* test(proxy/proxy_server): pin forwarding routes (PR2) (#28887)
* test(proxy): pin proxy_server.py forwarding-route behavior
PR2 of the proxy_server.py behavior-pinning project: fills the 12
forwarding-route test files added by the harness PR with happy + error
pins for all 52 LLM-facing routes (models, chat/completions, completions,
embeddings, moderations, audio, assistants, threads, utils, model-info,
model-metrics, queue). Every happy-path test asserts the full response
dict via normalize() so the gate enforces real shape pinning rather
than status codes.
* test(proxy): drop task-plumbing comments from PR2 test files
* test(proxy): tighten PR2 error-path status-code pins
Apply the same review feedback Greptile gave on PR1 (#28856) and PR3
(#28850) to PR2's forwarding-route tests:
- Replace permissive `>= 400` / `in (X, Y)` status assertions with the
exact 500/405 the handler actually returns, so a regression that
silently shifts the code now fails the pin.
- Add a body-presence check alongside each tightened status assertion
to satisfy _pin_check.py's no-status-only rule.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* test(proxy): pin proxy_server.py non-route surface behavior (PR1) (#28856)
* test(proxy): pin proxy_server.py non-route surface behavior (PR1)
Fills the 7 PR1 placeholder files under tests/test_litellm/proxy/proxy_server/
with behavior pins for the non-route surface of proxy_server.py:
lifecycle/init/shutdown, ProxyConfig class methods, DB-overlay config scrubbers,
spend counters, background-health helpers, OpenAPI customization, exception
handlers, and streaming-generator helpers.
233 tests cover 101 pin-list symbols (1+ happy + 1+ error each). New-tests-only
coverage on litellm/proxy/proxy_server.py: 32.80% line / 20.91% branch (PR1
gate: 25% line / 18% branch). Full directory runs in ~22s with -n 4.
Plan: https://www.notion.so/Plan-Pin-proxy_server-py-behavior-2026-05-25-36c43b8acdab81ee845fd5365128a2fc
* test(proxy): address Greptile review comments on test_lifecycle.py
- test_initialize_signature_is_async_with_expected_params: hard-code
expected_param_count so a signature change actually trips the gate
(previously both sides of the comparison were len(sig.parameters)).
- test_check_request_disconnection_invalid_when_connected_times_out:
patch asyncio.sleep so the test no longer spins for ~1.2 s of real
wall-clock; timeout lowered to 0.05 s.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* test(proxy/proxy_server): pin control-plane routes (PR3) (#28850)
* test(proxy/proxy_server): pin misc routes (PR3, partial)
Adds happy + error tests for the misc control-plane routes:
GET /, /routes, /adaptive_router/state, /get_logo_url,
/get_image, /get_favicon.
Also gitignores .pin_list.txt (used by the pin gate).
* test(proxy/proxy_server): pin login/SSO routes (PR3, partial)
Adds happy + error tests for the 5 login/SSO control-plane routes:
GET /fallback/login, POST /login, POST /v2/login, POST /v3/login,
POST /v3/login/exchange. Mocks authenticate_user and
create_ui_token_object at their imported location.
* test(proxy/proxy_server): pin onboarding routes (PR3, partial)
Adds happy + error tests for the 2 onboarding control-plane routes:
GET /onboarding/get_token, POST /onboarding/claim_token. Wires a
MagicMock async context manager for prisma_client.db.tx() and
signs the onboarding JWT with the patched master_key.
* test(proxy/proxy_server): pin model_cost_map reload routes (PR3, partial)
Adds happy + error tests for the 5 model-cost-map control-plane routes:
POST /reload/model_cost_map, POST|DELETE|GET
/schedule/model_cost_map_reload(/status), GET /model/cost_map/source.
Attaches litellm_config to mock_prisma per-test (the table is not in
the default _PRISMA_TABLES fixture).
* test(proxy/proxy_server): pin anthropic_beta_headers reload routes (PR3, partial)
Adds happy + error tests for the 4 anthropic-beta-headers control-plane
routes: POST /reload/anthropic_beta_headers, POST|DELETE|GET
/schedule/anthropic_beta_headers_reload(/status). Stubs
db.litellm_config (not in default _PRISMA_TABLES) and monkeypatches
reload_beta_headers_config so no network calls fire.
