* feat(skills): add a litellm-setup agent skill
* fix(skills): run the quickstart for Docker with Postgres in litellm-setup
Use scripts/quickstart.sh for the Docker plus Postgres path instead of a
hand-rolled Postgres container, keep uv with the user's own Postgres, load
.env as data instead of sourcing it, pin the uv Python range, chmod an
existing .env, list bedrock_converse and vertex_ai rows in the cost map
lookup, ask before editing the shell profile, and stop the health wait
when the proxy exits
* fix(skills): guide empty Postgres, docker sudo, and key fixes in litellm-setup
Ask for a new empty database on the uv path and DIRECT_URL behind a pooler,
add the baseline error to troubleshooting, and drop inherited database
settings in the loader line. Check python3 and lsof, explain Docker's
permission denied, give quickstart commands by the folder's path, and fix
provider keys by recreating the container or deleting the quickstart model.
Drop the structure-only test.
* fix(skills): keep shell profiles untouched when litellm-setup installs uv
The uv installer edits shell profiles unless UV_NO_MODIFY_PATH is set, so the skill now sets it and puts ~/.local/bin on PATH for later commands. It also says litellm --setup runs in a separate terminal and how to retire the shared master-key UI login
* fix(skills): offer litellm --setup only on the uv path
The Docker paths install no host litellm CLI, and the old wording also passed the skill's own step number on to the user
* fix(skills): ask before using an env provider key, print model names config.yaml accepts, probe the port with curl
* fix(skills): state the env key default in the question, chmod the wizard config, keep uv's bin dir on PATH
* fix(skills): keep litellm-setup on its own .env and install when the shell has others
* fix(skills): read the setup wizard's config without printing keys and hand off the exact restart command
* fix(skills): hide the database-access dev skill from end-user skill installs
* fix(skills): give the litellm --setup path a restart command that keeps its config
* docs(skills): point litellm --setup users to the master key in litellm_config.yaml
* fix(skills): hide every non-end-user skill, use Azure deployment names, keep the restart block out of the user's shell
* test(skills): find non-end-user skills in-process instead of through git
* docs(skills): price Azure deployments with base_model and put uv on PATH in the start block
* refactor(rust-bridge): require the native extension
_native ships in every wheel and the sdist will not install without it, yet the bridge loaded it optionally and carried None paths that could fail open for fork safety, exception mapping and OTLP errors. Delete loader.py and import _native directly. Tests inject a fake module through NativeBinding(source=...) or with_source() instead of patching the loader
The install smoke checks now verify the compiled module, and tests fail instead of skipping when _native is missing. The interactions spec canary installs the project so it has the extension
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ci): build Rust bridge in Windows smoke tests
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(providers): add ZeroGPU as an OpenAI-compatible provider
Registers zerogpu through the JSON provider registry so zerogpu/<model> routes to
https://api.zerogpu.ai/v1/chat/completions with ZEROGPU_API_KEY and an optional ZEROGPU_API_BASE.
Adds LlmProviders.ZEROGPU, the constants.py provider and endpoint lists, cost map entries for the
10 ZeroGPU text generation models, the endpoint matrix, the Add Model form fields, the README row
and the dashboard provider entry
* feat(zerogpu): add capability flags verified against the live API
Live calls to https://api.zerogpu.ai/v1/chat/completions confirmed tools, tool_choice and json_schema
response_format on 8 of the 10 catalog text models, cached token reporting on deepseek-v4.1-flash,
gpt-4.1-mini, gpt-5.4-nano and gpt-5.6-luna, and reasoning_effort on gpt-5.6-luna. LFM2.5-1.2B-Instruct
answers stream requests with plain JSON instead of SSE and LFM2.5-1.2B-Thinking returns 500 on every
request, so both stay out of the cost map until the API serves them correctly
* feat(zerogpu): price LFM2.5-1.2B-Instruct
Adds zerogpu/LFM2.5-1.2B-Instruct to the cost map with the catalog prices and context window. It
gets no capability flags because the live API ignores tools, response_format and
max_completion_tokens for this model, so LiteLLM drops tool params for it instead of sending them.
