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)
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#25506
* address greptile review feedback
* [Test] UI - Models: Add E2E tests for Add Model flow
Add E2E tests covering:
- Test connection with bad credentials shows failure modal
- Adding a specific model and verifying it appears in All Models table
- Adding a wildcard route and verifying it appears in All Models table
- Verifying model dropdown shows provider-specific models (existing test updated)
Added data-testid attributes to UI components to support stable test selectors.
Tests verified passing 3/3 consecutive runs with zero flakiness.
* address greptile review feedback (greploop iteration 1)
Add cleanup helper to delete models created during tests, preventing
stale data accumulation across repeated test runs.
* fix CI: replace data-testid selectors with text/role-based selectors
The data-testid attributes added to React components are not present
in the CI-built UI output. Switch to using getByRole and getByText
selectors which work with the rendered DOM regardless of build cache.
* remove unnecessary cleanup helper
The database is freshly seeded on every test run via seed.sql,
so per-test cleanup is not needed.
---------
Co-authored-by: Yuneng Jiang <yuneng@berri.ai>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
* fix: emit input_json_delta for tool args bundled in first streaming chunk
Some providers (xAI, Gemini) include tool_call function arguments in the
same streaming chunk as the function name/id. The AnthropicStreamWrapper
was discarding the trigger chunk entirely when starting a new content
block, which silently dropped the input_json_delta carrying tool
arguments. This caused tool_use blocks to arrive with empty input {}.
Now queue the processed_chunk after content_block_start when it carries
non-empty input_json_delta data. Backward compatible: providers that send
empty arguments in the first chunk (OpenAI-style) are unaffected since
the condition checks for truthy partial_json.
* test: add tests for input_json_delta emission on bundled tool args
Covers the fix for providers (xAI, Gemini) that bundle tool_call
arguments in the same streaming chunk as the function name/id.
Verifies the AnthropicStreamWrapper emits input_json_delta after
content_block_start, and that empty-arg chunks (OpenAI-style) are
unaffected.
* style: apply Black formatting to streaming_iterator.py
* fix: mirror input_json_delta fix to sync __next__ and add sync tests
* test: make no_extra_delta tests assert explicitly instead of passing silently
Extend existing test modules with coverage for the instructions merge
logic, upstream cache, ContextVar-based injection, and client-side
capture — following each file's established patterns.
Made-with: Cursor
Block cross-team key update/regenerate operations by raising when the caller is not a member of the target key's team, and add unit coverage for deny/allow team membership paths.
Made-with: Cursor
- Omit messages whose list content is empty after stripping thinking blocks
- Retry only on HTTP 400 plus invalid-signature body match
- Return response inline from retry loop; drop unreachable None guard
- Tests: thinking-only turn dropped, non-400 no retry
Made-with: Cursor
Strip thinking blocks from the request body and retry once when Anthropic returns an invalid thinking signature error (e.g. after credential or deployment change). Applies to all BaseAnthropicMessagesConfig providers (direct Anthropic, Bedrock, Vertex, Azure AI).
Made-with: Cursor
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
* feat: add litellm.compress() for BM25-based context compression
Adds a compress() utility that reduces context size for LLM calls using
BM25 relevance scoring (with optional semantic embeddings via
litellm.embedding()). Messages below a token threshold pass through
unchanged; messages above are scored, ranked, and the lowest-relevance
ones replaced with stubs. Originals are cached and a retrieval tool is
injected so the model can recover dropped content on demand.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(compress): truncate high-scoring messages instead of fully stubbing them
When a relevant message was too large to fit in the token budget it was
replaced with a stub, leaving the LLM with no real content to work with.
Now the highest-scoring overflow message is truncated (first 70% + last 30%
of words) to fill the remaining budget, so the LLM always receives actual
content rather than just a retrieval pointer.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(bm25): add prefix expansion so query terms match inflected doc tokens
"cook" now matches "cooking", "auth" matches "authentication", etc.
