mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-10 08:28:25 +00:00
601 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
ryan-crabbe-berri
|
f069da8e0e
|
fix(anthropic): report temperature/top_p as supported only when the model keeps them (#50144)
* fix(anthropic): report temperature/top_p as supported only when the model keeps them Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(vertex_ai): accept the generic unsupported-param message for Claude batch rows 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> |
||
|
Nate Armstrong
|
067f93340f
|
refactor(router): delete the python router core, the rust core is the only core (#50178) | ||
|
Kerry Lu
|
f25fff42a6
|
fix(openai): never send OPENAI_ADMIN_KEY as the bearer token for a deployment without an api_key (#50218)
* fix(openai): authenticate raw chat requests with the deployment api_key only, never OPENAI_ADMIN_KEY
openai 3.x request options default to bearer_auth plus admin_api_key_auth, so a deployment whose api_key is empty sent Authorization: Bearer <OPENAI_ADMIN_KEY> to its api_base. Pass security={"bearer_auth": True} when the installed SDK's make_request_options accepts it (openai 2.x has no admin key fallback and no security kwarg)
* test(openai): assert the admin key never reaches the wire whether the SDK sends unsigned or refuses
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
|
||
|
Mateo Wang
|
88ea40e69c
|
fix(github-copilot): send the GitHub token directly instead of exchanging it (#50126)
* fix(github-copilot): use GitHub token directly Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(github-copilot): expire API base cache Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(github-copilot): restore authenticator coverage Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(github-copilot): update direct token auth tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(github-copilot): cover direct-token error paths Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(github-copilot): satisfy type-discipline gate 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> |
||
|
Pasqual Troncone
|
728c687418
|
fix(mistral): a named tool_choice is dropped, the model picks any tool (#39737)
* fix(mistral): a named tool_choice is dropped, the model picks any tool
Mistral's chat API takes tool_choice as an enum or as an object naming
one function, {"type": "function", "function": {"name": ...}}. The
mapper only handled strings, so the object was skipped and the request
reached Mistral with no tool_choice at all.
The pin is now rebuilt from the function name alone, since Mistral
rejects fields it does not define. Enum mapping is unchanged, and an
object without a usable name is still left out.
Fixes #39736
* fix(mistral): reject a tool_choice Mistral cannot take unless drop_params is set
* fix(mistral): warn when drop_params drops an unusable tool_choice
Return the unsupported tool_choice error as a value and raise it in
map_openai_params, so the helper models the failure and the caller owns
the exception. A tool_choice dropped under drop_params now logs a
warning naming the value and why Mistral cannot take it.
* fix(mistral): leave tool_choice to the no-tools removal when no tools are sent
An unusable tool_choice on a request with no tools answered 400, while the
merge base and every other OpenAI-compatible route strip tool_choice from
such a request and answer 200. Map tool_choice only when tools are present.
---------
Co-authored-by: Pasqual Troncone <pasqual.troncone@stratebi.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
|
||
|
quietjules
|
5a392b9e5f
|
fix(bedrock)!: keep Claude's thinking when response_format json_schema is set (#49696)
* fix(anthropic): stop forcing the response_format json tool when Claude will think A forced tool call skips Claude's thinking. The json_schema emulation forced json_tool_call unless thinking.type was enabled, so adaptive thinking and the models that think by default (Opus 5, Sonnet 5, Haiku 5.5, and the always-on families) lost their thinking on every structured-output request. AnthropicModelInfo.response_format_tool_can_be_forced is now the one check the Anthropic, Bedrock Converse (including the native output fallback) and Databricks paths use. It leaves the tool unforced when thinking is requested in any form or the model thinks by default, and keeps forcing it when the request turns thinking off (thinking disabled or reasoning_effort none) on a model that accepts forced tools. The new thinking_on_by_default cost map key marks Opus 5, Sonnet 5 and Haiku 5.5 on the providers that reach these paths, and a miss-only fallback rule covers unmapped Claude 5 and later ids. * fix(bedrock): route native output and thinking token counts by whether Claude will think Bedrock's native output opt-in now uses the same will-think check as the json tool, so Claude 5 models that think by default with no thinking param go native. Converse also asks for /usage/output_tokens_details on those models, so reasoning tokens are reported for them. * fix(anthropic): tell Claude to answer through the unforced response_format tool Moves the integration tests that check the forced JSON tool from Claude 5 models to Opus 4.8, since Claude 5 models now keep their default thinking and take the unforced tool or native output * fix(anthropic): keep open-object schemas on the json tool when Claude will think Native output closes every object, so an open object came back empty. Also declare thinking_on_by_default in the Rust model catalog and expect the Converse thinking-token field in test_main * fix(anthropic): hold streamed prose until the JSON tool decides the answer In json mode with the unforced JSON tool, Claude can write its working before it calls the tool. The stream now holds that text, drops it when the JSON tool answers, and sends it when Claude calls a caller tool or skips the JSON tool, matching the non-streamed reply. * test(anthropic): build the stream test events without nested comprehensions * fix(anthropic): keep always-on thinking models unforced, open objects native when thinking, and the tool instruction Claude-only * test(anthropic): keep main's open-object integration cases and cover the unforced tool on a default-thinking model * fix(anthropic): treat thinking False as thinking off so the JSON tool stays forced Cover thinking False on the Anthropic and Converse forcing tests, and pin that a Converse json_schema stream with the unforced JSON tool never sends Claude's working text as content * fix(anthropic): drop the thinking False forcing case that completion never reaches litellm.completion turns thinking False into no thinking param before any route sees it, so the case was dead on the request path and False keeps meaning the model's default * test(bedrock): collect the Converse json_schema stream chunks in one assignment --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
ryan-crabbe-berri
|
42b4cfc5bf
|
fix(nvidia_riva): send the api key exactly once by calling riva over grpc directly (#50140)
* fix(nvidia_riva): send the api key once per call by talking to Riva over grpc directly Drops nvidia-riva-client from the stt-nvidia-riva extra. Depending on its version it sent the bearer token zero times on plaintext or twice on TLS, so token-checking Riva deployments rejected every request (#50059). The provider now declares the few Riva messages it uses, opens its own grpc channel and puts authorization and function-id on each call exactly once * test(nvidia_riva): run the provider against a real grpc server built from nvidia's own definitions * fix(nvidia_riva): validate endpointing settings with pydantic before building the riva message * test(nvidia_riva): check the key is sent once over tls, and drop a comment that restated the code |
||
|
qibinjin
|
91f039f4e5
|
fix(azure): strip output-only reasoning content from Responses input (#50046)
* fix(azure): strip output-only reasoning content from Responses input * test(azure): cover idless encrypted reasoning replay * fix(azure): preserve existing status handling during reasoning replay * fix(azure): scope reasoning content filtering by provider * fix(azure): drop status and content from replayed reasoning items * fix(azure): forward non-object input items and drop reasoning content on every Azure route * fix(azure): drop replayed reasoning content only under drop_params Reasoning status is still dropped on every Azure route. Caller-set reasoning content now follows the created_by convention from #48783: it is dropped when drop_params is on and forwarded otherwise, so Azure answers its own 400. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
shrey
|
85fdea0fd1
|
fix(guardrails): apply guardrail masks to Bedrock InvokeModel Claude requests and replies (#49947) | ||
|
ryan-crabbe-berri
|
74783d38ea
|
fix(github_copilot): let per-user connections work with a custom GitHub client ID (#50116)
GitHub only issues Copilot tokens through copilot_internal/v2/token to its own Copilot apps, so a custom GITHUB_COPILOT_CLIENT_ID signed users in and then failed with no Copilot access. With a custom client ID, look up the account at copilot_internal/user for the seat and Copilot API address and send the user's GitHub token straight to Copilot. The default client ID keeps the token swap. |
||
|
zoveki
|
784754ca48
|
fix(azure)!: answer 401 when Entra rejects the deployment's credential (#49863)
* fix(azure): answer 401 when Entra rejects the deployment's credential A ClientAuthenticationError from the Entra token provider (wrong, expired or rotated client secret) used to surface as a retryable 500 carrying the app's client id and Entra trace ids. Map it to a 401 AuthenticationError that keeps the AADSTS code and first sentence with GUIDs redacted, on both the direct token fetch and the provider handed to the OpenAI SDK client. Network failures stay 500. * fix(azure): keep network failures to Entra a retryable 500 azure-identity wraps a transport failure in ClientAuthenticationError, so the 401 mapping now skips errors whose cause chain holds ServiceRequestError or ServiceResponseError * fix(azure): cover async token providers and Entra 5xx, and scope caller-sent Entra credentials * fix(azure): map only AADSTS-coded Entra rejections to 401 and keep caller credential failures out of cooldown An Entra ClientAuthenticationError now answers 401 only when its message carries an AADSTS code, its HTTP status is not 429 or 5xx, and the code is not the AADSTS50196 throttle, so a chained credential's outage or throttle stays a retryable error. Caller-sent Entra fields no longer change the deployment id; a 401 from a value the caller sent skips the shared deployment's cooldown instead. The Azure AI Foundry agent token fetch maps the same rejection, and the A2A endpoint answers it with HTTP 401. * fix(router): count router default_litellm_params as configured Entra credentials when deciding cooldown * fix(azure): keep transient Entra codes retryable and scope 401 handling to Entra rejections ClientSecretCredential drops Entra's HTTP status, so throttling and transient codes (AADSTS50033, 50196, 90006, 90024, 90033, 90055) now stay retryable instead of mapping to 401. The A2A endpoint answers 401 only for an AuthenticationError caused by an Entra token rejection, and the router skips cooldown for a caller-sent Entra field only on Azure-family deployments. The azure/ Decisions route and the Bing grounding search tool now map an environment-credential rejection to the same 401. * fix(azure): map only known Entra credential rejections to 401 and cover the OIDC token exchange Unlisted AADSTS codes keep the retryable 500, the router skips the 401 cooldown only when an Entra rejection caused it, and a federated token Entra rejects answers the same 401 on Azure chat, Responses and A2A agents * fix(azure): answer 401 for Entra rejections on the /azure passthrough and token counting The fallback hop skips cooldown when Entra rejected a credential the caller sent, Prometheus counts a deployment's own Entra rejection as a deployment failure again, and an OIDC exchange error keeps Entra's headers so Retry-After reaches the router. * fix(azure): keep a no-op caller Entra field from skipping cooldown and redact the passthrough 401 message A caller-sent Entra field now skips the deployment's cooldown only when it differs from the deployment, its named credential, the router defaults, the AZURE_* environment variables and the default scope. An empty value counts as unset, so a deployment whose own secret is wrong still cools down when the caller's field changes nothing about the token request. The /azure passthrough's Entra 401 message goes through the same internal hostname redaction as other client-facing errors. * fix(router): compare a caller's Entra field with the value the deployment uses A caller-sent Entra field skipped the cooldown only when it matched no configured source, so a value equal to an environment default the deployment overrides (a stale AZURE_CLIENT_SECRET, say) counted as the deployment's own and let a caller's rejected credential cool down a working deployment. The check now resolves the value the deployment would use without the caller, in order from the router defaults, the deployment, its named credential, the AZURE_* environment variables and the default scope, and skips the cooldown only when the caller's value differs from it. * fix(azure): follow the settings merge for empty Entra fields and keep non-rejection OIDC exchange errors unchanged * fix(azure): count only the failed attempt's Entra rejection and ignore a non-callable token provider * fix(azure): keep the streaming Entra rejection inside the failed attempt --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Meryem Sakin
|
4a7fb30b0a
|
fix(guardrails)!: check Anthropic and Responses request tools in tool_permission pre_call (#41011)
* fix(guardrails): check Anthropic-format request tools in tool_permission pre_call
The pre_call hook only collected tools shaped as {"type": "function", "function": {...}},
so flat tools from /v1/messages ({"name", "input_schema"}) and /v1/responses
({"type": "function", "name"}) were never checked and deny rules silently passed.
Reuse the shared anthropic_tool_names helper so every request tool name is checked,
and handle Anthropic tool_choice {"type": "tool"} in both block and rewrite modes.