* test(proxy/proxy_server): pin invitation routes (PR3, partial)
Adds happy + error tests for the 4 invitation control-plane routes:
POST /invitation/new, GET /invitation/info, POST /invitation/update,
POST /invitation/delete. Patches _user_has_admin_privileges /
_user_has_admin_view to avoid extensive get_user_object mocking.
* test(proxy/proxy_server): pin config CRUD routes (PR3, partial)
Adds happy + error tests for the 8 config-CRUD control-plane routes:
POST /config/update, POST|GET /config/field/update|info, GET /config/list,
POST /config/field/delete, POST /config/callback/delete,
GET /get/config/callbacks, GET /config/yaml. Attaches litellm_config
to mock_prisma per-test.
* test(proxy/proxy_server): tighten pin assertions per review
- test_routes_misc.py: `b"" in response.content` is trivially true;
replace with `len(response.content) > 0` so an empty 405 body trips
the gate.
- test_routes_login_sso.py: `len(response.content) >= 0` is trivially
true; tighten to `> 0`.
- test_routes_anthropic_beta.py: replace brittle string-literal checks
on the serialized JSON (`'"interval_hours": 12' in payload`) with
`json.loads` + dict access so the assertion survives any serializer
spacing.
- test_routes_config.py: `assert status_code in (404, 500)` was too
permissive; the handler re-raises HTTPException(404) verbatim, so
pin 404 strictly.
---------
Co-authored-by: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add AWS ECS Fargate stack with Aurora Postgres (IAM auth), ElastiCache Redis, S3, ALB with path-based routing to gateway/backend/ui components, Application Auto Scaling, and automated DB bootstrap + prisma migration via local-exec provisioners
- Add GCP Cloud Run stack with Cloud SQL Postgres (password auth), Memorystore Redis, GCS, external HTTPS load balancer with serverless NEGs and URL map routing, and automated prisma migration via Cloud Run Job
- Both stacks support typed proxy_config input mirroring the helm chart's gateway.config.proxy_config, per-component extra env vars, and Secret Manager references for provider API keys
- Gateway/backend services depend on terraform_data.migration so they never start before the schema is in place, eliminating crash-loop windows on first apply
- AWS stack uses IAM database authentication with a one-shot Fargate bootstrap task that creates and grants the rds_iam role to the application user; GCP stack uses password auth assembled at container startup to avoid Cloud SQL Auth Proxy sidecar complexity
- Add .gitignore rules for Terraform state files, plan files, tfvars inputs, provider binaries, and crash logs while explicitly keeping .terraform.lock.hcl for provider version pinning
- Include terraform.tfvars.example files, provider lock files, and comprehensive README documentation covering architecture, TLS setup, image pull strategies, and quick-start instructions for both stacks
Co-authored-by: Yassin Kortam <yassinkortam@g.ucla.edu>
* Refactor Bedrock response stream shape handling
- Introduced a module-level constant `BEDROCK_RESPONSE_STREAM_SHAPE` to cache the response stream shape, eliminating the need for per-instance caching in `BedrockEventStreamDecoderBase`.
- Updated relevant methods to utilize the new constant, improving performance by avoiding redundant loading of the shape.
- Added tests to ensure the shape is loaded correctly at import time and is consistent across different modules.
- Added a new mock server script for testing Bedrock pass-through functionality.
* Refactor response parsing for Bedrock and SageMaker
- Improved code readability by formatting the parsing method calls in `AWSEventStreamDecoder` for both Bedrock and SageMaker response stream shapes.
- Added blank lines for better separation of code blocks in `invoke_handler.py` and `common_utils.py` to enhance maintainability.
* Enhance error handling for Bedrock and SageMaker response stream shape loading
- Wrapped the loading logic in `_load_bedrock_response_stream_shape` and `_load_sagemaker_response_stream_shape` with try-except blocks to gracefully handle exceptions.
- Added logging to warn when the response stream shape cannot be pre-loaded, ensuring the module imports cleanly.