LFM2.5-1.2B-Thinking stays out of the cost map
* fix(zerogpu): reject transcription requests before calling the upstream API
ZeroGPU only serves chat completions, so drop it from the OpenAI transcription transport set. A zerogpu transcription request now fails locally instead of hitting an /audio/transcriptions endpoint that does not exist
* test(zerogpu): cover the responses and messages bridges
Both endpoints reach ZeroGPU through chat completions, so assert the request each one sends upstream and the reply it returns
* refactor(zerogpu): move zerogpu out of the provider list tails
New upstream providers append to the end of openai_compatible_endpoints, openai_compatible_providers and providers.json, so an entry at the tail conflicts with every one of them. Placing zerogpu next to long-stable entries keeps those merges clean. No behavior change
* fix(zerogpu): price cached input for qwen3-30b-a3b-fp8
The ZeroGPU model catalog (https://docs.zerogpu.ai/docs/model-catalog, checked 2026-10-09) lists cached input for qwen3-30b-a3b-fp8 at $0.05 per 1M tokens. Without cache_read_input_token_cost, cached tokens were billed at the full $0.10 input rate
* revert(zerogpu): leave the audio transcription provider set unchanged
Per review, keep OPENAI_AUDIO_TRANSCRIPTION_PROVIDERS as upstream defines it. This PR only covers chat completions, and ZeroGPU now serves /audio/transcriptions anyway, so the local refusal and its test are removed
* fix(zerogpu): add max_tokens so trim_messages can size ZeroGPU history
trim_messages reads max_tokens as the fallback for max_input_tokens and evaluates it eagerly, so without it the lookup raised, got swallowed, and the full history came back untrimmed. max_tokens matches each model's maxTokens in ZeroGPU's models API (https://api-dashboard.zerogpu.ai/api/models, checked 2026-10-10)
* test(zerogpu): record mocked requests on a recorder object
The mock handler appended to a list the caller passed in, which AGENTS.md
forbids. A recorder now owns the captured requests as a tuple
* fix(zerogpu): cap max_tokens at each model's output limit
Each cap is the max_output_tokens ZeroGPU stores for the model in its production models table (read 2026-10-20), the same column its /v1/models serves as max_length. That gives 65536 for deepseek-v4.1-flash, 32768 for gpt-4.1-mini and gpt-oss-120b, 128000 for gpt-5.4-nano and gpt-5.6-luna, 8192 for LFM2.5-1.2B-Instruct and llama-3.1-8b-instruct-fast, and 16384 for qwen3-30b-a3b-fp8. glm-5.3-flash is stored as 32786, which reads as a typo for 32768, so that row uses 32768
trim_messages sizes history from max_input_tokens, so lowering max_tokens leaves it unaffected
* fix(zerogpu): flag prompt caching on glm-5.3-flash
Repeating the same ~4.3K-token prompt against ZeroGPU on 2026-10-20 returned cached_tokens of 4320 on some glm-5.3-flash calls. gpt-oss-120b and llama-3.1-8b-instruct-fast returned 0 on all nine calls, and qwen3-30b-a3b-fp8 never returned cached_tokens, so they stay unflagged. Their cached prices stay as ZeroGPU publishes them, so any cache hit is still billed at the right rate
* fix(zerogpu): set gpt-5.4-nano context window to 272000
ZeroGPU accepts a 271001-token gpt-5.4-nano prompt and rejects 273000 tokens as over the context window (checked 2026-10-21), so max_input_tokens is 272000 rather than the 400000 its catalog lists
* fix(zerogpu): list zerogpu models for zerogpu/* wildcards
zerogpu had no models_by_provider entry, so get_provider_models("zerogpu") returned None and a zerogpu/* wildcard listed no models. zerogpu_models is now filled from the cost map rows like openinfer_models and registered in models_by_provider
* fix(zerogpu): flag gpt-5.4-nano as a reasoning model
ZeroGPU honors reasoning_effort on gpt-5.4-nano (checked 2026-10-21). Without it the model spends 0 reasoning tokens, and with low or high it spends 32 or more. LiteLLM only treated it as a reasoning model by falling back to OpenAI's bare gpt-5.4-nano row, so get_model_info and /model/info reported supports_reasoning as null. The row now carries the flag itself
* fix(zerogpu): flag deepseek, glm, gpt-oss and qwen3 as reasoning models
ZeroGPU's /v1/models marks these four as reasoning models and accepts reasoning_effort on all of them (checked 2026-10-21), but LiteLLM rejected the param with UnsupportedParamsError because their rows had no supports_reasoning flag. glm reports reasoning_tokens under reasoning_effort, and gpt-oss and qwen3 spend hidden reasoning tokens on every reply. The gpt-oss test case now expects reasoning_effort to reach ZeroGPU
* fix(zerogpu): set gpt-oss-120b context window to 128000