Fixes #40583
* fix(guardrails): detect Responses API named tool_choice in tool_permission
Responses API named choices put the name at the top level ({"type": "function", "name": ...}),
so rewrite mode removed the denied tool but left a tool_choice pointing at it.
* test(guardrails): run tool_permission pre_call tests through real default_on gating
Build the guardrail as an always-on pre_call guardrail instead of patching should_run_guardrail.
* test(guardrails): type the new tool_permission pre_call test parameters
* fix(guardrails): keep the Responses API custom tool type distinct
Anthropic's user-defined tools carry type "custom", so pre_call mapped
that to "function" for tool_type rules. The Responses API has its own
custom tool type, and mapping it let a custom tool slip past a
tool_type deny rule when the default action is allow.
Normalize only for the formats where custom means a plain function, and
read tool names directly in the rewrite path, which never needed a type.
* test(guardrails): cover flat tools through Messages and Responses
Add blocked and permitted flat-tool cases through the running proxy, with
endpoint coverage and metadata for the current e2e harness
Require a guardrail policy verdict when checking denied tools so an
unrelated provider error cannot satisfy the regression test
Co-authored-by: Christopher Krah <christopher.krah@plexito.de>
* fix(guardrails): check namespace and nameless tools and relax tool_choice in tool permission rewrite
* fix(guardrails): check forced, grouped, loaded, and hosted tools by their real type
* fix(guardrails): drop references to removed tools and count loaded tools in tool permission rewrite
* fix(guardrails): check tools sent outside top-level tools in tool permission
* fix(guardrails): judge namespace members by their bare name as a fallback and keep rewrites valid for Gemini, Bedrock and hosted tools
A namespace member is checked by namespace__name first, and by its bare name when no rule names the joined one. Rewrite mode now prunes Gemini allowedFunctionNames and turns off forced calling when no function is left, drops a removed hosted tool from allowed_tools, reads Bedrock toolSpec and systemTool blocks by name, skips cachePoint markers, and leaves a tools field that is not a list for the provider to reject instead of failing with a 500
* fix(guardrails): let only name rules decide a namespace member's bare-name fallback
* fix(guardrails): judge malformed tool types, empty Gemini name lists and pass-through Anthropic tools like the endpoints do
A tool or tool_choice whose type is not a string now reads as untyped instead of crashing the guardrail with a 500, and a null type key is never read as a Gemini tool part. An empty allowedFunctionNames list no longer turns off the functions a rewrite kept. An Anthropic custom tool reads as a function by its input_schema on every route, so a pass-through route judges it the same as /v1/messages. A Responses WebSocket frame now forwards the extra_body tools a rewrite stripped
* fix(guardrails): judge a named hosted tool by its type and keep a nested chat custom tool custom
* fix(guardrails): keep judging Anthropic client tools and type-named server tools by their name
* fix(guardrails): judge a named tool by its name alone only when the name is its type's own
* fix(guardrails): judge the function a tool names beside a declaration list or a top-level name
* fix(guardrails): judge Gemini hosted keys whatever the tool type and a namespace's function
* fix(guardrails): judge legacy functions entries like tools and send Gemini a namespace's members
* fix(guardrails): judge a namespace member by every name a provider reads and send Gemini its schema converted
* fix(guardrails): judge a legacy functions entry as a function and relax a tool_choice in extra_body
* fix(gemini): keep a namespace whole when inlining its members would repeat a function name
* fix(guardrails): judge a namespace member by every bare name that shares its qualified name
* fix(vertex_ai): declare a repeated namespace member name once instead of sending namespace names to Gemini
* fix(guardrails): judge a tool_choice sent in extra_body like a top-level one
A forced name only extra_body.tool_choice carried was never checked, so block mode let a denied name through to the provider
* fix(guardrails): judge a Gemini namespace member returned by its bare name and force a named namespace's members
* test: keep formatter churn out of the tool_permission and Gemini test files
* fix(guardrails): judge extra_body.input tools, argument-aware alias rules, and exact forced Gemini functions
Tools loaded in extra_body.input are now checked and stripped like top-level input. A returned
namespace member is judged by the alias whose first name rule its arguments satisfy. A forced
Gemini name that matches a top-level function keeps that function. Alias grouping and Gemini
declaration dedupe now run in one pass instead of quadratic scans.
* fix(guardrails): judge and rewrite every tool field sent inside extra_body
extra_body is merged into the upstream body, so functions, function_call,
mcp_servers and toolConfig nested there reached the model unjudged. Treat
extra_body as a second request layer that is collected and rewritten the
same way as the top-level request.
* fix(guardrails): judge Gemini hosted keys by key and count only the tools a provider receives after extra_body
* fix(guardrails): relax a tool_choice that names a dropped namespace member by its bare name
Gemini and Anthropic chat send namespace members under their bare names, so rewrite mode now treats a dropped member's bare name, and an emptied namespace's own name, as removed when no kept tool still carries it
* fix(gemini,guardrails): keep a top-level function over a same-named namespace member and leave malformed tool values to the provider
Gemini and Vertex chat now declare a top-level function over a namespace member that shares its name, so a forced call gets the top-level schema. post_call judges a returned name a top-level tool carries as that tool, and pre_call no longer raises on an unhashable or non-string tool name, input item type, or function_call name.
* fix(guardrails): judge a returned namespace member named like a hosted MCP server as that member
* fix(gemini,guardrails): send a namespace as main did when another tool has a member's name
Gemini chat inlines a namespace's members only when no other tool, namespace
member, or legacy functions entry declares the same name, and otherwise sends the
namespace by its own name as main did. A tool_choice naming such a namespace
forces the namespace itself. The tool permission post_call reads top-level names
the way Gemini declares them and judges a call the Responses bridge tags with a
namespace as that member.
* fix(gemini): send colliding namespace members as namespace__name functions and judge them in post_call
When a namespace member shares a name with another tool, Gemini chat now gets that namespace's members as namespace__name functions instead of one function named after the namespace, so every function it can call is a name the rules judged. Declared names are counted once, and a forced member maps to each holder's qualified name.
post_call judges a returned namespace__name as that member, by its qualified or bare name the way pre_call does, so a bare-name allowlist or denylist applies to it.
* fix(gemini): keep generated member names unique and let a top-level function own its exact name
A namespace that listed a member twice, or a generated namespace__name that
repeated a top-level function, sent Gemini two declarations with one name, and
Gemini answered 400 where main answered 200. A name a namespace lists twice is
now one member, and a top-level function keeps its exact name.
post_call now judges a returned name a top-level function declares as that
function, never as the namespace member the name could also mean.
* fix(gemini): qualify namespace members by the namespace's top-level name
The guardrail judges a member as `name__member` from the namespace's top-level
name. Gemini built the name from `function.name` when the tool also carried one,
so a request could pass pre-call and reach Gemini under a name no rule judged.
* fix(vertex_ai): force only the namespace members Gemini is sent
A forced namespace or member on Gemini chat could still allow a generated name that a top-level function or an earlier namespace owns, so tool_choice forced an unrelated function. The forced names now come from the same collision checks the declarations use
* fix(vertex_ai): reject a forced namespace Gemini gets no member of, and resolve forced names in one pass
* fix(guardrails): judge a namespace member by a rule on its namespace's name
---------
Co-authored-by: Christopher Krah <christopher.krah@plexito.de>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
|
||
|
Kerry Lu
|
e69da69891
|
feat: update EmpirioLabs models in model_prices_and_context_window.json (#49980)
* feat: update EmpirioLabs models in model_prices_and_context_window.json * chore(endpoints): regenerate provider endpoint support for the EmpirioLabs cost map rows * fix(empiriolabs): drop the retired max_tokens field, route embeddings and remove the unrouted rerank row The cost map test rejects any row carrying max_tokens, so every EmpirioLabs row keeps max_input_tokens and max_output_tokens only. The provider JSON now lists /v1/embeddings so embedding(model="empiriolabs/text-embedding-v4") reaches the OpenAI-compatible embeddings route instead of failing provider lookup. The qwen3-rerank row goes away because no rerank route exists for the provider. Endpoint support regenerated from the cost map * fix(empiriolabs): mark audio input and image embedding input on the rows the provider lists as multimodal The three vision embedding rows get supports_embedding_image_input and the eleven chat rows whose input_modalities on GET https://api.empiriolabs.ai/v1/models include audio get supports_audio_input, so capability checks stop treating them as text only * fix(empiriolabs): carry the long-context price tiers on the 24 rows the provider bills in bands EmpirioLabs bills 24 of these models at a higher rate once the prompt passes 32K, 128K, 256K, 272K or 512K tokens, and the rows carried only the first band, so a 300K-token qwen3-7-plus request was priced at a third of the real cost. Each of those rows now carries input_cost_per_token_above_<N>k_tokens, output_cost_per_token_above_<N>k_tokens and, where the row already has cache_read_input_token_cost, cache_read_input_token_cost_above_<N>k_tokens for every band, taken from pricing[].min_context on GET https://api.empiriolabs.ai/v1/models for the base rows and from the Variants rate card on docs.empiriolabs.ai/models/<id> for the six variant rows * feat(empiriolabs): bill the per-call web search fee reported in usage.tool_usage EmpirioLabs charges a flat fee per invoked web_search, web_search_image or image_search call and reports the counts in usage.tool_usage on the chat response. The JSON provider config now carries that count as usage.server_tool_use.web_search_requests when providers.json sets special_handling.web_search_requests_from_tool_usage, the per-call web search cost path bills the usage-reported count instead of flooring to one call, and the 39 EmpirioLabs rows the provider lists a per-call search price for carry it as search_context_cost_per_query, from unit_pricing on GET /v1/models for base rows and the Variants rate card on docs.empiriolabs.ai for variant rows * fix(openai_like): mark the dict signature of transform_parsed_response_dict as matching BaseConfig for LIT001 * fix(openai_like): mark both dict annotations of transform_parsed_response_dict for LIT001 --------- Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Kerry Lu
|
b662f3f7a4
|
feat(decisions): add EmpirioLabs AI as a decisions provider (#49977)
* feat(decisions): add EmpirioLabs AI as a decisions provider empiriolabs/aplomb-1 now works with litellm.decisions and litellm.systemone, the proxy /v1/decisions and /v1/systemone routes, the decision model guardrail and the Admin UI. Requests go to POST /v1/decisions on the EmpirioLabs AI API with the System One body, keyed by EMPIRIOLABS_API_KEY with an optional EMPIRIOLABS_API_BASE Chat models keep routing through the existing OpenAI-compatible JSON provider, and a test pins that * ci: run the EmpirioLabs AI decisions tests in the llms unit shard * fix: align EmpirioLabs registration with CI gates --------- Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Kerry Lu
|
df78b16941
|
feat(openai): bill gov.api.openai.com FedRAMP endpoint with 1.1x uplift (#49951)
* feat(openai): bill gov.api.openai.com FedRAMP endpoint with 1.1x uplift * chore(openai): trim FedRAMP uplift diff * refactor(openai): bill the FedRAMP endpoint through its own fedramp_uplift_multiplier key * fix(ui): regenerate fedramp_uplift_multiplier doc comment in schema.d.ts * style: ruff format utils.py and reorder fedramp_uplift_multiplier in schema.d.ts * fix(openai): infer data_residency from OPENAI_BASE_URL and litellm.api_base when api_base is unset * test(cost): cover get_fedramp_uplift_multiplier fallback paths * fix(cost): apply fedramp_uplift_multiplier in batch_cost_calculator * fix(openai): derive data_residency from a supplied client's base_url * test: type the supplied-client data_residency test params --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
fd4cef22ea
|
refactor: clean up fresh tech debt in proxy auth reads, chatgpt credential forwarding, messages drop_params reads, router context signatures and spend log reads (#46643)
* refactor: clean up fresh tech debt in proxy sub-call budget checks, model search and logger init Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor: clean up fresh tech debt in otel baggage metadata, model budget limiter and batch line items Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * Revert "refactor: clean up fresh tech debt in otel baggage metadata, model budget limiter and batch line items" This reverts commit |
||
|
tavren27
|
b9ad61d4f6
|
fix(agentic)!: surface a failed agentic follow-up call instead of the pre-loop tool call (#49227)
