test: handle fireworks ai instability

Add VertexAI Anthropic passthrough - cost calculation, token tracking (…

…BerriAI#11611)

* fix(vertex_ai/anthropic): extract vertex credentials from correct dict

Fixes passing credentials for vertex anthropic via `/v1/messages`

* fix(vertex_ai/anthropic): working e2e vertex ai anthropic messages via `/v1/messages`

Ensures vertex anthropic models can be called via /v1/messages

* fix(vertex_passthrough_logging_handler.py): fix vertex anthropic logging to emit the model name on spend logs

enables observability of passthrough route

* fix(vertex_passthrough_logging_handler.py): don't redefine variable

* fix(vertex_passthrough_logging_handler.py): log cost + token usage for anthropic passthrough requests on vertex ai

fix(streaming_handler.py): respect is_finished = False in hidden params

internal logic for preventing ending stream early

fix(proxy/_types.py): add budget reset at to litellm budget full table

(ui) new build

test fix test_aaauser_personal_budgets

build(config.yml): weaken grype check for nightly - python3.13 known …

…cve - blocked on chainguard to release a fix

Will call this out on release note, but this an upstream python3.13 issue  and shouldn't block nightly releases

feat: add add azure endpoint for image endpoints

[Fix]: /v1/messages - return streaming usage statistics when using li…

…tellm with bedrock models (BerriAI#11469)

* fix: using litellm with claude code bedrock

* fix: usage for bedrock with /messages

* fix: bedrock_sse_wrapper

* tests: test for test_chunk_parser_usage_transformation

* test fix

fix: gemini-2.0-flash-preview-image-generation test