Adds TestBedrockInvokeCacheTokenBilling covering the Bedrock InvokeModel path:
- baseline: no cache tokens, prompt_tokens equals input_tokens
- cache_read: prompt_tokens inflated by design, prompt_tokens_details carries breakdown
- cache_creation: same pattern for write tokens
- cost_calculation_correct_with_cache_read: core billing regression test
- cost_calculation_correct_with_cache_creation: write-rate billing regression test
- back_to_back_requests_cost: full end-to-end scenario (cache write then read)
These lock in the fix from PR #25517 - cache tokens were being double-counted
in AnthropicConfig.calculate_usage causing 10-50x inflated cost on cache reads.
Adds a GHA that fails PRs to main unless the head branch is
'litellm_internal_staging' or 'litellm_hotfix_*'. Also fails merge_group
events since merge queue is not in use.
Current fix includes
- Updates test case
- Optimized query with docstring. The change leverages deduplication and sorting logic from SQL
- Added a bench script to differentiate peak memory usage before and after
Mixtral-8x7B-Instruct-v0.1 is no longer on Together AI's serverless tier
and now requires a dedicated endpoint, causing multiple tests to fail in CI:
- test_together_ai.py::TestTogetherAI::test_empty_tools
- test_completion.py::test_completion_together_ai_stream
- test_completion.py::test_customprompt_together_ai
- test_completion.py::test_completion_custom_provider_model_name
- test_text_completion.py::test_async_text_completion_together_ai
Qwen/Qwen3.5-9B is currently serverless on Together AI and supports
function calling, satisfying BaseLLMChatTest capability requirements.
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Waiting to run
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py, 30, 8) (push) Waiting to run
The previous v1.83.3 changelog was generated against v1.83.0-nightly and
missed ~3 weeks of work. This regenerates it against the previous stable
release and restructures the LLM API Endpoints section to group by API
type (Responses, Batch, Count Tokens, Video Generation, Pass-Through,
etc.) matching the convention used in v1.82.3, v1.82.0, and v1.81.14.
Adds ~25 previously uncited PRs, cross-section duplications for
cross-cutting changes, and a verified first-time-contributors list.
- Add 8 content PRs that merged directly to the release branch outside the listed staging PRs: #23769 (Ramp callback), #25252 (JWT OAuth2 override), #25254 (AWS GovCloud mode), #25258 (batch-limit cleanup), #25334 (router custom_llm_provider), #25345 (Triton embeddings), #25347 (tag-based routing), #25358 (Baseten pricing attribution)
- Add @kedarthakkar to new contributors (first-ever PR via #23769)
- Update RELEASE_NOTES_GENERATION_INSTRUCTIONS: require walking git log range between release tags in addition to staging PRs, and verify new-contributor status per author rather than trusting the GH release body floor
Add 50 tests across 3 files covering the new MaskedHTTPStatusError,
safe response helpers, _redact_string in error paths, Gemini
interactions x-goog-api-key header auth, and RAG ingestion header
usage.
Fix missing early-validation for Gemini API key in _get_token_and_url()
which caused TypeError when key was None (headers got None value).
Harmonize error messages between the two validation sites.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Gemini API keys embedded in URLs as ?key= query parameters leak through
httpx error tracebacks, which are then captured by traceback.format_exc()
and forwarded to logging callbacks, Slack/Teams alerts, and HTTP client
responses.
Short-term: all httpx.HTTPStatusError handlers now raise
MaskedHTTPStatusError(...) from None, which masks the URL and breaks
exception chaining so the original error never appears in tracebacks.
Long-term: moved all Gemini/Vertex URL constructions from ?key={api_key}
to x-goog-api-key header (Google's documented auth method), so the key
is never in the URL at all. WebSocket realtime is the only exception
since WS clients cannot use custom headers.