* fix(agentic): surface a failed agentic follow-up call instead of the pre-loop tool call * fix(agentic): surface failed follow-ups from the OpenAI chat dispatcher and update pinned integration tests * fix(agentic): end a capped agentic turn on chat and responses instead of a retried 500 * fix(openai): run agentic hooks after the first call's error handling so a follow-up error keeps its own type and message * fix(agentic loop): end capped turns on every chat path and bill the first call when a follow-up fails A turn refused at max_agentic_loops now drops the internal tool calls of every hook that claims calls in it, while a call the client declared survives. The hosted_vllm and openai chat paths now carry the loop depth, fingerprints and max_agentic_loops into the follow-up, so they stop at the cap instead of looping forever. A failed follow-up call now records the first call's usage and cost on the request's failure log before the error reaches the client. A code interpreter sandbox that is missing or fails becomes the tool call's output for the model to handle, so the turn completes without a retry. On native streaming /v1/messages a hook or follow-up failure now reaches the client as an Anthropic error event with the mapped type, and compresr declares its retrieve tool so the stream holds it back. Comments and docstrings the branch added against the repo rule are removed * fix(agentic loop): bill retried attempts and clean up what failed or capped turns return The router's retry loop now carries each failed attempt's paid first call into the request's billing, so a request whose follow-up keeps failing bills every first call on its failure row, and one that recovers bills the failed attempt's first call on its success row. A failure row no longer adds unpriced estimated tokens on top of attempts that were billed, so its tokens match its spend A sandbox failure now answers the model with a fixed sentence and marks the code_interpreter_call as failed, without the sandbox's error text. Code interpreter on /v1/responses with Claude now runs its loop, because the bridged inner call no longer strips the hook's own markers Dropped internal tool calls leave the kept calls numbered from 0, also on a replayed stream. A capped native /v1/messages stream now says the loop hit its limit and that max_agentic_loops raises it, instead of asking the client to retry The agentic refusal and hook error logs no longer include the model or the exception text, and the agentic loop helpers take typed messages, params, and read-only fingerprints * fix(agentic loop): keep a recovered retry's cost breakdown on the response it returns A retried agentic request that recovers no longer adds the failed attempt's first call to its success row. The proxy keeps the follow-up's own row for that request id, so the added spend never showed up in the stored row, and that duplicate row is tracked separately. When every attempt fails, the failure row still bills each attempt's first call Pricing a first call for the failure row no longer replaces the request's cost breakdown. Before, a recovered retry answered with x-litellm-response-cost-original, -input, and -output from the failed attempt's first call. Now its headers and logged breakdown match a request that succeeds on its first try * fix(agentic): stop retrying a request whose agentic follow-up failed and bill every round it served An error raised by an agentic follow-up after the first call was served now carries a typed mark, so the router's retry loops, the mid-stream retry, and litellm's num_retries wrapper raise it as is instead of rerunning the whole request. A failure of the first call itself still retries, and fallbacks still run. The failure row bills every round the loop served before the failure, at any depth, and a later attempt that succeeds bills what the failed attempts paid on its success row, with the cost breakdown and the response cost headers adding up. The error response's x-litellm-response-cost reports the same amount its failure row bills. Failure rows outside agentic hooks keep the prompt-token estimate they had before. A refused tool call now matches by id among the refused ids, or by name among refused calls that carry no id, so a name-only refusal next to an id refusal is no longer kept. * fix(code_interpreter): delete a session sandbox whose code run failed so the next call starts a fresh one * fix(code_interpreter): delete only the session sandbox that failed, never its replacement * test(code_interpreter): type the session sandbox test helpers * fix(proxy): report what a failed agentic follow-up's failure row bills on /v1/messages errors * fix(agentic): keep the no-retry mark through error mapping and bill only failed follow-ups on success An agentic loop error that is not a provider error, such as the streaming chat cap or a crash in a hook's plan build, now keeps its no-retry mark when litellm maps it to an APIConnectionError, so the router no longer reruns every paid round. The mark is stored on the exception, so a built-in error can carry it too. A crash in a hook's plan build on /v1/messages and /v1/responses bills the first call on its failure row. A recovered attempt adds a failed attempt's usage to its success row only when that attempt was a failed agentic follow-up. Other failed attempts, such as a dropped stream, log their own row as on main. A code interpreter sandbox that fails while running the code now says the code may have run but its result is lost, instead of saying the code did not run. * test(responses): bill a retried MCP request each attempt on its own row again Round 4 stopped adding a non-agentic failed attempt to the success row, so this test goes back to main's assertions: the success row bills only its own rounds and the failed attempt's first round stays on its own failure row * fix(spend): name a failed follow-up attempt the success record already bills With the usage meter on, a failed agentic follow-up attempt gets its own charge-eligible record, and the request's success record also carries that attempt's usage and cost once the success row bills it. The success record now lists the attempt's record ids in included_attempt_ids, so a reader can tell the success record already covers it. Nothing changes when the meter is off * fix(spend): count a billed failed follow-up's tokens on the success row * fix(spend): bill a failed follow-up on a fallback served from cache * fix(spend): show a billed failed follow-up in a cached fallback's cost breakdown * fix(spend): keep a failed follow-up's billing state off the request-merged call details * fix(spend): record the cost breakdown of a successful agentic follow-up The chat agentic loop returned the follow-up response with the cost its own internal call had already stamped, so the request's logging reused that cost and never recorded cost_breakdown on the spend row. The loop now drops that stamped cost unless the follow-up was served from the cache, and the request prices the response itself --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Mateo Wang
|
d5ca88900c
|
fix(anthropic): answer an upstream Anthropic 529 as 529 overloaded_error on /v1/messages (#46063)
* fix(anthropic): answer a 503 as 529 overloaded_error on /v1/messages
Anthropic's error contract has no 503, so a client built against it (Claude Code) treats a 503 from /v1/messages as a plain 5xx and retries it ten times instead of taking its overload path. A Bedrock 503 now leaves /v1/messages and /v1/messages/count_tokens as 529 overloaded_error, for both a JSON answer and a stream that fails before its first byte.
An Anthropic 529 overloaded_error now maps to litellm.ServiceUnavailableError (503) instead of InternalServerError (500), so OpenAI-shaped routes answer it as 503, the status OpenAI documents for an overloaded engine, and router retry and allowed-fails policies key it as ServiceUnavailableError.
* test(proxy): expect overloaded_error on a 503 stream error after a keepalive ping
* fix(proxy): record the 529 the Anthropic routes answer and type the chat stream error frame
The messages route stamps the answered status on the exception before post_call_failure_hook runs, so the spend log row, the OTel server span, the failed-request metric, and alerting record the 529 the client saw instead of the deployment's 503, while the deployment failure metric and cooldown keep the deployment's own status. A chat completions stream error frame names the type its status stands for instead of the null .type ServiceUnavailableError carries. An Anthropic-shaped 503 envelope passes through as 529 overloaded_error through a validated TypedDict, and count_tokens answers every ProxyException as the Anthropic envelope. Five integration tests that pinned 503 on the messages route now expect 529
* test(proxy): expect the top-level Anthropic envelope from count_tokens errors
count_tokens now answers a ProxyException as a JSONResponse carrying the
Anthropic error envelope instead of raising HTTPException, which FastAPI
wrapped in {"detail": ...}. The three legacy error-format tests now read
the response body and check that no detail wrap is left.
* test(proxy): cover the 529 overloaded_error answer across routes, cooldown, and retry budgets
* fix(anthropic): keep Anthropic overloads as InternalServerError and answer 529 from the provider status
An upstream Anthropic 529 stays litellm.InternalServerError (status 500) so
InternalServerErrorRetries, InternalServerErrorAllowedFails, SDK handlers,
and the OpenAI-shaped routes behave as on main. The error now carries
provider_status_code, and the /v1/messages routes answer 529
overloaded_error from it.
* refactor(proxy): unwrap a mid-stream fallback error once instead of recursing for the provider status
* fix(anthropic): keep count_tokens' detail body, end keepalive streams with an Anthropic error event, and log any 529 as an overload
* test(integration): cover the audit round 3 cells and expect 529 on the count_tokens 503 cases
* fix(proxy): re-raise an unchanged stream HTTPException as itself and walk nested mid-stream fallbacks for the provider status
* fix(proxy): walk nested mid-stream fallbacks without recursion
* fix(anthropic): preserve 503s and answer upstream 529s on messages routes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic): answer an upstream Anthropic 529 as 529 on count_tokens
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): use integration coverage for keepalive errors
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>
|
||
|
Kerry Lu
|
ce73cf8b9d
|
chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974)
* chore(cost-map): remove the 52 rows whose provider retired them before 2026 * test(utils): pin the proxy function-calling parity case to azure/gpt-4.1 * test(batches): price the Azure batch-logging regression case against gpt-4.1 --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Aditya Batra
|
e9a6a25fe3
|
feat(providers): add Wally as an OpenAI-compatible provider (#45662) | ||
|
devin-ai-integration[bot]
|
d1e4b50d6a
|
fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
* fix(router): keep a deployment's token limits off the shared backend cost map key Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): preserve catalog token limits on shared keys Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): use catalog for shared token limits Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(anthropic): drop the class attribute patch from the deployment max_tokens test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): avoid provider auth during catalog key resolution Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: mateo <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Kerry Lu
|
65950dba8b
|
fix(main)!: carry the full per-call price entry on the logging object instead of writing litellm.model_cost (#49532)
* fix(main): price per-request custom pricing from the logging object instead of writing litellm.model_cost * fix(main)!: carry the full per-call price entry on the logging object instead of writing litellm.model_cost Direct SDK calls build one ModelInfo from the cost map row plus every custom pricing field on the call and price from it, so audio, tiered and directional per-second rates apply without touching litellm.model_cost. Router calls keep their registered deployment entry. completion_cost(completion_response=...) alone no longer sees per-call prices, pass custom_cost_per_second or custom_cost_per_token * test(cost): assert the exact per-second charge for per-call cost_per_second * fix(main): price Router request overrides and flat rates over inherited tiers in the per-call entry A Router call that sets its own price is priced from it over the registered deployment entry, PTU zeroing applied as at registration. Flat token rates on a call drop an inherited tiered_pricing table, which generic_cost_per_token would otherwise prefer * fix(main): keep tier rates for directions a call does not override and bill per-second-only calls per second A flat rate set on a call is written into every tier for that direction instead of dropping the tier table, so the other direction keeps its tier price. A call that sets only a per-second rate on a model with catalog token rates clears those token rates for the call so the per-second path applies * fix(main): apply a call's flat rate to its own tiered_pricing table when it supplies one * refactor(main): move per-call price entry resolution into litellm_core_utils/per_call_pricing The resolution logic is pure cost-map work with no dependency on dispatch, so it lives next to ptu_pricing and main.py keeps only the call sites in completion() and embedding() Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * refactor(cost): rename per_call_model_info parameter to requested_model_info_override Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
norkelbyte
|
3b35ae340d
|
fix(rate-limit): estimate embedding image and audio data URIs as media in TPM pre-call checks (#49831)