ZeroGPU routes gpt-oss-120b across several upstream backends, and at least one of them returns 413 past a 128000-token window, so max_input_tokens uses that as the safe floor. The backends reached on 2026-10-21 accepted up to about 131K prompt tokens, so this only gives up a little headroom on the larger ones
* feat(zerogpu): call ZeroGPU's Responses API natively
ZeroGPU serves /v1/responses for all nine catalog models, so LiteLLM no longer bridges Responses requests through chat completions. Native calls return ZeroGPU's reasoning output items for glm, gpt-oss and qwen3, which the bridge dropped. Checked live on 2026-10-22 through litellm.responses for every model, non-streaming and streaming, plus a gpt-oss tool call. LFM2.5-1.2B-Instruct streams correctly now that ZeroGPU's text_generation lane emits Responses SSE
* fix(zerogpu): stop inferring the zerogpu provider from api_base alone
Listing https://api.zerogpu.ai/v1 in openai_compatible_endpoints rerouted bare model names on that api_base from openai to zerogpu. A bare gpt-5.6-luna call with verbosity used to return 200 and started raising UnsupportedParamsError. Drop the entry and its api_base-alone test, so zerogpu is only selected through the zerogpu/ prefix
* fix(zerogpu): price gpt-6-luna, llama-3.2-3b, LFM2.5-1.2B-Thinking and qwen3.6
A zerogpu/* wildcard served these four chat models with no cost-map row, so their calls logged $0 spend. Add rows at ZeroGPU's catalog prices from https://api-dashboard.zerogpu.ai/api/models, with context windows and output caps from ZeroGPU's models table. LFM2.5-1.2B-Thinking has no cached price, like LFM2.5-1.2B-Instruct. gpt-6-luna is flagged supports_reasoning because LiteLLM already routes gpt-6 names as reasoning models. Checked live on 2026-10-28, all four now report nonzero response_cost
* fix(zerogpu): drop the retired max_tokens field from the zerogpu rows
Upstream #48471 retired max_tokens from the cost map in favor of max_input_tokens and max_output_tokens, and test_no_row_carries_the_retired_max_tokens_field failed on all 13 zerogpu rows. Every row already carries the same value in max_output_tokens, so nothing is lost. The zerogpu limits test now checks that each row's output limit fits its context window
* chore(zerogpu): regenerate provider endpoint support for zerogpu
Upstream #48619 generates provider_endpoints_support.json from the cost map and checks it in CI, and the hand-written zerogpu entry no longer matched. Regenerated with scripts/generate_provider_endpoints_support.py. Only the zerogpu entry changed, and it now matches what the generator emits for other JSON-registry providers such as openinfer
* fix(zerogpu): flag tools, json_schema and prompt caching on gpt-6-luna
ZeroGPU serves function calling, tool_choice, json_schema response_format and prompt caching on gpt-6-luna, so set supports_function_calling, supports_tool_choice, supports_response_schema and supports_prompt_caching on its row in both cost maps. Checked live on 2026-10-28, a weather tool call came back with the right arguments, json_schema output validated, and repeated prompts reported 3260 of 3263 tokens cached
* fix(zerogpu): set qwen3.6-35b-a3b context to 262144 and flag its tools and reasoning
ZeroGPU accepts up to 262,144 input tokens on qwen3.6-35b-a3b and serves tools, tool_choice, json_schema response_format and reasoning_effort on it. Raise max_input_tokens from 16384 and set supports_function_calling, supports_tool_choice, supports_response_schema and supports_reasoning in both cost maps. Before this, LiteLLM rejected tools and reasoning_effort for the model. Checked live on 2026-10-28, a 209,905-token prompt succeeded, an oversized one was refused with a 262144-token limit, and tool calls, json_schema output and reasoning_effort all worked
* fix(zerogpu): flag vision on gpt-6-luna and qwen3.6-35b-a3b
ZeroGPU reads image inputs on gpt-6-luna and qwen3.6-35b-a3b, so set supports_vision on both rows in both cost maps. Checked live on 2026-10-28, both models named the animal in an image_url photo, and the image showed up in their prompt token counts
* feat(rust): one typed decline from core up to each host
Rust core says it cannot serve a request with one Decline that travels
unchanged through llms and inference up to the host. The Python bridge
raises RustBridgeDeclined for it in route_failure before the public
exception mapping, so dispatch falls back to legacy Python instead of
failing the call, and the gateway answers 501. Every route collapses
errors after the send with Error::after_send, which keeps a provider
answer and a response fault as they are and nests anything else as the
source of an invalid response, so a billed call can never read as a
decline. Response-side cases that used to decline are now
ErrorDetail::Unhandled response faults.
