Gating the mock testing request params behind
general_settings.dangerously_allow_mock_testing_request_params (#35423) turned
every fallback, retry and timeout drill in tests/test_fallbacks.py into a 400:
the build_and_test job mounts proxy_server_config.yaml, which never opted in.
Opt that config in. It is the config the CI proxy runs with, and the suite it
serves exists to drive synthetic failures.
Add a unit test that ties the two together: it scans the top-level tests/test_*.py
files build_and_test globs for gated param names and fails if the config they run
against has not opted in, so the next change to either side is caught in a fast
lint-tier job rather than a Docker E2E.
* fix(proxy): build redis usage cache from REDIS_* env when cache backend is not Redis
Selecting a semantic (or any non-Redis-KV) response cache left
redis_usage_cache unset, silently downgrading cross-pod rate limits,
parallel-request limits, spend coordination, and the pod lock manager
to per-pod in-memory state. Fall back to a standalone RedisCache built
from REDIS_* environment variables, mirroring the existing
use_redis_transaction_buffer escape hatch, which now shares the same
helper.
Resolves LIT-3861
* feat(proxy): configure the coordination redis independently of the response cache
Adds general_settings.coordination_redis, an explicit block for the Redis
the proxy uses for cross-pod rate limits, parallel-request limits, spend
tracking, the pod lock manager, and shared health checks. Resolution order
is the explicit block, then a plain-Redis response-cache backend, then the
REDIS_* environment. Cluster and sentinel targets are supported, and a
cluster target now builds a RedisClusterCache so cluster-aware consumers
take the cluster path.
Admins can configure it from the Caching page of the dashboard via
/coordination_redis/settings, which reports which source is in effect,
redacts credentials on read, and offers a connection test. Settings saved
there are read back at startup so they take effect on restart.
Also fixes redis client construction so an explicitly configured host
outranks REDIS_URL in the environment. Previously the url branch stripped
the caller's host and port, so an explicit block, or a connection test
typed into the dashboard, silently targeted whatever REDIS_URL named
* fix(ui): move coordination_redis_settings into renamed _components directory
---------
Co-authored-by: Yucheng Zhu <yucheng@berri.ai>
Several CI jobs run the proxy against a model whose api_base is a shared
"fake OpenAI endpoint" hosted on Railway
(exampleopenaiendpoint-production.up.railway.app) so the E2E runs return
canned responses without paying for or depending on a live provider. When
that single deployment is down, every one of those jobs fails with
"404 Application not found" even though nothing in the PR is broken; the
whole repo is coupled to the uptime of one free external service.
This adds tests/_fake_openai_endpoint_server.py, a small canned-response
OpenAI-shaped server (chat, text, embeddings, streaming with usage, and the
"429" rate-limit special case), and a reusable start_fake_openai_endpoint
CircleCI command that runs it on host port 8190 and waits until healthy. The
affected jobs now inject FAKE_OPENAI_API_BASE pointing at the local server,
and the example configs they mount resolve api_base from that env var. The
intentionally bad fallback URL in proxy_server_config.yaml is left untouched
so the fallback test still exercises a failing upstream.
Wired into build_and_test, litellm_router_testing,
db_migration_disable_update_check, proxy_logging_guardrails_model_info_tests,
proxy_spend_accuracy_tests, proxy_multi_instance_tests,
proxy_store_model_in_db_tests, and proxy_build_from_pip_tests.
* feat(bedrock): add bedrock mantle gemma 4 models (#30264)
* feat(bedrock): add bedrock mantle gemma 4 models
* test(bedrock): harden mantle local cost fixture
* feat(responses): enable the responses API for the Tensormesh provider (#30209)
* feat(responses): enable the responses API for the Tensormesh provider
* Update litellm/llms/openai_like/providers.json
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(langfuse_otel): mark LLM spans as generations (#30250)
* fix(bedrock): stop stream_chunk_size leaking into invoke request bodies (#30240)
stream_chunk_size is a LiteLLM-internal knob for re-chunking the HTTP
response stream. The invoke transformations splat optional_params into the
provider request body without dropping it, and Bedrock rejects unknown
fields, so any bedrock/invoke request that sets the parameter fails with
ValidationException: stream_chunk_size: Extra inputs are not permitted.
Drop it in the invoke dispatcher (covers cohere, titan, mistral, meta,
ai21) and in the Claude messages-format request builder (the route used
for bedrock/invoke Anthropic models)
* fix(bedrock): stop buffering streamed tool-call argument deltas (#30231)
* fix(bedrock): stop buffering streamed tool-call argument deltas
Two issues made Bedrock tool-use streaming arrive as a single end-of-stream
burst through LiteLLM while plain text streamed fine.
First, the anthropic-beta allowlist mapped fine-grained-tool-streaming-2025-05-14
to null for bedrock and bedrock_converse, so the header was silently stripped.
Without that beta, Anthropic models on Bedrock buffer tool input server-side and
emit all toolUse.input deltas at once (verified against converse-stream and
invoke-with-response-stream directly). Bedrock accepts the beta via
additionalModelRequestFields.anthropic_beta, so it is now forwarded.
Second, the streaming reads re-chunked the AWS event stream with
iter_bytes(chunk_size=1024). httpx's ByteChunker only releases full 1024-byte
blocks, so the small early events (messageStart, contentBlockStart, first
deltas) sat in the buffer until enough bytes accumulated, pushing
time-to-first-byte from ~1.4s to ~8.5s on buffered tool-use streams. The
default is now no re-chunking; an explicit stream_chunk_size is still honored.