* fix(rate-limit): estimate embedding image and audio data URIs as media in TPM pre-call checks * fix(rate-limit): count embedding media as media only on models that embed it A data URI sent to a text-only embedding model is read as text, so it keeps the text estimate there. On models flagged supports_embedding_image_input, image and audio use the chat media estimates and PDF and video count at most the model's max_input_tokens. The same estimate now feeds project and key limits, the usage-based, latency and cost routers' deployment tpm, and the deployment itpm check. * fix(proxy): count embedding media only where the backend reads it as media Vertex AI, Gemini, Azure AI and Bedrock count a strict base64 data URI as media per item. Cohere counts it as media only when the whole batch is media, and Voyage, OCI and unknown models keep the text estimate. File blocks carrying a data URI count like the bare URI. The router context window pre-call check and the batch limiter now use the same estimate, resolving each deployment or JSONL row model to its backends. The cost map gains supports_embedding_image_input on voyage/voyage-multimodal-3 and oci/cohere.embed-multilingual-image-v3.0. * fix(router): hold each embedding media item to the context window on its own A PDF or video data URI alone already reserves at most the model's max_input_tokens, but the context window pre-call check then ran the blanked input through the Responses transform and added a few framing tokens, so a PDF that Vertex accepts got a 400. When every input item is media, the check now returns the largest item's media estimate, since an embedding request embeds each item separately * fix(proxy): leave embedding media out of the context check and narrow Bedrock media scope The router context window check now counts only the text of an embedding input, so Titan image lists no longer 400. Bedrock Marengo and Nova with a PDF keep the text estimate since they read those inputs as text or reject them, async_invoke Nova counts images as media, and the unused batch limiter change is dropped. * fix(bedrock): bill Cohere embeddings by Bedrock's input token count header * fix(embeddings): check data URI base64 in place and keep Bedrock Cohere text usage The strict base64 check now scans the payload in place instead of decoding and re-encoding a full copy. Bedrock's billed token header is used only for image requests, so text-only Bedrock Cohere usage matches main. The deployment itpm estimator change is reverted, since the router never passes embedding input to that check. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
yuneng-jiang
|
883a2d1572
|
revert(bedrock): restore STS identity probe behavior before #49763 (#49939) | ||
|
yuneng-jiang
|
e1c03c5423
|
fix(e2e): restore main qualification across providers and UI (#49763)
* test: check an unsupported budget sort field
* test: wait for dashboard navigation readiness
* test: support clustered provider caches with live fallback
* Revert "test: check an unsupported budget sort field"
This reverts commit
|
||
|
devin-ai-integration[bot]
|
083961731c
|
fix(model_prices): consolidate verified provider metadata and pricing (#49361)
* fix(databricks): mark audio and video input support on the Gemini 3.5 to 3.8 Flash rows * fix(model_prices): add Vertex AI and Together AI retirement dates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): correct perplexity agent api pricing and add gemini-4-argon, nemotron-3.5-super Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): consolidate verified pricing and Aplomb metadata Absorb verified pricing from #49547 and #49548 and Aplomb 1 metadata from #49539. Preserve provider tiers and remove an identical duplicate retirement key. Co-authored-by: Liutasil501 <schmid.martin501@gmail.com> Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore(model_prices): sync generated EmpirioLabs endpoint metadata Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): verify Nebius and EmpirioLabs model metadata Verify canonical EmpirioLabs rows from #49695 against published model pages, preserving pricing tiers and excluding unverified variants and specialty billing. Add Nebius models and cached-input prices from the official catalog and correct the Voyage legacy input limit. Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): absorb Bedrock Opus 5 batch prices, Vertex Omni Flash limits and Gemini 2.5 shutdown dates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): drop the EmpirioLabs rows and endpoint flags from this sync * fix(model_prices): merge main and dedupe the gemini-2.5 deprecation_date keys * fix(model_prices): set supports_video_input on the two new Nebius video models * fix(model_prices): add Azure AI Claude Mythos 5.1 and match Foundry max effort support Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com> |
||
|
zoveki
|
baddc67041
|
fix(anthropic)!: carry prompt_cache_breakpoint to cache_control on chat completions to Claude (#49783)
* fix(anthropic): carry prompt_cache_breakpoint to cache_control on chat completions to Claude
A content part carrying OpenAI's prompt_cache_breakpoint on a /v1/chat/completions request to Claude (Anthropic, Bedrock Invoke and Converse, Vertex AI, Azure AI) now reaches Claude as cache_control {"type": "ephemeral"} on the same block, so prompt caching works for OpenAI-shaped clients instead of the marker being stripped.
Only parts OpenAI accepts the marker on are translated, a client cache_control on the same block wins, and Converse translates only for models that take cache points. A 30m ttl or a malformed marker answers UnsupportedParamsError without drop_params and becomes a default 5m mark or no mark with it.
* fix(anthropic): hold translated prompt_cache_breakpoint marks to the 4-breakpoint cap
Marks past Claude's 4 cache breakpoints now answer 400 without drop_params and
keep the earliest under it, counting the client's own message, tool, and
top-level cache_control marks. The ttl and malformed-marker errors name
drop_params for proxy users too and no longer name a single provider.
* fix(bedrock): count Converse tool cache points in the breakpoint cap and gate unmapped models
A client tool cache_control or a tool_config injection point becomes a Converse tool
cachePoint, so it now takes one of the 4 slots before a translated marker does.
Converse only translates prompt_cache_breakpoint for a model the cost map says takes
prompt caching. An unmapped model such as an application inference profile ARN opts in
through model_info supports_prompt_cache_breakpoint, so a marker sent to every model of a
mixed fleet no longer turns a non-caching profile's 200 into Bedrock's 403.
Router prompt-caching affinity now treats a marked block like a cache_control one, and
requests without a marker skip the translation after one pass over their messages.
* fix(bedrock): count only the tool cache points Converse sends against the breakpoint cap
* fix(anthropic,bedrock): cap only the cache breakpoints each provider sends, and drop marks Nova cannot take on tool results
* perf(anthropic,bedrock): find the breakpoint cut-off by binary search so trimming many marks stays fast
* fix(anthropic): drop the duplicate drop_params left by the main merge
* fix(bedrock): let an inference profile's cache breakpoint flag win over its base_model
* fix(anthropic): keep the first and last prompt_cache_breakpoint marks past the cap
Under drop_params the translated marks that fit the cap are now split between
the start and the end of the request, so the stable prefix and the newest turns
both stay cached. The cap count also includes a native tool search tool that
keeps its cache_control on the wire.
Bedrock Converse now translates the marker only for the Claude and Nova
families, which Bedrock documents as taking cache checkpoints, unless the
deployment sets supports_prompt_cache_breakpoint. A guarded user turn keeps its
cache mark when the request fits the cap.
* refactor(bedrock): decide guarded cache marks with a typed bool helper
* fix(bedrock): validate guarded blocks before reading their cache mark
* fix(anthropic): let injection points replace client marks and keep non-Claude routes untranslated
When a deployment sets cache_control_injection_points, the client's
prompt_cache_breakpoint marks are dropped on targets that do not read them, so
the operator's injection points decide every Claude breakpoint.
OpenCode Go models served over the Anthropic messages endpoint translate the
marker only for Claude, and guarded Converse text keeps a cache mark only on a
model known to take cache points.
* fix(anthropic): keep client marks unless a message injection point replaces them on a translating route
A tool_config-only injection point no longer strips client prompt_cache_breakpoint marks, a flagged Bedrock profile no longer counts as reading the marker natively, and guarded Converse text skips the tool count when no message carries a cache mark.
* fix(anthropic): keep Bedrock and Claude deployments flagged for the marker on cache_control injection
A supports_prompt_cache_breakpoint flag on a Bedrock profile or a Claude deployment made the injection hook write OpenAI markers and prompt_cache_options, which Bedrock answers 400 for. Routes that translate the marker now never take the OpenAI dialect.
* fix(bedrock): reserve only the tool cache points Converse sends when trimming Claude cache marks under drop_params
* fix(anthropic): name the marker's accepted ttl values in the malformed prompt_cache_breakpoint 400
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
|
||
|
tavren27
|
482f3c37ed
|
fix(azure_ai): keep azure_ad_token out of the request body (#49769)
* fix(azure_ai): keep azure_ad_token out of the request body azure_ad_token is not a litellm-owned param, so get_optional_params routes it into extra_body and the azure_ai chat and Claude transformations merge it into the JSON body. Azure AI Foundry then rejects the call with 400 Unknown parameter / Extra inputs are not permitted. The Authorization header already comes from litellm_params, so drop the extra_body copy once at the top of the azure_ai dispatch, as the azure branches do. Type litellm.open_ai_chat_completion_models and open_ai_text_completion_models as Set[str] so the basedpyright gate does not grow from the untyped optional_params read. * fix(azure_ai): keep Entra credentials out of every azure_ai request body * fix(azure_ai): keep the Entra token out of the image edit form * fix(azure_ai): keep Entra credentials out of image edit extra_body too --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
norkelbyte
|
864b98acec
|
fix(bedrock)!: fail a Nova Sonic realtime session whose Bedrock stream drops instead of closing 1000 (#49170)
* fix(bedrock): fail a Nova Sonic realtime session whose Bedrock stream drops instead of closing 1000 The Bedrock SDK ends the output stream the same way for a dropped connection as for a session that sent sessionEnd, so the handler treated a dropped stream as a clean finish. The client got a 1000 close with no error event and the router logged 200 OK with no retry An output end now counts as clean only after the client left and the handler began closing the Bedrock input. An earlier end raises a 503 BedrockError, so the client gets an error event and a 1011 close, the failure handlers run, partial spend is still logged, and a retry of a committed session is still refused * fix(bedrock): fail a dropped Nova Sonic session right away and log it as failed When Bedrock's output side ends mid-session, by a drop or a modeled stream error, the client side no longer spends the close timeout sending close messages into the dead input stream, so the error reaches the app right after the drop. A session the app ends itself still sends Bedrock its close messages and closes the input The replay refusal now leads with the committed cause, so the error event and the cut 1011 close reason both start with it. It stays a 400 and is tagged as a failure outside the selected deployment, so router retries and fallbacks of a dropped session no longer add extra failure counts A clean realtime session now counts once toward its deployment's cooldown success counter, so cooldown reads the real failure rate instead of 100 percent. Realtime tpm and rpm counting is unchanged The spend row of a session the provider ended now reads failure with its error information, while the events already forwarded are still billed. A session the app ended keeps logging success * fix(bedrock): agree on a dropped realtime session's failure across loggers and the spend row A realtime session's success event now reports status failure, with the same error_information the spend row stores, when the session recorded a provider failure in its metadata. Usage already streamed stays billed and the router still counts one cooldown failure The spend row builder now runs every row's error_information through sanitize_error_information_for_spend_logs (DB size cap plus prompt redaction), so the realtime failure rows get the same treatment as the proxy failure hook, which no longer sanitizes on its own to avoid truncating twice Drop the selection-failure tag on the committed-session refusal, since the shared logging object already keeps a retried refusal out of cooldown, and pin the router's realtime success counting with an OpenAI realtime deployment * fix(bedrock): count realtime router successes only for sessions that logged one, and log first-turn drops The router counts a realtime success only when the session's success handlers ran, so a refused handshake or an upstream close before any frame no longer offsets its failure. The success event's payload status stays success again, so each logger gets one failure record per dropped session, while the spend row still reads failure from the metadata the Bedrock handler records. A committed Bedrock session that fails before any logged event now gets one zero-cost Logs row. After an output failure the input stream is closed in the background, so the SDK body writer finishes without delaying the client's error. Every input send failure reports the same 503 stream-ended cause as an output drop * fix(realtime): count a router success only for a session that ended cleanly A realtime session the upstream closes with 1011 or 1006 after its first frame now marks itself as ended abnormally where that close is seen, in the shared relay and in the OpenAI Live handler, so the router no longer counts it as a cooldown success. The success callbacks still run, so the proxy keeps the budget and parallel-slot settlement it had A Bedrock session that fails before Bedrock sends any usage now logs no success event, as on base. The spend-row failure fields go into a new metadata mapping instead of the request's own dict, validated with a pydantic TypeAdapter instead of an unchecked TypeIs guard. The handler tests drop a wall-clock bound and type their helpers * fix(bedrock): log a dropped realtime session's usage from its own logging state The failure event replaced the shared standard_logging_object while the queued success dispatch was still running its callbacks, so loggers received $0 and 0 tokens for a billed dropped session. * fix(proxy): settle a rate-limit reservation once when a request logs a failure and a success A dropped realtime session fires a failure event and then a success event for the same call. The v3 limiter refunded the TPM reservation on the failure and released it again on the success, so the key's TPM counter went negative. The success path now skips a reservation the failure already released and marks it settled for a later failure. The realtime handler test callbacks are typed * fix(rate-limit): settle each token reservation once when a request logs both a failure and a success A dropped realtime session logs a success for its usage and then a failure. After a success the limiter now clears every reserved amount (TPM, PTU, ITPM, OTPM), so a later failure refunds nothing twice. A new reservation written in the same context after a released one now starts clean, so reserve, fail, reserve, succeed charges the second request's usage once instead of 78 TPM or 28 ITPM for 27 and 20 used * fix(rate-limit): take a token hold before awaiting so concurrent success and failure callbacks settle it once * fix(rate-limit): track the ITPM/OTPM hold's release apart from TPM so a nested pre-call keeps the request's project IO charge * test(rate-limit): pin the split hold-release flags across nested MCP pre-calls * fix(realtime): count a relay that fails on its own as an abnormal end * test(realtime): pin the relay failure exit with a client frame the provider rejects --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