The rust-error skill documents declined() as the first question both
boundaries ask, and the Python suites pin that a native decline reaches
the dispatcher before any provider IO.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(rust): keep post-provider hook failures terminal
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http
The workspace moves to reqwest 0.13, so litellm-http no longer carries a
second reqwest just for rmcp. The mcp feature, its pool and its proxy
conversion go away, and the gateway hands rmcp a pooled NoRedirect client
that already carries the TLS, proxy and timeout settings
The Client test helpers collapse into for_test, a no-redirect client
without TLS or proxy settings, and wrap_for_test for the few tests that
need a hand-built reqwest client
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(http): honor transport settings for Rust WebSockets
The Responses WebSocket connected through tokio-tungstenite with its own
native-roots TLS, so it ignored the configured CA bundle, verify flag,
client certificate, proxies and timeouts. The handshake now goes through
a pooled reqwest client (ClientVariant::WebSocket, HTTP/1.1, no
redirects) and upgrades the response, so it shares the settings every
other outbound request uses
The upgrade response is checked for the Sec-WebSocket-Accept key, the
Upgrade and Connection headers and a subprotocol that was offered
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(http): build outbound requests as reqwest::Request
OutboundRequest was a hand-rolled copy of reqwest::Request. Routes now build
a reqwest::Request directly and RequestSigner reads the body bytes back out
of it, so the signer still covers exactly what is sent. SigV4 signing moves
onto HeaderMap and takes the method, which drops the BTreeMap plumbing and
the header casing table
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(http): make litellm_http::Error the one opaque error
transport::Error and media::Error fold into litellm_http::Error, an
Arc<Repr> newtype whose private variants keep the typed reqwest, io,
rustls and tungstenite causes and own every message. Callers can no
longer build an error with a message of their own. They ask through
dispatched, is_request, status, upstream_response and tls_source
One From<reqwest::Error> now classifies connect, network and timeout
and strips the URL. The WebSocket handshake reports each failed check
as its own variant and owns its connect timeout. OCR drops the media
variants it mirrored, and inference::Error maps a header the signer
computes to Unsupported for every route, not only chat
The error rules move out of AGENTS.md into the rust-error skill, which
also records the decisions behind this design
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(rust): split rust-error skill into thin SKILL.md with references
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): render causes once and ask predicates at the boundaries
The four WebSocket handshake variants collapse into Handshake(HandshakeFault), and media download failures no longer answer dispatched() since they happen before the provider call
ErrorDetail in llms and auth-types, the inference error and the OCR error now store their cause in a field named cause with no #[source], so to_string() carries it exactly once and source() is None. Tests that walked the chain now destructure the variant and downcast the cause
The gateway asks is_unsupported() and is_missing_credential() on the inference and OCR errors instead of matching through nested enums, and litellm_auth::Error answers is_missing_credential() for both
The rust-error skill gains axum and pyo3 references, boundaries.md describes the real predicate order and the known divergences, the testing example asserts dispatched() correctly, and shape, classification, conversions, messages-and-causes and recipes agree with the code again
* docs(rust): focus the rust-error gateway page on the error flow and add a rust-gateway skill
The former axum page toured gateway-inference: its status match, the envelope
table, an extractor, the unsupported route and the Sse closure. Those details
belong to the gateway crates and go stale with them. The page is now gateway.md
and follows an error from the provider failure through each From into
IntoResponse, where it is classified once and rendered by surface and framing.
The gateway-structure material moves to a new rust-gateway skill: envelopes per
API surface, extractors and path registration, SSE relay, and the router test
harness.
* test(inference): pin provider URL redaction on every route's transport error
Chat, Messages, Responses and transcription each get a route-level test that
fails if a reqwest error reaches the caller with its URL. The Messages stream
decoder also takes body errors through litellm_http::Error like every other
reqwest error
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(rust-error): adopt std source chains and add litellm-error Report
Messages describe their own layer and the cause is the source, boundaries
render the chain once with litellm_error::Report. Corrects skill claims
the audit found stale against the code.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): keep causes as sources across http, auth, secrets, cache and utility crates
Messages describe their own layer and every cause is a typed source,
predicates match exhaustively, and boundaries render with
litellm_error::Report. Media downloads no longer count as dispatched,
Error::upstream bounds the provider body itself, and a forwarded
header SigV4 cannot sign is the caller's fault.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): keep causes as sources in llms and the gateway crates
ErrorDetail loses its string variant, OCR provider variants become data,
host faults stop counting as the caller's, a tunnelled transport error
classifies the same on every stream path, and each gateway crate has one
Error with one status() and extractors that reject in its envelope.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): nest llms errors in inference and ask predicates in route tests
litellm_inference::Error nests litellm_llms::Error instead of mirroring
its variants, host driver faults get their own variant, every predicate
matches exhaustively, and route tests ask predicates instead of matching
transport variants.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): map bridge and gateway-inference errors once and render them with Report
RustUpstreamError has one constructor that always sets headers, argument
checks raise typed errors mapped once, OCR asks upstream_response(), the
Responses stream error event comes from the error type, gateway-inference
loses its string variants, and auth faults classify through one
litellm_auth predicate on every route.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(rust-error): carry OCR provider headers as a HeaderMap and keep outages off the caller
The OCR provider error and get_error_class take reqwest's HeaderMap, the
bridge turns it into Python's (name, value) pairs once. Credential
acquisition and provider SDK failures are no longer the caller's fault,
the UI hides auth and backend causes, and chat keeps a provider answer
as is.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(rust-error): correct skill claims against the aligned code
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): fix the remaining sweep findings in gateway, llms, auth and cache crates
Auth rejections hide their backend cause on every inference renderer,
path parameters reject in the surface envelope, Textract's unsupported
document and Azure DI's unparseable poll URL get typed variants, the
credential chain exposes its last failure as the source, gateway-mcp
asks predicates over rmcp errors, and the S3 and Azure blob transports
classify through litellm_http::Error.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(rust-error): fix the remaining sweep findings on the Python side
host-python keeps a native error's chain and returns blocking-pool
cancellation instead of panicking, Vault transport failures convert
through litellm_http::Error so no URL reaches Python, the bridge asks
predicates instead of matching three levels into Vault errors, and the