* test(bedrock): cover explicit stream_chunk_size on sync invoke path
* test(bedrock): cover stream_chunk_size plumbing through converse completion
* test(bedrock): cover stream_chunk_size default in legacy BedrockLLM streaming
* test(bedrock): merge converse handler tests into existing mapped test file
pytest imports test modules by basename in non-package test dirs, so the new
tests/test_litellm/llms/bedrock/chat/test_converse_handler.py collided with
the pre-existing tests/test_litellm/llms/chat/test_converse_handler.py and
broke collection in CI. Move the new tests into the existing file
* feat(otel): emit v2 cost breakdown + stamp tracer scope version (#30156)
Read the StandardLoggingPayload cost_breakdown into a typed LLMCost on
LLMCallSpanData and emit each component under litellm.cost.* (absent
components omitted, so spans stay sparse). Stamp litellm.__version__ as
the instrumentation scope version so every v2 span carries a
deterministic scope.version.
Tests under tests/test_litellm/integrations/otel/.
* fix(proxy): cancel in-flight upstream LLM request on client disconnect (opt-in) (#30223)
* fix(proxy): cancel in-flight upstream LLM request on client disconnect (opt-in)
On the non-streaming path, base_process_llm_request awaited the LLM call
with no disconnect monitoring; when the HTTP client went away the
upstream request kept running until completion or request_timeout (6000s
default), holding a backend slot (e.g. a vLLM GPU slot) for output
nobody would read
Add an opt-in general_settings.cancel_on_disconnect flag, default off,
so the default code path is unchanged. When enabled, a receive-based
watcher task observes http.disconnect and cancels the asyncio.gather
driving the upstream call. The resulting CancelledError is converted to
HTTPException 499 only when the disconnect event is set, so
server-initiated cancellations still propagate as-is. The 499 then flows
through _handle_llm_api_exception like any other failure, meaning
post_call_failure_hook still releases max_parallel_requests slots and
fires spend and alerting callbacks; it is logged at info level instead
of a full traceback
Also removes the dead check_request_disconnection helper in
proxy_server.py (zero call sites) along with its behavior-pin tests
Builds on the receive-based design from #25776
Addresses #13774. Re-fixes #22805 (regressed after the #14295 revert)
Co-authored-by: CreateRandom <18438707+CreateRandom@users.noreply.github.com>
* fix(proxy): scope 499 quiet logging to disconnects and harden watcher
Address the two P2 findings from the Greptile review on #30223. The
info-level logging in _log_llm_api_exception now applies only to the
disconnect-specific HTTPException (status 499 plus the shared
_CLIENT_DISCONNECT_DETAIL message), so any other 499 raised by hooks or
guardrails keeps its full traceback. The disconnect watcher now catches
exceptions from request.receive() (e.g. a transport reset) and logs a
warning instead of dying silently, making the degradation to no-op
visible; a test pins that the LLM call is not cancelled in that case
---------
Co-authored-by: kursad <kursad.lacin@brado.net>
Co-authored-by: CreateRandom <18438707+CreateRandom@users.noreply.github.com>
* fix(bedrock): grant aws-external-anthropic:* in OIDC session policy for claude_platform (#30200) (#30205)
The inline STS session policy passed to assume_role_with_web_identity
acts as an IAM PERMISSION CEILING — effective permissions are the
intersection of the role's identity policies and this policy. Any
action not listed is silently denied even when the IAM role grants it.
#27678 added the bedrock/claude_platform/<model> route but its
service-side action namespace is aws-external-anthropic:*, not
bedrock:*. Without a matching statement here, every claude_platform
request via OIDC (GCP federation, EKS Pod Identity webhook, etc.) 403s
with 'no session policy allows the aws-external-anthropic:CreateInference
action' — even with a fully permissive identity policy.
Add a second ClaudePlatformLiteLLM statement covering CreateInference,
CreateBatchInference, CancelBatchInference, DeleteBatchInference,
CountTokens, Get*, List*. Keep aws:SecureTransport=true parity with the
bedrock statement.
Static creds + IRSA flow through different code paths and are not
affected.
Fixes#30200
* fix(proxy): set Retry-After header on RouterRateLimitError 429 responses (#30098)
* Set Retry-After header on RouterRateLimitError responses
When all deployments for a model are in cooldown, the proxy returns a
429 whose cooldown timing is only available by parsing the error
message string. RouterRateLimitError already carries cooldown_time, so
expose it as a standard retry-after header in
_handle_llm_api_exception. The value is rounded up so clients never
retry before the cooldown window ends.
Fixes#27823.
* Set Retry-After after response-headers hook so cooldown wins
The cooldown-derived retry-after was assigned before the
post_call_response_headers_hook merge, so a callback returning a
retry-after key (including a stale or empty value) silently clobbered
it. Move the RouterRateLimitError block after the callback merge so the
cooldown value is authoritative for this error type.
* fix(router): route aspeech through async_function_with_fallbacks (#30104)
* fix(router): route aspeech through async_function_with_fallbacks
Router.aspeech selected a deployment and awaited litellm.aspeech
directly, so TTS requests got no retry on failure and no failover to
backup deployments; the except block only fired an exception alert and
re-raised. Every other router endpoint (acompletion, aembedding,
atranscription, arerank) already delegates to
async_function_with_fallbacks
Mirror the atranscription pattern: move deployment selection and the
litellm.aspeech call into a private _aspeech method, then have the
public aspeech set kwargs["original_function"] = self._aspeech and
await self.async_function_with_fallbacks(**kwargs). _aspeech also picks
up the shared _get_async_openai_model_client helper and the same
total/success/fail call accounting the sibling endpoints use
Fixes#27778.