tessellark
|
5b546259d5
|
fix(cache_control)!: keep one deployment's prompt-cache opt-in from reaching siblings on the same model (#49685)
* fix(cache_control): read the routed deployment's own prompt-cache flag, not a sibling's shared cost-map entry Two deployments that share one model string share one key in the live litellm.model_cost map, and router registration writes each deployment's supports_prompt_cache_breakpoint into that key. The cache control hook read the live map, so a flagless deployment picked up a sibling's opt-in and sent prompt_cache_options and prompt_cache_breakpoint upstream, which the provider rejects with a 400 When a call carries the routed deployment's model_info, the prompt cache checks now use its declared supports_prompt_cache_breakpoint, and fall back to the loaded catalog instead of the live map. This covers the hook on completion, acompletion, Responses and the /v1/messages route, the azure_ai chat transform, the OpenAI Responses transform under drop_params, and the /v1/messages to Responses adapter * fix(prompt caching): read each deployment's own breakpoint flag in the openai and bedrock readers A deployment's own supports_prompt_cache_breakpoint now picks OpenAI's prompt_cache_breakpoint only where the request goes out OpenAI-shaped on a provider other than openai, such as azure_ai OpenAI models and bedrock_mantle. Bedrock on every route and providers that build Anthropic messages keep cache_control, which Bedrock Converse turns into cachePoint The openai chat reader now passes the routed model_info and checks base_model. The Bedrock cache point reader takes the deployment's flag first and, for a routed call with no flag, reads the catalog as loaded instead of the live map that sibling deployments write into. model_info is threaded from the converse transform, the factory message and tool builders, and the responses bridge * fix(prompt caching): keep gateways on cache_control and read register_model opt-ins on routed calls A declared supports_prompt_cache_breakpoint picks OpenAI's breakpoint only on providers hosting OpenAI's API or for a model the cost map lists under the provider, so OpenRouter, LiteLLM proxy, and vLLM deployments keep cache_control as before. Routed calls read the loaded catalog plus the user's own register_model entries, never router registrations. * fix(prompt caching): honor a deployment's own supports_prompt_caching on Bedrock and its declared litellm_provider on gateways * fix(prompt caching): keep wildcard cache flags off matched models, read deployment flags for auto caching and base_model aliases * test(anthropic): cover auto caching on an unmapped Claude deployment * fix(cache_control): keep the merge base's reads where the per-deployment flag changed them A register_model entry under a provider-prefixed name reaches routed calls again, since the overlay now resolves the bare and prefixed names the way runtime registrations are stored. The hook and the openai chat reader no longer judge base_model, as at the merge base, so a client base_model sent under allow_client_pricing_override cannot pick OpenAI's breakpoint and get a 400. A Bedrock deployment flag that is not a real true reads as false again, as at the merge base. An azure_ai wildcard's supports_prompt_cache_breakpoint speaks for each model it matches again, as at the merge base. Other wildcards still leave both cache flags to the catalog. The s10/s11 Bedrock wire test asserted that a flagless deployment inherits its sibling's flag on a shared ARN, which is the leak this PR removes. It now asserts that each deployment keeps its own flag and that a flagless unmapped ARN keeps its cache points after the delete. * fix(cache_control): let the later register_model entry win between a bare and a provider-prefixed name Routed calls read register_model entries through an overlay that merged the bare name after the provider-prefixed one whatever order they were registered in, so a later opt-out under one name lost to an earlier opt-in under the other. Each registration now moves its key to the end of the kept registrations, and the overlay merges both names oldest first, which matches what SDK calls read from the live model map. Also lists the wildcard cache flag helper in the router coverage script, since the hook's wildcard tests drive it rather than calling it by name. * fix(cache_control): keep register_model entries visible while a cost map reload replays them The previous commit moved a re-registered name to the end of the saved registrations by removing and re-adding it, and the overlay walked that dict to order a bare and a provider-prefixed name. A reload replays every saved entry, so a request on another thread could briefly miss an entry or fail on a dict that changed size mid-walk. Entries are written in place again, a per-name sequence records which registration came last, and both the overlay and the reload replay order by it, so the later registration still wins after a reload. * fix(cache_control): read a string or numeric supports_prompt_caching as the bool it spells and find register_model entries under any route prefix A deployment flag stored as "true", 1, "false" or 0 (POST /model/new and quoted YAML keep strings) now means that bool on the Bedrock cachePoint reader and Anthropic auto caching, and any other value falls to the catalog. register_model records which names wrote to each catalog row, so an opt-out under bedrock/ or bedrock/converse/ reaches routed calls like one under anthropic/. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Emerson Gomes
|
ecb8ef5ca8
|
feat(realtime)!: support latest OpenAI audio models (#35600)
* feat(realtime): support latest OpenAI audio models * fix(transcription): type SDK stream duration metadata explicitly * fix(realtime): preserve transport settings and translation duration * refactor(realtime): reuse SDK client initialization * fix(audio): bill finalized streams and authorize transcription models * refactor(audio): keep transcription pricing selection together * fix(realtime): reconcile model metadata and test contracts * fix(realtime): preserve provider duration and model capabilities * fix(realtime): keep transcription validation compatible with cost map guard * fix(realtime): address transcription and billing review findings * fix(realtime): preserve input usage and provider routing * fix(realtime): bill retained output and route Azure aliases * fix(realtime): reject malformed provider durations * fix(realtime): preserve batch cache rates and Azure v1 routes * fix(transcription): reject nonfinite provider durations * refactor(realtime): align annotations with current lint rules * fix(realtime): preserve translation deployment pricing and input usage * test(transcription): verify synchronous stream finalization * fix(realtime): retain missing translation input usage at close * fix(transcription): reject streams that bypass output guardrails * fix(realtime): reconcile audio protocols billing and current CI * fix(realtime): trust confirmed formats and authorize default models * fix(realtime): preserve absent models and reject unsupported guardrails * fix(realtime): reject translation policy pipelines * chore(ci): rerun transient infrastructure timing failure * fix(realtime): reconcile audio protocols with current upstream * fix(audio): validate provider responses at SDK boundaries * fix(realtime): preserve minimum OpenAI SDK compatibility * fix(realtime): preserve deferred Live session authorization * fix(realtime): preserve upstream authentication and transcription behavior * fix(audio): scope provider duration precedence to configured models * fix(typing): avoid Final declarations inside transcription cost loop * refactor(audio): reuse transcription mapping and duration resolution * fix(realtime): enforce model budgets and preserve translation routing * fix(audio): log streamed transcripts whose done event reports detected languages * fix(audio): pass stream, languages and keywords through unchecked for non-OpenAI transcription providers Providers without a streaming transcription handler got UnsupportedParamsError for stream=True, languages and keywords, where the merge base forwarded them as provider-specific params. Only openai and azure validate them now. * fix(audio): bill streamed gpt-transcribe from the provider's reported duration The stream path computed cost after logging had replaced the transcription's duration usage, so it fell back to the measured file length while the unstreamed call billed the provider's seconds. * fix(transcription): log streamed transcription usage from the provider response The stream logging path built the spend payload from the response after its duration usage was transformed away, so whisper-1 with stream=true and streamed gpt-transcribe logged an empty usage object. Bill and log from the provider's TranscriptionResponse in both the sync and async paths. * fix(realtime): keep main's routing, protocol and transport behavior around the new translation routes - Send OpenAI realtime and translation client_secrets and calls through litellm's httpx client again, so ssl_verify and custom CA settings apply and upstream errors keep main's shape - Use the input transcription model as the session model only for transcription sessions - Drop the new /openai/v1 translation aliases and record each lazy feature's own routes, so the /openai pass-through and the MCP routes resolve as on main - Let a configured Azure realtime_protocol win for every model, with GA as the default only when none is set - Return x-litellm headers on streamed transcriptions and mark the request done - Refuse translation sessions before connecting upstream when realtime guardrails apply or the provider is not OpenAI or Azure - Accept json and text for gpt-transcribe, and drop other formats under drop_params instead of failing - Bill translation sessions on output audio seconds only, at the single published rate - Document the 201 SDP answer on the translation calls routes and the transcription 200 response * fix(realtime): restore main behavior for guardrails, Azure transcription, and realtime clients Streamed transcription runs unstreamed when a deployment post_call guardrail applies, so the guardrail still sees the transcript. Azure transcription maps v1, latest and preview to the default dated version on the deployments route for every model. The SDK client secret keeps session.model ahead of model, realtime WebSockets connect to api_base again, realtime metadata keeps only guardrails, and managed agents need an explicit transcription model. Reverts the two unrelated streamed Responses error codes and the duplicate cached_tokens_details field, and the gpt-transcribe format check only reads the request provider's cost map entry. * fix(realtime): keep main's transcription, client secret and route behavior where the PR changed it Transcription reaches every provider as on main again, sends stream only when asked, forwards language and languages together, keeps form key order, bills provider seconds only when above zero, honors base_model for the new flags, keeps main's Azure api_version on the proxy path, and streams carry chat's headers, an error event on a mid-stream failure, and a spend row when the stream ends early. Translation cost reads both per-second rates from one source and spend rows carry the billed seconds. Realtime transcription WebSockets keep model in the upstream URL outside OpenAI's hosts, client secrets forward explicit nulls, accept conversation and delay, and answer 400 on a malformed body, the /openai translation paths are back to main, translation refuses only for guardrails realtime sessions run, nested aliases resolve and later session.update models are authorized, translation client secrets run per-model auth, beta clients bridged to GA get beta-shaped session events, and transcription sessions send the deployment model in both shapes. * fix(realtime): address review findings on transcription billing, streaming and realtime auth Per-second pricing replaces token billing only when the priced entry sets no token rates, translation rates fall back per key to the cost map, transcription cache keys include languages and keywords, a stream request a post_call guardrail forces unstreamed comes back as redacted SSE, Azure beta clients are bridged only for GA-only deployments, nested transcription models on the realtime WebSocket are checked against the key, and translation spend carries key and team metadata * fix(azure): pick the GA realtime protocol for deployments whose model_info.base_model is GA-only * fix(realtime): preserve prior merge resolutions after rebase * fix(realtime): enforce translation policies and normalize Azure transcription URLs * fix(cookbook): stop translation once output idles after the upload ends * fix(realtime): bill translation on input audio and drop pre-read stream cost headers Translation spend now uses the input audio seconds the session sent, priced through input_cost_per_second, instead of the translated output duration. A streamed transcription no longer returns cost headers before the stream is read, since the cost is only known after the last event. Also removes an unused realtime guardrail helper. * fix(realtime): drop top-level session nulls, bill dropped transcription streams, and bridge beta response fields Client secret, translation and transcription session bodies drop top-level nulls again, as main did, while nested nulls such as turn_detection still pass through. Transcription client secrets send the deployment model as session.model. A streamed transcription the client drops still runs its success callbacks, and the stream ends with data: [DONE] like OpenAI's. The beta to GA bridge maps max_response_output_tokens, speed and noise reduction, remaps response.create, and drops temperature under drop_params. The Entra token for realtime HTTP routes is fetched off the event loop * test(e2e): cover realtime translation, live transcription, client secrets, and