- Route publisher/model ids (e.g. xai/grok) to .../endpoints/openapi; keep model in JSON body
- Add model_prices keys for vertex_ai/openai/xai/grok-*
- Document xAI Grok on vertex_partner (aligned with GPT-OSS)
- Add tests for create_vertex_url and body-model heuristic
Made-with: Cursor
Success handlers already run when CustomStreamWrapper or
CachedResponsesAPIStreamingIterator finishes replay. Logging at
cache-hit time for acompletion/completion streaming duplicated spend
and callbacks. Align tests with deferred behavior.
Made-with: Cursor
_base_process_chunk only encodes response IDs when parsed_chunk contains
a top-level "response" key. Align test_process_chunk_completed_response_
updates_id_and_usage_cost with that contract and test_base_responses_api_streaming_iterator.
Made-with: Cursor
The test supplies a minimal PDF base64 payload but expected the wrong
constant (base64 for "test"). Assert against the same pdf_b64 value
and drop the unused import.
Made-with: Cursor
* fix(bedrock): handle document content blocks in Converse API message conversion
Document content blocks (used for PDF support) were silently dropped
during message conversion for Bedrock's Converse API. The content block
processing loop only handled text, image_url, and file types — document
blocks were skipped without warning, causing the model to respond as if
no document was provided.
Adds document block handling in three locations:
- Sync user message processing (_bedrock_converse_messages_pt)
- Async user message processing (_bedrock_converse_messages_pt_async)
- Tool result conversion (_convert_to_bedrock_tool_call_result)
Fixes#24641
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use _validate_format for proper MIME type to Bedrock format mapping
Address Greptile review: naive media_type.split("/")[1] produced invalid
Bedrock format names for complex MIME types (e.g. OOXML → docx, text/plain
→ txt, text/markdown → md). Now reuses BedrockImageProcessor._validate_format
which handles all MIME types correctly via mimetypes + fallback.
Also fixes test assertions to expect correct Bedrock format values and adds
text/plain and text/markdown test cases.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: reject non-base64 document sources with a clear error
URL-type document sources (e.g. {"type": "url", "url": "..."}) would
crash with an opaque KeyError on missing 'media_type'. Guard at the top
of _process_document_message and raise a clear ValueError since Bedrock
Converse only supports base64-encoded document sources.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The /v2/model/info endpoint (used by the UI's Models + Endpoints page)
was not resolving access group names when filtering models by team.
When a team has models: ["Group-A"] where "Group-A" is an access group,
_filter_models_by_team_id() passed it as a literal model name to
get_model_list(), which found no deployments with that name. This caused
the UI to show all models instead of only team-accessible ones.
The request-time auth path (model_in_access_group in auth_checks.py)
correctly resolves access groups via get_model_access_groups(). This
fix applies the same resolution in _filter_models_by_team_id() for both
the in-memory router lookup and the database fallback query.
Tests added:
- test_filter_resolves_access_group_names
- test_filter_resolves_mix_of_access_groups_and_literal_names
- test_filter_excludes_models_from_other_access_group
- test_filter_db_fallback_receives_resolved_model_names
The previous fix for the TOCTOU bypass relied on a per-instance asyncio.Lock,
which closed the window only within a single proxy worker. Multi-replica
deployments still raced across processes — A and B both read counter=99,
both passed validation, both incremented to 100/100 → effective limit doubled.
Add `CHECK_AND_INCREMENT_BY_N_SCRIPT` Lua script that processes any number of
(window_key, counter_key, limit, increment, ttl) descriptors atomically with
all-or-nothing semantics: if any descriptor would exceed its limit, no counter
is modified and the script returns OVER_LIMIT with the offending descriptor's
state. When Redis isn't configured, the in-memory fallback uses the existing
asyncio.Lock for single-process atomicity.
Expose this as `_PROXY_MaxParallelRequestsHandler_v3.atomic_check_and_increment_by_n`
and rewire both call sites:
- batch_rate_limiter._check_and_increment_batch_counters: replace the
read_only=True check + separate async_increment_tokens_with_ttl_preservation
with a single atomic call passing the batch's (request_count, total_tokens)
as the increment.
- dynamic_rate_limiter_v3._check_rate_limits: bundle model_saturation_check
(always enforced) and priority_model (enforced only when saturated) into
one atomic call. When priority is unenforced, increment its counter via
the existing should_rate_limit(read_only=False) path for tracking only.
Update structural regression tests to assert the new atomic path is used
rather than the legacy two-phase pattern.