* fix(router): apply deployment kwargs and rpm semaphore in _aspeech
Bring _aspeech fully in line with _atranscription: call
_update_kwargs_with_deployment so deployment metadata, model_info,
timeout, and default litellm params flow into the request, and wrap
the litellm.aspeech call with the max_parallel_requests semaphore plus
async_routing_strategy_pre_call_checks so TTS respects rpm limits the
same way the other router endpoints do
Also add a unit test that exercises _aspeech directly and asserts the
deployment metadata reaches the underlying call
* fix(slack_alerting): stop false-positive hanging request alerts for requests below the alerting threshold (#30106)
* fix(slack_alerting): skip hanging request alerts below the threshold
The hanging request check alerted on any cached request whose
completion status was not yet recorded, with no minimum age check.
Since the background loop runs every alerting_threshold / 2 seconds,
any request that happened to be in flight at a check fired a
"hanging - Ns+ request time" alert even if it was only seconds old,
producing a steady stream of false positives.
Add a created_at timestamp to HangingRequestData, stamped when the
request enters the hanging request cache, and skip requests younger
than alerting_threshold without evicting them, so a later check can
still alert if they never complete. Extend the cache TTL from
threshold + 60s to 1.5x threshold + 60s; with the age check, entries
only become alertable after threshold seconds, and the check period
is threshold / 2, so the old TTL could evict a genuinely hanging
request before any check saw it cross the threshold.
Fixes#27855.
* fix(slack_alerting): alert once per hanging request
The min-age gate stops false positives for young in-flight requests, but
a genuinely hanging request still re-alerted on every checker tick within
the cache TTL. With the wider TTL (1.5x threshold + 60s) that is 1-2 extra
Slack notifications per stuck request at the default 600s threshold.
Flag a HangingRequestData entry as alerted once its alert fires and skip
flagged entries on later ticks, so each hang produces exactly one alert.
The cache reference is mutated in place, so the TTL is untouched and still
handles cleanup. Adds a regression test asserting one alert across multiple
ticks.
Fixes#27855.
* fix(health): treat all-proxy-models keys as unrestricted in /health (#30087)
* fix(health): treat all-proxy-models keys as unrestricted in /health
A key granted all model permissions stores the literal
"all-proxy-models" marker in its models list. The /health access
filter compared that marker against real model_names, so the model
list filtered down to nothing and the WebUI health check returned
healthy_count=0, unhealthy_count=0 with HTTP 503. Skip the filter
(both the live path and the background-cache model_id scoping) when
the marker is present, matching how auth_checks treats
SpecialModelNames.all_proxy_models.
Fixes#29744.
* fix(health): resolve all-team-models sentinel to the team allowlist
Same failure shape as the all-proxy-models case: a key carrying the
literal "all-team-models" entry matches no real model_name, so the
/health access filter would zero out the model list. Resolve the
sentinel to the key's team models when team_id is set, matching
get_key_models in model_checks.py. Without a team_id the sentinel
stays unresolved and matches nothing, denying rather than widening
access, mirroring _resolve_key_models_for_auth_check.
* feat(proxy): auto-enable drop_params for Claude Code requests (#30218)
* feat(proxy): auto-enable drop_params for Claude Code requests
Claude Code identifies itself with a claude-cli/<version> user agent and
sends Anthropic-specific params (top_k, thinking, etc.) on every request.
When the proxy routes those requests to a non-Anthropic provider, the
unsupported params fail the call unless drop_params is configured. Detect
the Claude Code user agent in add_litellm_data_to_request and default
drop_params to true for those requests, without overriding an explicit
drop_params value sent by the caller.
* feat(proxy): respect operator litellm_settings drop_params over Claude Code default
An explicit drop_params in the operator's litellm_settings (true or false)
now suppresses the Claude Code user agent default, so an operator who
deliberately configured drop_params: false keeps strict param validation
for Claude Code clients too. The auto-default only fills the gap when
neither the request body nor the config sets a value.
* fix(snowflake): migrate to native endpoints with auto-routing for Claude models (#29964)
* fix(snowflake): migrate to native Cortex REST API endpoints
Replaces the legacy /api/v2/cortex/inference:complete endpoint with the
native OpenAI-compatible /api/v2/cortex/v1/chat/completions endpoint,
fixing error 390142 (Incoming request does not contain a valid payload)
when using model: snowflake/<model> in LiteLLM proxy.