streamed transcription * fix(realtime): close review gaps in translation billing, transcription streams, and Azure GA Bill translation sessions from the deployment's own per-second rates, add per-second prices for Azure gpt-4o transcribe models, keep stream-scoped guardrails seeing the caller's stream flag, map mid-stream transcription errors to LiteLLM exceptions with a [DONE] frame, map GA responses back to the beta shape for bridged beta clients, honor the minting key's guardrail opt-out on translation calls, restore the Azure transcription session URL, and flag GA-only Azure realtime models * fix(realtime): bill a translation rate the deployment omits from the session model * test(e2e): check translated speech is not English instead of exact French wording * fix(realtime): keep main's behavior for non-bridged backends, stream error frames, gateway URLs and Azure transcribe prices Remap beta events to GA only for bridged beta clients and translation sessions, bridge beta clients on GA-pinned Azure deployments, log error-only upstream sessions as failures, flag dated Azure GA realtime models, drop the unpublished Azure per-second transcribe rates, log a mid-stream transcription failure once, keep main's SSE error frame outside transcription, drop unsupported transcription params under drop_params, keep the caller's Azure auth headers, keep a gateway /v1 path, let key opt-outs release string-callback guardrails on translation, and keep the cookbook waiting while a long upload is still sending * fix(realtime): keep the proxy's realtime session gate off translation sessions A key that opts out of a legacy callback guardrail now gets a working translation session, since the transcription-guardrail gate no longer sends a realtime session.update the translation upstream rejects * fix(realtime): keep websocket model limits, bill measured transcription length, route transcription sessions on the allowed model A WebSocket opened without a query model now authorizes as an empty model, transcription cost prefers the measured upload length over the provider's reported seconds, transcription sessions overwrite nested models with the authorized top-level model again, and a non-boolean transcription stream value answers 400 or is dropped under drop_params. * fix(ci): copy the rust bridge extension into the openapi docs gate's base worktree * fix(model-catalog): accept the realtime translation endpoints in the cost map * fix(cookbook): close the translation session and read until session.closed * fix(realtime): treat an empty transcription stream as unset and pass the cost-map guard An empty `stream` form value runs the transcription unstreamed again, as OpenAI does, instead of answering 400. The four translate cost-map entries drop the translation routes from supported_endpoints until the main branch's catalog parser accepts them, and the nested transcription model lookup uses the router registry entry point. * test(proxy): drop the mid-stream error frame pin that main's error shape change replaced * fix(transcription): bill uploaded seconds when a stream fails mid-transcript * fix(proxy): bill uploaded seconds when a streamed transcription breaks mid-stream * fix(audio): keep transcription's positional arguments and redact streamed error details - Move the new languages, keywords and stream options to the end of transcription's parameters, so a prompt or format passed by position keeps its meaning - Redact internal hostnames, paths and tracebacks from a streamed transcription's mid-stream error event, as chat streams already do - Move the CA-bundle check for the realtime HTTP routes, which serves real TLS on loopback, from the unit suite to the SDK integration suite * fix(audio): stream the guarded transcript to SDK callers that asked for a stream * fix(logging): keep a streamed transcript out of callbacks that turned off message logging A streamed transcription's assembled response reached success callbacks with its text intact under turn_off_message_logging or a callback's message_logging=False, because the shared streaming redactor had no transcription branch. It now redacts the text, as the unstreamed call already does * fix(proxy): stream a transcription the deployment streamed when the client sent no stream field --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
tessellark
|
f4a2e2b3af
|
fix(anthropic): send an https PDF image_url to Claude as a document (#49708)
Some checks are pending
unit / router (push) Blocked by required conditions
unit / rust-bridge-harness (push) Blocked by required conditions
unit / auth-checks (push) Blocked by required conditions
unit / budgets (push) Blocked by required conditions
unit / custom-logging (push) Blocked by required conditions
unit / db-and-spend (push) Blocked by required conditions
unit / endpoints-and-responses (push) Blocked by required conditions
unit / enterprise-routing (push) Blocked by required conditions
unit / guardrails-hooks (push) Blocked by required conditions
unit / jwt-and-keys (push) Blocked by required conditions
unit / key-generation (push) Blocked by required conditions
unit / logging-misc (push) Blocked by required conditions
unit / mcp-oauth (push) Blocked by required conditions
unit / proxy-runtime (push) Blocked by required conditions
unit / proxy-server-core (push) Blocked by required conditions
unit / root (push) Blocked by required conditions
unit / proxy-utils (push) Blocked by required conditions
unit / ui-unit (push) Waiting to run
unit / docs (push) Waiting to run
unit / helm (push) Waiting to run
unit / OpenAI 2.20.0 compatibility (push) Blocked by required conditions
unit / OpenAI 3.0.0 compatibility (push) Blocked by required conditions
unit / OpenAI 3.25.0 compatibility (push) Blocked by required conditions
unit / redis-py 5.3.1 compatibility (push) Blocked by required conditions
unit / redis-py 6.4.0 compatibility (push) Blocked by required conditions
unit / redis-py 7.4.1 compatibility (push) Blocked by required conditions
unit / redis-py 8.0.1 compatibility (push) Blocked by required conditions
unit / coverage (push) Blocked by required conditions
unit / unit passed (push) Blocked by required conditions
GitHub Actions Security Analysis / zizmor (push) Waiting to run
* fix(anthropic): send an https PDF image_url to Claude as a document A PDF link sent as image_url to Claude on Anthropic went out as an image block and Anthropic answered 400. A link whose path ends in .pdf is now downloaded like Vertex links are, and the served Content-Type picks the document or image block, so CDN links that serve a PNG from a .pdf path keep working. An explicit format of application/pdf sends a url document with no download. PDF media types match regardless of case or parameters, and count_tokens picks the same block as the request. * fix(anthropic): download https PDF links off the event loop The proxy downloaded an https link ending in .pdf synchronously while building the Anthropic request, so on an async call every other request on that worker waited for the download. Those links are now inlined before the request is built, the same way http links already are, and the /v1/messages guardrail write-back does the same. A non-string format on an image_url is ignored the way it already was inside the image_url mapping, instead of raising an AttributeError. * fix(anthropic): send a PDF link the proxy cannot download as a link and keep guardrail url blocks as sent * test(anthropic): expect the PNG media type the served bytes carry at a .jpg path * fix(anthropic): bound the PDF link download and keep query-string PDF names Give up on a .pdf link after NON_LLM_CONNECTION_TIMEOUT instead of the client's 6000 s default, fall back to main's whole-URL extension check so download?file=report.pdf still counts as a PDF, treat application/x-pdf as a PDF, and set the url document's application/pdf format only for the guardrail write-back so other /v1/messages providers send what main sends * fix(anthropic): probe a .pdf link and send it to Claude as a url document Instead of downloading a .pdf link and inlining it as base64, ask the host for its first kilobyte and send the link as a url document when it serves a PDF. Every other link goes out as the url image main sends, so robots.txt handling, caching and the wire format stay as they are on main. Also restore the guardrail adapter and the content type inference to main, keep the client's url document blocks (title, context, citations, cache_control) through the guardrail write-back, treat a PDF filename in the query string as a PDF link, probe links concurrently on the sync path, cap the async probe's read at the download limit, and catch only transport, URL and SSRF failures in the probe * fix(anthropic): read only the first kilobyte when probing a PDF link, and restore each url document from its own place The probe now streams the response and keeps the first 1 KB, so a host that ignores Range no longer fills memory with up to 20 parallel bodies. The guardrail write-back now matches url documents inside a tool_result and outside one separately, since the write-back moves tool results ahead of other content * fix(anthropic): remember each PDF link probe's verdict and cap its total time, and skip the probe on Bedrock invoke * fix(anthropic): keep a PDF probe's error status for a minute, not ten --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
ryan-crabbe-berri
|
4573fa1f31
|
fix(embeddings): honor the caller's timeout on Cohere sync and HuggingFace embedding requests (#48593)
* fix(embeddings): honor the caller's timeout on Cohere sync and HuggingFace embedding requests Bedrock Cohere embeddings ran the sync request with the client default instead of the timeout passed to litellm.embedding, and HuggingFace embeddings dropped it on both the sync and async paths. Pass the timeout through to the HTTP request on each path. Fixes #47301 Fixes #47299 * fix(huggingface): pass the caller's timeout to the embedding model lookup too Without input_type the handler first fetches the model's pipeline tag from huggingface.co, and that GET still used the default timeout. Thread the caller's timeout through both lookup helpers and the transform step so every request the embedding makes honors it. Refs #47299 * fix(huggingface): keep the unreachable async lookup path untouched The async model lookup helper and the call_type="async" transform branch are never reached, since the async embedding path transforms through the sync lookup. Leave them as they were so the change only touches requests that actually run. |
||
|
Devin Gupta
|
216041e243
|
feat(decisions): add Parallel AI web-grounded decisions (#49188)
* feat(decisions): add Parallel AI web-grounded decisions * fix(decisions): name the Parallel model decision * fix(parallel_ai): restrict environment credentials to trusted decision endpoints * fix(decisions): keep Parallel evidence fields off other providers and handle missing confidence Only fields a provider names reach the OpenAI response, so existing providers keep their base shape. A malformed api_base answers 400 on both credential paths. The complexity router classifier and the Playground handle a provider that omits confidence. Regenerates the lazy OpenAPI snapshot and the dashboard API types * chore(cost-map): declare the Decisions routes on parallel_ai/decision The provider endpoint files are generated from the cost map, so the row must name both routes for the generated System One flag to hold * fix(decisions): report no classifier confidence when a provider omits it A choice answer with no confidence is a valid classifier answer, so the complexity router picks its tier and leaves classifier_confidence and the confidence signal out instead of reporting a different metric in its place. Also show the Parallel AI logo in the provider picker and add a Parallel translation fixture captured from the live API for both Decisions routes. * fix(decisions): keep a token-priced row on token billing when it also sets a query price A plain input_cost_per_query bills flat only on a row with no token price, and input_cost_per_query_decisions always bills flat, so a custom Decisions row that already bills tokens costs the same as before this PR * fix(decisions): bill a deployment's query price and accept Parallel bases that end in a route A proxy request logs through an object built before the router picks the deployment, so a query price on litellm_params never reached Decisions billing. Parallel Search accepts a base ending in /v1/search and shares PARALLEL_AI_API_BASE with Decisions, so Decisions now accepts that base and one ending in /v1/decisions. * fix(decisions): keep per-query billing and optional confidence on Parallel only A query price on any other Decisions provider moved that provider off token billing, and a choice or score answer with no confidence became a 200 with a null for every provider. Both now apply to Parallel alone, so other providers bill and fail as they do on main. A Parallel deployment with explicit zero token rates and a query price read as free, so every budget check was skipped while it billed per call. It now counts as priced. The dashboard key for Parallel is now PARALLEL_AI so a served bundle that predates the provider still sends parallel_ai as the provider slug, and the README table lists the provider. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
08b951a814
|
fix(vllm): list hosted_vllm wildcard models when the server has no api key (#40066)
