrails in
_run_deferred_stream_guardrails to eliminate duplicate API calls.
CI fails because LITELLM_MASTER_KEY is not set, causing
encrypt_value_helper to error on NoneType.encode(). Patch it
to pass through values unencrypted in the test.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Skip the integration test that requires a live proxy and OPENAI_API_KEY
(removed from CI/CD). Add deterministic mock test covering the same
add → delete → double-delete-fails lifecycle.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PR #24755 renamed `azure_api_key_header` to `AZURE_AI_API_KEY_header` in
the test file but did not update the actual function signatures of
`get_api_key()` and `_user_api_key_auth_builder()`, causing TypeError
on all affected test cases.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Substring matching for user_id and key_alias on /key/list is now gated
by caller role (admin only) rather than by whether user_id was auto-set.
This closes the gap where a non-admin explicitly passing their own
user_id still got contains-based filtering, which could surface keys
belonging to other users with overlapping IDs.
Adds three unit tests covering the substring, exact-match, and default
code paths in _build_key_filter_conditions. Restores the existing
member-team test to assert exact matching as a security regression guard.
Substring matching for user_id and key_alias now applies unconditionally.
The admin-only flag was unnecessary since user_ids are typically UUIDs/emails
where substring collisions are not a practical concern. Updated existing test
to assert the new filter structure.
Models associated with a team only through access groups (not directly in
team.models) were not appearing on the /ui/?page=models page. The API
authorization path already resolved access groups correctly, but the
/v2/model/info listing endpoint only checked team.models.
Add _add_access_group_models_to_team_models() which batch-fetches all
distinct access groups in a single find_many query, then resolves each
team's access group models into deployments and merges them into the
team_models dict.
Fix agent health check tests failing with 500 errors in parallel CI by
mocking prisma_client to None. Fix documentation validation tests using
CWD-relative paths that break depending on the working directory.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When fastest_response=true with comma-separated models, the response
model field was stamped with the entire comma-separated string. Now
uses the x-litellm-model-group header from the winning response to
return the correct model name.
Made-with: Cursor
Add DEFAULT_MANAGEMENT_OBJECT_IN_MEMORY_CACHE_TTL to both async_set_cache
calls in sync_user_role_and_teams for consistency with all other user cache
writes. Add 3 tests covering cache invalidation on role change, team change,
and no-op when nothing changes.
Add None-token test cases to both proxy_unit_tests and test_litellm
to cover the guard added in the previous commit. Also add -> bool
return type annotation to is_jwt().
During SSO login, bearer tokens are stripped from the OAuth response
before role mapping runs. Custom role claims encoded inside the JWT
access token are lost, so map_jwt_role_to_litellm_role() returns None
and the user falls back to internal_user_viewer.
process_sso_jwt_access_token() now returns the decoded JWT payload, and
a new _sync_user_role_from_jwt_role_map() receives it so
jwt_litellm_role_map works correctly during SSO login.
Budget checks on API keys, teams, and team members were not enforced in
multi-pod deployments because user_api_key_cache is intentionally
in-memory-only. Each pod tracked spend independently, so with N pods
the effective budget was N × max_budget.
Introduces a separate spend_counter_cache (DualCache wired to
redis_usage_cache) with atomic increment/read helpers:
- increment_spend_counters(): awaited in cost callback (not create_task)
to update both in-memory and Redis before the next auth check
- get_current_spend(): reads Redis first (cross-pod authoritative),
falls back to in-memory, then to cached object .spend from DB
Budget check functions (_virtual_key_max_budget_check,
_team_max_budget_check, _check_team_member_budget) now read spend via
get_current_spend() instead of cached object .spend fields.
When Redis is not configured, falls back to in-memory-only counters
(same as current single-instance behavior).
Fixes#23714
- Remove HTTP_PROXY/HTTPS_PROXY from blocklist (legitimately used in corporate envs)
- Add NO_PROXY/no_proxy to blocklist (prevents bypassing proxy monitoring)
- Remove dead code in _is_valid_user_id (space exception was unreachable)
- Update tests accordingly
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add input validation to get_user_id_from_request (length limit, control char rejection) and a blocklist of dangerous environment variable keys in _load_environment_variables to prevent PATH/LD_PRELOAD/PYTHONPATH override via config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Cache LITELLM_ENABLE_TEAM_STALE_ALIAS_BYPASS at module level to avoid hot-path secret lookups
- Add clarifying comments for should_include_deployment team isolation logic
- Add negative assertion for update_team.assert_not_called() in test
- Add docstring clarification for _get_team_deployments helper pattern
- Add explicit assertion message in test_get_model_list_alias_optimization
Made-with: Cursor
- Use O(1) team index lookup instead of map_team_model in alias guard
- Fix MockPrismaClient to validate where clause filters
- Add comment explaining DB query trade-off for team deployments
Made-with: Cursor
- Skip model_aliases rewrite if model resolves to team deployments
- Add test coverage for sibling-preservation branch
- Update MockPrismaClient to support sibling deployment scenarios
Made-with: Cursor