- Updated tests to verify that loading failures return `None` instead of propagating exceptions.
* Implement error handling for missing response stream shapes in Bedrock and SageMaker
- Added checks in `_parse_message_from_event` methods to raise appropriate errors when `BEDROCK_RESPONSE_STREAM_SHAPE` or `SAGEMAKER_RESPONSE_STREAM_SHAPE` is None, ensuring clearer error reporting.
- Updated logging messages to reflect the unavailability of event-stream decoding for both Bedrock and SageMaker.
- Enhanced unit tests to verify that the correct exceptions are raised when the response stream shapes are not loaded.
- New reusable workflow that spins up a LiteLLM container from the
release image, exposes it via cloudflared tunnel, and triggers
test runs on the Railway-hosted observatory
- Integrates into ghcr_deploy.yml for RC and stable releases
- Can also be triggered manually via workflow_dispatch
- Add placeholder litellm_config.yaml for observatory test models
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add /v1/vector_store/list route for OpenAI API compatibility (fixes test_routes_on_litellm_proxy)
- Fix Bedrock Converse API model format (bedrock_converse/ → bedrock/converse/)
- Fix Nova Premier inference profile prefix (amazon. → us.amazon.)
- Add STABILIZATION_TODO.md to .gitignore
Tested locally - all affected tests now pass
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(vector_stores/): initial commit adding Vertex AI Search API support for litellm
new vector store provider
* feat(vector_store/): use vector store id for vertex ai search api
* fix: transformation.py
cleanup
* fix: implement abstract function
* fix: fix linting error
* fix: main.py
fix check
* Get the basics of the integration working.
* Cleanup bytez integration.
* Update user agent for Bytez integration.
* Use the config class directly. Create the start of the docs.
* Finish up bytez documentation. Include a provider integration guide.
* Fix typing bug in custom_logger_utils. Add tests for bytez integration.
* Add token tracking for model usage for Bytez integration.
* Create a units test for the Bytez config.
* Make changes to Bytez transformation code per PR feedback.
* Cleanup coment in Bytez transformation test.
* Remove LRU usage for bytez integration.
* Consolidate Bytez tests into a single file. Conform to project structure for tests.
* Fix linting error with Bytez impl.
* Schedule budget resets at expectable times (#10331)
* Enhance budget reset functionality with timezone support and standardized reset times
- Added `get_next_standardized_reset_time` function to calculate budget reset times based on specified durations and timezones.
- Introduced `timezone_utils.py` to manage timezone retrieval and budget reset time calculations.
- Updated budget reset logic in `reset_budget_job.py`, `internal_user_endpoints.py`, `key_management_endpoints.py`, and `team_endpoints.py` to utilize the new timezone-aware reset time calculations.
- Added unit tests for the new reset time functionality in `test_duration_parser.py`.
- Updated `.gitignore` to include `test.py` and made minor formatting adjustments in `docker-compose.yml` for consistency.
