* fix(invoke_handler.py): fix converse streaming - return signature + ensure consistency with anthropic api response
* build(model_prices_and_context_window.json): fix anthropic api claude-3-7 max output tokens
with beta header this is 128k
Resolves https://github.com/BerriAI/litellm/issues/8964
* feat(handler.py): handle new anthropic 'thinking_delta' block on streaming
Fixes https://github.com/BerriAI/litellm/issues/8825
* fix(transformation.py): support a 'format' parameter for image's
allow user to specify mime type
* fix: pass mimetype via 'format' param
* feat(gemini/chat/transformation.py): support 'format' param for gemini
* fix(factory.py): support 'format' param on sync bedrock converse calls
* feat(bedrock/converse_transformation.py): support 'format' param for bedrock async calls
* refactor(factory.py): move to supporting 'format' param in base helper
ensures consistency in param support
* feat(gpt_transformation.py): filter out 'format' param
don't send invalid param to openai
* fix(gpt_transformation.py): fix translation
* fix: fix translation error
* Fix missing signature_delta in thinking blocks when streaming from Claude 3.7 (#8797)
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* test: update test to enforce signature found
* feat(refactor-signature-param-to-be-'signature'-instead-of-'signature_delta'): keeps it in sync with anthropic
* fix: fix linting error
---------
Co-authored-by: Martin Krasser <krasserm@googlemail.com>
* fix(core_helpers.py): handle litellm_metadata instead of 'metadata'
* feat(batches/): ensure batches logs are written to db
makes batches response dict compatible
* fix(cost_calculator.py): handle batch response being a dictionary
* fix(batches/main.py): modify retrieve endpoints to use @client decorator
enables logging to work on retrieve call
* fix(batches/main.py): fix retrieve batch response type to be 'dict' compatible
* fix(spend_tracking_utils.py): send unique uuid for retrieve batch call type
create batch and retrieve batch share the same id
* fix(spend_tracking_utils.py): prevent duplicate retrieve batch calls from being double counted
* refactor(batches/): refactor cost tracking for batches - do it on retrieve, and within the established litellm_logging pipeline
ensures cost is always logged to db
* fix: fix linting errors
* fix: fix linting error
* fix(common_utils.py): handle $id in response schema when calling vertex ai
Fixes issue where `$id` present in response_schema was not accepted by vertex ai
* test(test_vertex.py): add unit test to ensure $id stripped out of vertex schema
* test(test_router_tag_routing.py): add unit test for tag-based routing on embeddings
* fix(router.py): pass request kwargs on async embeddings to async_get_available_deployment function
* fix(router.py): require request kwargs to always be passed in
ensures tag-based routing always works, across endpoints
* feat(langfuse_prompt_management.py): support using prompt management per langfuse project with key/team based logging
* fix: fix linting error
* fix: fix test
* fix: fix test
* fix: fix test
* fix: fix linting error
* fix(route_llm_request.py): move to using common router, even for client-side credentials
ensures fallbacks / cooldown logic still works
* test(test_route_llm_request.py): add unit test for route request
* feat(router.py): generate unique model id when clientside credential passed in
Prevents cooldowns for api key 1 from impacting api key 2
* test(test_router.py): update testing to ensure original litellm params not mutated
* fix(router.py): upsert clientside call into llm router model list
enables cooldown logic to work accurately
* fix: fix linting error
* test(test_router_utils.py): add direct test for new util on router
* add cookieUtils
* use utils for clearing cookies
* on logout use clearTokenCookies
* ui use correct clearTokenCookies
* navbar show userEmail on UserID page
* add timestamp on token cookie
* update generate_authenticated_redirect_response
* use common getAuthToken
* fix clearTokenCookies
* fixes for get auth token
* fix invitation link sign in logic
* Revert "fix invitation link sign in logic"
This reverts commit 30e5308cb3223981c715e723cdd3a6d2ee3aaa4b.
* fix getAuthToken
* update setAuthToken
* fix ui session handling
* fix ui session handler
* add cookieUtils
* use utils for clearing cookies
* on logout use clearTokenCookies
* ui use correct clearTokenCookies
* navbar show userEmail on UserID page
* fix(streaming_handler.py): fix deepseek reasoning content streaming
Fixes https://github.com/BerriAI/litellm/issues/8939
* test(test_streaming_handler.py): add unit test to streaming handle 'is_chunk_non_empty' function
ensures 'reasoning_content' is handled correctly
PostgreSQL treats unquoted identifiers as lowercase by default. In our query, we're using "DailyTagSpend" (with capital letters), but PostgreSQL will be looking for "dailytagspend" (all lowercase).
* fix(proxy_server.py): fix setting router redis cache, if cache enabled on litellm_settings
enables configurations like namespace to just work
* fix(redis_cache.py): fix key for async increment, to use the set namespace
prevents collisions if redis instance shared across environments
* fix load tests on litellm release notes
* fix caching on main branch (#8858)
* fix(streaming_handler.py): fix is delta empty check to handle empty str
* fix(streaming_handler.py): fix delta chunk on final response
* [Bug]: Deepseek error on proxy after upgrading to 1.61.13-stable (#8860)
* fix deepseek error
* test_deepseek_provider_async_completion
* fix get_complete_url
* bump: version 1.61.17 → 1.61.18
* bump: version 1.61.18 → 1.61.19
* vertex ai anthropic thinking param support (#8853)
* fix(vertex_llm_base.py): handle credentials passed in as dictionary
* fix(router.py): support vertex credentials as json dict
* test(test_vertex.py): allows easier testing
mock anthropic thinking response for vertex ai
* test(vertex_ai_partner_models/): don't remove "@" from model
breaks anthropic cost calculation
* test: move testing
* fix: fix linting error
* fix: fix linting error
* fix(vertex_ai_partner_models/main.py): split @ for codestral model
* test: fix test
* fix: fix stripping "@" on mistral models
* fix: fix test
* test: fix test
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* fix(prometheus.py): fix prometheus team metric to handle custom metrics
* fix(prometheus.py): fix prometheus metrics to handle custom metadata + team id
* fix(gpt_transformation.py): handle image url being sent as str to openai
* fix: fix unit testing
* fix(o_series_transformation.py): support passing image url as string for o models as well
* (UI) Error Logs improvements - Store Raw proxy server request for success and failure (#8917)
* ui render error logs
* add proxy_server_request to spend logs metadata
* _add_proxy_server_request_to_metadata
* proxy track cost callback fixes
* _add_proxy_server_request_to_metadata
* test spend logs
* test_async_post_call_failure_hook
* (UI) - Allow Internal Users to View their own logs (#8933)
* ui fix leftnav, allow internal users to view their own logs
* pass user_id in uiSpendLogs call
* ui filter logs for internal user
* fix internal users page
* ui show correct message when store prompts is disabled
* fix internal user logs
* test_ui_view_spend_logs_with_user_id
* test spend management endpoint
* ui new build
* Add `supports_pdf_input: true` for specific Bedrock Claude models (#8655)
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Takashi Iwamoto <takashi.iwamoto@enechange.co.jp>
Ishaan Jaff