Changes:
- litellm/llms/snowflake/chat/transformation.py: route to native
/cortex/v1/chat/completions, remove Snowflake-specific tool_spec
payload transformation, remove content_list response handling,
add stream to supported params
- litellm/llms/snowflake/anthropic/transformation.py (new):
SnowflakeCortexAnthropicConfig routes Claude models to /cortex/v1/messages
with anthropic-version header and Anthropic->OpenAI response transform
- tests: 29 unit tests covering URL routing, auth headers, payload
format, and response parsing
* fix(snowflake): map max_tokens to max_completion_tokens for native endpoint
* fix: handle multi-turn tool conversations and OpenAI→Anthropic tool format conversion
- _extract_system_and_messages now preserves tool_calls from assistant messages
and converts them to Anthropic tool_use content blocks
- tool role messages are converted to user role with tool_result content blocks
(as required by Anthropic Messages API)
- Added _transform_tools_to_anthropic() to convert OpenAI tool format
(type/function/parameters) to Anthropic format (name/input_schema)
- Added comprehensive tests for multi-turn tool conversations
Addresses review feedback on PR #29964
* test: add coverage for malformed JSON and non-string tool arguments
* fix(tests): update chat transformation tests for native OpenAI-compatible endpoint
* style: apply black formatting
* fix: resolve mypy type errors in anthropic transformation
* fix: correct mypy type: ignore error codes (attr-defined)
* fix: use max_tokens instead of max_completion_tokens for Snowflake endpoint compatibility
* refactor: merge Anthropic config into unified SnowflakeConfig with auto-routing
- Remove separate SnowflakeCortexAnthropicConfig and anthropic/ directory
- SnowflakeConfig now auto-routes based on model name:
- Claude models → /messages endpoint (Anthropic format)
- All others → /chat/completions endpoint (OpenAI format)
- No new provider needed (stays as SNOWFLAKE = 'snowflake')
- Tool message transformation for Claude: tool_calls → tool_use blocks,
tool role → user with tool_result
- OpenAI → Anthropic tool format conversion (parameters → input_schema)
- Addresses Greptile feedback about unwired SnowflakeCortexAnthropicConfig
* fix: use max_completion_tokens for /chat/completions (Snowflake deprecated max_tokens on this endpoint)
* fix(tests): update assertions for Claude auto-routing to /messages endpoint
* fix(snowflake): add tool_choice conversion and preserve max_completion_tokens in Anthropic path
* fix(snowflake): use ChatCompletionMessageToolCall objects and strip model prefix on OpenAI path
* fix(snowflake): collect multiple system messages to prevent guardrail override
* chore: remove committed .pyc files and add __pycache__ to .gitignore
* fix: remove unused Union import
* fix: restore original .gitignore (accidentally replaced in earlier commit)
* feat(snowflake): add streaming response handler for both Anthropic and OpenAI SSE formats
* fix: remove unused AsyncIterator and Iterator imports
* fix: add missing total_tokens to ChatCompletionUsageBlock
* fix(snowflake): coalesce consecutive tool results into single user message for Anthropic
* fix(snowflake): handle message_start event for streaming input_tokens tracking
* fix: evict last deleted model in multi-instance deployments (#28608)
* fix: evict last deleted model in multi-instance deployments
_delete_deployment had an early return when db_models was empty,
preventing eviction of the last deleted model during reconciliation.
- Remove len(db_models)==0 early return from _delete_deployment
- Return None (not []) from _get_models_from_db on DB failure so
callers can distinguish a transient failure from a genuinely empty DB
- Guard _update_llm_router against None to skip updates on DB failure
Fixes#28443
* test: remove dead MagicMock assignment in type_mismatch test
* fix: update test to pass [] not None to _update_llm_router
test_ProxyConfig__update_llm_router_bad_proxy_logging_raises was passing
None as new_models to get through to the proxy_logging_obj check, but
the None guard we added now returns early before reaching that path.
Pass [] instead so the test exercises the intended AttributeError case.
Signed-off-by: Rudra Dudhat <contact.rdudhat@gmail.com>
* chore: regenerate API types to sync schema.d.ts with proxy OpenAPI spec
Signed-off-by: Rudra Dudhat <contact.rdudhat@gmail.com>
---------
Signed-off-by: Rudra Dudhat <contact.rdudhat@gmail.com>
* fix: invalidate Redis spend counter on /key/reset_spend (#29694)
* fix: set Redis spend counter to reset_to value on /key/reset_spend
Previously, the Redis spend counter was always set to 0.0 after a reset,
even when reset_to was a non-zero value (partial reset). This caused
the budget to be under-enforced for up to 60 seconds until the counter
expired and fell through to the DB.
Now the counter is set to the actual reset_to value, so partial resets
are reflected correctly and budget enforcement is consistent.
* test: update reset_key_spend test to match direct cache set
The implementation now sets spend_counter_cache directly instead of
calling _invalidate_spend_counter. Update the test to verify the
in_memory_cache.set_cache call with the correct key, value, and ttl.
---------
Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
* fix: add scaleway models pricing (#27659)
* fix: Add embeddings support for Scaleway provider
* fix: resolve merge conflicts
* fix(main): clarify backend route handling for Swagger static assets (#30196)
* fix(main): clarify backend route handling for Swagger static assets
* fix(allowlist): add BACKEND_MOUNT_PATHS for Swagger static assets
* fix(voyage): route multimodal embeddings to correct endpoint (#30193)
* fix(voyage): route multimodal embeddings to correct endpoint
* test(voyage): cover multimodal embedding edge cases
* test(voyage): cover api key fallback
* fix(voyage): raise early on missing api key and malformed image url
* test(voyage): cover utils routing and helper
* fix(voyage): route supported openai params for multimodal models
* style: apply black formatting
* fix(ui): infer Azure API version from API base (#30204)
* fix(ui): infer Azure API version from API base
* fix(ui): address Azure API version feedback
* Update litellm/llms/snowflake/chat/transformation.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat(datadog): add team-scoped Datadog callback support (#29947)
Enable teams to configure their own Datadog credentials via
POST /team/{team_id}/callback, following the same pattern as Langfuse.
* Merge pull request #29528 from aanchal22/litellm_byok-alias-merge
fix(proxy): atomic merge for team model aliases and team.models on BYOK create
* feat: add EmpirioLabs as an OpenAI-compatible provider (#30278)
Co-authored-by: Adam Dalloul <adam.d.developer@gmail.com>
* fix: resolve failing tests and lint in snowflake/team endpoints
- Black-format snowflake/chat/transformation.py to fix lint failure
- Update Anthropic config test to expect default max_tokens of 4096 (matches implementation)
- Add AsyncMock + execute_raw mock to team_model_add cache-refresh pin test
- Add model_dump mock and patch cache/logging in test_uses_atomic_array_append_with_dedup
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(test): update test_db_error_new_model_check for new _delete_deployment logic
_delete_deployment no longer short-circuits on empty db_models — it now
treats [] as a valid empty-DB state and proceeds to check config models.