last string-built PyErrs become typed errors mapped once.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* build(deps): refresh compatible dependencies flagged by OSV
* refactor(rust): remove redundant client construction comment
* test(rust): cover configured MCP proxy and CA bundle
* fix(http): preserve native WebSocket trust and optional protocols
* fix(http): allow plain WebSockets without native roots
* fix(http): normalize provider URLs before building outbound requests
* fix(rust): preserve OCR download status and reduce error size
* fix(rust): preserve upstream bodies and bound diagnostics only
* test(rust): preserve bridge serialization boundary in body regression
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(http): build outbound requests as reqwest::Request
OutboundRequest was a hand-rolled copy of reqwest::Request. Routes now build
a reqwest::Request directly and RequestSigner reads the body bytes back out
of it, so the signer still covers exactly what is sent. SigV4 signing moves
onto HeaderMap and takes the method, which drops the BTreeMap plumbing and
the header casing table
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(http): normalize provider URLs before building outbound requests
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(http): honor transport settings for Rust WebSockets
The Responses WebSocket connected through tokio-tungstenite with its own
native-roots TLS, so it ignored the configured CA bundle, verify flag,
client certificate, proxies and timeouts. The handshake now goes through
a pooled reqwest client (ClientVariant::WebSocket, HTTP/1.1, no
redirects) and upgrades the response, so it shares the settings every
other outbound request uses
The upgrade response is checked for the Sec-WebSocket-Accept key, the
Upgrade and Connection headers and a subprotocol that was offered
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(http): preserve native WebSocket trust and optional protocols
* fix(http): allow plain WebSockets without native roots
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http
The workspace moves to reqwest 0.13, so litellm-http no longer carries a
second reqwest just for rmcp. The mcp feature, its pool and its proxy
conversion go away, and the gateway hands rmcp a pooled NoRedirect client
that already carries the TLS, proxy and timeout settings
The Client test helpers collapse into for_test, a no-redirect client
without TLS or proxy settings, and wrap_for_test for the few tests that
need a hand-built reqwest client
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* build(deps): refresh compatible dependencies flagged by OSV
* refactor(rust): remove redundant client construction comment
* test(rust): cover configured MCP proxy and CA bundle
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages
Move the unified /v1/messages code out of a directory called pass_through, since it is not the
passthrough feature. The inner messages sub-package becomes native, and the Vertex AI partner
model experimental_pass_through package becomes messages. The old packages stay as import shims
that warn once and alias every submodule in sys.modules, so old deep imports still resolve
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(anthropic): keep Final variables out of loops in the rename shim
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): match the warning text in the rename shim test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(anthropic): resolve old pass_through imports lazily through a meta path finder
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(anthropic): mark the alias loader spec restore for the type discipline gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(anthropic): format the renamed package shim
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(anthropic): keep the rebind-ok marker on the spec restore line
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(anthropic): carry the new package search path on alias specs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): declare the shim test locals Final
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
gpt_5_transformation.py becomes gpt_reasoning_transformation.py (OpenAI and Azure),
the Bedrock anthropic_claude3_transformation.py files become anthropic_claude_transformation.py,
anthropic_claude2_transformation.py becomes anthropic_legacy_text_completions_transformation.py,
and vertex_ai_partner_models/llama3 becomes vertex_ai_partner_models/llama. Class and symbol
names are unchanged.
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(rust): add circuit-breaker crate and guard redis-client with it
* fix(circuit-breaker): ignore stale probe drops
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(http_handler): name the timeout phase and the limit that fired instead of 'after None seconds'
Every HTTP verb on both handlers raised litellm.Timeout with the per-call
timeout argument interpolated into the message, which is None whenever the
caller relied on the client default, and always said "Connection" even for a
read timeout. One helper now reads the limit httpx actually enforced from the
failed request and names the phase that fired
Fixes#14635
* fix(rust_bridge): name the timeout phase in the vault timeout message to match the httpx handler
* fix(http_handler): drop the unreachable timeout fallbacks httpx already rules out
* refactor(rust_bridge): drop a doc comment that restated the timeout helper
Update certifi, Rust trust roots, and the Docker CA bundle to remove emSign ECC Root CA - G3
Require the fixed certifi release in litellm-core and retain libssl3 in Docker runtimes for Prisma compatibility
Co-authored-by: shin-berri <shin-laptop@berri.ai>
Every other crate names its error Error. The format crates already re-exported
it under that name, so only the inference crate and a few importers change
* refactor(rust-bridge): detect Python-only features in the catalog instead of Rust declines
* refactor(rust-bridge): split and document route-specific detectors
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Native Responses now hands back the same managed ids as Python: the
resp_ id carries the provider and deployment, encrypted-content items get
encitem_ ids and wrapped content under affinity routing, and container ids
become cntr_ ids. Encoded encrypted-content items in the input are restored
before the provider request. The codec lives in inference-responses with
goldens taken from litellm/responses/utils.py
* fix(databricks): use the native Anthropic route for Claude /v1/messages
Claude models on a Databricks workspace were bridged through chat completions on /v1/messages, which drops the safeguards field and never returns safeguard_results. They now call the workspace's /serving-endpoints/anthropic/v1/messages, the proxy forwards the client's anthropic-beta and anthropic-version headers to Databricks deployments, and the beta header map marks dangerous-tool-use-2026-09-03 as supported there. Any route whose platform does not take that beta drops safeguards together with it instead of answering 400. Non-Claude Databricks models keep the chat completions bridge
* fix(databricks): derive the dangerous-tool-use beta from safeguards instead of forwarding client betas
A Databricks Claude serving endpoint answers 400 to betas Claude Code sends on every turn, prompt-caching-scope-2026-01-05 among them, so the proxy no longer forwards the client's anthropic-beta header to Databricks deployments. The beta the classifier needs is derived from the safeguards body field, the same way the Azure AI route derives it. The Rust beta-header mirror stops rejecting the Databricks dangerous-tool-use cell so its config-cell test matches the JSON again
* fix(databricks): keep the billing block, build the messages route once, and pass the partner user agent
* fix(databricks): route Unity Catalog Claude names to the gateway messages route and keep env credentials
Unity Catalog model-service names now reach the AI Gateway's native Anthropic
route instead of a serving-endpoints path that answers 404 for them, and the
native route resolves the key and base through the same order the chat route
uses, so environment-only deployments keep working.