Without this, short query terms scored 0 against longer inflected forms
in documents, causing the wrong message to be kept.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add routing correctness test and eval harness for litellm.compress()
- test_simple_compression: parametrized test verifying BM25 routes the
right message based on query ("How to cook?" keeps cooking, "Fix auth"
keeps auth content)
- eval_compression.py: end-to-end eval harness comparing baseline vs
compressed model performance on HumanEval-style coding problems
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(eval): add SWE-bench Lite compression eval harness
Uses princeton-nlp/SWE-bench_Lite_bm25_27K which bundles ~27k tokens of
BM25-retrieved repo context per problem — large enough to meaningfully
stress litellm.compress() without Docker or GitHub API calls.
Proxy eval metrics (no test runner needed):
- has_diff: model produced a valid unified diff
- file_overlap: fraction of gold-patch files in generated patch
- exact_file_match: generated patch touches exactly the right files
Run: python tests/eval_swe_bench.py --model gpt-4o --problems 10
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(eval): robust dataset loading + sys.path fix for worktree imports
- Add HuggingFace API fallback so the SWE-bench loader doesn't need
the `datasets` library (avoids pyarrow/numpy binary compat issues)
- Insert repo root into sys.path so compression module resolves
from worktrees
- Use direct import of litellm_compress to avoid __getattr__ issues
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* improve compression quality: line-based truncation, multi-message budget, 70% default target
- Switch truncate_message from word-based to line-based splitting to
preserve code structure (function boundaries, indentation)
- Allow multiple messages to be truncated instead of burning entire
budget on one overflow message
- Raise default compression target from 50% to 70% of trigger for
better quality/cost tradeoff
- Add --compression-target CLI arg to SWE-bench eval harness
- Move tests to canonical locations (tests/test_litellm/, scripts/)
- Add docs page and sidebar entries for compress()
Eval results (5 problems, Opus, trigger=10k):
Hunk overlap delta improved from -0.417 to -0.221
Content similarity now matches baseline (+0.006)
Cost savings: 72%
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add SWE-bench performance results to compress() docs
Include benchmark table from Opus eval (5 problems, trigger=10k)
showing 72% cost savings with file-level quality fully preserved.
Add metric explanations and eval runner examples.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(eval): use tolerance-based hunk overlap metric
The exact line-number matching was too brittle — LLM-generated patches
often target the right code region but with slightly offset line numbers.
Switch to hunk-level overlap with a 10-line tolerance window so nearby
edits count as matches. This better reflects actual patch quality.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add compression_interception callback for LiteLLM Proxy
Add a proxy callback that automatically compresses incoming /v1/messages
payloads above a configurable token threshold, runs the retrieval tool
loop server-side, and returns the final response. This brings compress()
support to proxy deployments (e.g. Claude Code via /v1/messages).
- New callback: litellm/integrations/compression_interception/
- Proxy config: compression_interception_params in litellm_settings
- Support for input_type param in compress() (openai vs anthropic)
- Docs: proxy setup instructions with YAML config example
- Tests: 139-line unit test suite for the interception handler
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Revert "feat: add compression_interception callback for LiteLLM Proxy"
This reverts commit 72bd5cb152.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Previously these were silently dropped with a verbose warning, which
could break observability integrations without surfacing a clear error.
Now raises ValueError with remediation steps (configure server-side
or pass the resolved value) so callers get immediate, actionable feedback.
- Only use_chat_completions_api and openai/chat_completions/ opt into the bridge
- Extract MCP gateway and file_search emulation dispatch to cut responses() size
- Update docs and tests
Made-with: Cursor
- Add use_chat_completions_api (keep use_responses_api_bridge as deprecated alias)
- Support openai/chat_completions/<model> model prefix for the same behavior
- Forward use_chat_completions_api in file_search emulation inner calls
- Update response_api.md and extend unit tests
Made-with: Cursor
- Add automatic conversion of Vertex AI batch prediction JSONL to OpenAI format
- Preserve custom_id via Vertex AI labels for request correlation
- Fix Content-Length header mismatch in transformed responses
- Add comprehensive tests for batch output transformation
Made-with: Cursor
Brings the date-range branch in line with the non-date-range branch which
already hashes sk- prefixed tokens before querying. Adds coverage for
filter-combination behavior in view_spend_logs.