Mock get_config to return the two router deployments so they appear in
combined_id_list and are protected, which matches the real-world scenario
where a DB error occurs but the models are config-backed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(proxy): register cancel_on_disconnect in ConfigGeneralSettings and config list (#30295)
* feat(proxy): register cancel_on_disconnect in ConfigGeneralSettings and config list
Follow-up to #30223 per maintainer review: documents the flag in
ConfigGeneralSettings with a short description and adds it to
allowed_args in get_config_list so the UI and /config/list expose it.
A test pins that /config/list returns the field with type Boolean,
which requires both registrations to be present
* chore(ui): regenerate schema.d.ts for cancel_on_disconnect
---------
Co-authored-by: kursad <kursad.lacin@brado.net>
* fix(datadog): never fall back to env DD_API_KEY for caller-supplied destinations
Team/key-scoped Datadog loggers could be pointed at an arbitrary dd_agent_host or
dd_site while omitting dd_api_key, causing the proxy's global DD_API_KEY to be sent
as the DD-API-KEY header to that destination. Gate the env-var fallback behind an
allow_env_credentials flag, set to False when the destination is caller-supplied,
mirroring the existing langfuse/langsmith pattern.
---------
Signed-off-by: Rudra Dudhat <contact.rdudhat@gmail.com>
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
Co-authored-by: daitran-tensormesh <dai@tensormesh.ai>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Muspi Merol <me@promplate.dev>
Co-authored-by: fangkang <fangkangm@gmail.com>
Co-authored-by: Chris Hoogeboom <chris.hoogeboom@gmail.com>
Co-authored-by: kursadlacin <kursadlacin@gmail.com>
Co-authored-by: kursad <kursad.lacin@brado.net>
Co-authored-by: CreateRandom <18438707+CreateRandom@users.noreply.github.com>
Co-authored-by: hcl <chenglunhu@gmail.com>
Co-authored-by: Filippo Menghi <113345637+Cyberfilo@users.noreply.github.com>
Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: sfc-gh-nashukla <navnit.shukla@snowflake.com>
Co-authored-by: Rudra Dudhat <contact.rdudhat@gmail.com>
Co-authored-by: Michael <52305679+michaelxer@users.noreply.github.com>
Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
Co-authored-by: Quentin Champenois <26109239+Quentinchampenois@users.noreply.github.com>
Co-authored-by: mauriceberentsen <mauriceberentsen@live.nl>
Co-authored-by: lost9999 <56498264+lost9999@users.noreply.github.com>
Co-authored-by: GaetanVDB07 <86427581+GaetanVDB07@users.noreply.github.com>
Co-authored-by: Aanchal Khandelwal <aan2210khandelwal@gmail.com>
Co-authored-by: Adam Dalloul <adam_dalloul@icloud.com>
Co-authored-by: Adam Dalloul <adam.d.developer@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(ci): extend record/replay proxy to chat, embeddings, moderations, rerank, anthropic
The record/replay proxy that took the gpt-image-1 spend E2E off the live OpenAI
path now fronts every provider, so the other real-provider E2Es stop paying for
and depending on live calls each commit. It keys per upstream and selects a
non-OpenAI provider by a /__recorder_upstream/<host>/ path prefix carried on the
model's api_base, since some litellm handlers (cohere rerank) drop custom
request headers. Wired into build_and_test (chat, embeddings, moderations,
image), the otel job (cohere rerank), and the anthropic-messages job via a
reusable start_openai_record_replay_proxy command.
Dropped the time.time()/uuid prompt cache-busters in the build_and_test chat
tests, whose config has the response cache off, so identical requests are
recordable. The image spend test now asserts a repeat call still bills spend,
failing loudly if the proxy response cache is ever turned on.
Responses, the anthropic passthrough, bedrock, and fake-endpoint tests are left
live: their lifecycles, api_base assertions, providers, or fake targets make a
stateless body-keyed cache either break them or add nothing.
* docs(ci): note the recorder command's OpenAI default upstream and prefix override
Addresses a review note: the shared start_openai_record_replay_proxy command
defaults the upstream to OpenAI, so a non-OpenAI model must carry the
/__recorder_upstream/<host>/ prefix on its api_base. Document that in the
command description so a future caller does not assume the default follows the
provider.
* test(ci): record/replay OpenAI image gen so the spend E2E isn't outage-bound
The dockerized spend test test_key_info_spend_values_image_generation curls
the proxy for a gpt-image-1 image, which wildcard-routes to real api.openai.com
on every commit; an OpenAI outage then reddens unrelated PRs and each run pays
for an image.
Add an in-repo record/replay reverse proxy (tests/_openai_record_replay_proxy.py)
that sits between the proxy and OpenAI. The first run, and the first after the
recording lapses, records live; subsequent runs replay from the shared Redis
cassette store. The proxy keeps its real separate-process HTTP topology; only
the image model's api_base is pointed at the recorder in CI via
IMAGE_GEN_RECORDER_BASE_URL, which is unset elsewhere so it falls back to
api.openai.com.
Recordings lapse 24h after write and are never refreshed on read, matching the
VCR persister contract, so provider drift is still caught. Replayed responses
drop upstream framing/server headers (content-length, transfer-encoding,
content-encoding, date, server) so the re-serving layer recomputes them,
honoring the Bedrock content-length lesson.
* test(ci): close recorder http client on app shutdown
Add a Starlette lifespan that closes the self-created httpx.AsyncClient on
teardown, and leave caller-injected clients untouched so reuse across
create_app calls is not broken. Covers the unclosed-client ResourceWarning
raised in review.
* test: modernize models used in CircleCI e2e test suites
Replaces obsolete models (gpt-4o, gpt-4o-mini, gpt-3.5-turbo,
claude-3-5-sonnet-20240620, claude-sonnet-4-20250514) with current
equivalents across the e2e_openai_endpoints and
proxy_e2e_anthropic_messages_tests CircleCI jobs.