* Fixed linting
* Fix for mypy
* Fixed testcase for reset
* fix(duration_parser.py): move off zoneinfo - doesn't work with python 3.8
* test: update test
* refactor: improve budget reset time calculation and update related tests for accuracy
* clean up imports in team_endpoints.py
* test: update budget remaining hours assertions to reflect new reset time logic
* build(model_prices_and_context_window.json): update model
---------
Co-authored-by: Prathamesh Saraf <pratamesh1867@gmail.com>
* build(litellm-proxy-extras/utils.py): correctly generate baseline migration for non-empty db
* fix(litellm-proxy-extras/utils.py): Fix issue in migration, where if a migration fails during baselining, all are still marked as applied
* fix(prisma_client.py): don't pass separate schema.prisma to litellm-proxy-extras
use the one in litellm-proxy-extras
* fix(litellm-proxy-extras/utils.py): support passing custom dir for baselining db in read-only fs
Fixes https://github.com/BerriAI/litellm/issues/9885
* fix(utils.py): give helpful warning message when permission denied error raised in fs
* build(model_prices_and_context_window.json): add vertex ai gemini-2.5-flash pricing
* build(model_prices_and_context_window.json): add gemini reasoning token pricing
* fix(vertex_and_google_ai_studio_gemini.py): support counting thinking tokens for gemini
allows accurate cost calc
* fix(utils.py): add reasoning token cost calc to generic cost calc
ensures gemini-2.5-flash cost calculation is accurate
* build(model_prices_and_context_window.json): mark gemini-2.5-flash as 'supports_reasoning'
* feat(gemini/): support 'thinking' + 'reasoning_effort' params + new unit tests
allow controlling thinking effort for gemini-2.5-flash models
* test: update unit testing
* feat(vertex_and_google_ai_studio_gemini.py): return reasoning content if given in gemini response
* test: update model name
* fix: fix ruff check
* test(test_spend_management_endpoints.py): update tests to be less sensitive to new keys / updates to usage object
* fix(vertex_and_google_ai_studio_gemini.py): fix translation
* test(base_llm_unit_tests.py): add test to ensure drop params is respected
* fix(types/prometheus.py): use typing_extensions for python3.8 compatibility
* build: add cherry picked commits
* fix message.error
* fix add return_wildcard_routes
* ui edit modelAvailableCall
* fetchAvailableModelsForTeamOrKey
* ui set all models for a team
* ui define common helpers
* edit create key button
* fix viewing model display names
* fix editing team models
* update gitignore
* add jest testing for ui
* Revert "add jest testing for ui"
This reverts commit 98f9a3ebfd.
* fix(ui/): revert user team key view
* fix(view_key_table.tsx): fix default team view - show all personal keys
* fix(navbar.tsx): fix custom logo
Fixes https://github.com/BerriAI/litellm/issues/7895
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* fix(utils.py): e2e azure tts cost tracking working
moves tts response obj to include hidden params (allows for litellm call id, etc. to be sent in response headers) ; fixes spend_Tracking_utils logging payload to account for non-base model use-case
Fixes https://github.com/BerriAI/litellm/issues/7223
* fix: fix linting errors
* build(model_prices_and_context_window.json): add bedrock llama 3.3
Closes https://github.com/BerriAI/litellm/issues/7329
* fix(openai.py): fix return type for sync openai httpx response
* test: update test
* fix(spend_tracking_utils.py): fix if check
* fix(spend_tracking_utils.py): fix if check
* test: improve debugging for test
* fix: fix import
* refactor: move gemini translation logic inside the transformation.py file
easier to isolate the gemini translation logic
* fix(gemini-transformation): support multiple tool calls in message body
Merges https://github.com/BerriAI/litellm/pull/6487/files
* test(test_vertex.py): add remaining tests from https://github.com/BerriAI/litellm/pull/6487
* fix(gemini-transformation): return tool calls for multiple tool calls
* fix: support passing logprobs param for vertex + gemini
* feat(vertex_ai): add logprobs support for gemini calls
* fix(anthropic/chat/transformation.py): fix disable parallel tool use flag
* fix: fix linting error
* fix(_logging.py): log stacktrace information in json logs
Closes https://github.com/BerriAI/litellm/issues/6497
* fix(utils.py): fix mem leak for async stream + completion
Uses a global executor pool instead of creating a new thread on each request
Fixes https://github.com/BerriAI/litellm/issues/6404
* fix(factory.py): handle tool call + content in assistant message for bedrock
* fix: fix import
* fix(factory.py): maintain support for content as a str in assistant response
* fix: fix import
* test: cleanup test
* fix(vertex_and_google_ai_studio/): return none for content if no str value
* test: retry flaky tests