* fix(proxy): expand wildcard models for providers with model info but no cost map entry Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(vllm): stop requiring an api key to list vllm models Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): preserve model ids during wildcard expansion Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(vllm): forward api key for model discovery Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(vllm): support bearer auth for model discovery Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(vllm): list hosted_vllm models from the server chat uses, with a bounded wait The hosted_vllm listing now resolves HOSTED_VLLM_API_BASE and HOSTED_VLLM_API_KEY like hosted_vllm chat, instead of the /vllm pass-through's VLLM_API_BASE, and waits at most NON_LLM_CONNECTION_TIMEOUT rather than the completion timeout. vllm/* keeps listing nothing, since its chat runs in process. The router pass-through now forwards the deployment's api_key. * fix(vllm): skip the placeholder key, honor deployment TLS and headers, and retry failed listings after a minute * fix(discovery): cache only timed-out model listings, so a fast failure is tried again on the next call * fix(proxy): list wildcard models off the event loop, so a hung provider no longer stalls other requests * fix(utils): keep a concurrent call's model listing when another call times out * fix(proxy): run model discovery on its own thread pool and keep credential lookups off the event loop * fix(proxy): stop the file credential lookup at the first match before listing wildcard models The fallback lookup now walks the allowed model names lazily, in the same order as before, so a hung vLLM server is listed only when no configured name serves the requested provider. The vLLM auth headers no longer mutate the caller's headers dict. * fix(proxy): try every configured wildcard route before listing any wildcard's models in the file credential lookup * fix(proxy): answer model lists from cached listings first and share one listing per server * test(vllm): give the self-signed cert fixture fixed validity dates * fix(proxy): skip wildcard servers a key cannot reach on /v1/model/info /v1/model/info listed every wildcard deployment and filtered by the key afterwards, so a key limited to one model waited on every wildcard server and sent listing calls to servers it cannot use. The listing now skips a wildcard whose patterns match none of the key's models before it asks the server. A key or team granted hosted_vllm/* with no deployment of that name now lists no models, like openrouter/*, since chat answers 400 for every id the environment server would list. * fix(proxy): match a wildcard's own row pattern before asking its server The /v1/model/info pre-filter matched a key's models against both the deployment name and its litellm_params.model, so a key granted hosted_vllm/* still asked a vllm-secure/* -> hosted_vllm/* server whose rows it can never see. It now matches only the pattern expansion names the rows with, picked by one shared helper. * test(vllm): cover the vLLM listings and no-slash wildcard aliases the patch left unrun Adds tests for hosted_vllm get_models with and without a server, vllm/* never asking a configured server, and /model/info pre-filtering of wildcard aliases whose name has no slash. Drops a test comment that only repeated a method signature. --------- Co-authored-by: jesus <jesus@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
ryan-crabbe-berri
|
28c80048ed
|
fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
* fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: type the allowed_tools tool_choice fixtures Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: raw regex for the allowed_tools provider gate match Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(tool_choice): move the allowed_tools provider gate out of completion() so pyright can still analyze it Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(tool_choice): keep the allowed_tools helpers typed so the basedpyright gate stays level Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(tool_choice): type the allowed_tools validation boundary with Any instead of casts Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(tool_choice): widen tool_choice to object at the allowed_tools helpers with a cast-ok reason Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(tool_choice): drop allowed_tools test docstrings, type the new tests, and revert unrelated reformatting Also reword the allowed_tools 400 so it no longer blames the flat Responses layout for every malformed choice --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
tavren27
|
94b5b6386a
|
fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
* fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool Opus 5.5 and Sonnet 5.5 on Bedrock cannot force the json tool, so a json_schema request without thinking sent an unforced json tool the model ignored. The opt-in native output key now also applies when the model map says the model cannot force a tool, and the Opus 5.5 commercial Bedrock rows carry the opt-in key. The GovCloud Opus 5.5 rows carry it as false, like the Sonnet 5.5 GovCloud rows * fix(bedrock): keep json tool with thinking on Opus 5.5 and Fable 5.1, and GovCloud on the tool Native output without thinking now applies to every Bedrock Claude model that cannot force the json tool unless supports_bedrock_native_structured_output is false, so Opus 5.5 needs no opt-in row and keeps the json tool when thinking is requested, as #46870 chose. The invoke chat path keeps the native output_format it built instead of inlining it, and GovCloud region-path ids read their own false rows. * fix(bedrock): clean caller output_format schemas before sending them natively on invoke * fix(bedrock): keep Mantle Claude on the json tool and send a caller's output_config.format natively on invoke * fix(bedrock): keep the faked Converse stream for native output that replaces the json tool A json_schema stream that goes native only because the model can't force the json tool now keeps the json tool's faked stream, so it still needs only bedrock:InvokeModel. /v1/messages builds a native-output retry only where it sends native output, and the Mantle test drops its mutable capture. * test(bedrock): cover native output and the opt-out in the invoke json-mode refusal tests --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
mika-lt
|
183212e8be
|
feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689)
* feat(anthropic): pick beta allowlist row per deployment, add mid-2026 beta rows, surface input_transformations
Foundry-hosted anthropic deployments now filter anthropic-beta by the azure_ai row on /v1/messages and chat completions, the bundled config gains the mid-conversation-system-clear-at-2026-08-21 row plus the tool-changes and output-config betas on azure_ai and vertex_ai from a live probe, and Anthropic's input_transformations array reaches chat completions in provider_specific_fields (non-streaming and the first streaming chunk).
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(types): type the provider_specific_fields source dict and beta row test helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): input_transformations reaches chat completions and /v1/messages
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(types): read the Anthropic response as a Mapping when building provider_specific_fields
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): fold deployment-row tests into the filtering file and mirror the new beta in the Rust table
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drop the duplicated beta tuple and mark filter results Final
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(azure_ai): forward the seven betas Foundry accepts on the azure_ai beta row
A Foundry-hosted anthropic deployment now filters through the azure_ai row, which
dropped compact-2026-01-12, fast mode, fine-grained tool streaming, inline tools,
oauth, output-128k, and token-efficient tools. Foundry answers 200 to each, and
without compact-2026-01-12 a compaction request answers 400, so the row now allows
all seven on both the Python map and the Rust table
* fix(anthropic): keep pass-through and beta-less requests off the Foundry beta row
An openai/ deployment that passes /v1/messages through to a Foundry host lost
every beta, and a request without betas read the beta table from GitHub.
Only an anthropic deployment on a Foundry host now takes the azure_ai row,
and the check reads the provider and host before the table.
* test(anthropic): point the beta-gated wire legs whose row lacks clear-at at a native Databricks deployment
* style(rust): wrap the azure_ai beta header test case the way rustfmt does
* fix(anthropic): forward unlisted betas to Foundry and keep Foundry calls off the Rust messages route
An anthropic deployment on a Foundry host now drops only the betas the azure_ai row marks
unsupported on /v1/messages, and forwards betas the table does not list as sent, as main did.
cognitiveservices.azure.com counts as a Foundry host. The Rust messages route sends an async call
with a Foundry api_base to Python, which filters by row. A sync call stays on Rust, since Python has
no sync /v1/messages handler. The json_mode chat response keeps input_transformations,
and the first /v1/messages call with betas loads the beta table off the event loop.
* fix(anthropic): run the advisor loop for an anthropic deployment on a Foundry host
The advisor interceptor treated every anthropic deployment as native, so a Foundry-hosted one
received the advisor_20260301 tool and Foundry answered 400. Interceptors now get the
deployment's beta row from resolve_beta_provider, so that deployment runs litellm's advisor
loop the same way an azure_ai deployment does
* test(anthropic): drive the Foundry advisor loop test through recorded HTTP
The test now intercepts the Foundry and Anthropic HTTP calls with respx instead of patching litellm's own sub-call helper, so it checks what Foundry receives: no advisor_20260301 tool and no advisor beta
* fix(anthropic): leave the advisor loop to the providers it ran for on main and tidy the PR's tests
Reverts
|
||
|
tavren27
|
640a87f70d
|
fix(gemini): resend once with the placeholder signature when the other backend rejects a replayed thought signature (#49697)
* fix(gemini): resend once with the placeholder signature when the other backend rejects a replayed thought signature Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(integration): gemini tool-call signature rejected by the backend is resent once with the placeholder Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(gemini): keep the placeholder resend inside the cache rebuild so either rejection order ends in an accepted body Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(gemini): resend a cached-prefix signature inline and cover native generateContent When the rejected signature sits inside a cachedContents prefix, the placeholder resend now carries the history inline, since replacing the signature in the request body cannot reach the cache. The native generateContent handlers get the same one-time resend. * fix(gemini): send the history inline when Vertex rejects a signature while creating the cache * fix(gemini): keep the context cache on a signature resend and go inline only when that is rejected too --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
jesus-berri
|
cc142a8191
|
fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
The /deepgram/v1/listen WebSocket refuses nova-3-medical with 1008 because the cost map has no streaming row for it. Deepgram's pricing page does not list Nova-3 Medical, so the new row uses the $0.0077/min streaming launch price from Deepgram's 2025-03-03 announcement deepgram/streaming/nova-3 and nova-3-multilingual were $0.0048 and $0.0058 per minute against $0.0077 and $0.0092 on deepgram.com/pricing as of 2026-11-02, so they are updated too Resolves LIT-10393 |
||
|
Prabal Pratap Singh (ZeroX)
|
b3c397e964
|
feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393)
* feat(hosted_vllm): keep vLLM's stop_reason and token_ids on chat choices Non-streamed hosted_vllm chat completions moved vLLM's choice-level stop_reason and token_ids into provider_specific_fields, so clients written against vLLM could not find them where vLLM puts them. They are now also set on the choice itself, and the copy in provider_specific_fields stays for existing readers. Fixes #47945 * feat(hosted_vllm): keep stop_reason and token_ids on streamed chunks and proxy stream output Streamed chat finish chunks and streamed /v1/completions finish chunks now carry vLLM's stop_reason. Each stream chunk keeps the token_ids vLLM sent with it, including held-back empty chunks, and the proxy no longer strips those chunks as empty usage chunks or drops the fields in its fast serializer. * fix(hosted_vllm): keep the upstream choice index on token-id-only stream chunks * fix(hosted_vllm): keep vLLM choice fields for null, cache hits, n>1, and streamed completions Response conversion keeps stop_reason and token_ids on the choice for any OpenAI compatible response, cache replays carry them, finish fields are recorded per choice index, text completion streams keep token_ids, and the proxy passes only these two keys through, nulls included. * fix(hosted_vllm): send empty text on token-id chunks, keep fields on their own choice, and keep null stop_reason on slow-path streams Token-id-only chunks now carry an empty content or text string, a finish chunk only takes stop_reason and token_ids from its own upstream choice, content chunks no longer repeat stop_reason, the slow stream serializer keeps a null stop_reason or token_ids, and fields cached under provider_specific_fields come back on the choice * fix(hosted_vllm): keep stop_reason on the last content chunk, keep both fields in built stream responses, and key the cache on return_token_ids * fix(hosted_vllm): keep another choice's final token_ids and stop_reason on their own stream chunk With n above 1, a finish-only vLLM chunk for a choice other than the one the single finish chunk carries was dropped or taken as choice 0's finish, losing that choice's last token_ids. It now goes out as an id-only chunk on its own choice index. * fix(hosted_vllm): send the first choice's finish chunk before another choice's later token-id chunks * fix(streaming): keep each streamed text completion choice on its own index * fix(streaming): finish each streamed text completion choice on its own index and null token_ids in redacted logs * fix(proxy): drop token_ids from guarded streams, redact choice-level provider fields, and keep one message_delta per Anthropic stream * fix(proxy): skip token-id-only chunks on guarded streams and put stop_reason on the final text chunk * fix(proxy): drop token_ids from the logged and cached response of a guarded stream * fix(proxy): drop token_ids under per-chunk stream checks and redact text-completion stream choices * fix(caching): key return_token_ids and continuation_token sent in extra_body * fix(streaming): drop token ids from streamed chunks while post_call_rules run vLLM holds text back behind a possible stop string but sends its token ids at once, so an SDK stream sent ids before litellm.post_call_rules checked their text. While those rules are set, streamed choices drop token_ids and chunks that carry only ids are skipped, as the proxy already does ahead of a per-chunk check * fix(streaming): keep vLLM fields when a stream's only choice index is not 0 --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
simonp9
|
61da6fcb4d
|
fix(mcp)!: answer 400 for a hosted MCP tool a translated route cannot run, drop it under drop_params (#48931)