- gpt-4o -> gpt-5.5 (responses API e2e tests)
- gpt-4o-mini -> gpt-5-mini (websocket responses, oai_misc_config)
- gpt-4o-mini-2024-07-18 -> gpt-4.1-mini-2025-04-14 (fine-tuning,
still actively fine-tunable)
- gpt-4 / gpt-3.5-turbo target_model_names example -> gpt-5.5 /
gpt-5-mini
- bedrock claude-3-5-sonnet-20240620 batch entry -> haiku-4-5-20251001
(also aligning oai_misc_config model_name with what
test_bedrock_batches_api.py actually requests)
- bedrock claude-sonnet-4-20250514 (deprecated, retires 2026-06-15)
-> claude-sonnet-4-5-20250929
* test: point bedrock-claude-sonnet-4 alias at Sonnet 4.6, not 4.5
Greptile/Cursor flagged that after the previous commit, the
bedrock-claude-sonnet-4 alias collided with bedrock-claude-sonnet-4.5
(both pointed to claude-sonnet-4-5-20250929). Rename to
bedrock-claude-sonnet-4.6 and point it at the Sonnet 4.6 Bedrock ID
(us.anthropic.claude-sonnet-4-6, already in the litellm model
registry) so the alias name matches the underlying model version.
* test: modernize models across remaining CI-mounted configs & tests
Expands the modernization sweep to all CircleCI-mounted proxy configs
and to test directories where the model literal is a fixture/route key
(not the test's subject).
Config changes:
- proxy_server_config.yaml: bump gpt-3.5-turbo / gpt-3.5-turbo-1106 /
gpt-4o / gemini-1.5-flash / dall-e-3 underlying models; rename
gpt-3.5-turbo-end-user-test alias to gpt-5-mini-end-user-test; bump
text-embedding-ada-002 underlying to text-embedding-3-small. User-
facing aliases (gpt-3.5-turbo, gpt-4, text-embedding-ada-002, etc.)
preserved for backward compatibility with tests.
- simple_config.yaml, otel_test_config.yaml, spend_tracking_config.yaml:
bump gpt-3.5-turbo underlying to gpt-5-mini.
- pass_through_config.yaml: claude-3-5-sonnet / claude-3-7-sonnet /
claude-3-haiku entries replaced with claude-sonnet-4-5 / claude-
haiku-4-5 / claude-opus-4-7.
- oai_misc_config.yaml: align alias name with the gpt-5-mini rename.
Test changes (proactive: claude-sonnet-4-20250514 / claude-opus-4-
20250514 retire 2026-06-15):
- tests/llm_translation/test_anthropic_completion.py: bump 3 references
+ paired Vertex AI ID to claude-sonnet-4-5.
- tests/llm_translation/test_optional_params.py: bump 2 references.
- tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py
and test_bedrock_anthropic_messages_test.py: bump router fixtures
using the deprecated model IDs.
- tests/pass_through_unit_tests/base_anthropic_messages_tool_search_test.py:
modernize docstring examples.
- tests/test_end_users.py: update references to renamed alias.
* test: modernize placeholder model literals in router_unit_tests
Mass replace_all on fixture/placeholder model literals across the
router_unit_tests/ suite (model name is a routing key / label, not the
test subject). Sub-agent sweep so far — additional commits will follow
for logging_callback_tests/, enterprise/, top-level tests/test_*.py,
and other CI-mounted dirs.
Mappings applied:
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 / claude-3-opus-20240229 /
claude-3-haiku-20240307 / claude-3-5-sonnet-20240620 ->
claude-sonnet-4-5-20250929 / claude-opus-4-7 /
claude-haiku-4-5-20251001 as appropriate
Explicitly preserved:
- gpt-4o-mini-* variants (transcribe, tts, etc.) where they're current
- gpt-4-turbo / gpt-4-vision-preview / gpt-4-0613 (subject literals)
- JSONL batch body literals
- Mock LLM response model fields (must match upstream)
- Fake/mock identifiers
* test: modernize placeholder model literals across remaining CI suites
Sub-agent sweep across logging_callback_tests/, guardrails_tests/,
enterprise/, pass_through_unit_tests/, otel_tests/,
llm_responses_api_testing/, batches_tests/, spend_tracking_tests/,
litellm_utils_tests/, unified_google_tests/, and a few top-level
tests/test_*.py files where the model literal is a fixture or
placeholder (router model_list, mock standard logging payload, mock
callback data) rather than the test's subject.
Mappings applied (see scope notes below):
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5.5 (corrected from initial gpt-5 — bare gpt-5
is not a valid OpenAI alias; only gpt-5.5 / gpt-5.4 / gpt-5.2-codex
/ gpt-5-mini exist)
- gpt-4o-mini (bare) -> gpt-5-mini
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 -> claude-sonnet-4-5-20250929
- claude-3-opus-20240229 -> claude-opus-4-7
- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001
- claude-3-5-sonnet-20240620/20241022 -> claude-sonnet-4-5-20250929
- claude-3-7-sonnet-20250219 -> claude-sonnet-4-6
- gemini-1.5-flash -> gemini-2.5-flash
- gemini-1.5-pro -> gemini-2.5-pro
Explicitly preserved (not modernized):
- llm_translation/ tests where model is the SUBJECT (provider-specific
translation/transformation logic). Only the deprecated 20250514
references were already bumped in a prior commit.
- Cost-calc / tokenizer subject tests in test_utils.py (skip-ranges
documented by the sub-agent).
- Bedrock model IDs in test_health_check.py path-stripping tests.
- JSONL batch request bodies and mock LLM response bodies (must match
upstream literal).
- Langfuse expected-request-body JSON fixtures (cost values are exact-
match-asserted; changing the model would shift response_cost).