Tests: 4/4 TOCTOU tests pass, 59 existing rate-limiter tests pass, no
regressions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The batch rate limiter (`_check_and_increment_batch_counters`) and the
dynamic rate limiter (`_check_rate_limits`) implemented rate limiting in
two disjoint awaits: a `should_rate_limit(read_only=True)` check followed
by a separate increment. Concurrent requests could all observe the same
pre-increment state, all pass enforcement, and all then increment —
multiplying the effective quota by the concurrency level.
Demonstrated bypass (see new test):
- Batch: 5 concurrent batches of 40 tokens each against TPM=100 consumed
200 tokens (100% over).
- Dynamic: 5 concurrent priority="high" requests against RPM=2 all
passed Phase 1 + Phase 3.
Wrap both critical sections in a per-instance asyncio.Lock so the read
and increment execute atomically within a process. Multi-replica
deployments still rely on Redis Lua atomicity for cross-process safety;
that is a follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
vcrpy's aiohttp stub captures response bodies via 'await response.read()',
which drains aiohttp's StreamReader. Downstream consumers of the same
ClientResponse (litellm's AiohttpResponseStream, which iterates
response.content.iter_chunked) then see an empty body and surface as
JSON 'Expecting value: line 1 column 1 (char 0)' errors on every
record-path call.
The previous workaround set litellm.disable_aiohttp_transport=True for
the whole VCR-active session, which made the tests exercise pure httpx
instead of the production aiohttp transport. That hid the production
transport from coverage and surfaced its own bugs (e.g. the Azure
DELETE-with-empty-body case fixed in upstream staging).
Replace the workaround with a targeted monkey-patch that re-feeds the
captured body into the StreamReader via unread_data after vcrpy records
it. Tests now run through the same transport customers do, both on
first record and on replay, for both unary and streaming endpoints.
Verified locally against api.anthropic.com with the production
LiteLLMAiohttpTransport: record path passes (real network, 4.2s),
replay path passes (Redis cache, 1.8s).
The Anthropic replay tests hardcoded specific token counts and content
strings ('Hello! How can I help you today?', prompt_tokens == 12). On a
fresh CI Redis those values must match a pre-recorded cassette that
doesn't exist, so the first run hits the live API and gets different
real bytes back.
Assert on shape instead: non-empty content, positive token counts,
finish_reason in the known set, and (for streaming) more than one chunk.
The tests still exercise the full transformation pipeline end-to-end and
catch shape regressions; drift in the exact text/token counts is
expected and now tolerated.
When model_info.id equals model_name (common for batch models), the router
resolves via has_model_id and returns one deployment dict instead of a list.
The dict branch incorrectly iterated deployment keys (model_name,
litellm_params, model_info), producing non-string values that broke
LiteLLM_ManagedFileTable validation on managed file upload.
Normalize list vs dict by wrapping single deployments and extracting
model_info.id for each response pair.
Add regression tests including the batch model id == model_name case.
Made-with: Cursor
Azure OpenAI's responses-API DELETE endpoint rejects requests that carry
a JSON body with: "Unexpected body with size 2. This API method does
not accept a request body.". The default LiteLLMAiohttpTransport silently
elides empty-dict bodies on DELETE so this was masked, but the pure-httpx
transport (used when DISABLE_AIOHTTP_TRANSPORT=True or under vcrpy/respx
patching) sends literal '{}' (2 bytes), which Azure rejects.
Only attach json= when the provider's transform actually returned a
non-empty dict; otherwise issue a bodyless DELETE.
litellm's default LiteLLMAiohttpTransport routes requests through aiohttp,
which sits below httpx and is invisible to vcrpy's httpx-stub interception.
Under vcrpy + aiohttp, requests reach the real network but responses come
back through the stubbed httpx transport as empty 200s, surfacing as
'Unable to get json response - Expecting value: line 1 column 1 (char 0)'
in providers like Anthropic, Gemini, and any other path that exercises the
aiohttp transport.
Disabling the aiohttp transport when the VCR persister is registered
forces all calls through pure httpx, which vcrpy can record and replay
correctly.
The async/sync delete_response_api_handler always passed json=data into
httpx.delete, where data is {} from the transformer. httpx serializes that
to a 2-byte body. The Azure Responses DELETE endpoint now rejects any
request body with code: unexpected_body, breaking
test_basic_openai_responses_delete_endpoint on the llm_responses_api_testing
job. Build the kwargs dict and only set json= when data is truthy.
Add unit tests that patch httpx.delete and assert json/data are not in the
captured kwargs for the Azure DELETE path (sync and async).