* (UI) Fix viewing members, keys in a team + added testing (#6514)
* fix listing teams on ui
* LiteLLM Minor Fixes & Improvements (10/28/2024) (#6475)
* fix(anthropic/chat/transformation.py): support anthropic disable_parallel_tool_use param
Fixes https://github.com/BerriAI/litellm/issues/6456
* feat(anthropic/chat/transformation.py): support anthropic computer tool use
Closes https://github.com/BerriAI/litellm/issues/6427
* fix(vertex_ai/common_utils.py): parse out '$schema' when calling vertex ai
Fixes issue when trying to call vertex from vercel sdk
* fix(main.py): add 'extra_headers' support for azure on all translation endpoints
Fixes https://github.com/BerriAI/litellm/issues/6465
* fix: fix linting errors
* fix(transformation.py): handle no beta headers for anthropic
* test: cleanup test
* fix: fix linting error
* fix: fix linting errors
* fix: fix linting errors
* fix(transformation.py): handle dummy tool call
* fix(main.py): fix linting error
* fix(azure.py): pass required param
* LiteLLM Minor Fixes & Improvements (10/24/2024) (#6441)
* fix(azure.py): handle /openai/deployment in azure api base
* fix(factory.py): fix faulty anthropic tool result translation check
Fixes https://github.com/BerriAI/litellm/issues/6422
* fix(gpt_transformation.py): add support for parallel_tool_calls to azure
Fixes https://github.com/BerriAI/litellm/issues/6440
* fix(factory.py): support anthropic prompt caching for tool results
* fix(vertex_ai/common_utils): don't pop non-null required field
Fixes https://github.com/BerriAI/litellm/issues/6426
* feat(vertex_ai.py): support code_execution tool call for vertex ai + gemini
Closes https://github.com/BerriAI/litellm/issues/6434
* build(model_prices_and_context_window.json): Add 'supports_assistant_prefill' for bedrock claude-3-5-sonnet v2 models
Closes https://github.com/BerriAI/litellm/issues/6437
* fix(types/utils.py): fix linting
* test: update test to include required fields
* test: fix test
* test: handle flaky test
* test: remove e2e test - hitting gemini rate limits
* Litellm dev 10 26 2024 (#6472)
* docs(exception_mapping.md): add missing exception types
Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183
* fix(main.py): register custom model pricing with specific key
Ensure custom model pricing is registered to the specific model+provider key combination
* test: make testing more robust for custom pricing
* fix(redis_cache.py): instrument otel logging for sync redis calls
ensures complete coverage for all redis cache calls
* (Testing) Add unit testing for DualCache - ensure in memory cache is used when expected (#6471)
* test test_dual_cache_get_set
* unit testing for dual cache
* fix async_set_cache_sadd
* test_dual_cache_local_only
* redis otel tracing + async support for latency routing (#6452)
* docs(exception_mapping.md): add missing exception types
Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183
* fix(main.py): register custom model pricing with specific key
Ensure custom model pricing is registered to the specific model+provider key combination
* test: make testing more robust for custom pricing
* fix(redis_cache.py): instrument otel logging for sync redis calls
ensures complete coverage for all redis cache calls
* refactor: pass parent_otel_span for redis caching calls in router
allows for more observability into what calls are causing latency issues
* test: update tests with new params
* refactor: ensure e2e otel tracing for router
* refactor(router.py): add more otel tracing acrosss router
catch all latency issues for router requests
* fix: fix linting error
* fix(router.py): fix linting error
* fix: fix test
* test: fix tests
* fix(dual_cache.py): pass ttl to redis cache
* fix: fix param
* fix(dual_cache.py): set default value for parent_otel_span
* fix(transformation.py): support 'response_format' for anthropic calls
* fix(transformation.py): check for cache_control inside 'function' block
* fix: fix linting error
* fix: fix linting errors
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* ui new build
* Add retry strat (#6520)
Signed-off-by: dbczumar <corey.zumar@databricks.com>
* (fix) slack alerting - don't spam the failed cost tracking alert for the same model (#6543)
* fix use failing_model as cache key for failed_tracking_alert
* fix use standard logging payload for getting response cost
* fix kwargs.get("response_cost")
* fix getting response cost
* (feat) add XAI ChatCompletion Support (#6373)
* init commit for XAI
* add full logic for xai chat completion
* test_completion_xai
* docs xAI
* add xai/grok-beta
* test_xai_chat_config_get_openai_compatible_provider_info
* test_xai_chat_config_map_openai_params
* add xai streaming test
---------
Signed-off-by: dbczumar <corey.zumar@databricks.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Corey Zumar <39497902+dbczumar@users.noreply.github.com>