- gpt-3.5-turbo-instruct (text-completion endpoint; no modern OpenAI
equivalent).
- Top-level tests calling the proxy through user-facing aliases
(gpt-3.5-turbo, gpt-4, text-embedding-ada-002, dall-e-3) — aliases
in proxy_server_config.yaml stay; only the underlying model was
bumped.
- tests/test_gpt5_azure_temperature_support.py (the test's whole point
is model-name handling).
- Fake / mock / openai/fake identifiers.
Notable side fixes:
- test_spend_accuracy_tests.py: UPSTREAM_MODEL now matches what
spend_tracking_config.yaml's proxy actually routes to (gpt-5-mini),
resolving a latent inconsistency.
- proxy_server_config.yaml: bare `gpt-5` alias renamed to `gpt-5.5`
(bare gpt-5 is not a valid OpenAI alias).
- test_batches_logging_unit_tests.py: explicit_models list entries
kept distinct (gpt-5-mini + gpt-5.5) after bulk rename.
* test: fix CI failures from model modernization sweep
CI surfaced 4 categories of regression from the bulk modernization:
1. Azure deployment names are customer-specific. Reverted:
- tests/litellm_utils_tests/test_health_check.py: azure/text-
embedding-3-small -> azure/text-embedding-ada-002 (the CI Azure
account does not have a text-embedding-3-small deployment).
- tests/logging_callback_tests/test_custom_callback_router.py:
same revert for two router fixtures driving aembedding.
2. gpt-5 family does not accept temperature != 1. Tests that pass a
custom temperature swapped from gpt-5-mini to gpt-4.1-mini (modern
non-reasoning OpenAI mini that still accepts temperature/logprobs):
- tests/logging_callback_tests/test_datadog.py
- tests/logging_callback_tests/test_langsmith_unit_test.py
- tests/logging_callback_tests/test_otel_logging.py
3. proxy_server_config.yaml's gpt-3.5-turbo-large alias was routing to
gpt-5.5 (a reasoning model that rejects logprobs). The proxy test
tests/test_openai_endpoints.py::test_chat_completion_streaming
exercises logprobs/top_logprobs through that alias. Bumped the
underlying model to gpt-4.1 (non-reasoning, still modern).
4. tests/logging_callback_tests/test_gcs_pub_sub.py asserts against a
pinned JSON fixture (gcs_pub_sub_body/spend_logs_payload.json) with
hardcoded model="gpt-4o" and a model-specific spend value. Reverted
the litellm.acompletion calls in the test to model="gpt-4o" so the
fixture's exact-match assertions still hold.
5. tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py:
anthropic.messages.create routing to openai/gpt-5-mini returned an
empty content[0] with max_tokens=100 (reasoning-token consumption).
Swapped to openai/gpt-4.1-mini.
* test: fix Assistants API model + 2 cursor[bot] review nits
1. pass_through_unit_tests/test_custom_logger_passthrough.py: gpt-5.5
isn't accepted by the /v1/assistants endpoint
("unsupported_model"). Switch to gpt-4.1-mini (modern, Assistants-
API-supported, non-reasoning).
2. example_config_yaml/pass_through_config.yaml: the previous sweep
bumped the claude-3-7-sonnet alias to claude-opus-4-7, which is a
tier change (Sonnet -> Opus). Map to claude-sonnet-4-6 to keep the
Sonnet tier intact. (Cursor bugbot review.)
3. example_config_yaml/simple_config.yaml: model_name was left as
gpt-3.5-turbo while the underlying was bumped to gpt-5-mini, which
muddles the "simple" example. Make both sides gpt-5-mini so the
most basic example is a straight 1:1 mapping again. (Cursor bugbot
review.)
* fix: revert gpt-4/gpt-3.5-turbo alias underlying to non-reasoning models
tests/test_openai_endpoints.py::test_completion calls the proxy alias
"gpt-4" with temperature=0, and other tests call gpt-3.5-turbo with
custom temperature / logprobs / the legacy /v1/completions endpoint.
The earlier modernization mapped both aliases to gpt-5.5 / gpt-5-mini,
which are reasoning models that reject temperature != 1 and don't
expose /v1/completions. Map the aliases to gpt-4.1 / gpt-4.1-mini
(modern non-reasoning OpenAI models) instead — keeps user-facing
aliases preserved while picking a current underlying that still
supports the parameters/endpoints the tests exercise.
DALL-E 2 and DALL-E 3 were removed from the OpenAI API on 2026-05-12,
causing e2e image-generation tests to fail with "model does not exist".
Swap all live-API DALL-E references in proxy-backed tests to gpt-image-1
and update the dall-e-2 alias in proxy_server_config.yaml to point at
openai/gpt-image-1 (preserves any historical dall-e-2 callers).
gpt-3.5-turbo-0301 was removed from the model cost map, so every call
had response_cost=0 and team member spend never increased. The wait
helper also returned True after 3s regardless of whether spend updated.
- Switch fake-openai-endpoint to gpt-3.5-turbo (has pricing in cost map)
- Remove premature early-return in wait_for_team_member_spend_update
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix proxy config
* fix(responses api): fix streaming ID consistency and tool format handling (#12640)
* fix(responses): ensure streaming chunk IDs use consistent encoding format
Fixes streaming ID inconsistency where streaming responses used raw provider IDs
while non-streaming responses used properly encoded IDs with provider context.
Changes:
- Updated LiteLLMCompletionStreamingIterator to accept provider context
- Added _encode_chunk_id() method using same logic as non-streaming responses
- Modified chunk transformation to encode all streaming item_ids with resp_ prefix
- Updated handlers to pass custom_llm_provider and litellm_metadata to streaming iterator
Impact:
- Streaming chunk IDs now format: resp_<base64_encoded_provider_context>
- Enables session continuity when using streaming response IDs as previous_response_id
- Allows provider detection and load balancing with streaming responses
- Maintains backward compatibility with existing streaming functionality
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(types): add explicit Optional[str] type annotation for model_id
This resolves MyPy type checking error where model_id could be None
but wasn't explicitly typed as Optional[str].