The native route is limited to Databricks foundation-model Claude names, an
unlisted provider forwards safeguards and the beta as sent, and the ten betas
the workspace rejects are marked unsupported for Databricks in the beta map
and its Rust mirror.
* test(rust): expect Databricks to drop the advanced-tool-use beta
* fix(databricks): keep passthrough safeguards, partner user agent, and classifier fallback
Only the OpenAI-compatible JSON providers drop safeguards now, so a
deployment opted into /v1/messages passthrough forwards the field and
the beta as sent. When a route drops safeguards and the proxy has a
classifier model, the proxy answers the verdict itself, as the chat
completions bridge did. The Databricks Messages route also reads the
databricks_user_agent param like the chat route.
* fix(databricks): drop rejected server tools under drop_params, short-circuit web search, route UC names from a full Messages URL
* fix(databricks): drop container on the native Messages route, as the chat completions bridge did
* fix(databricks): keep every api_base on a route the workspace serves and gate the derived beta on the map
Gate the dangerous-tool-use beta derivation on the beta map the way #43955 does, so GitHub Copilot, DeepSeek, and opt-in passthroughs keep the merge base wire. Recognize /serving-endpoints/anthropic api_bases, fall back to the merge base routing for an api_base path the workspace trim does not know, strip Bedrock invocation metrics from the streamed message_stop, forward client betas to Databricks filtered by the map, and keep tool_choice when a dropped server tool has no name
* test(databricks): cover the native Messages route, derived beta and JSON provider safeguards drop on the wire
* test(anthropic): expect the dangerous-tool-use beta derived from safeguards next to the client's betas
* fix(databricks): send client anthropic headers only on the native Messages route and keep SDK auth
Databricks chat completions, called directly or through the Messages bridge,
no longer receive the client's anthropic-beta and anthropic-version, as at the
merge base. The native Messages route still forwards them, filtered by the
beta map, without counting them as caller credentials, so a deployment with no
api_key keeps falling back to Databricks SDK auth. A pathless api_base goes to
the native route only for Unity Catalog names, matching the chat route.
* test(databricks): cover SDK auth with client anthropic headers and a Unity Catalog workspace root on the native route
* fix(databricks): keep client anthropic headers off an opted-in passthrough api_base
A databricks Claude deployment whose api_base is no workspace route and that opts
into /v1/messages with supported_endpoints falls back to the OpenAI-like
passthrough. That config does not filter betas through the beta map, yet it
received the native-only Databricks header entry, so Claude Code's
prompt-caching-scope beta reached the upstream raw and got a 400 where the merge
base answered 200.
Each Messages config now says whether it is the provider's native route, the
OpenAI-like passthrough says no, and the handler passes that answer when it
reads provider-specific headers, so native-only entries reach only native configs.
* test(databricks): cover client anthropic betas on an opted-in passthrough api_base
A databricks Claude deployment whose api_base is no workspace route and whose
model_info.supported_endpoints opts into /v1/messages takes the OpenAI-like
passthrough. The cell sends Claude Code's prompt-caching-scope and context-1m
betas through the proxy and asserts the caller gets the upstream's message and
the gateway receives no anthropic-beta, as on the merge base. The scripted
gateway answers 400 on the prompt-caching-scope beta, as the real one does
* fix(anthropic): keep beta map loads off shared threads and build the safeguards evaluator only when the proxy classifies
Unfiltered configs such as first-party Anthropic never read the beta map to decide safeguards support. Filtered configs await the map on its dedicated loader before reading it, on both the native and the MCP paths. The native handler decides after the upstream call and builds the evaluator only when the proxy classifies, so malformed messages keep the upstream 400. The Databricks dispatch tests assert the dispatched route instead of the config class, and the sail and Eden AI wire rows expect safeguards dropped, as JSON providers do.