Additionally hardened all outbound credential paths:
- WebSocket close reasons now pass through _redact_string()
- Callback pipeline (failure_handler) redacts traceback_exception and
error_str before forwarding to integrations (Langfuse, Datadog, etc.)
- Slack/Teams alert messages redacted in send_llm_exception_alert,
ProxyLogging.failure_handler, and post_call_failure_hook
- HTTP error responses in proxy SSE and health endpoints redacted
- Exception messages in exception_mapping_utils redacted
- print_verbose() stdout output redacted when set_verbose=True
- HTTPHandler.put() now has MaskedHTTPStatusError (was missing)
Pre-select "Internal User Viewer" in the Global Proxy Role dropdown
on both the standalone and embedded Invite User forms so admins don't
have to remember to pick a role, and the default lands on the least
privileged option rather than silently posting an undefined role.
user_dashboard.tsx imports getCookie from @/utils/cookieUtils, but the
vi.mock factory in user_dashboard.test.tsx only exports clearTokenCookies.
Vitest throws `No "getCookie" export is defined on the "@/utils/cookieUtils"
mock`, breaking all three beforeunload-listener tests.
Add getCookie to the mock factory so it matches the current imports.
The Logs view's Team ID filter dropdown was reading `allTeams` from the
root `teams` state in page.tsx, which the Teams page search overwrites
with its filtered subset. Applying a team search on the Teams page made
filtered-out teams disappear from the Logs filter dropdown.
Swap the Team ID filter to use the existing `TeamDropdown` component via
a small `FilterTeamDropdown` wrapper that adapts it to the filter slot's
`FilterOptionCustomComponentProps` contract. The dropdown now drives its
own `useInfiniteTeams` query against `/v2/team/list` with server-side
search and an isolated react-query cache, unreachable from root state.
Rename the now-unused `hookAllTeams` destructure to `allTeams` so the
`KeyInfoView` passthrough receives the hook's unpolluted fetch instead
of the polluted prop, and drop the dead `allTeams` prop from
`SpendLogsTable` and both of its call sites.
Vertex AI rejects requests containing both search tools (googleSearch,
enterpriseWebSearch, urlContext) and function declarations with error:
'Multiple tools are supported only when they are all search tools.'
When _merge_tools_from_deployment() combines deployment-level search
tools with user-request function tools (e.g. via MCP), the mixed tool
list causes a 400 error. This fix detects the conflict in _map_function()
and drops search tools, keeping function declarations.
Non-search tools like code_execution and computerUse are preserved.
Fixes#23337
* fix(router): discard oldest entry when trimming latency list in lowest_latency strategy
The lowest_latency routing strategy keeps a rolling window of the most
recent latency and time-to-first-token measurements per deployment. When
the window is full, the strategy was discarding the *newest* value
instead of the oldest, because the trim used
`[: max_latency_list_size - 1]` (keeping indices 0..N-2) rather than
`[1:]` (dropping index 0 and keeping indices 1..N-1).
Since new values are appended at the end, the bug meant the most recent
measurement was always dropped once the list reached capacity. The
routing decisions then relied on stale data (including any early-spike
values that never aged out), and timeout penalties written via
`async_log_failure_event` were silently discarded as well.
Fix the slice in all five call sites (sync + async log_success_event for
both latency and time_to_first_token, and async_log_failure_event for
the timeout penalty) and add regression tests covering each path.
* test(router): cover async TTFT trim path in lowest_latency regression tests
Adds test_ttft_list_trimming_discards_oldest_entry_async, an async
counterpart to test_ttft_list_trimming_discards_oldest_entry that drives
async_log_success_event with a ModelResponse and completion_start_time so
the async time_to_first_token trim branch is actually exercised.
Previously no test touched that code path: the sync TTFT test used
log_success_event, and the async latency test passed a plain dict
response_obj without stream/completion_start_time, so TTFT was never
computed and the async trim was unreached. Verified load-bearing by
reverting only the async TTFT slice — the new test fails and all others
pass.
* format