* fix(types): handle None case for litellm_metadata access
Prevents 'Item None has no attribute get' error by checking for None
before accessing litellm_metadata dictionary.
* test: add comprehensive tests for streaming ID consistency
Adds unit and E2E tests to verify streaming chunk IDs are properly encoded
with consistent format across streaming responses.
## Tests Added
### Unit Test (test_reasoning_content_transformation.py)
- `test_streaming_chunk_id_encoding()`: Validates the `_encode_chunk_id()` method
correctly encodes chunk IDs with `resp_` prefix and provider context
### E2E Tests (test_e2e_openai_responses_api.py)
- `test_streaming_id_consistency_across_chunks()`: Tests that all streaming chunk IDs
are properly encoded across multiple chunks in a real streaming response
- `test_streaming_response_id_as_previous_response_id()`: Tests the core use case -
using streaming response IDs for session continuity with `previous_response_id`
## Key Testing Approach
- Uses **Gemini** (non-OpenAI model) to test the transformation logic rather than
OpenAI passthrough, since the streaming ID consistency issue occurs when LiteLLM
transforms responses rather than just passing through to native OpenAI responses API
- Tests validate that streaming chunk IDs now use same encoding as non-streaming responses
- Verifies session continuity works with streaming responses
Addresses @ishaan-jaff's request for unit tests covering the streaming ID consistency fix.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(lint): remove unused imports in transformation.py
Removes unused imports to fix CI linting errors:
- GenericResponseOutputItem
- OutputFunctionToolCall
* test: remove E2E tests from openai_endpoints_tests
Remove streaming ID consistency E2E tests as requested by @ishaan-jaff.
Keep only the mock/unit test in test_reasoning_content_transformation.py
* revert: remove streaming chunk ID encoding to original behavior
This reverts the streaming chunk ID encoding changes to understand the original issue better.
Original behavior was:
- Streaming chunks: raw provider IDs
- Streaming final response: raw IDs (PROBLEM!)
- Non-streaming final response: encoded IDs (correct)
The real issue: streaming final response IDs were not encoded, breaking session continuity.
* fix(responses): encode streaming final response IDs to match OpenAI behavior
Fixes streaming ID inconsistency to match OpenAI's Responses API behavior:
- Streaming chunks: raw message IDs (like OpenAI's msg_xxx)
- Final response: encoded IDs (like OpenAI's resp_xxx)
This enables session continuity by ensuring streaming final response IDs
have the same encoded format as non-streaming responses, allowing them
to be used as previous_response_id in follow-up requests.
Changes:
- Add custom_llm_provider and litellm_metadata to LiteLLMCompletionStreamingIterator
- Update handlers to pass provider context to streaming iterator
- Apply _update_responses_api_response_id_with_model_id to final streaming response
- Keep streaming chunks as raw IDs to match OpenAI format
Impact:
- Session continuity works with streaming responses
- Load balancing can detect provider from streaming final response IDs
- Format matches OpenAI's Responses API exactly
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* test: update unit test to match correct OpenAI-compatible behavior
Updates the unit test to verify streaming chunk IDs are raw (not encoded)
to match OpenAI's responses API format:
- Streaming chunks: raw message IDs (like msg_xxx)
- Final response: encoded IDs (like resp_xxx)
This reflects the correct behavior implemented in the fix.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* cleanup
* TestBaseResponsesAPIStreamingIterator
---------
Co-authored-by: Javier de la Torre <jatorre@carto.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat(main.py): use asyncio.sleep for mock_Timeout=true on async request
adds unit testing to ensure proxy does not fail if specific Openai requests hang (e.g. recent o1 outage)
* fix(streaming_handler.py): fix deepseek r1 return reasoning content on streaming
Fixes https://github.com/BerriAI/litellm/issues/7942
* Revert "fix(streaming_handler.py): fix deepseek r1 return reasoning content on streaming"
This reverts commit 7a052a64e3.
* fix(deepseek-r-1): return reasoning_content as a top-level param
ensures compatibility with existing tools that use it
* fix: fix linting error
* fix(base_utils.py): supported nested json schema passed in for anthropic calls
* refactor(base_utils.py): refactor ref parsing to prevent infinite loop
* test(test_openai_endpoints.py): refactor anthropic test to use bedrock
* fix(langfuse_prompt_management.py): add unit test for sync langfuse calls
Resolves https://github.com/BerriAI/litellm/issues/7938#issuecomment-2613293757
* feat(router.py): add retry headers to response
makes it easy to add testing to ensure model-specific retries are respected
* fix(add_retry_headers.py): clarify attempted retries vs. max retries
* test(test_fallbacks.py): add test for checking if max retries set for model is respected
* test(test_fallbacks.py): assert values for attempted retries and max retries are as expected
* fix(utils.py): return timeout in litellm proxy response headers
* test(test_fallbacks.py): add test to assert model specific timeout used on timeout error
* test: add bad model with timeout to proxy
* fix: fix linting error
* fix(router.py): fix get model list from model alias
* test: loosen test restriction - account for other events on proxy
* feat(health_check.py): set upperbound for api when making health check call
prevent bad model from health check to hang and cause pod restarts
* fix(health_check.py): cleanup task once completed
* fix(constants.py): bump default health check timeout to 1min
* docs(health.md): add 'health_check_timeout' to health docs on litellm
* build(proxy_server_config.yaml): add bad model to health check