* test(databricks): cover a loaded beta map that marks the safeguards beta unsupported
A remote beta map that nulls dangerous-tool-use for databricks while the bundled map allows it must send neither safeguards nor the beta to the serving endpoint, with or without a client beta, and the caller gets a 200 with no verdict.
* test(anthropic): annotate the MCP beta map recordings as Final
* fix(anthropic): drop safeguards on routes without the classifier only under drop_params
A route whose upstream does not answer safeguards (a JSON provider, or a map
that marks the dangerous-tool-use beta unsupported) now forwards the field and
the beta as the merge base did unless drop_params is set or the proxy runs its
own classifier, matching how litellm treats any unsupported param. Databricks
keeps dropping both, since its merge base bridge never forwarded the field.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* feat(openinfer): add OpenInfer as OpenAI-compatible provider
Register OpenInfer in the JSON provider registry with catalog models,
proxy create fields, and unit coverage so requests route via openinfer/
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(openinfer): assert catalog invariants instead of vendor rates
Pinning per-token prices made CI fail when the vendor list changed. Keep
the backup agreement and positivity checks our code owns.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(openinfer): add openinfer to the Rust OpenAI-compatible provider mirror
* fix(openinfer): align catalog with OpenInfer's live /v1/models
Replace the four catalog rows with the two models OpenInfer serves and
publishes a price for (@oi/GLM-5.3-Flash, @oi/Qwen3.5-27B), using its
listed per-token rates and context windows, and price-check them in tests
* fix(openinfer): use OpenInfer's native Responses and Messages APIs, allow tools on unpriced models, price Qwen3.5-9B
Declare /v1/responses and /v1/messages for openinfer, since OpenInfer serves both natively. Let JSON providers declare provider-wide capabilities in providers.json, read through get_provider_info, so tool calls reach OpenInfer for models without a cost map row. Send max_completion_tokens as is, set output caps to each model's context window, mark the three rows as reasoning models, add Qwen3.5-9B at its listed rate, and wire openinfer into models_by_provider so the openinfer/* wildcard lists its models.
* fix(openinfer): let a model's own capability row win over provider defaults in get_model_info
Provider defaults now only fill capability fields the cost-map row leaves unset, so a row or deployment that turns function calling off stays off. Also marks openinfer_models as Final.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(rust): add the dangerous-tool-use beta when an anthropic /v1/messages request carries safeguards
* test(rust): check the dangerous-tool-use beta reaches the wire with safeguards
* fix(rust): derive the dangerous-tool-use beta only for hosts with a beta map column
DeepSeek and the other hosts without a column in anthropic_beta_headers_config.json
keep forwarding safeguards and client betas as sent. Adds the wire-level audit tests.
* fix(rust): add the safeguards beta on Azure AI and Claude Platform hosts
Azure AI and Claude Platform Messages transforms now add the
dangerous-tool-use beta for a non-null safeguards field, through the
Azure AI and Anthropic beta-map columns. The safeguards wire and chaos
tests get unique file names so they do not collide with the Python
fix's tests, the Python-route test asserts the fixed behavior behind a
BUG skip, and the DeepSeek test checks that no beta is added
* fix(rust): keep Claude Platform out of the safeguards beta until a route can prove it
Claude Platform has no beta-map column and no QA account, so it goes back to sending
safeguards with no derived beta, like DeepSeek. Also release held chaos-test requests
before the thread pool waits on them, and mark the no-column test as rstest.
* fix(rust): derive the safeguards beta for Claude Platform and keep the null-cell test off Databricks
Claude Platform on AWS answers 400 to safeguards without dangerous-tool-use-2026-09-03 and 200 with it, so its Messages transform derives the beta through the Anthropic column again. The null-cell case now uses only Bedrock Converse, since Databricks support for the beta is changing in a sibling PR.
* fix(rust): drop a null safeguards key instead of sending it without its beta
Anthropic rejects any safeguards key, null included, when the
dangerous-tool-use beta is missing, so an explicit "safeguards": null on the
Rust gateway still answered 400. The shared Messages transform now drops a
null safeguards key on every host, as the proxy already drops None params
before calling Rust, so it answers 200 with no beta.
The scripted peer in the integration wire tests now rejects the key on
presence, matching the real API.
* test: cover Bedrock Mantle in the null safeguards case and match the vendor's non-list wording
The Rust null-safeguards regression test now also runs for bedrock_mantle, whose beta is keyed on the field being present. The scripted Anthropic peer answers a non-list safeguards value with the real API's "valid array" wording.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* ci(cost map): remove the generated model prices JSON schema
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(cost map): keep schema-independent cost map tests after dropping the schema
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(cost map): keep the schema file until main's guard stops requiring it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(cost map): let bot sync PRs keep touching the schema file until it is deleted
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(rust-bridge): let each route host pick the body params
The native routes projected request body params from a name list, hard-coded in
Rust for Messages and read from `PARAMETERS` for Chat Completions and Responses.
Each route host now answers `body_params(request)` over the keywords the call would
send, so the Python side owns which params reach the provider. No behavior change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(rust-host): use read-only body parameter types
Co-Authored-By: yujonglee.dev@gmail.com <yujong@berri.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(rust-bridge): move the route host modules under host/routes
Each native route's Python half lived in its own `<route>/route_host.py`, apart
from the shared host modules Rust also imports by name. They now sit together in
`litellm/rust_bridge/host/routes/<route>.py`, with their unit tests moved to the
mirrored path. No behavior change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(rust-host): reference messages route alias
Co-Authored-By: yujonglee.dev@gmail.com <yujong@berri.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The route host now reports get_configured_request_timeout() in MessagesSettings, and prepare uses the call timeout first, then that setting, then the 600s default. Before this, litellm_settings.request_timeout and REQUEST_TIMEOUT were ignored on the native path, so a long turn that works on Python timed out after 10 minutes
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The Responses route now resolves openrouter alongside openai. The
OpenRouter config reuses the OpenAI request and response transforms and
owns only its bearer credential (OPENROUTER_API_KEY, then OR_API_KEY) and
base URL (OPENROUTER_API_BASE). Wire model ids follow Python's
get_llm_provider, including the openrouter/auto native id with an
explicit provider. The Python route host no longer hands litellm.openai_key
to OpenRouter.
The OpenRouter live test lives in tests/live/openrouter.rs and returns
early when the provider key is not exported, so cargo test stays offline
by default instead of hiding it behind --ignored.
Co-authored-by: nate-berri <nate@berri.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* fix(vertex): report an unreadable credentials file as a read failure
Tell a path apart from inline JSON by shape, not os.path.exists().
Fixes#40166
* test(vertex): narrow pytest.raises to the expected message
* fix(vertex): log the credentials path instead of returning it to the caller
* refactor(vertex): log the credential source decision where it is made
* fix(vertex): handle paths open() rejects with a bare ValueError
* fix(vertex): redact the credentials path before it reaches the log
* test(vertex): cover the brace fallback and non-text credentials file
* test(vertex): exclude the unreachable exhaustiveness guard from coverage
* refactor(vertex): read the failure's fields off the matched object
CodeQL's py/uninitialized-local-variable does not follow keyword capture
patterns in a match statement and reported `path` and `reason` as possibly
unbound. Narrowing on the class and reading the attributes says the same thing
without a suppression.
* fix(vertex): accept a read-only mapping in extract_aws_params
* fix(vertex): keep encoded credentials out of the log and cover the legacy route
* fix(vertex): give one message for every credentials file failure and pick file or JSON by shape in Rust
* fix(vertex): read a `{`-named key file in Rust, name base64 there, and give one message when Google auth rejects a credentials file
* fix(vertex): read an unreadable `{`-named key file as a file, cap key file reads, and drop storage advice from the file message
* test(vertex): integration cells for credentials file and inline value failures
* test(vertex): drive the Rust messages cell through Vertex Claude
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* refactor(rust-bridge): return an unstarted Execution from native entrypoints and drive it in Python
Rust's run_call built Python streams itself and imported
litellm.rust_bridge.streams by name, so sync calls were driven in Rust
while async calls came back as a Rust-made coroutine. Every native
inference entrypoint now returns one unstarted Execution and
public_execution.py drives it with lifecycle.run or lifecycle.drive,
wrapping streams and _hidden_params on the Python side. Rust only
imports the lifecycle step classes through StepTypes, and
python-bridge/src/lifecycle.rs, PythonLifecycle and streams.py are gone.
The adapter trusts the _native.pyi contract with a single cast instead
of a per-request runtime_checkable isinstance. Binding tests assert the
adapter starts the execution and returns its completed value rather
than checking callable identity.
* refactor(rust-bridge): fold lifecycle and public_execution into one execution module
The public stream wrappers only forwarded to the lifecycle streams and added the
header dict, so the streams now carry _hidden_params themselves. lifecycle.py no
longer held any call lifecycle, just the Execution driver, so it is renamed to
execution.py and absorbs the synchronous and asynchronous adapters
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(rust-bridge): keep execution.py free of third-party imports
The host-python tests load execution.py into a bare interpreter, so the
pydantic header validation broke them. The stream head comes from the
binding's encode_stream_head, which always builds a str-keyed dict
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(host-python): preserve pre-async hook coverage after execution handoff
* style(rust-bridge): sort litellm_host_python imports
Co-Authored-By: Yujong Lee <yujong@berri.ai>
* test(rust-bridge): drive unstarted native calls through execution in the split lifecycle tests
Co-Authored-By: Yujong Lee <yujong@berri.ai>
* fix(rust-bridge): mark execution TypeVar as Final
Co-Authored-By: Yujong Lee <yujong@berri.ai>
* test(rust-bridge): cover stream close, read failure, and sync suspension in execution
Co-Authored-By: Yujong Lee <yujong@berri.ai>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