* fix(bedrock, gemini, deepseek, databricks, gigachat, anthropic): answer 400 for a hosted MCP tool a route cannot run, drop it under drop_params A `type: "mcp"` tool sent to a route that rebuilds tools for its provider (Bedrock Converse and Nova, Bedrock Invoke Claude, Vertex AI Claude, Vertex AI and Google AI Studio Gemini, DeepSeek, Databricks Claude, GigaChat) was dropped silently and the request still answered 200. These routes now answer UnsupportedParamsError (400) naming the model, route and server, and pointing to the LiteLLM MCP gateway. Under drop_params the tool is dropped with a warning, other tools are kept, and no empty tools field is sent. Anthropic, Azure AI Claude and Claude Platform on AWS keep mapping the tool to the MCP connector. Native Responses providers and raw OpenAI-compatible forwarders are unchanged. * fix(mcp): check hosted MCP tools once per request and keep base tool_choice handling Each route now runs one request-level step before its param mapping. When the drop leaves no tools, the request sends no tools, tool_choice or parallel_tool_calls. Converse and GigaChat go back to their base tool_choice and empty-tools handling. * refactor(deepseek): hold the sent tools in a tuple * fix(mcp): keep tool_choice for legacy functions when every hosted MCP tool drops * fix(mcp): answer 400 for MCP servers a route cannot run on Messages, Ollama and the Responses playground /v1/messages requests with mcp_servers on a chat-adapter or Responses-bridge route now answer 400 naming each server, or drop it with a warning under drop_params, instead of being forwarded or silently ignored. Ollama generate no longer pastes a hosted MCP tool (headers included) into the prompt, and ollama_chat filters hosted MCP tools the same way. The Admin UI Responses playground now sends litellm_proxy/mcp references like the other endpoints. * fix(ollama): leave JSON mode off when drop_params drops every hosted MCP tool Ollama generate set format json for any request with tools, even after the hosted MCP check dropped all of them, so a plain answer came back as JSON or as a call to a tool the model never had. The check now runs before the JSON mode switch, which stays on only while a tool is left for the prompt. * fix(messages): honor additional_drop_params for mcp_servers and read the beta map only for hosted MCP tools * fix(mcp_security): accept gateway server names and toolsets the gateway resolves The guardrail compared litellm_proxy/mcp/<name> refs against registry keys, which are server ids, so a saved server referenced by name, alias, or toolset name was blocked although the gateway routes it. It now resolves each ref the way the gateway does and still blocks unknown names. * fix(tool_fields): keep MCP drop warnings on one log line Server labels, model names, and routes come from the caller, so a line break in one could forge extra log lines. The drop warnings now strip CR and LF from each value. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
jesus-berri
|
05b76878b0
|
fix(cohere): map Cohere v2 finish_reason on non-streaming chat responses (#49529)
* fix(cohere): map Cohere v2 finish_reason on non-streaming chat responses * fix(cohere): default a missing Cohere v2 finish_reason to stop instead of raising A 200 body without finish_reason used to return stop and started raising KeyError after the mapping change, so fall back to COMPLETE |
||
|
zoveki
|
6be98d8c75
|
fix(bedrock)!: give Invoke and Mantle Claude the model's own default max_tokens (#49692)
* fix(bedrock): resolve Invoke Claude default max_tokens from the base model id Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(bedrock): build Invoke Claude request params without mutating Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(bedrock): type tool-search normalizer return to clear unknown-type gate Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(bedrock): resolve Invoke and Mantle Claude default max_tokens from the deployment id, ARN base_model, and Mantle row * fix(bedrock): default Invoke Claude max_tokens from the deployment's own cap and honor AnthropicConfig Read the called deployment's model_info.max_output_tokens before the base model's cost row, skip the shared regional key the router fills from every deployment, and leave the default to litellm.AnthropicConfig(max_tokens) when it is set. * fix(bedrock): send the mapped default max_tokens on bedrock_mantle Claude chat * fix(bedrock): bound a global AnthropicConfig max_tokens by the deployment's own cap * test(bedrock): annotate the new Mantle default max_tokens tests with Final * refactor(bedrock): inject the AnthropicConfig max_tokens reader into the Invoke Claude config --------- Co-authored-by: mateo <mateo@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
zoveki
|
508a98586e
|
fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
* fix(databricks): join plain text blocks for non-Claude json_object requests * fix(databricks): join only the last message for json_object and drop cache_control under drop_params Databricks checks for "json" only in the last message, so earlier turns now go out as sent and only the last message, plus any system messages merged into it, is joined into a string. Under drop_params a text block's cache_control is dropped so that message can be joined too, and without it the request still goes out as a list. * fix(databricks): skip dropped assistant turns and blank parts when joining for json_object The json_object join picked the last message before the request transform drops bare assistant turns, so a trailing thinking-only or reasoning-only turn (a Responses input ending in a reasoning item included) left the real last user message as a list and Databricks still returned its 400. The pick now skips the turns that transform drops. The join also ran when only one part had text, which sent whitespace-only parts the existing empty block filter used to drop on requests that already worked. It now joins only two or more non-blank parts, so a request with one non-blank part goes out exactly as before. Without drop_params, a message with a message-level cache_control now goes out as sent instead of being rewritten into one cached block. * fix(databricks): join json_object text parts only on models Databricks hosts Databricks checks for the word "json" only on the models it hosts (databricks-* pay per token names and system.ai.* AI Gateway names). An external model endpoint skips that check and takes a list of text parts today, so its request now goes out as sent instead of joined. The drop_params read now goes through drops_unsupported_params, and a test pins that a text block with a truthy non-string text is kept. * fix(databricks): reject a text part holding a non-string locally with a clear 400 * refactor(databricks): reject a non-string text part at the transform_request boundary * fix(databricks): read pydantic message objects in the non-string text check --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
tessellark
|
f91774e2f9
|
fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
* fix(fireworks): keep developer items in place for models that accept a later system message * fix(fireworks_ai): keep developer items in place for short Fireworks model names and stop flagging gpt-oss-120b * fix(fireworks): drop the mid-conversation system flag from nemotron-lightning nemotron-lightning-3p5-30b-a3b followed a later instruction less often with the developer item kept in place than folded, so both of its cost map keys go back to folding. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
tessellark
|
a2ab27373f
|
fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
* fix(proxy): count the context_management edits /v1/messages applies on every bridged provider * fix: apply context_management edits in count_tokens on Responses bridges, compaction blocks and Bedrock Claude The Responses bridge now applies the same edits inference applies for every provider, the chat bridge cuts the history at a client compaction block, and Bedrock Claude forwards the edits AWS accepts with their beta to the mantle and runtime count APIs instead of dropping them. * refactor(count_tokens): return count-view failures as values and raise them once in the caller * fix(bedrock): keep the runtime's 400 when mantle does not serve the model it retries * fix(count_tokens): forward context edits on Vertex and Azure Claude counts and keep Bedrock's mantle answer without edits * fix(proxy): count edited bodies on native routes without a count API, keep counts on editor failures * fix(proxy): keep the Bedrock pass-through count shape and provider 400s on empty bridged bodies The pass-through count picks Converse or InvokeModel from the content again, and the edited InvokeModel count wraps string turns in text blocks. A bridged view with no messages sends the body as before. Azure and Vertex load the beta config off the event loop before a count with edits, and a model with no deployment reads drop_params from the request and router defaults. * fix(bedrock): send an empty-string turn as is when a count forwards context edits Wrapping an empty string into a text block made AWS reject the count with 'text content blocks must be non-empty', while base and /v1/messages accept the empty string. Only non-empty string turns are wrapped now. * test(azure_ai): compare the count's betas with the betas Azure inference sends * test(azure_ai): record the Azure inference request with respx instead of appending to a list --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
tavren27
|
a0b1edc0a0
|
fix(providers): trim prompt_cache_breakpoint to what each API takes under drop_params (#49064)
* fix(openai): trim a malformed prompt_cache_breakpoint under drop_params on chat completions * fix(openai): leave a non-object content part for OpenAI to reject under drop_params * fix(openai): trim an unsupported prompt_cache_breakpoint ttl on every path and on azure_ai chat under drop_params * fix: trim prompt_cache_breakpoint to what Azure and Mantle accept under drop_params Azure OpenAI chat now gets the same content part trim as OpenAI chat, and the Azure and Foundry gates also read a deployment's declared base_model. Each Responses config keeps only the ttl its API takes: Azure keeps 30m, and Mantle keeps no ttl. A trimmed ttl is logged at debug. * fix(responses): trim prompt_cache_breakpoint only on APIs known to read it Other Responses providers get the marker whole or not at all, as on main. Azure chat now trims for a deployment with no base_model unless the cost map marks the model as not reading breakpoints, and Azure AI Foundry Responses keeps Azure's 30m-only shape. * fix(azure): trim prompt cache breakpoints only for deployments known to read them Azure and Azure AI Responses keep main's whole-or-nothing rule for unmapped deployment names, an opted-in custom OpenAI host trims the ttl and keeps the mode, and Azure chat strips every marker for a known non-reader under drop_params * fix(providers): keep main's marker handling where the target won't trim it A /v1/responses model with unknown breakpoint support on OpenAI's host gets a marker whole or not at all, as on main. The chat to Responses bridge keeps main's whole-marker check when a non-bool global drop_params leaves the target's trim off. A hyphenated name like gpt-5-6-sol now reads as gpt-5.6. * fix(providers): read a non-version hyphen suffix like -32k as part of the model name * fix(providers): keep main's reading of a dotted minor version like gpt-5.6o * fix(providers): keep main's breakpoint shape for unmapped Mantle models and skip the Azure lookup without drop_params --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
mika-lt
|
40e4e512d0
|
fix(anthropic): stream azure_ai natively on an Azure OpenAI host on /v1/messages (#49216)
* fix(anthropic): stream azure_ai natively on an Azure OpenAI host on /v1/messages The /v1/messages bridges got the requested model (azure_ai/gpt-6-luna) with the resolved provider (azure), so the Responses bridge faked the stream and the chat bridge called a deployment named azure_ai/gpt-6-luna (404). Pass the resolved provider prefix when the requested prefix is a different known provider. * test(anthropic): cover the bridged model with respx and a regional bedrock_mantle id * fix(anthropic): carry azure_ai env credentials into bridged /v1/messages calls When an azure_ai deployment's api_base and key come only from AZURE_AI_API_BASE and AZURE_AI_API_KEY, the provider the async wrapper derived from the model alone replaced the model's own resolution, so the bridged call lost both and failed. The model's own resolution now wins when it names the same provider, an explicit provider that disagrees still wins, and the bridge carries the resolved key and base. * fix(anthropic): keep the caller's key, proxy routing and MCP credentials on bridged /v1/messages calls * fix(anthropic): keep an azure deployment's Entra credential over the env key on bridged /v1/messages calls * fix(anthropic): skip the sign-in lookup for chatgpt and github_copilot model prefixes on bridged /v1/messages calls * fix(anthropic): keep the Azure credential of an azure_ai deployment that sets its own api_base on bridged /v1/messages calls * test(anthropic): annotate the parameters of the bridged /v1/messages tests --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Kaustubh Anil Jain
|
6f3251c7e3
|
fix(responses): serialize sequence_number on every bridged streaming event (#44944)
* fix(responses): serialize sequence_number on every bridged streaming event * test(responses): cover sequence_number on bridged streaming events * fix(responses): read undeclared fields through dict accessors and number guardrail block continuations * fix(responses): scope dict reads that see undeclared fields to Responses stream events Moves the extras-aware __getitem__, get, __contains__ and items from the shared response base onto a new base for the 37 stream event classes, so usage, Gemini, Interactions and moderation objects keep reading __dict__ and Gemini responses keep _hidden_params out of .get * fix(router): renumber Responses stream events only after a fallback takes over A stream that never falls back now keeps its provider's own sequence numbers, repeats included, so a starting_after resume still matches them. After a fallback the wrapper continues above the highest number the client saw * fix(guardrails): keep Responses stream numbers unique when LLM Shield flushes held text The restorer's flush copied the last delta and kept its sequence_number, so a native stream repeated a number and a bridged stream sent the flush unnumbered. A flush now takes the done event's slot and later events move up by one, and a stream the provider never closed numbers its flush after the last event. Also pins the created_at in the streaming iterator test fixture instead of reading the clock. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |