478 commits

Author	SHA1	Message	Date
moyai-berriai[bot]	f370235bb4	fix(guardrails)!: preserve Bedrock Converse redactions and honor tool-only scans (#45874) ... * fix(guardrails): preserve Bedrock Converse redactions and honor tool-only scans * Preserve main's per-block streaming fixes and regression coverage * fix(bedrock): apply Converse guardrail rewrites texts-first and keep main's write-backs Map tool results onto their text and json parts only, accept a structured row the flat texts already reproduce, let a flat-text mask win over a structured leaf, ignore texts that do not line up with the request when structured rows come back, keep tool call arguments out of the rows under skip_tool_message_in_guardrail and send no tool definitions to tool-only guardrails * fix(bedrock): accept blank content on tool-call-only Converse turns A vendor that returns "" or [] where an assistant row carried only tool calls no longer fails the request closed. Also type the leaf lookup without Any and restore the original layout of the existing unit tests. * fix(bedrock): scan additionalModelRequestFields in Converse guardrail rows and split the handler Guardrails that read structured_messages instead of texts (Akto, Prompt Security, CrowdStrike AIDR and others) stopped seeing strings in additionalModelRequestFields, which Bedrock can forward into the model prompt. Those strings now go to the guardrail as one user row placed before the conversation, and a row-only edit to them is written back. The Converse to OpenAI row conversion moves to litellm/llms/bedrock/chat/converse_to_openai.py and the returned-row diffing to structured_edits.py, so the handler keeps only the glue. Rows record the Converse path of every text part, scope flags travel as one value, and path lookups return a value instead of raising. Unit tests use a real CustomGuardrail subclass instead of mocks, and the integration vendor modes get descriptive names. * fix(bedrock): keep new Converse helpers inside the type discipline rules * test(bedrock): pin Converse row edits that change shape, role or placement * fix(bedrock): type the Converse body once so its edits keep their reference * fix(bedrock): list request-field texts where their Converse row sits * fix(bedrock): send a reshaped Converse tool result as one text block A vendor that compresses or summarises a tool result, such as Headroom collapsing a JSON list into a table string, returned a 500 because the row could not be split back into the original text and JSON parts. The tool result now carries the vendor's string as one text block where its parts were, keeping images and documents in place. It still fails closed when the flat texts masked that tool result or the row changed its tool call id. * fix(bedrock): apply guardrail tool edits on Converse and keep compression guardrails off it A guardrail that masks a Converse tool description or schema now has that mask written into toolConfig, a tool it removes is dropped, and a tool it adds, renames or reorders is refused before Bedrock. Headroom, Compresr and TypeSafe get only the flat texts on Converse again, as on main, because the pass-through route has no loop to answer their retrieve tool * test(bedrock): refuse a guardrail that changes a Converse tool's kind * fix(bedrock): keep partial-row and row-rebuilding guardrails on flat Converse texts OpenAI moderation, the LLM judge, CrowdStrike AIDR, Prompt Security, PANW Prisma AIRS and HiddenLayer scan only part of the rows or rebuild their returned texts from them, so on Converse they get the flat texts only, as on main. When a vendor returns changed rows, its texts are applied only if they keep the flat layout and change only rows the vendor also changed, so row-shaped texts of the same length no longer overwrite unrelated Converse fields. * test(bedrock): pin how flat texts sit next to rewritten Converse rows * fix(bedrock): keep the Bedrock guardrail on flat Converse texts With experimental_use_latest_role_message_only, the Bedrock guardrail places its mask by counting text parts per row, and Converse rows do not line up with the flat texts, so the mask could land in tool call arguments. Give it the flat texts only, as on main. * fix(bedrock): keep Akto on flat Converse texts Akto maps its masked payload back onto the flat texts by value, and a Converse row joins or serialises tool call arguments and JSON tool results, so a masked card there could not be placed and the request was blocked. Give Akto the flat texts only, as on main, where the mask is applied. * fix(bedrock): list request-field texts last again, as on main Flat texts listed additionalModelRequestFields strings right after the system prompt, so flat-text guardrails got a different order than on main. Akto's live verdict on a benign request depends on that order and started blocking it. Rows already keep their own order and texts that do not follow rows are dropped, so the flat texts go back to main's order. * fix(bedrock): list request-field texts next to their row for row readers Row readers that rebuild texts from rows could swap a masked request field with a masked user turn when the field strings came last. Row readers now get those strings right after the system prompt, where their row sits. Flat-text guardrails keep the end-of-list order. * fix(bedrock): list nested request-field texts in their row's order for row readers Row readers that rebuild texts from rows could write a masked request field onto a sibling key when the field held nested objects, because the texts walked the fields depth first and the row breadth first. Row readers now get those strings in the row's own order. * fix(bedrock): walk request fields breadth first instead of resolving each path Resolving every request-field string by its path revalidated the parent object per string, so a wide additionalModelRequestFields took seconds. The string walk now goes breadth first for row readers, the same order the row lists them, in one pass. A unit test pins that texts and rows map the same way when the vendor masks them differently. * fix(bedrock): fail closed when a vendor's rows drop a mask its texts carry When a vendor returns changed rows whose texts do not line up with them, the rows win. A text the vendor masked on a field its rows left untouched (a tool call argument, say) then reached Bedrock unmasked. Refuse that rewrite instead, unless the edited body holds the changed text elsewhere, as texts rebuilt from the rows do. * fix(bedrock): read same-length texts by position when rows drop a mask Matching a dropped text against any string of the edited body let a row mask on another field with the same token cancel it, so the raw tool call argument still went out. Texts of the length that was sent are now checked position by position, and only texts of another length, which cannot be placed, are matched by value. * test(bedrock): count each rebuilt text against the rows' edits * fix(bedrock): keep PromptGuard on flat texts and refuse texts that cannot be placed PromptGuard rebuilds its returned texts from the user rows, and a vendor that does so while masking only row content let a card in a tool call argument reach Bedrock, which main masked. PromptGuard now gets the flat texts as on main, and a reply whose rows changed next to texts of another length fails closed, since what those texts mask cannot be checked. * test(bedrock): let the structured checks decide the unsafe tool call and missing row cases The replies in these tests carried texts that no longer matched the sent texts, so the new refusal for texts that cannot be placed answered first and the tool call and row count checks went unexercised. * fix(bedrock): send request field strings to row readers after the conversation, where main puts them Row readers got the additionalModelRequestFields row before the conversation. Singulr judges only the latest user message, so an injection in a request field that main blocked reached Bedrock. The row and its texts now come last, as main sends those strings in texts * test(bedrock): pin nested request field order for flat readers and the texts view Both request field tests now use nested fields whose depth-first and breadth-first orders differ, so a flat reader getting the row order or a texts view written in main's order fails * refactor(bedrock): ask each guardrail whether Converse should hand it rows Converse picked the guardrails that get only the flat texts from a list of provider names. CustomGuardrail now has supports_structured_messages, True by default, and the ten classes on that list override it to return False, so the handler asks the guardrail instead of the list. Every guardrail class gets the same answer as before * fix(bedrock): keep Singulr on flat Converse texts as on main Singulr wraps each flat text as a user message and its backend judges only the latest user message, so on main a Converse tool result was the turn it judged. Handed rows, the tool result arrives with role tool and the latest user row is the original question, so an injection in a tool result reached Bedrock. Singulr now returns False from supports_structured_messages * fix(bedrock): keep Qualifire on flat Converse texts as on main Qualifire builds its evaluation input from the last user row only when that row's content is a string, so Converse rows (content-block lists) gave an evaluation_id policy an empty input. Opt it out of structured messages so it gets main's flat texts again. * fix(bedrock): keep Conduct on flat Converse texts as on main The conduct-litellm-guard plugin scans only user rows, so with Converse rows a system prompt, assistant text or tool result left its scan. Opt it out of structured messages so it gets main's flat texts again, all sent as user turns. * fix(bedrock): refuse tool removals that leave a toolConfig Bedrock rejects A guardrail that removed every tool, or the tool toolChoice names, produced an empty tools list or a dangling toolChoice that Bedrock answers with an opaque ValidationException. Refuse those rewrites before Bedrock, like other tool changes this route cannot carry. * fix(bedrock): list request-field strings in main's order for every guardrail The request-field row walked additionalModelRequestFields breadth first, and guardrails that get rows had their texts follow that order. With two or more strings the last text changed, so Ovalix, which blocks only when the last text is flagged, rewrote an injection main blocked. The row now walks the fields in the order main lists them in the texts, and the texts use main's order for every guardrail. * test(bedrock): pin a container's own request-field strings before its nested ones * test(bedrock): pin tool_policy and MCP end-user filtering on Converse tools * fix(bedrock): rebuild Converse tools the guardrail changed and drop blanked text like chat A guardrail that adds, renames, reorders or retypes a tool now gets its list sent to Bedrock, converted the way chat completions converts tools, with cache points kept behind their tool. When every tool is removed, toolConfig is dropped and earlier tool calls and results become text, as chat does. Text blocks a guardrail blanks are dropped, and a turn left empty fails closed. The body copies used to place edits are JSON copies, so deeply nested tool JSON no longer hits the recursion limit. * test(bedrock): keep the client tool schema on Converse masks and refuse deep JSON text drops cleanly * fix(guardrails): keep Airia on flat texts for Bedrock Converse so its redactions still apply * fix(guardrails): a pipeline step whose rewrite the endpoint cannot apply follows on_fail on_error: allow sent the original request on when the endpoint refused a guardrail rewrite it could not apply, so a Converse request the guardrail masked reached Bedrock raw. The refusal now counts as a fail on every endpoint. * fix(guardrails): a pipeline step blocks when its rewrite cannot be applied, whatever on_fail and on_error say A rewrite the endpoint cannot apply is neither a content verdict nor a technical error, so on_fail next or allow and on_error allow must not send the original request on * test(bedrock): trim the Converse guardrail tests Drops the chaos and per-vendor integration cells and the duplicate unit cases, and leaves the existing handler tests as they are on main * fix(bedrock): put Converse request-field strings in the latest user message for row readers A guardrail that judges only the latest user message, like Noma v2, read the additionalModelRequestFields row placed after the conversation, so a request with extended thinking or anthropic_beta sent the user's card to Bedrock and let an injection through. Those strings now follow the latest user message's text in its row, and get a user row of their own only when no user message has text. * fix(bedrock): create toolConfig when a guardrail adds the first Converse tool A guardrail that returned a tool for a Converse request with no toolConfig got a 500, since the tool write-back only rebuilt an existing list. It now creates toolConfig, as chat completions does. Guardrails that get only flat texts have their returned tools ignored, as on main. * test(guardrails): check Converse flat-text opt-outs without patching apply_guardrail Each built-in opt-out is checked through its own supports_structured_messages(), the handler's flat path through an injected scripted guardrail, and Headroom through the real class, which would call its unreachable service if it got rows * fix(guardrails): keep Converse tool matching and write-back linear in request width Matching each returned tool rescanned the whole tool list, and every write-back step revalidated the list or object it passed through, so a request with thousands of tools or request fields held the event loop for seconds. Returned tools are now looked up by name in one index, and path steps read the child directly. * fix(guardrails): let later Converse guardrails scan guardContent text When a guardrail removes every tool on a Converse request that carries guardrailConfig, tool results are rewritten as guardContent blocks. The flat text extractor read only top-level text, so a later masker in the same request never saw them and a card in a tool result reached Bedrock unmasked. Chat completions and /v1/messages keep tool results visible to later guardrails after the tools are removed. The extractor now reads guardContent text the same way the structured rows already do, so flat-text guardrails also scan guardContent text a caller sends. * fix(guardrails): keep caller guardContent out of Converse flat texts and send tool history as plain text Flat-text guardrails read only top-level text blocks again, as on main. A guardContent block after the caller's text no longer becomes the last text, so guardrails that judge the last text (HiddenLayer, Qualifire) check what the caller wrote When a guardrail removes every tool, earlier tool calls and results are now written as plain text blocks instead of guardContent. Later guardrails still scan and mask them, and Bedrock's own guardrail keeps checking every message, since a single guardContent block makes it skip all plain text * fix(guardrails): split a newline-joined Converse message back into its parts A vendor that returns a multi-part message as one newline-joined string now has its masks written back to each part, guardContent included, when no part sent already holds a newline. * fix(bedrock): keep Converse tool history as tool messages until send and match chat on emptied turns When a guardrail removes every tool, the tool calls and results stay tool messages for the guardrails after it, so a scan_only_tool_results guardrail still masks them. The toolConfig with no tool is dropped and the history turned into text only when the request is signed, as chat completions does at request build. A caller's toolConfig with no tool gets the same treatment, where Bedrock returned 400 Request-field strings join the latest user message that has text when a tool-result-only turn follows it, so a guardrail judging only that message reads the caller's text with them A turn the vendor empties entirely is sent as written, as on main and chat completions, instead of a 500 Messages go to the guardrail through a JSON round trip instead of a deep copy, and a reply that changes nothing returns early, so a long Converse conversation guards about as fast as on /v1/messages --------- Co-authored-by: moyai-devin-berriai[bot] <336287033+moyai-devin-berriai[bot]@users.noreply.github.com> Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>	2026-10-17 20:38:14 -07:00
devin-ai-integration[bot]	4bebcdf757	fix(databricks): use the native Anthropic route for Claude /v1/messages (#46091) ... * fix(databricks): use the native Anthropic route for Claude /v1/messages Claude models on a Databricks workspace were bridged through chat completions on /v1/messages, which drops the safeguards field and never returns safeguard_results. They now call the workspace's /serving-endpoints/anthropic/v1/messages, the proxy forwards the client's anthropic-beta and anthropic-version headers to Databricks deployments, and the beta header map marks dangerous-tool-use-2026-09-03 as supported there. Any route whose platform does not take that beta drops safeguards together with it instead of answering 400. Non-Claude Databricks models keep the chat completions bridge * fix(databricks): derive the dangerous-tool-use beta from safeguards instead of forwarding client betas A Databricks Claude serving endpoint answers 400 to betas Claude Code sends on every turn, prompt-caching-scope-2026-01-05 among them, so the proxy no longer forwards the client's anthropic-beta header to Databricks deployments. The beta the classifier needs is derived from the safeguards body field, the same way the Azure AI route derives it. The Rust beta-header mirror stops rejecting the Databricks dangerous-tool-use cell so its config-cell test matches the JSON again * fix(databricks): keep the billing block, build the messages route once, and pass the partner user agent * fix(databricks): route Unity Catalog Claude names to the gateway messages route and keep env credentials Unity Catalog model-service names now reach the AI Gateway's native Anthropic route instead of a serving-endpoints path that answers 404 for them, and the native route resolves the key and base through the same order the chat route uses, so environment-only deployments keep working. The native route is limited to Databricks foundation-model Claude names, an unlisted provider forwards safeguards and the beta as sent, and the ten betas the workspace rejects are marked unsupported for Databricks in the beta map and its Rust mirror. * test(rust): expect Databricks to drop the advanced-tool-use beta * fix(databricks): keep passthrough safeguards, partner user agent, and classifier fallback Only the OpenAI-compatible JSON providers drop safeguards now, so a deployment opted into /v1/messages passthrough forwards the field and the beta as sent. When a route drops safeguards and the proxy has a classifier model, the proxy answers the verdict itself, as the chat completions bridge did. The Databricks Messages route also reads the databricks_user_agent param like the chat route. * fix(databricks): drop rejected server tools under drop_params, short-circuit web search, route UC names from a full Messages URL * fix(databricks): drop container on the native Messages route, as the chat completions bridge did * fix(databricks): keep every api_base on a route the workspace serves and gate the derived beta on the map Gate the dangerous-tool-use beta derivation on the beta map the way #43955 does, so GitHub Copilot, DeepSeek, and opt-in passthroughs keep the merge base wire. Recognize /serving-endpoints/anthropic api_bases, fall back to the merge base routing for an api_base path the workspace trim does not know, strip Bedrock invocation metrics from the streamed message_stop, forward client betas to Databricks filtered by the map, and keep tool_choice when a dropped server tool has no name * test(databricks): cover the native Messages route, derived beta and JSON provider safeguards drop on the wire * test(anthropic): expect the dangerous-tool-use beta derived from safeguards next to the client's betas * fix(databricks): send client anthropic headers only on the native Messages route and keep SDK auth Databricks chat completions, called directly or through the Messages bridge, no longer receive the client's anthropic-beta and anthropic-version, as at the merge base. The native Messages route still forwards them, filtered by the beta map, without counting them as caller credentials, so a deployment with no api_key keeps falling back to Databricks SDK auth. A pathless api_base goes to the native route only for Unity Catalog names, matching the chat route. * test(databricks): cover SDK auth with client anthropic headers and a Unity Catalog workspace root on the native route * fix(databricks): keep client anthropic headers off an opted-in passthrough api_base A databricks Claude deployment whose api_base is no workspace route and that opts into /v1/messages with supported_endpoints falls back to the OpenAI-like passthrough. That config does not filter betas through the beta map, yet it received the native-only Databricks header entry, so Claude Code's prompt-caching-scope beta reached the upstream raw and got a 400 where the merge base answered 200. Each Messages config now says whether it is the provider's native route, the OpenAI-like passthrough says no, and the handler passes that answer when it reads provider-specific headers, so native-only entries reach only native configs. * test(databricks): cover client anthropic betas on an opted-in passthrough api_base A databricks Claude deployment whose api_base is no workspace route and whose model_info.supported_endpoints opts into /v1/messages takes the OpenAI-like passthrough. The cell sends Claude Code's prompt-caching-scope and context-1m betas through the proxy and asserts the caller gets the upstream's message and the gateway receives no anthropic-beta, as on the merge base. The scripted gateway answers 400 on the prompt-caching-scope beta, as the real one does * fix(anthropic): keep beta map loads off shared threads and build the safeguards evaluator only when the proxy classifies Unfiltered configs such as first-party Anthropic never read the beta map to decide safeguards support. Filtered configs await the map on its dedicated loader before reading it, on both the native and the MCP paths. The native handler decides after the upstream call and builds the evaluator only when the proxy classifies, so malformed messages keep the upstream 400. The Databricks dispatch tests assert the dispatched route instead of the config class, and the sail and Eden AI wire rows expect safeguards dropped, as JSON providers do. * test(databricks): cover a loaded beta map that marks the safeguards beta unsupported A remote beta map that nulls dangerous-tool-use for databricks while the bundled map allows it must send neither safeguards nor the beta to the serving endpoint, with or without a client beta, and the caller gets a 200 with no verdict. * test(anthropic): annotate the MCP beta map recordings as Final * fix(anthropic): drop safeguards on routes without the classifier only under drop_params A route whose upstream does not answer safeguards (a JSON provider, or a map that marks the dangerous-tool-use beta unsupported) now forwards the field and the beta as the merge base did unless drop_params is set or the proxy runs its own classifier, matching how litellm treats any unsupported param. Databricks keeps dropping both, since its merge base bridge never forwarded the field. --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>	2026-10-18 02:44:38 +00:00
Mateo Wang	68a8b12ab3	fix(proxy)!: end a chat completions stream with an error event when a guardrail blocks mid-stream (#46953) ... * fix(proxy): end a chat completions stream with an error event when a guardrail blocks mid-stream A streaming guardrail that raised an HTTPException after the first chunk re-raised it inside the SSE generator, so the 200 body was cut off with no finish_reason, no error event and no [DONE]. Build the error frame through sse_error_payload instead, keeping the status, message and structured detail, and encode values JSON cannot represent as strings so the frame always goes out. * fix(proxy): keep early guardrail blocks on their HTTP status and end mid-stream errors with [DONE] A guardrail block before the first chunk is raised again, so its response stays the 400 event-stream body it is on main. A mid-stream error event now carries the failure hook's replacement error when one is returned, is followed by data: [DONE] on OpenAI-format streams, and leaves the Gemini route's raise unchanged. Error details JSON cannot encode are written as strings instead of breaking the event. * fix(proxy): keep a per-chunk guardrail block on the first chunk on its event-stream 400 * fix(proxy): treat a keepalive ping as a started stream so a later guardrail block ends in-band * fix(proxy): encode non-JSON guardrail details in early stream error frames An early guardrail block whose detail holds a value JSON cannot encode sent 400 headers and then cut the body. The error frame now writes such a value as its string form, the same as the mid-stream event. The keepalive test now runs on a virtual clock instead of real sleeps. * fix(proxy): show an in-band stream error event as an error in the CLI, Python client, and dashboard playgrounds ChatClient.completions_stream raises StreamError on a data frame carrying an error, so litellm-proxy chat prints the block reason and keeps the partial reply out of history. The prompt playground and the Interactions playground read the same frame through a shared streamErrorMessage helper. Adds the audit's integration cells for chat stream error events, and makes the endpoint tests' failure-hook mocks return None so they check the real error payload. * fix(proxy): print stream error text verbatim in the CLI and read split error events in the prompt playground The CLI printed the server's error message as Rich markup, so a closing tag like [/pii] in a guardrail message crashed lite chat. The prompt playground now buffers partial lines across reads, ChatClient raises only on a non-empty error, StreamError redacts keys like the other client exceptions, and StreamError is exported from litellm.proxy.client * fix(proxy): print CLI stream errors without Rich highlighting or emoji codes * test(proxy): cover the CLI's plain-text 400 error print * test(proxy): annotate the new client stream test locals as Final * fix(proxy): send the failure hook replacement on Responses streams and before the first chunk * fix(proxy): end a Responses stream with response.failed when it fails on a built-in exception * fix(proxy): keep a failure hook replacement before the first chunk in-band so bare stream routes still answer it A non-HTTP failure whose hook returns an HTTP error was raised before the first chunk, which create_response turned into the hook's status but which a bare StreamingResponse route such as /queue/chat/completions answered as a 200 with zero bytes. Only the original HTTP errors raise now. The replacement goes out as the stream's error event, which create_response still answers with the hook's status as a JSON error. Adds audit round 2's integration cells for failure hook replacements on chat and Responses streams, built-in exceptions on Responses streams, and the Python client. * test(proxy): cover a queue stream whose failure hook replaces a failure before the first chunk The audit cell posts to /queue/chat/completions with a callback that raises before the first chunk and a failure hook that answers 403. It checks for a 200 event stream whose only event is the replacement, then one [DONE], with the callback's own message absent	2026-10-17 18:00:12 -07:00
Mateo Wang	75faaeab64	feat(count_tokens)!: configurable token_count_framing and token_count_model, count source in the response (#46777) ... * feat(count_tokens): configurable token_count_framing and token_count_fallback_model, count source in the response Count endpoints now say where each number came from in litellm_count_source (provider, fallback_model, local_estimate) and name the fallback model in litellm_count_fallback_model. When the provider answers 400 or 404 for a model it cannot count, the proxy counts the same request with token_count_fallback_model. token_count_framing adds a per-model constant to local estimates. Both settings ship in the cost map for Bedrock Claude Sonnet/Haiku 5.5, Bedrock Kimi K3, and Databricks Kimi K3 and DeepSeek V4 Flash, and can be overridden in model_info. * test(count_tokens): classify the new cost map keys in the schema generator and expect count_source in exact-shape tests * test(count_tokens): e2e matrix against real inference and integration wire tests for count source, fallback and framing * fix(count_tokens): keep the provider error when local counting is disabled, name the fallback error, keep settings in cooldown Moves the cost map lookup off the event loop * ci(cost map): bound token_count_framing to non-negative and token_count_fallback_model to non-empty * fix(count_tokens): keep a failed fallback's own status, ship fallbacks only where they count, add system.ai framing A fallback model that answers 404 returns the requested model's error unchanged, and any other fallback failure answers with its own status and message. The eu, apac, au and jp Sonnet and Haiku 5.5 entries no longer ship the Opus 5.5 fallback, which AWS serves only in us-east-1. A configured empty token_count_fallback_model turns the shipped fallback off. Config framing accepts whole-number floats and rejects negatives. The Databricks system.ai Kimi K3 and DeepSeek V4 Flash names carry the same framing as their serving endpoint names, and the e2e matrix runs on Bedrock Haiku 5.5 too. * test(databricks): list the system.ai Kimi K3 and DeepSeek V4 Flash names with their published DBU rates * fix(count_tokens): skip a token count fallback model for an hour after it answers 404 on that deployment A us. or global. Sonnet 5.5 deployment outside us-east-1 paid two extra Bedrock calls and about 200 ms on every count, since Opus 5.5 cannot count there either. The Kimi K3 e2e also runs the large system prompt shape now. * test(count_tokens): use the shared integration port allocator in the fallback wire test * fix(cost map): keep the Databricks system.ai entries to framing only, so their spend stays as today * test(count_tokens): cover the fallback 404 skip, inference profile base_model, shipped framing, and deployment-scoped token count settings Adds integration cells for a fallback model that answers 404, an application inference profile ARN deployment whose base_model carries the shipped fallback, and the shipped Kimi K3 framing with token_count_framing 0 turning it off. Adds unit tests that keep token count settings off the shared backend cost map key and that store a token count setting on PATCH only when the operator changed it * fix(count_tokens): keep the counter's own 400 and the provider's error when a framed estimate cannot read the body A 400 the OpenAI or Gemini counter returns before calling the provider is the caller's answer, so it no longer tries the fallback model or a framed estimate. When the framed local estimate cannot read a content block, the client gets the provider's error instead of a 500. Adds /audit round 2's integration tests for the fallback leg's converted body, the Anthropic envelope on fallback failures, and both framing cases. * fix(count_tokens): answer the provider's error whenever a framed estimate raises A tool schema the local estimate cannot format, such as a boolean subschema or an array with no items, raised AttributeError or KeyError and answered a 500 on a framed deployment whose provider had already answered 400. Any estimate failure now answers the provider's own error. * fix(count_tokens): load the custom tokenizer inside the guarded framed estimate A framed deployment whose custom_tokenizer could not load answered a 500 or 503 where the provider had already answered 400, because the tokenizer was selected outside the estimate's error handling. Selecting it inside answers the provider's error, logs a warning with the estimate's error, and still raises the Rust extension's fork-guard errors. * fix(count_tokens): look up framing under the deployment's custom_llm_provider * fix(count_tokens): share one tokenizer download per worker and bound the wait after a provider error A framed deployment whose custom_tokenizer is not cached locally made every count wait out the Hugging Face hub's whole retry cycle when the hub could not be reached, and a burst of those loads held the default thread limiter that every count's cost map lookup also needs. Counts on a worker now share one download per minute, a failed download is reused for the rest of that minute, and after a provider error a count waits at most 5 s before answering the provider's error. The swallowed-estimate warning logs only the error type. * fix(count_tokens): keep one tokenizer download per key running and load the local route per request * test(count_tokens): type the scripted counter and wait on events instead of wall time where possible * fix(count_tokens): run framed tokenizer loads on their own capped threads and answer a tokenizer panic with the provider error Framed loads used anyio's default 40 threads, so a hub that drops packets let about 40 hanging loads stall every count on the worker. Loads now run on a per-worker pool of 4, and a count that finds 4 loads running answers the provider's error at once. Any finished load is reused for a minute after it finishes, so a load that fell back to tiktoken is not retried on every count. A pyo3 PanicException from the tokenizer, while loading or counting, now answers the provider's error instead of a plain 500 * feat(proxy): count tokens with token_count_model in its pinned region token_count_model {model, region} replaces token_count_fallback_model. Bedrock Sonnet and Haiku 5.5 count with Opus 5.5 in us-east-1, or Melbourne for au. profiles, and a failure names the region to enable * fix(count_tokens): use the renamed count model constant in the e2e test and list token_count_model with the object keys * fix(proxy): keep the upstream error envelope when adding the region hint * test(proxy): annotate the token count setting echo test * ci(cost map): require non-blank token_count_model strings and test the region rules * fix(count_tokens): answer the token_count_model's error even when framing is set * fix(count_tokens): keep the provider error for Google contents instead of a framed estimate * fix(count_tokens): estimate Google contents the route translated to messages * fix(count_tokens): keep the provider error for Google contents with non-text parts * test(proxy): drive tokenizer wait and cost map tests by events and a skippable loop clock * fix(count_tokens): check Google text-only parts without a KeysView comparison basedpyright flags * feat(proxy): count Bedrock Kimi K3 tokens exactly with its pinned tokenizer * test(bedrock): keep the Kimi K3 image check in-process * fix(count_tokens): join the region hint to an upstream message that already ends with a period Also pins that a blank token_count_model in config falls through to the cost map default * fix(count_tokens): count Gemini tool-call turns and Responses tools, and stop tokenizer retries from stalling counts The Google countTokens route estimates contents with functionCall, functionResponse and thoughtSignature parts again, and still answers the provider error for media, thought and unknown parts The Kimi K3 exact count renders Responses API and Anthropic tools through the chat tool translation the Vertex count already used, now shared from the prompt factory, and falls back to the estimate when the Converse body cannot carry a tool A failed Kimi K3 tokenizer load is retried in the background without making counts wait, and a load still running after the wait logs a warning * fix(count_tokens): count Kimi K3 tools the way Bedrock inference sends them A flat Responses API function or custom tool becomes the chat tool the Responses route sends to inference, and every other tool goes to the Converse body as is, so hosted tools Bedrock drops are left out of the count instead of being counted or turning it into an estimate. * test(count_tokens): annotate new token counter test locals with Final * fix(count_tokens): keep shipped count regions inside the deployment's geography A plain Bedrock Sonnet or Haiku 5.5 deployment in a non-US region no longer sends its count prompt to us-east-1. Global count models and configured token_count_model keep their pinned region. Also expect litellm_count_source in the Vertex Llama count test main added * fix(count_tokens): resolve count settings off the event loop	2026-10-17 17:11:27 -07:00
joshua-berri	3fb95c8fe3	fix(batches): preserve spend across malformed output and metadata failures (#47184) ... * fix(batches): preserve recoverable spend and terminal reconciliation state * fix(batches): narrow validated envelope types * fix(batches): serialize stored metadata when releasing claims * fix(batches): sanitize metadata before claiming completed batches * refactor(batches): expose existing metadata serializer for shared use --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>	2026-10-17 17:10:22 -07:00
Shivam Rawat	c58fc0c996	fix(rag)!: use team provider credentials and allow viewer and JWT team access (#45497) ... * fix(rag): use team provider credentials and allow viewer and JWT team access Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(rag): assert persisted managed store data excludes team credentials Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(jwt): run real team model checks in the route denial test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(rag): scope team provider credentials to openai vector stores Bedrock and other providers kept their pre-PR credential and region resolution: a team bedrock deployment's region no longer overrides the caller's region on RAG query. Query tests now fake the provider at the HTTP boundary with a real vector store registry. * fix(rag): use only the team's own OpenAI deployment for RAG credentials * fix(rag): ignore caller credential fields the query search never uses when picking team credentials * fix(rag): treat blank credential fields as absent when picking team credentials * test(rag): delete the stores the integration ingests create before the owned proxy exits * fix(proxy): let a restricted key use the team deployment its wildcard or model covers A key restricted to gpt-4o on a team whose own OpenAI deployment is openai/* never resolved that deployment's credentials, because the key allowlist was matched against the deployment's public name literally. The allowlist now matches a wildcard on either side the way request authorization does, through the auth layer's own helper, so /rag, /files and /batches resolve the team deployment for every key that may call a model on it. * fix(batches): read a restricted key's batch input through its team deployment The batch access check downloaded the input JSONL with the proxy's OPENAI_API_KEY while the upload and the create used the team deployment, so a key restricted under a team openai/* deployment could not create a batch when the two keys belong to different OpenAI projects. The read now resolves the team deployment the way the create does when no model pins it Adds the audit cells for keys restricted under the team wildcard on /rag, /files and /batches, and for the rag-vs-chat split of a key restricted to a global exact-name deployment * fix(rag): load deployments oldest first, reject file_id on stores that cannot take one, and show ingest errors in the dashboard * fix(rag): pick the team deployment with the lowest id, return 400 for caller mistakes, keep the ingest id in errors, and show partial success in the dashboard * fix(rag): pick the team's oldest OpenAI deployment so adding one never moves the team * fix(rag): keep config file team deployments first and try JWT teams in sorted order A team's config file OpenAI deployments now win in file order, as on the base, before its DB ones oldest first, so upgrading never moves a team that has both. A JWT in several teams tries them in sorted order, so every worker resolves the same team. * fix(rag): return 400 for Bedrock, S3 Vectors and Gemini store config mistakes on ingest * fix(rag): keep forwarded provider keys on /rag/query and mixed JWT team claims working A forwarded x-api-key now counts as a caller credential, so the /rag/query search uses it over the team deployment as at the merge base. Sorting the JWT team claim compares entries as text, so a stray number or null no longer turns into a 401. A Gemini store with no proxy key is a 500 again, and a non-string vector_store_id keeps the merge base's 400 message. * fix(rag): let a forwarded provider key win over team credentials on files, batches and ingest * fix(rag): keep team credentials when a request carries its own key or api_base A forwarded x-api-key or a body api_key now replaces only the key of the team deployment, keeping its api_base, as chat completions does. A body litellm_credential_name no longer turns team credentials off on /v1/batches. * fix(batches): keep the team key on the team host when a request sends only api_base A request api_base now replaces the team deployment's api_base only when the request also brings its own api_key, and a non-string api_key or api_base is ignored, as on the merge base. * fix(files): ignore a blank request api_key or api_base next to team credentials * fix(files): answer 400 for a request api_key that cannot be sent as an HTTP header * fix(rag): honor a body drop_params for a forwarded key that cannot be an HTTP header * fix(rag): read the request field for drop_params only on multipart ingest bodies * fix(rag): type the ingest body read for drop_params * fix(batches): count a model-routed batch's input with the deployment key it is created with * fix(batches): reject a batch create whose x-litellm-model headers name different models * fix(rag): treat a null provider and whitespace store credentials as unset when picking team credentials * refactor(files): type the team deployment the credential resolver ranks --------- 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>	2026-10-17 23:51:48 +00:00
Misbah Syed	8b442f00fc	fix(proxy): count the whole minor line in the upgrade notice for patch releases (#46942) ... * fix(proxy): count the whole minor line in the upgrade notice for patch releases A patch release's notes only list its backports, so v1.105.1 showed "0 new features, 1 fix, and 0 other updates" even though upgrading from v1.104.x brings everything in v1.105.0 too. When the latest release is a patch, also fetch the recent release list and sum the stable releases on the same major.minor line (skipping rc/dev prereleases and drafts). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(proxy): use tuples for release lists and sync the dashboard API types Satisfies the LIT001 type-discipline gate and regenerates the latest_release_info description in schema.d.ts. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(proxy): cover the bad release-list payload and non-semver latest tag Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(proxy): type the release-line Counters so basedpyright sees no unknowns Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(proxy): fetch earlier patches of the minor line by tag Reading the first page of /releases could miss the line's .0 release when prereleases push it off the page, and one unrelated release with a null body failed validation for the whole list. Fetch each earlier patch tag directly instead (v1.105.0 .. v1.105.N-1), skip tags with no stable release, and treat a null release body as empty notes. --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-17 15:49:57 -07:00
yuneng-jiang	4bafebbcdc	fix(ui): take the dashboard's user role and identity from the server (#47025) ... * fix(ui): take the dashboard's user role and identity from the server Adds an internal GET /management/v1/users/me that returns the user id, role and email the proxy resolved for the calling key. The dashboard now reads identity from it instead of the session cookie's claims, so its navigation and role gating always match what the backend authorizes. The layout waits on it behind the existing loading screen, and a failed lookup clears the session and returns to login. Sessions that must change their password can also read it * fix(ui): sign out when the current user lookup fails and wait for it on chat The dashboard layout now holds the loading screen and signs out when /management/v1/users/me fails, instead of mounting the shell and looping back to loading as each consumer refetched the failed query. The chat layout also waits for the identity so its panels never query without a user id. The lookup goes through the typed client with the regenerated schema.d.ts * fix(ui): send the session's auth header on the first user lookup and keep chat closed until authorized The first lookup runs before AuthProvider registers the custom header name, so it now reads auth_header_name from the session cookie. Chat also waits for isAuthorized, so a failed lookup no longer mounts the shell with an empty user id * fix(ui): type the dashboard callers of the now typed user id useAuthorized used to hand back the cookie's user id untyped, which hid six strict type errors in its callers. The id is now string | null, so the production build failed. Callers handle the null case, and query key filters accept the boolean blocked filter * fix(ui): look up the current user only after the proxy URL is discovered Pages outside the dashboard shell, like chat and connect, could start the lookup before UI config discovery set the proxy base URL. On a split-origin deployment both attempts then hit the UI origin and a valid session was signed out * fix(ui): keep a loaded identity while UI config discovery reruns Pausing the lookup by passing a null token switched the query key, so on the dashboard the identity the layout had already loaded vanished until the shell's own UI config request finished. The key now stays the same and only the fetch waits for discovery	2026-10-17 14:39:33 -07:00
Mateo Wang	897dda7920	fix(router)!: stop a chat-mode Mantle deployment from rewriting the shared Responses routing row (#46263) ... * fix(router): stop a chat-mode Mantle deployment from rewriting the shared Responses routing row A deployment with an explicit custom_llm_provider and model_info.mode: chat used to overwrite the shared litellm.model_cost row, moving every other deployment and plain SDK calls onto Chat Completions until restart, because the downgrade guard read a double-prefixed key and never fired. The guard now reads the real key, and a deployment's own mode decides its routing in responses_api_bridge_check, except on chatgpt and github_copilot where Chat Completions is dead for responses-mode models. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(responses): keep the bridge-check mode tests in the sharded bridge flag file Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): let a deployment mode pin replace only the shared-row mode so the bridge capability rules still run Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): keep Responses-only backends bridged under a deployment chat pin and satisfy the type gate Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): give the bridge casts a reason and drop the bare noqa so the type discipline gate passes Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): keep a responses row with no supported_endpoints bridged under a deployment chat pin Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): read the downgrade guard's mode from the row registration writes A chat-mode openai/<name> deployment merged into the bare <name> row while the guard read openai/<name>, so the guard never fired and the shared responses row turned to chat. An explicit responses/ prefix now also outranks a deployment's chat pin. * fix(router): let an explicit responses/ prefix outrank a registered chat row The router now registers a chat-pinned openai/responses/<model> deployment under its own name, so the lookup found mode chat and the request went to Chat Completions as responses/<model>. * fix(router): keep the shared row's mode for every deployment pin and honor the pin on /v1/messages A deployment's mode pin now never rewrites the shared cost-map row in either direction, including the responses/-stripped twin key, so siblings and SDK calls keep routing by the registered mode. The backend key formula goes back to main's, which keeps capability fields off rows that registration never wrote at base. The /v1/messages adapter and handler read the deployment's model_info, so a chat-pinned deployment gets a plain reasoning effort on chat completions. * fix(router): keep copilot responses opt-in, make unmapped pins order-free, send Mantle auto summary as auto A responses pin on a github_copilot model or a model missing from the cost map still marks the shared row, since that is how those models opt into the Responses API. A chat pin never marks a row, so registration order no longer matters. Mantle's OpenAI path gets summary auto in place of the auto summary detailed. The Azure o3-pro and o3-deep-research rows drop Chat Completions, which Azure does not serve for them. * fix(router): skip a non-string model_info.mode when keeping the registered mode * fix(router): keep chat-pinned Mantle tool calls and summaries on the Responses API A Mantle row that also serves the Responses API now follows the GPT-5 tool and reasoning summary bridge rules, since Mantle Chat Completions rejects function tools on gpt-5.4+ unless reasoning is off and rejects the summary aliases. Mantle chat gets a dict reasoning_effort as its effort level. The opt-in auto summary asks each Responses config for its level, auto on Mantle's OpenAI path, so a client's own detailed summary follows drop_params as at base. No mode replaces a registered responses mode, and chatgpt and github_copilot rows take any pin until they are responses, which restores the Copilot chat opt-out. * fix(responses): ask the target for its auto summary level on the chat bridge and reasoning_effort * test(integration): run the Mantle region-prefixed v1 base case again This PR routes that deployment by its own chat pin, so the case passes and no longer needs the skip * fix(bedrock_mantle): keep web search and reasoning summaries on the Responses API under a chat pin A chat-pinned Mantle GPT-5 deployment now sends web_search_options and a dict reasoning_effort carrying a summary to the Responses API, which serves them. Mantle Chat Completions drops n above 1 and a reasoning summary under drop_params and answers 400 without it. The /v1/messages adapter probes the bridge with only the client's own summary, so an auto-injected one never moves the request * fix(bedrock_mantle): check n and reasoning summaries only on the Chat Completions request * fix(router): keep a non-string deployment mode off the shared routing row A deployment whose model_info.mode was an int, a list, or an object still reached the shared cost-map row, so an unpinned sibling on the same backend stopped routing to the Responses API. The shared registration now drops a mode that is not a string, and the deployment keeps its own raw value. Adds integration cells for per-deployment routing across the OpenAI and Anthropic SDKs, raw httpx, wildcard routes, malformed modes, an upstream outage, config changes under traffic, and a worker kill plus restart. * test(integration): find each routing cell's spend row by the response it logged A bridged call logs its row under the wrapped Responses id, which the caller never sees on a streamed Messages answer, so look the row up by the answer's own ids and the upstream ids for its marker. Int and list modes 500 their own model group on main too, so those cells check only the sibling, and the summary cell sends the auto level Mantle's Responses path accepts * fix(bedrock_mantle): run extra_body fields through the chat checks A chat-pinned Mantle request that nests n or reasoning_effort in extra_body now gets the same 400, drop, and effort-level handling as the top-level fields. The bridge test injects a MockTransport client instead of patching HTTPHandler.post. * test(router): cover nested reasoning_effort routing, messages thinking summaries and per-target auto summary levels * fix(router): probe a pinned deployment's own API on /health and keep a requested summary beside an extra_body effort * fix(router): keep a custom-priced deployment's mode pin off the shared backend row on each request * fix(router): run per-request custom pricing through the shared mode guard so a health probe keeps the row's mode * fix(router): drop the debug log that wrote a request's model name from keep_registered_mode * test(router): cover custom-priced chat pins, their health probes and summary aliases beside an extra_body effort * fix(proxy): pass only the mode pin to a /health probe so a failing probe never cools its deployment down * test(router): cover failing health probes leaving their deployment out of cooldown, with and without background checks * test(router): kill the worker that holds burst calls, so the worker kill cell never depends on how the kernel spread them * fix(router): route a fine-tune the same whichever deployment registers first Main's register_model now seeds an unmapped fine-tune's row from its base model's built-in row, mode included, on the first registration. The mode guard read only the live row, so a responses pin marked the shared row only when it registered before its siblings. The guard now reads the row the registration merges onto, the live row or else the row it would seed. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 21:39:14 +00:00
Mateo Wang	ef1d3959a0	fix(count_tokens)!: answer 400 for Vertex partner models without a count API and OpenAI-shaped provider errors on /v1/responses/input_tokens (#47163) ... * fix(count_tokens): answer 400 for Vertex partner models without a count API and OpenAI-shaped provider errors on /v1/responses/input_tokens * fix(count_tokens): answer 400 for Vertex Mistral counts and type the input_tokens error tests Vertex has no count-tokens route for Mistral or codestral models, so they now get the same 400 as other partner models without a count API instead of a 404 that points operators at IAM. * fix(count_tokens): unwrap prefixed provider errors on /v1/responses/input_tokens * fix(count_tokens): say LiteLLM, not Vertex, cannot count a Vertex partner model * fix(count_tokens): count a Vertex partner model with its configured custom_tokenizer and unwrap prefixed flat provider errors * fix(count_tokens): keep the 400 for contents-only Vertex partner counts with a custom_tokenizer * fix(count_tokens): pass through an OpenAI provider error that omits param or code * fix(count_tokens): keep the status-based type for Anthropic count errors on the Responses route * test(count_tokens): cover the Vertex partner count gate and Responses count error shapes on a real proxy * test(count_tokens): add regression tests for the Vertex partner count gate and Responses count error shapes	2026-10-17 21:15:38 +00:00
Kerry Lu	1552b5b69f	fix(proxy): warn at boot when a config environment_variables key replaces a value already set in the process environment (#47165) ... Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 20:52:01 +00:00
devin-ai-integration[bot]	4273996985	fix(spend_logs): persist user email in spend log metadata so it shows in UI request logs (#41150) ... * fix(spend_logs): persist user email in spend log metadata so it shows in UI request logs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(spend_logs): update payload expectations for user email metadata Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(gcs_pubsub): add user_api_key_user_email to the spend log fixture Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(spend_logs): drop untyped metadata key args from the debug log to keep the type gate flat Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(spend_logs): pass metadata keys to the debug log as a lazy %-style argument Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(spend_logs): store user email in spend logs only behind store_user_email_in_spend_logs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * revert(spend_logs): store user email in spend logs by default, drop store_user_email_in_spend_logs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(spend_logs): store an empty user email as null, narrow the expected payload test diff Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: jesus <jesus@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 13:26:09 -07:00
alberto	bbd446b476	fix(proxy): report requested model in streamed Responses response.model (#46662) ... * chore: Add failing test case Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> * fix: Restamp nested response.model in streamed Responses events Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> * chore: Add tests Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> * chore: Run format and lint, and fix Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> * fix: Type nested Responses restamp to satisfy basedpyright gate Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> * fix(proxy): restamp the nested model on streamed response.queued events Background streams send response.queued as a GenericEvent, so its nested response.model still carried the backend name. Also drop the new comments * fix(proxy): restamp a nested response kept as a dict on streamed lifecycle events * test(proxy): drive typed events through the nested restamp no-op test * fix(proxy): restamp the nested model on guardrail block frames in streamed responses * test(proxy): assert a cache-polled background response reports the requested model * fix(proxy): restamp nested model on dict events and on every SSE data line --------- Signed-off-by: Alberto Perdomo <aperdomo@redhat.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>	2026-10-17 19:52:10 +00:00
yuneng-jiang	4846cfabc7	fix(vector-stores): keep proxy context out of provider vector store metadata (#47021) ... * fix(vector-stores): keep proxy context out of provider vector store metadata The proxy merged its request context (user_api_key_* fields, endpoint, user_agent, requester_ip_address, litellm_api_version) and the router's deployment info into the vector store request's metadata. For vector stores that field is also OpenAI's own metadata, which is capped at 16 keys, so a store created with a team key was full on creation and every later metadata update returned 400. Vector store routes now keep that context in litellm_metadata, like batches, files and responses, and the router does the same for avector_store_create. Provider-side metadata holds only what the caller sent. Adds db_scripts/strip_vector_store_internal_metadata.py, an opt-in script that removes the proxy-written keys from stores created before this change. It is a dry run unless --apply is passed. * fix(vector-stores): page the metadata cleanup script without recursion and tolerate non-string values Listing every store recursed once per page, which overflows the interpreter stack on large projects. Pages are now walked iteratively. Metadata values are no longer required to be strings, and a malformed response exits 2 with a fixed message instead of a traceback that could echo metadata values. * fix(vector-stores): read proxy agent id, tags and spend_logs_metadata from litellm_metadata Vector store routes now keep proxy context in litellm_metadata, but the v3 limiter only read agent_id from metadata, and logging let provider metadata tags or spend_logs_metadata replace the proxy's values. A string tags value also crashed get_request_tags. The limiter now prefers the proxy-resolved agent_id in litellm_metadata. Logging combines list tags from both buckets (metadata first, deduplicated) and merges dict spend_logs_metadata with litellm_metadata winning, ignoring values of the wrong type. * fix(vector-stores): narrow the logging fallback to mistyped caller values The tag union and spend_logs_metadata merge changed logged tags and spend_logs_metadata on every route that has both metadata buckets, deduped tags quadratically, and stopped background interaction polling from keeping string tags as sent. Caller values now win exactly as before, and the proxy's litellm_metadata tags or spend_logs_metadata only replace a caller value of the wrong type. The limiter reads agent ids through a pydantic model instead of a cast and ignores non-string ids. * fix(vector-stores): log the proxy's full tag list on litellm_metadata routes On routes that keep proxy context in litellm_metadata, the proxy builds litellm_metadata.tags from the caller's tags plus key, team and header tags, but get_request_tags preferred the caller's metadata.tags. A caller sending metadata.tags on a vector store call dropped the key's tags from request_tags, which tag spend tracking reads. get_request_tags now prefers a non-empty litellm_metadata tag list, and falls back to metadata.tags as before. * fix(vector-stores): strip LiteLLM-written keys at the provider boundary instead of moving metadata buckets Moving vector store proxy context into litellm_metadata broke shared readers (agent limits, request tags, merged logging metadata), and fixing them widened the change to every litellm_metadata route. This reverts the bucket move, the router change and the reader fixes, so proxy context stays in metadata exactly as on main. Vector store create and update now drop the keys LiteLLM itself writes (user_api_key*, requester and deployment keys, agent ids) from the metadata sent to the provider, in the shared optional-param helper both paths use. The cleanup script reuses the same key list. * fix(vector-stores): pass non-string metadata keys through the provider metadata filter * fix(vector-stores): strip LiteLLM-written metadata keys only on proxy and router calls * fix(vector-stores): send the provider exactly the metadata the caller sent through the proxy * fix(vector-stores): snapshot caller metadata from the raw request body and keep it out of logged request bodies * fix(vector-stores): copy the parsed-body metadata when the raw request body cannot be reparsed	2026-10-17 12:51:47 -07:00
joshua-berri	4143e0869e	fix(batches): handle empty models when logging batch cost (#47155) ... Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>	2026-10-17 12:49:31 -07:00
mrinal-berri	a79dae764f	fix(proxy): route team key vector store calls to a team model of the store's provider (#46894) ... * test(vector-stores): reproduce team key search routed to a team model of the wrong provider A team key's model-less vector store search picks the team's first deployment, so a langgraph team model turns a Bedrock store search into "Vector store search is not supported for langgraph". Cover map_team_model picking by provider and a registered Bedrock store search reaching Bedrock with the registry's credentials. * fix(router): match model-less team deployment to the requested provider map_team_model now takes an optional custom_llm_provider. With no model given, it returns the first team deployment serving that provider, or None when none does, instead of the team's first deployment. Without a provider it behaves as before, so BYOK teams calling raw vector store IDs keep their team key. * fix(proxy): pass the vector store provider when mapping team models Vector store search, retrieve, update and delete pass the store's custom_llm_provider to map_team_model, so a team key's model-less call lands on a team deployment of that provider, or on the direct path with the store's own credentials when the team has none. Other model-less routes keep today's behavior. * fix(proxy): type the vector store provider passed to map_team_model Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(vector-stores): cover team key vector store search provider routing end to end Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * style(proxy): ruff format route_llm_request.py Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): type vector store routing tests and mock Bedrock transport Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): pin model-less vector store calls when a public name mixes providers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): keep team provider routing in map_team_model 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>	2026-10-17 14:32:03 -05:00
ryan-crabbe-berri	f6ae25939e	feat(guardrails): add num_retries to generic_guardrail_api for checks lost after connect (#46965) ... * feat(guardrails): retry generic_guardrail_api checks lost after connect with num_retries * fix(guardrails): close each guardrail retry connection before the next attempt and cap num_retries at 5 A failed retry's fresh client stayed open until every later retry finished, so a check that kept timing out held one idle client per retry. Each retry now closes its own client as soon as it ends, and num_retries is capped at 5 so the retry chain stays shallow * refactor(guardrails): type the generic_guardrail_api inbound header sanitizer as a mapping Keeps the type check gate at its merge-base count after the num_retries constructor params added unknown kwargs errors in the Qohash subclass * chore(guardrails): regenerate OpenAPI snapshot and UI types for num_retries, allow the retry client The guardrail retry opens its own client on purpose to get a new connection and closes it after the attempt, so the per-request async client check allowlists generic_guardrail_api.py	2026-10-17 12:22:41 -07:00
Yassin Kortam	4b635f18e4	fix(mcp): bound paginated tools/list by LITELLM_MCP_TOOL_LISTING_TIMEOUT (#46513) ... Preserve explicit per-server timeouts while bounding paginated listing Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 12:16:46 -07:00
Yassin Kortam	7049a5ff4d	fix(mcp)!: register the gateway's own DCR client for bridge servers instead of relaying the caller's loopback redirect (#46940) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 12:14:28 -07:00
Yassin Kortam	03e3e71efa	fix(proxy): let proxy_admin_viewer store its own MCP credentials (#46994) ... Co-authored-by: michelligabriele <gabriele.michelli@icloud.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 11:31:37 -07:00
devin-ai-integration[bot]	8226b2be9a	fix(otel): report cache hits at zero cost with a cache-hit flag in V1 and V2 spans (#43604) ... * fix(litellm): report zero cost and cache-hit attrs on cache-served spans * fix(litellm): stamp cache-hit marker on HiddenParams carriers and restore probe side effects gauntlet-mini on ace57d25f verified two live gaps. TextCompletionResponse and ResponsesAPIResponse carry _hidden_params as a HiddenParams object, so the dict-gated marker write skipped them and the served hit still stamped the full price. The marker write is now container-agnostic, which it already was for the partial-embedding stamp, and a regression test exercises the carrier end to end. _uncached_response_cost also restores billed_token_rates, zero_cost_warned, and the response_cost_failure_debug_information key alongside cost_breakdown, so the probe leaves no pricing state on the call it reads. * test(caching): cover cache-hit marker on HiddenParams carriers through the caching handler * fix(logging): keep the uncached price probe's restores to the state it can leak * fix(otel): emit V2 LLM-call span for cache hits with explicit cache attributes Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(otel): read cache payload fields defensively without casts Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore(otel): clarify pyright suppression reason on cache payload reads Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(otel): build the cache-hit view from typing_extensions.TypedDict so import works on Python 3.10 and 3.11 * fix(otel): report cache hits at zero cost everywhere and mark misses Cache hits now carry a zero cost breakdown and a zero hidden response cost, the /v1/messages hit cost header follows chat and responses hits, every span carries litellm.cache_hit, V2 hit spans drop server.address, an async hit keeps the provider-prefixed model name, and the V2 attribute budget counts preset keys * fix(otel): send a 0 cost header on cache hits and keep hits out of deployment TPM Cache hits now send x-litellm-response-cost: 0.0 on chat, responses and /v1/messages, while a fresh call whose cost is 0 still sends no header. The async hit path stamps the same model name as main again. Stamping the provider-prefixed name made a hit's tokens count toward the deployment's TPM limit, so repeated cached requests hit 429s under usage-based routing. Drop comments that restated fields and annotate new test values as Final. * fix(otel): keep the served pricing basis on a cache hit's cost breakdown A hit's breakdown now keeps service_tier, data_residency, vertex_location, and the discount and margin rates the served call recorded, with every amount at 0, so savings reports still read the basis. The hit header test now drives the live non-streaming header path. * fix(otel): send zero breakdown headers on a cache hit and give hit spans a fresh call's cost keys A hit's x-litellm-response-cost-original, -input, and -output headers now read 0.0 instead of going missing or carrying the full price. A hit's cost breakdown now comes from pricing the response as fresh, so every route exports the same keys, pricing basis, and rates with every amount at 0. * test(integration): assert zero cost and the cache-hit flag on cache-served OTel V1 and V2 spans * test: wait for the cache entry before the cache-hit request and build cost headers without a route_request double * test: annotate the new cache-hit unit test locals with Final --------- Co-authored-by: shrey kharbanda <shreshth@berri.ai> 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>	2026-10-17 18:25:32 +00:00
yucheng-berri	223800f916	fix(presidio): stop overlapping entity spans from corrupting numbered PII tokens (#47024) ... * fix(presidio): resolve overlapping entity spans in numbered tokens anonymization (#42130) Mirror of BerriAI/litellm#42133 by @PINYOPATTANAWASANPORN, squashed onto main with the unit test moved to tests/unit after the test tree relocation * fix(presidio): label an overlapping run by its outermost detection, add integration coverage A run of overlapping detections now takes its entity type from the highest-scoring detection that no other detection in the run contains, matching Presidio's own anonymizer, so a phone number with a date-shaped fragment inside stays PHONE_NUMBER. The resolver returns typed detections instead of Any. * fix(presidio): drop the redundant comment in the numbered token loop * fix(presidio): bump a numbered token another part of the request already holds Each message and content part numbers its tokens from 1 into one request-wide pii_tokens map. Collapsing overlapping detections made an overlapping value's token well formed, so it collided with the same type in another part and both restored as the later value. A token that maps to a different value now moves to the next free number, and a token for the same value is reused * fix(presidio): give a clashing token a spare number instead of scanning for one Scanning upward from the clashing number probed every token an earlier part had claimed, so two parts with thousands of values of one type took seconds of synchronous work. No token in the map is numbered above the map's size, so numbers above both that size and the part's run count are always free * test(presidio): make the anonymizer double reject detections the analyzer never returned Pick the token in one conditional expression instead of reassigning it, and have the scripted anonymizer answer 500 when the proxy forwards spans that differ from the analyzer's, so the default-scope cells check what was sent --------- Co-authored-by: PINYO PATTANAWASANPORN <pattanawasanporn@gmail.com> Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>	2026-10-17 11:21:03 -07:00
Kerry Lu	571ef3e2ae	fix(responses): run pre_call guardrails on every Responses WebSocket turn and bill each turn its own guardrail cost (#47013) ... * fix(responses): run pre_call guardrails on every Responses WebSocket turn and bill each turn its own guardrail cost * test(responses): keep the websocket unit test file on main's formatting * fix(responses): type the websocket frame guard for the lint gates * fix(responses): pass the websocket frame guard as a named parameter and mark the guardrail dict edits * fix(responses): bill a guardrail-rejected Responses WebSocket frame as a failed request with its guardrail cost * fix(responses): type the recorded guardrail records as Mapping for the lint gate * fix(responses): bill a rejected websocket frame through the spend logger only so the connection keeps its rate-limit slot * fix(responses): guard nested response.create frames, strip forged user_api_key_* frame metadata, copy guarded tools back and give each rejected frame its own spend row id * fix(responses): mark the spend logger's bare-dict failure hook for the type gate * fix(responses): reject response.create frames that carry input at both levels and keep billing of a rejected frame non-blocking * fix(responses): name the non-blocking billing catch for the strict lint gate * fix(responses): keep the admitted guardrail list on every websocket frame, a frame cannot replace it with its own guardrails list * test(responses): wait for the key spend total before asserting it in the websocket guardrail cost test * fix(responses): copy the admitted metadata shallowly per websocket frame, the OTEL parent span cannot be deep-copied * fix(responses): reject a WebSocket turn a pre_call guardrail rerouted to another model * fix(responses): bill a rerouted WS turn and carry Presidio pii_tokens from the frame guard to the socket unmasker * fix(responses): default pii_tokens through default_factory, Python 3.13 rejects a mappingproxy dataclass default * fix(responses): run the per-frame guardrail walk on managed Responses WebSockets too * fix(responses): unmask managed Responses WebSocket replies with the frame guard's Presidio pii_tokens * fix(responses): strip client guardrail cost records from WS frames so a blocked frame bills the real scan * fix(responses): forward a WS frame without the fields a guardrail deleted --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 11:00:51 -07:00
Yassin Kortam	8b1859c50d	fix(mcp)!: cap the ID-JAG credential by its signed resource claim and refuse a resource the gateway does not serve (#47094) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 10:25:44 -07:00
Kerry Lu	0349cff097	fix(backend): retain Prometheus metrics during startup (#47129) ... Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 17:10:42 +00:00
devin-ai-integration[bot]	46ae68021e	fix(anthropic): carry safeguard_results and stop_details in synthesized message_delta events (#46096) ... * fix(anthropic): carry safeguard_results and stop_details in synthesized message_delta events When the proxy renders a complete Anthropic Messages response as an SSE stream for a client that asked to stream, the message_delta event carried only stop_reason and stop_sequence. A real Anthropic stream puts safeguard_results and stop_details inside message_delta.delta, so a client such as Claude Code auto mode lost the server-side classifier verdict and a refusal lost its stop_details. Both stream builders now copy those keys from the source response through one shared helper when they are present. * fix(guardrails): keep safeguard_results and stop_details when re-emitting a rewritten Anthropic stream A post-call guardrail that rewrites an Anthropic stream (presidio, bedrock, tool permission, model armor) now carries the upstream message_delta safeguard_results and stop_details into the re-emitted stream. The router fallback message_start no longer leaks those final fields early * fix(guardrails): keep stop_details and safeguard_results in rewritten Anthropic streams without explanations A guardrail that rewrites a /v1/messages stream now carries stop_details (type and category) and the dangerous_tool_use verdicts for the tool calls it still delivers, with every explanation dropped so a masked stream never echoes the unmasked text through those fields. * fix(guardrails): copy only upstream stop_details and forward-compatible safeguard_results into rewritten Anthropic streams A rewritten stream now takes stop_details and safeguard_results from the upstream message_delta alone, so a refusal the upstream sent without stop_details is never given one by the OpenAI round trip. Unknown safeguard types, statuses, reasons and extra fields pass through, a verdict follows a tool call only when its input is unchanged, and tool_permission keeps the explanations since it rewrites no text. * fix(guardrails): apply the safeguard_results and stop_details rules to policy pipeline stream rewrites * fix(router): deliver a refused stream built from a finished agentic turn instead of falling back Websearch, MCP and advisor streams replay a complete reply whose tools already ran, so a refusal fallback would run every tool again. Also give the recovered response's message_start a null stop_details as the API sends it, drop safeguard_results a masking rewrite cannot read, and add the audit cells for synthesized streams. * test(router): annotate the finished-turn refusal stream test locals with Final --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>	2026-10-17 16:48:37 +00:00
Mateo Wang	82ca10cc2d	feat(bedrock): apply bedrock_request_metadata_fields on the /bedrock pass-through routes (#47040) ... * feat(bedrock): apply bedrock_request_metadata_fields on the /bedrock pass-through routes * fix(bedrock): move Invoke body requestMetadata into the signed header and match Bedrock's ASCII whitespace rule * fix(bedrock): keep Invoke body requestMetadata in the body and answer bad metadata as AWS does Invoke requests whose body already carries requestMetadata keep the resolved pairs in the body instead of the 8,500-character signed header. Malformed caller metadata now answers 400 with the ValidationException error type the AWS SDK expects, and drop_params drops bad pairs on both the pass-through routes and /v1/chat/completions. The caller-pair dedupe is linear, and the chat validator treats \s as ASCII whitespace, as Bedrock does * fix(bedrock): match Bedrock's 400s and header limit on pass-through request metadata Invoke metadata too long for the 8,500-character header now goes in the body, Invoke requestMetadata null answers 400 like Bedrock, Converse type errors carry SerializationException, violation messages name the failing key, and the reserved user_api_key_ prefix is matched case-insensitively after trimming whitespace * fix(bedrock): trim the Invoke metadata header to Bedrock's limit and drop bad requestMetadata under drop_params without the setting * fix(bedrock): leave /bedrock pass-through bodies as sent when request metadata forwarding is off Global drop_params no longer rewrites requestMetadata on the pass-through routes unless bedrock_request_metadata_fields is set. Chat keeps dropping bad pairs under drop_params. Adds a tests/integration wire test for the four pass-through actions and removes an unused parameter from the Invoke header helper. * test(bedrock): drive the pass-through metadata wire test with boto3's bearer key env var * fix(bedrock): trim the pass-through invoke metadata header and stop Nova invoke from checking metadata it drops * test(bedrock): cover pass-through metadata header trimming, malformed caller metadata, and chat drop_params on the wire * fix(bedrock): match requestMetadata keys and values against the whole string so a trailing newline cannot pass the 256-character limit	2026-10-17 14:01:50 +00:00
yucheng-berri	9f115be88d	fix(bedrock)!: scan Claude invoke-with-response-stream passthrough output with post_call guardrails (#46524) ... * fix(bedrock): scan Claude invoke-with-response-stream passthrough frames with post_call guardrails (LIT-9618) Invoke streams of Claude models now go through the same frame-by-frame relay as converse-stream. Each chunk frame's Anthropic event is scanned by the /v1/messages stream translation, a block ends the stream with an AWS exception frame, and a held stream gets its masks written back into re-encoded chunk frames. Claude is told by its model id or, behind an application inference profile, by the anthropic_version its request body carries. Streams of other model families stay as they were * test(bedrock): cover invoke stream vendor outage, upstream exception and release on scan (LIT-9618) * fix(bedrock): hold Claude invoke streams for guardrails the relay cannot run and mark each scan as streaming (LIT-9618) A guardrail released on scan or run in parallel left a Claude invoke-with-response-stream unscanned, while converse-stream holds the whole stream and scans it once. Claude invoke streams now take the same buffered path, with the rewrites written back into the chunk frames that carried each text. Each invoke scan also sends stream true and the events relayed so far as responses, as /v1/messages does, so a vendor can tie the scans of one streamed reply together. * refactor(bedrock): mark the request dicts the buffered stream paths hand to post_call hooks (LIT-9618) * fix(bedrock): scan a Claude invoke stream the upstream breaks off as a finished stream (LIT-9618) An invoke stream that ended on an upstream exception, without a message_delta stop_reason, was scanned as still in flight, so its tool input never reached the guardrail and a held stream released it unscanned. The scan and its scan key now close such a stream the way converse-stream treats the end of its upstream. * test(bedrock): pass the converse-stream endpoint where the tool call without input test frames its stream (LIT-9618) * test(bedrock): expect the ValidationException main now returns when a guardrail blocks a Claude invoke stream before its first frame (LIT-9618) * test(bedrock): type the Claude invoke event helpers in the passthrough guardrail tests * test(bedrock): type the remaining parameters of the Claude invoke stream tests * refactor(bedrock): bind the buffered invoke rewrite in its condition --------- Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>	2026-10-17 01:17:19 -07:00
yucheng-berri	ef1cb19351	fix(bedrock)!: stream Converse passthrough frames through post_call guardrails instead of buffering (#46307) ... * test(integration): Converse stream post_call guardrail relays frames as they arrive (LIT-9515) * fix(bedrock): stream Converse passthrough frames through post_call guardrails instead of buffering (LIT-9515) A post_call guardrail that scans through apply_guardrail now runs on /bedrock/.../converse-stream the way it runs on /v1/messages: frames reach the caller as the upstream sends them, every fifth frame and the end of the stream are scanned, and a block after the first frame ends the stream with an AWS exception frame. streaming_buffer_until_moderated still holds the stream and applies masks per content block. Guardrails that need the whole response (own async_post_call_success_hook, mask_response_content, native hooks, policy pipelines) keep the buffered path. * fix(bedrock): apply held Converse stream masks when the upstream ends with an exception frame (LIT-9515) * fix(proxy): log a relayed passthrough stream's spend before its mid-stream failure hook (LIT-9515) * fix(bedrock): close and report every way a relayed Converse stream ends (LIT-9515) - The framer ends the stream with an empty item once the upstream closes, so held masks are applied whether the upstream ends with messageStop, an exception or error frame, or a dropped connection - A guardrail HTTPException after the first frame reaches the relay, which logs the stream's spend, runs the failure hook and ends the stream with the exception frame, instead of ending inside the guardrail with no failure row - A failure before the first frame waits for the stream's spend to be logged, as a mid-stream failure does - Closing the response before its body starts closes the guardrail layers and the upstream - Each stacked guardrail layer gets its own copy of every frame, so an earlier layer's end-of-stream rewrite never reaches frames a later layer still holds - Deltas whose text ends in half a surrogate pair are decoded with the standard JSON parser * fix(bedrock): relay a Converse frame whose payload is not UTF-8 instead of ending the stream (LIT-9515) * test(integration): cover Converse stream relay failure, end-of-stream-only, stacked, disconnect and burst cells (LIT-9515) * fix(bedrock): estimate prompt tokens for a passthrough stream cut before Bedrock reports usage (LIT-9515) Bedrock sends usage only in the last frame of a stream, so a stream ended by a guardrail block or a client disconnect logged 0 prompt tokens while AWS still charges for the prompt. The stream collector now estimates them from the request the way chat completions streams do * fix(bedrock): read tool result blocks without recursion in the passthrough prompt estimate (LIT-9515) * fix(passthrough): keep the spend flush running when the wait for it is cancelled (LIT-9515) * fix(bedrock): keep a converse-stream buffered when its guardrail releases a held stream on scan (LIT-9515) A held post_call guardrail with streaming_buffer_release_on_scan releases each window as received once its scan passes, so the relay delivered the original text instead of the guardrail's masks. Such a stream keeps the buffered path, which applies masks per content block as on main. * fix(bedrock): keep a converse-stream buffered when a post_call guardrail runs in parallel (LIT-9515) The relay ran every guardrail in config order, so a run_in_parallel guardrail listed before a masking guardrail scanned the unmasked text. Main's buffered path runs parallel guardrails after the sequential ones and discards their rewrites, which the relay cannot reproduce, so these streams stay buffered * fix(bedrock): mark Noma v2 relay scans like chat and stop reading Bedrock when a held stream's client leaves - Noma v2 scans on the converse-stream relay carry stream, and the last one carries the finished Converse response with its stopReason, as chat sends them, so Noma keeps one record per reply. Other guardrails get the request unchanged. When the last sampled scan already covered the whole answer, the end-of-stream scan still runs for Noma so it gets the finished answer - A held relay stream whose client leaves before the first frame stops reading Bedrock and returns 499, like chat. When Bedrock sent nothing yet, the budget reservation and the parallel-request slot are released - A cancelled wait for the first streamed chunk now stops the upstream read instead of leaving it running - A Noma v2 scan cancelled before Noma answers records not_run instead of success with an empty response * fix(bedrock): send Noma the finished Converse reply's tool calls and reasoning as Converse blocks * fix(bedrock): give Noma the ended scan of a Converse reply that only calls a tool without input * test(bedrock): expect the ValidationException main now returns for a held block before the first frame Main's AWS-shaped passthrough errors (#46522) answer a guardrail block before the first frame with x-amzn-errortype ValidationException, so boto3 reads the code and the guardrail message instead of a bare 400. * fix(bedrock): keep held masks when an earlier sampled guardrail ends the Converse stream with its message A sampled guardrail that blocks with disable_exception_on_block ends the stream with its message as raw event-stream bytes. A held guardrail after it on the same key only read frame objects, so it never saw the messageStop, skipped its write-back and released the held text without its masks. The Converse handler now reads those bytes back into frames, so the held guardrail sees the end of the message and masks the text * fix(proxy): free the parallel slot when a caller leaves a Converse relay holding part of the first frame The relay skipped releasing the slot and budget reservation whenever a spend flush was scheduled, but a flush of a partial first frame builds no response and logs nothing, so the slot stayed held until it expired. The flush now says whether it logged the stream. --------- Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>	2026-10-17 00:53:53 -07:00
Kerry Lu	0a051efba7	test(e2e): event_loop_stalls perf case fails on a gateway event-loop hold over 100 ms that is not on its allowlist (#46974) ... * test(e2e): event_loop_stalls perf case reads the gateway's asyncio debug log and fails on a loop hold over 100 ms that is not on its allowlist The gateway runs the stdlib loop in debug mode (new LITELLM_EVENT_LOOP=asyncio knob next to PYTHONASYNCIODEBUG=1), the case replays the mixed body mix at 1 rps and groups asyncio's 'Executing <Task ...> took X seconds' lines by coroutine and location. Known holds are listed with the count they show today; anything else, or a known one past its count, fails the case. Opt-in through E2E_PERF_EVENT_LOOP=1 so the nightly build skips it * test(e2e): event_loop_stalls reads the pod list and pod logs through e2e_http instead of a raw httpx client * test(e2e): event_loop_stalls charges a hold to garbage collection when the gateway's debug-mode gc log accounts for it The proxy registers a gc.callbacks hook only when the event loop runs in debug mode and logs every collection over the loop's slow-callback threshold (generation, collected count, seconds). The case parser pairs such a pass with the hold line that follows it and reports the hold under a bounded garbage collection bucket instead of the task asyncio happened to blame, which made 7 of 10 local runs fail on a different task name each time. Holds the collector does not account for keep the strict allowlist, which gains the prisma first-query warm-up and the second pub/sub subscriber * test(e2e): event_loop_stalls allowlist caps set at twice the ten-run maximum --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-17 06:55:53 +00:00
Mateo Wang	355dea26e7	perf(cli): start lite without initializing the litellm SDK (#46803) ... * perf(cli): start lite without initializing the litellm SDK lite and litellm-proxy now enter through a small litellm_cli package that imports the CLI against an uninitialized litellm package and runs the SDK __init__ in place only when something first uses it, so commands start in a fraction of a second instead of loading about 3,000 modules first. * perf(cli): import only the lite subcommand being run Each lite subcommand now loads its module when Click looks it up, so lite logout no longer imports the autoroute wizard, agents, or the other command groups. importlib.import_module and attribute reads on the SDK also initialize it on first use, and an already imported litellm is kept as is. * fix(cli): initialize the SDK on a star import and test command bodies in thin mode A from litellm import * after lite loaded the CLI used to see only the names the thin package had, so it now runs the full SDK init first. The thin-vs-full parity test now also runs logout and whoami, not just --help * fix(cli): keep the import hooks until the lazy SDK init finishes A thread that imported SDK code after the init restored the interpreter imports could hold that module's import lock while waiting for the init, and the init then waited on the same lock, so both threads hung. Other threads now wait for the init before they load any new SDK code * fix(cli): retry a failed lazy SDK init on the next use instead of leaving it half-run * test(cli): bind the patched credentials client and autoroute dir in an order-independent way	2026-10-17 04:53:32 +00:00
devin-ai-integration[bot]	9f9a02b646	fix(mcp): log upstream exchange when an MCP health check fails (#44125) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: jesus <jesus@berri.ai>	2026-10-16 20:58:26 -07:00
Mateo Wang	610443519a	fix(proxy): unset DB environment variables removed from the row on every worker by row revision (#46709) ... * fix(proxy): unset DB environment variables removed from the row on every worker by row revision * fix(proxy): order the environment variables revision migration after main's and set its lock timeout * fix(proxy): snapshot the environment at the first DB sync even when no environment_variables row exists yet * fix(proxy): close gaps in DB environment variable reconciliation Grant the revision sequence to every role so a writer role with only table grants can still save environment_variables. Unset SSO keys that only the environment_variables row stored on the next SSO sync, while keeping keys the SSO settings table holds. Skip a revision-less row once a revision has been applied, so a stale cached row cannot bring a removed key back. Keep plaintext and undecryptable values when rotating the master key instead of dropping them from the row. * fix(proxy): keep env var revisions monotonic across DB copies and restores Stamp at least the old revision plus one on update so a copied row keeps rising, re-read a stale cached row from the writer and apply it when the database itself went back, unset dropped SSO keys when sso_settings are not loaded from the DB, and keep env values master key rotation cannot decrypt exactly as stored * fix(proxy): skip an env var row read before an overlapping sync that already applied a newer one * test(proxy): cover a read replica back on an older row and an SSO client removed from DB environment_variables * fix(proxy): keep config reads up when the writer is down, find the revision sequence by table schema, read the writer before rewriting env vars, and add the trigger under db push * test(proxy): model the writer database in the retry policy config update fake * fix(proxy): recheck the environment_variables row revision right before applying it A sync that started later could read a stale environment_variables row before an earlier sync applied a newer one, then pass the read-order check and apply the stale row, bringing back keys the newer row removed. The behind-the-applied-revision check now runs at apply time, re-reading the writer when the row is behind, and a writer row read while another sync applied a newer revision is dropped. The config sync tests now inject a fake database client and use the real get_config_param and its cache instead of replacing get_config_param. * test(proxy): keep encryption real in the SSO replica-lag test * test(proxy): inject a fake Prisma client in the env var replica-lag test * fix(proxy): keep the applied environment variables when the writer database is out of connections * test(proxy): cover a writer database out of connections in the env var integration tests	2026-10-17 03:51:05 +00:00
Yassin Kortam	fc484be77a	fix(proxy): keep the OIDC login refresh token as the ID-JAG subject when the SSO client is the ID-JAG client (#47004) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 18:28:20 -07:00
joshua-berri	6d0d0bb68b	feat: add Nace Drex decisions provider (#46523) ... * feat: add Nace Drex decisions provider * fix: expose Nace in dashboard provider metadata * ci: include Nace tests in the provider shard * fix: complete Nace provider catalog and preserve OpenRouter tests * test: mark Nace test directories as packages * fix: share Drex score parsing across decision providers --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>	2026-10-16 18:07:50 -07:00
jesus-berri	7f603da9f1	fix(openai_like)!: surface provider response headers on non-streaming chat completions (#46928) ... * fix(openai_like): surface provider response headers on non-streaming chat completions Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(openai_like): mark the header test locals Final * fix(proxy): leave out response header values HTTP cannot carry Non-streaming OpenAI-like chat now forwards every provider header, so on the httpx transport a provider header value outside latin-1 made the proxy answer 500 after the provider had served the call. get_custom_headers now leaves such a value out and keeps the other headers, which also ends the same 500 on streaming Adds integration cells for the provider request id on non-streaming chat and the Responses bridge, LiteLLM headers an upstream cannot overwrite, spend parity under an upstream cost header, the latin-1 case, and the logging callback payload * fix(cost): ignore an upstream response cost header that is negative or not a number * test(integration): cover invalid upstream cost headers and non-latin-1 headers on every endpoint * fix(prometheus): keep deployment metrics when a provider rate-limit header is not a number * test(prometheus): type the rate-limit header test and drop its clock reads * test(integration): cover deployment metrics under an unparseable provider rate-limit header --------- 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>	2026-10-16 17:25:50 -07:00
Mateo Wang	b39eadcb82	feat(openai)!: honor per-deployment workload identity on non-chat routes (#39966) ... * feat(anthropic): workload identity federation and pluggable identity sources Backend half of #38818 (internal copy of the fork PR #38013), rebuilt as one commit on top of litellm_internal_staging without the dashboard changes. Deployments on anthropic/ without a static api_key can exchange an OIDC workload assertion for a short-lived sk-ant-oat01 token through a shared RFC 7523 JWT-bearer engine. The assertion comes from a mounted token file, an env token, a LiteLLM-signed issuer, or Keycloak, chosen per deployment, per named credential, or through ANTHROPIC_IDENTITY_SOURCE. The federation fields are server-owned: refused inline in request bodies and on POST /model/new, proxy-admin only on credentials, and the token exchange is pinned to api.anthropic.com unless LITELLM_ANTHROPIC_WIF_ALLOWED_HOSTS adds a host. GET /credentials/{name}/jwks exports the public key set of a LiteLLM-signed credential for the Claude Console. The OpenAI federation trio from #39613 rides along on the backend side with the same server-owned handling. Fixes #28607 Resolves LIT-6107 Co-authored-by: derhornspieler <15236687+derhornspieler@users.noreply.github.com> * fix(anthropic): let batch-result downloads mint from deployment params and accept host:port allowlist entries The files handler enabled workload identity on batch-result downloads but never received the deployment's litellm_params, so a deployment authenticating through a named credential could only mint from process-wide env vars. It now threads litellm_params through to the auth header the way the batch retrieve path already does. LITELLM_ANTHROPIC_WIF_ALLOWED_HOSTS entries written as host:port were read by urlsplit as a scheme, so the allowlist kept the raw entry while the exchange compared bare hostnames and refused the gateway. Entries are now parsed as network locations whether or not they carry a scheme. * fix(types): move the WIF kwargs key sets to a leaf module so the kwargs funnel imports without a cycle * test(anthropic): pin case-insensitive matching of WIF exchange-host allowlist entries * fix(anthropic): end workload identity federation errors without a period so the router suffix reads cleanly * fix(proxy): decrypt stored litellm_params before the WIF write gate * fix(proxy): hide WIF secret references from /health output * fix(proxy): keep the proxy error shape on credential endpoint refusals * fix(proxy): hide identity token file paths from /health output * feat(openai): honor per-deployment workload identity on non-chat routes Image generation, audio speech and transcription, moderation, text completions, files, batches, and fine-tuning built their OpenAI client from the env vars alone, so a keyless deployment carrying openai_identity_provider_id, openai_service_account_id, and openai_identity_token_file failed with the api_key error on every route other than chat, Responses, and embeddings. Those handlers now build their client through the shared workload identity resolver, and the managed batch file-access credential extraction keeps the trio * fix(openai): cache workload identity clients and let deployment identity outrank process-wide keys Non-chat handlers built a fresh SDK client per call, so files, batches, fine-tuning, text completion and sync moderation exchanged the OIDC token on every request. The builders now reuse the cached workload identity client per identity, base, timeout, retries and organization; static-key clients are still built fresh. A process-wide OPENAI_API_KEY (or litellm.api_key / litellm.openai_key) no longer silently overrides a deployment's openai_identity_* params. An explicit distinct api_key on the deployment or call still wins. * fix(openai): keep shared workload identity clients on the process http session The workload identity client is cached and shared across requests, so it must never borrow the transport a single caller passed in. Static-key clients keep using the caller's http client; federated clients always ride the process-wide session. Also makes the http client helpers on BaseOpenAILLM public since the builder now needs them from outside the class. * test(openai): pin partial deployment identity beating the process key * test(openai): type the managed-object invoke callback * fix(anthropic): rename the federation workspace param so Bedrock's anthropic_workspace_id keeps working The Bedrock Claude Platform route already reads anthropic_workspace_id from optional_params, so banning that spelling as a server-owned federation parameter broke a pre-existing client capability. The federation field is now anthropic_federation_workspace_id (env ANTHROPIC_FEDERATION_WORKSPACE_ID), which restores the base branch's behavior for Bedrock callers, drops the Bedrock-specific hint from the refusal message, and deletes the unconditional ban constant that no longer had a reader * fix(auth): share one exchanged token across workers reading the same assertion Anthropic accepts each identity assertion exactly once, so two uvicorn workers reading the same token file both minting from it means the second exchange is denied with jti_reused. Minted tokens now land in a per-user 0700 cache directory guarded by a file lock, so workers on the same host reuse one exchange until the token expires or the assertion rotates. A 401 is only retried when the re-read assertion actually differs, and the denial hint explains jti_reused. LITELLM_TOKEN_EXCHANGE_CACHE_DIR moves the cache and an empty value disables it * feat(openai): honor deployment workload identity on image edits, vector stores, containers, videos, and evals The httpx-based OpenAI handlers built their Authorization header from the deployment api_key or OPENAI_API_KEY alone, so a keyless deployment carrying openai_identity_provider_id, openai_service_account_id, and openai_identity_token_file sent "Bearer None". They now resolve the bearer through resolve_openai_bearer_token, which exchanges the deployment's identity token the same way the SDK-based routes do. A deployment that carries only part of the identity trio now raises a 500 naming the missing field instead of silently falling back to the process key, and the SDK client builders take a factory for the static-key http client so the federated branch never touches litellm.client_session. * fix: keep anthropic federation from being shadowed or leaked An empty or whitespace-only ANTHROPIC_API_KEY counted as set, so a federated deployment sent an empty x-api-key on every call instead of minting a token. Blank values now read as unset, and a real static key on a federated deployment logs once that it outranks federation and nothing is being federated. The exchange-host allowlist matched hostnames only, so a second process on another port of an allowed host was trusted with the workload's identity token. An entry that names a port now trusts that port alone, while a bare host still trusts every port. The shared token store exists so the workers reading one projected token file do not each spend its single-use jti. A source that mints its own assertion per exchange shares nothing with another worker, so it no longer writes a live token to disk for a lookup that can never hit. * feat(openai): resolve per-deployment workload identity for the assistants routes OpenAIAssistantsAPI built its OpenAI and AsyncOpenAI clients from a locals() scrape, so a deployment carrying openai_identity_provider_id, openai_service_account_id and openai_identity_token_file never exchanged a token. Thread litellm_params through the class and build both clients with the shared workload identity builders. * fix: unlink a staged token file a failed write leaves behind The 401 denial hint now also says federation ignores ANTHROPIC_WORKSPACE_ID, which the Bedrock Claude platform provider already reads. * refactor: move anthropic jwks derivation behind a provider-owned tagged union * feat(openai): resolve per-deployment workload identity for image variations Build the image variations client through the shared workload identity builders instead of scraping locals(), and give the async path the async http session it was missing. Let a federation trio serve the model-less batch fallback, and hold the standard LRU size of exchanged tokens. * fix: unlink the staged token file when its write fails at close A buffered write only reaches the disk when the handle closes, so a full disk surfaces at close and left the staging file behind holding a usable token. * fix(anthropic): close the staging descriptor before writing the shared token file * fix(wif): judge federation writes by what they set, not what is stored The admin gate read the stored deployment, so a team admin lost edit, delete and Test Connection on any deployment carrying federation params. It now returns early unless the submitted fields touch the federation surface, and a Test Connection probe that points the deployment at its own api_base is still refused, with the 403 no longer wrapped into a 500 The rest of the same review pass: POST /model/new refuses only a blocking value of `blocked`, so a client that always sends `blocked: false` is not turned away; a request body can no longer pick which federated identity to mint as by naming a stored credential; an advisory refresh the executor refuses disarms the entry instead of wedging the identity until the follower timeout; the static-key shadow warning resolves its env fallback inside the cache instead of once per request; credential writes drop nulls before storing them; the token exchange validates the endpoint URL before reading an assertion and keeps refusing redirects across a client heal; /health hides every server-owned federation field from non-admins; and the async create_file and create_batch paths say which setting is missing when the provider resolves no URL * style(tests): keep two blank lines before the batch_cost_is_final block * test(batches): type the workload identity fallback test fixtures * fix(moderation): stop validating unrelated kwargs on the sync workload identity path * fix(auth): refuse server-owned workload identity keys in array form and inside a client router config * fix(openai): keep a deployment's own key ahead of workload identity on every route Thread the caller's own api_key into the identity resolver for embedding, transcription, moderation, image generation, and assistants so a deployment key equal to the process key still wins. A partial identity trio now falls back to a configured static key, unset max_retries keeps the SDK default, and /v1/decisions plus OpenAI count_tokens resolve the exchanged bearer for identity-only deployments * fix(containers): pass deployment params to container file auth headers Container file routes built their auth headers without the deployment's litellm_params, so a keyless deployment with an OpenAI workload identity sent Bearer None on upload, list, retrieve, delete and content calls * fix(openai): keep process-wide key precedence and move token exchange off the event loop Restore the merge base order where an explicit or process-wide OpenAI key wins over federation, so exporting OPENAI_API_KEY keeps working the way it did before. Run the header-building validate_environment calls (image edit, videos, containers, vector stores, vector store files) and the decisions and System One request preparation in a worker thread, so a slow token exchange no longer stalls the loop. Federate realtime websocket sessions, live sessions, realtime client secrets and transcription sessions, and the OpenAI moderation guardrail when no key is set. * fix(openai): answer 401 for a partial identity trio and federate realtime health checks A deployment with part of the workload identity trio and no static key now fails as an auth error naming the missing params, so the router does not retry it as a server error. The realtime health check sends the exchanged bearer for a keyless federated OpenAI deployment, and API token counting reads the same static keys as every other route before minting. * fix(openai): keep local token counting without an identity trio and federate the moderation guardrail from its own config * fix(openai): skip a partial-trio moderation guardrail and let vault keys win in token counting * test(integration): refuse caller-chosen identity params in user_config and bracketed form keys * fix(openai): send the honored secret manager key from SDK client builders A deployment whose OPENAI_API_KEY lives only in the secret manager now sends that key on image, assistants, files, batches, and other SDK-built routes instead of failing with no api_key, matching what the workload identity resolver already treats as a static key * test(openai): check the token exchange runs off the event loop instead of timing the loop --------- Co-authored-by: derhornspieler <15236687+derhornspieler@users.noreply.github.com>	2026-10-16 22:25:15 +00:00
ryan-crabbe-berri	9cf09c18fe	fix(providers): route Azure Responses past dated api versions, count Grok reasoning tokens on azure_ai, refresh provider sets after register_model, fix gpt-6.1-sol Azure rows (#46377) ... * fix(azure): add responses_api_version so the Responses route stops using the deployment chat api_version * fix(azure_ai): fold Grok reasoning tokens into completion_tokens like the xai provider * fix(utils): refresh provider model sets after register_model * fix(cost-map): align azure gpt-6.1-sol reasoning effort flags with the openai row * test(e2e): cover Azure Responses on a deployment pinned to a dated chat api_version * fix(utils): keep router deployment ids out of provider model sets register_model now refreshes the provider sets, so the per-request and router registrations keyed by a deployment id put those opaque ids into wildcard model listings. Those callers now pass add_to_provider_model_sets=False. * fix(azure): carry responses_api_version through the chat to Responses bridge completion() dropped responses_api_version from the litellm_params it hands the Responses bridge, so azure/responses/<model> on a dated chat api_version still built the 404ing /openai/responses URL. Also cover the auto-router marker never forwarding the new param. * fix(azure): stop listing a wrong set of reasoning efforts when none is rejected The message said only low, medium and high are supported, which is wrong for models that also take xhigh such as gpt-6.1-sol. * test(azure): use the latest grok and gpt-5.4 rows in the new azure tests * fix(proxy): list each wildcard-expanded model once A provider set can hold a model both bare and provider-prefixed, which now happens after any priced request registers its openai/<model> key, so the openai/* listing showed that model twice. * fix(azure): route Responses past dated GA api_versions by default A deployment pinned to a dated GA api_version such as 2024-10-21 for chat now sends Responses calls (create, get, delete, cancel, input_items and the azure/responses/ bridge) to the default Responses version, because those dated versions have no Responses route on Azure and 404. responses_api_version still overrides it, -preview, v1, latest and preview versions are kept, an api-version in the api_base query still wins, and chat keeps api_version as before * chore(azure_ai): mark the grok chunk_parser dict as an override contract * fix(azure): rewrite only the route's /openai segment when moving a call to v1 The v1 rewrite in the Azure URL builder replaced every "/openai" substring in the path, so a gateway api_base like https://apim.example.com/openai-gw/team turned into /openai/v1-gw/team/openai/v1/responses. Dated GA Responses calls now land on the v1 route by default, which made this reachable for them too, so the rewrite now only touches the last /openai path segment. The Responses version resolver no longer duplicates the builder's default for an unset api_version. Tests cover the gateway api_base case, the env AZURE_API_BASE query-string precedence, and the e2e suite now has one test for the dated GA default and one where only responses_api_version can make the call work * test(integration): cover Azure Responses api_version, Grok reasoning spend, wildcard listing and reasoning_effort none Wire tests pin the Azure route and query for chat, Responses and the azure/responses bridge on a dated GA api_version, and check responses_api_version never reaches the request body. Cost cases check azure_ai Grok folds reasoning tokens into completion_tokens and spend, streaming and not. A config-driven proxy checks /v1/models next to an openai/* wildcard lists each id once and never a deployment id. Azure gpt-6.1-sol rejects reasoning_effort none before reaching upstream and drops it with drop_params * fix(utils): list ai21 chat and vertex code models under their provider wildcard register_model now files ai21 chat models into ai21_chat_models, which models_by_provider never read, so a registered ai21 chat model dropped out of ai21/* listings. models_by_provider now reads ai21_chat_models and the vertex code chat and code text sets too. * fix(main): keep caller-chosen model names out of provider wildcard listings --------- Co-authored-by: yuneng-jiang <yuneng@berri.ai>	2026-10-16 15:23:46 -07:00
Mateo Wang	29cd11bec6	fix(sso): concurrent first sign-ins land on the winner's account, worker-kill test stops waiting on the reap (#46855) ... * fix(sso): concurrent first sign-ins land on the account the winner created, worker-kill test pins half its streams to each worker * test(integration): a worker kill returns once the worker is dead, the reap waits at block exit uvicorn can take a full worker healthcheck to reap a worker that died mid-ping, so kill() held the caller that long and peers held on the surviving worker hit their client timeout * fix(sso): a sign-in that loses the first-insert race joins the default teams The losing sign-in could read the winner's row before new_user added the default teams, so its CLI key was minted with no team. The race tests now run the real new_user against a fake user table	2026-10-16 14:58:05 -07:00
Mateo Wang	d76ec3a47e	fix(proxy)!: answer 400 for malformed tools on count_tokens instead of crashing (#46583) ... * fix(proxy): answer 400 for malformed tools on count_tokens instead of crashing A non-list tools value crashed the vector store lookup during auth and the built-in tool cost lookup in the failure logging path, so the proxy answered an unhandled 500 and closed the keep-alive connection. count_tokens now answers a 400 invalid_request_error for a malformed body, drops malformed tools when drop_params is on, and both lookups skip values of the wrong shape. * fix(proxy): skip non-list tools in the tool allowlist check Also validate the count_tokens body without recursion, which the recursion detector rejects. * test(integration): restore the int tools case on count_tokens The proxy now answers a non-list tools value with a 400, so the case is deterministic again. * fix(proxy): reject malformed tools at the LLM route entry and keep vector store checks on malformed ids * fix(proxy): apply drop_params like core when dropping malformed tools, and reject malformed tool vector store ids Check tools after request setup so the Claude Code default and the logged call type apply, read the request, global, and model group drop_params the way core does, drop tool_choice and friends with tools, cover Gemini generateContent, and answer 400 for a malformed tools[].vector_store_ids with the strict flag off * fix(proxy): keep the request's call type when logging a gate rejection after request setup The body-shape fallback relabeled a /v1/messages rejection as acompletion and a list-input /v1/responses rejection as aembedding, so it now only applies when the logging object carries no known call type * fix(proxy): share the malformed tools check across tool routes and honor drop_params per entry * fix(proxy): accept null vector_store_ids, read every named store id in auth, check the responses websocket * refactor(proxy): leave the responses websocket out of the request-level tool check * fix(proxy): let a request's additional_drop_params replace the deployment list and keep compact's call type on rejections * fix(proxy): read router default drop lists and deployment ids in the malformed tools check * fix(proxy): leave malformed tools to the router when it can pick another deployment Fallbacks, auto-routers, model strings, comma batches and team model names let the router pick a deployment after the proxy checks the request, so the proxy now forwards a malformed tools field there as main does, and only rejects it when the deployment it checks is the one that serves. Token counting never reroutes, so count_tokens and input_tokens keep reading the group they count with. additional_drop_params names are read the way core reads them, so a list with a non-string entry still names its strings. * test(integration): cover malformed tools on reroutable models, router defaults and deployment ids * fix(proxy): resolve malformed tools at the deployment the router picks * fix(proxy): keep provider-repaired tool schemas, honor fallback_on_unsupported_params, skip cooldown on malformed tools Empty schemas and JSON-string schemas pass the tools check the way litellm's provider paths already read them. The rejection is a BadRequestError subclass carrying the deployment's provider, so fallback_on_unsupported_params: false keeps the 400, and the router never cools a deployment down for a request litellm rejected before calling it. Adds the audit's pre_call guardrail and cross-provider bridge cells. * test(integration): expect a 400 for an empty-string tools field on /v1/messages Real Anthropic rejects tools "" with a 400 on main too, so the case joins the malformed tools test * fix(router): keep web search routing for tools passed as a tuple * fix(router): keep a deployment's own tools when drop_params drops a malformed request tools * test(router): list _merged_tools as covered through the deployment tools merge tests * fix(router): drop the request's tool settings with its malformed tools when deployment tools replace them * fix(router): skip a tool whose type is not a string in the web search filter instead of raising TypeError * fix(prometheus): keep deployment health metrics clean on a malformed tools rejection * test: type the new malformed tools tests * test: mark new test locals Final and type kwargs dicts	2026-10-16 14:57:53 -07:00
ryan-crabbe-berri	0dac61a555	fix(guardrails): accept Gemini tools in generic_guardrail_api, add opt-in forward_messages_as_sent, name the error type on fail-open (#46338) ... * fix(guardrails): accept Gemini tools and Anthropic content blocks in generic_guardrail_api, name the error type on fail-open GuardrailToolParam required a type key, so Gemini native tools (function_declarations, googleSearch) failed validation inside the hook and either returned a 500 or skipped the scan when fail_on_error was false. The type key is now optional and left out of the forwarded tool when absent, so an echoing guardrail server cannot write type: null into the provider request. structured_messages was re-validated against the chat completion message types, which silently emptied tool_result, tool_use, image and document content blocks to content: [] and dropped undeclared keys before the guardrail saw them. The request model now forwards rows as opaque mappings, which also retires the write-back shim that restored the original rows for echoed-back entries. The fail-open critical log line now carries error_type so a timeout, a refused connection and an upstream HTTP status can be told apart without the traceback. * fix(httpx): retry aiohttp server disconnects the way httpx does aiohttp raises ServerDisconnectedError when a kept-alive connection is closed by the peer before a response arrives, which is what a load balancer idle timeout shorter than AIOHTTP_KEEPALIVE_TIMEOUT produces. The transport mapped it to httpx.ReadError, which the handler's connection-error retry does not cover, so the request failed instead of being resent on a fresh connection. It now maps to httpx.RemoteProtocolError, the error httpx itself raises for the same condition, so the existing retry fires. * test(httpx): build the stub server reply in one bytes literal * fix(httpx): resend a dropped connection's request as sent and keep a streamed resend readable The connection-error retry closed its fresh client before a streamed body was read, so an aiohttp disconnect now billed a second upstream request and still failed. It also skipped masking on a status error from the resend, resent PATCH and DELETE as POST, dropped multipart files and ignored the handler's ssl_verify. The retry now resends the request the first attempt built, on a client with the handler's TLS settings, closes that client when a streamed body is closed, and masks a status error the same way the first attempt does. * fix(guardrails): log HTTPStatusError, not the masking wrapper, as the fail-open error_type * fix(guardrails): resend a generic guardrail check cut before any response A load balancer that closes an idle keepalive connection made the guardrail POST fail with "Server disconnected", because #46336 only resends POST on ConnectError. AsyncHTTPHandler.post now takes a keyword-only idempotent flag, defaulting to False, that gives a RemoteProtocolError the same single fresh-client resend PUT and DELETE get. Only GenericGuardrailAPI.apply_guardrail opts in, since a guardrail check is a pure verdict over the request. Every other POST keeps the #46336 rule The fail-open log line now puts error_type at the end so the pre-PR text stays contiguous for existing alert matchers test_rows_reach_the_guardrail_verbatim now reads the body off a real local guardrail server instead of mock call args * fix(http): keep a mid-body server disconnect a ReadError and move socket tests to integration A ServerDisconnectedError raised while reading a response body now stays httpx.ReadError, as it was before this PR. Only a disconnect before any response maps to RemoteProtocolError, which is the case the resend rule is about. Stream readers that end on ReadError, like the SAP stream iterator, keep their old behavior The loopback-server disconnect, TLS and guardrail resend tests move to tests/integration/sdk/test_disconnect_resend_wire.py, since tests/unit is in-process only. Unit keeps in-process MockTransport checks for the idempotent POST resend, masking on the resend, streamed and buffered client closing, the guardrail resend, and the guardrail receiving rows verbatim * fix(guardrails): resend a reset guardrail check and keep typed echoes on texts An idempotent POST now resends once on any network error after connect (ReadError, WriteError, RemoteProtocolError), so a guardrail behind a load balancer that answers a stale keepalive with a TCP reset rides it out too. That makes the aiohttp ServerDisconnectedError remap unnecessary, so it goes back to ReadError. This stops PUT and DELETE from stacking litellm's resend on top of aiohttp's own idempotent retry (4 sends instead of 2) and stops Vigil Guard from replaying its analyze POST on a disconnect Every resend now runs inside the method's own error mapping, so a timeout on the resend is a litellm.Timeout like the first attempt and a status error is masked once by the caller A guardrail server that parses rows with its own message types and echoes them back without the keys those types lack (annotations, tool_calls[].index) is read as an echo again, so its texts redaction reaches the LLM. A row only counts as an echo when no value changed and every key the chat completion types declare is kept The wire tests for the PUT/DELETE resend, its masking and its TLS settings now run on the httpx transport, where litellm's resend is the only retry, and the POST and guardrail tests cover both transports and both cut styles * test(guardrails): black box wire tests for generic guardrail shapes, fail-open error type and idle cut resend Integration tests against an owned proxy and scripted peers. Gemini native tools reach the guardrail and Gemini as sent, the guardrail sees chat rows and an Anthropic image block as sent, an echoing guardrail leaves a /v1/messages request unchanged, the fail-open log line names ConnectError, Timeout or HTTPStatusError, and a guardrail check cut on an idle pooled connection is resent once on each worker. Each fails at the merge base and passes at the head * fix(guardrails): check echoed rows without recursion and keep pytest.raises to one statement * refactor(guardrails): move the dropped-connection guardrail resend out of this PR The resend on a dropped or hung generic guardrail call, and the shared AsyncHTTPHandler retry rework behind it, move to a follow-up PR that adds a per-guardrail num_retries setting. This PR keeps the request and response shape fixes and the error_type on the fail-open log line * test(guardrails): pick the closed guardrail port from the integration port allocator Reading a port back from a port-0 bind trips TQ012, so the fail-open connect error case now takes its unused port from allocate_port * feat(guardrails): forward structured_messages as sent only behind forward_messages_as_sent generic_guardrail_api keeps main's OpenAI-format rows and echo comparison by default. Setting forward_messages_as_sent: true on the guardrail sends rows as the client sent them and treats an echo that only drops undeclared keys as unchanged --------- Co-authored-by: yuneng-jiang <yuneng@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 14:52:35 -07:00
yuneng-jiang	ac6300f380	fix(mcp): stop proxy-started legacy listeners from consuming server rpm (#46968) ... * fix(mcp): stop proxy-started legacy listeners from consuming server rpm The listener the proxy opens on notifications/initialized for legacy MCP sessions ran the server rate-limit admission once per target, so every session spent an rpm slot before the client sent anything. Admission is now injected into the listener and applied only to client-initiated subscriptions (subscriptions/listen and resources/subscribe). Authorization and its periodic recheck still run on every path. * test(mcp): key the fake admission window by caller and server * fix(mcp): stop subscription catalog refreshes from consuming server rpm A subscription listener lists the caller's catalog to diff list_changed events, at setup and on every upstream event. Those listings went through the normal per-server admission, so against an upstream that declares listChanged each legacy session spent several rpm slots before the client asked for anything. The listener now marks its targets as already admitted for its own lifetime, so its refreshes reuse the subscription's admission. Client requests on the session are still metered. * test(mcp): exercise subscription admission through the proxy rate limiter	2026-10-16 14:30:04 -07:00
devin-ai-integration[bot]	8bb8ac7f18	fix(proxy): keep a retried /v1/messages stream's spend log by logging the superseded attempt as a failure (#45136) ... * fix(proxy): keep a retried /v1/messages stream's spend log by logging the superseded attempt as a failure A /v1/messages stream the router retries before any content shares one logging object across both attempts. The superseded attempt's end-of-stream logging ran as a success (a usage-only or placeholder result) and claimed the request's one-shot success log, so the recovered stream's spend row was either missing or written under the superseded attempt's message id. The passthrough logging path now logs an Anthropic stream whose frames carry an `event: error` as a failure with whatever usage the provider reported, the way a dropped stream already does, and the router closes the superseded stream before it opens the retry so that logging is queued first. * fix(proxy): log a provider error frame through an attempt-scoped logging copy The error-frame failure stashed the superseded attempt's usage on the logging object the retry shares, so the retry's success log carried the failed attempt's token counts. The failure now logs through a copy of the logging object with its own model_call_details, and the helper moves into the Anthropic passthrough logging handler so the proxy streaming handler only routes by endpoint type. * fix(proxy): scope the error-frame failure log to streams closed at the frame A stream that ran to its end at the provider's error frame kept logging through the success route before this PR, and the attempt-scoped failure log is now taken only for a stream the router closed at that frame, with the copy made at the close so the retry's deployment never reaches it * chore: drop duplicate litellm import and mark the stream_ended rebind * fix(proxy): log only router-superseded attempts as error-frame failures A client that hangs up at a forwarded error frame closed the stream the same way the router closes a superseded attempt, so a non-retried stream lost its spend. The router now closes a superseded attempt through aclose_superseded_attempt, and only that close routes the attempt to the failure log * test: type the _settle helper's recorded events --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>	2026-10-16 21:19:58 +00:00
Mateo Wang	60af2c601d	fix(proxy): emit spend queue size after updates and flushes (#46956) ... Co-authored-by: Mateo <mateo@Mateos-MBP-2.localdomain>	2026-10-16 13:44:34 -07:00
ryan-crabbe-berri	c7b115b56a	feat(ui): add the 1 hour cache write cost to the add model and model edit forms (#46830) ... * feat(ui): add the 1 hour cache write cost to the add model and model edit forms Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(e2e): cover both cache write tiers in the add model and edit forms Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(ui): hoist the expected pricing payload out of the inline assertion Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(ui): share the per-token conversion between both cache write tiers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(ui): derive the touched pricing field type from the pricing field list Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(ui): collapse the duplicated pricing source keys into one map Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): convert add model pricing once for all selected models and describe the 1 hour fallback Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(e2e): type the cache write tier deployment read back and fill the 1 hour field Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * style(e2e): keep the cache write tier spec on the dashboard prettier config 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>	2026-10-16 13:44:24 -07:00
Yassin Kortam	f02449ad38	feat(sso): retain the SAML assertion at login as the saml2 subject token for oauth2_id_jag (#46745) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 12:16:56 -07:00
Yassin Kortam	3501e36fa9	feat(sso): capture the IdP id_token on Microsoft and Google logins for oauth2_id_jag (#46747) ... Resolves LIT-9671 Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 12:16:56 -07:00
Yassin Kortam	bca7650e8f	feat(mcp): accept an ID-JAG as an RFC 7523 jwt-bearer grant on the gateway token endpoint (#46748) ... Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 12:16:55 -07:00
Kerry Lu	339fd90836	fix(proxy): streaming responses hand the event loop back every 50 ms instead of holding it for the whole buffered stream (#46925) ... * fix(proxy): streaming responses hand the event loop back every 50 ms instead of holding it for the whole buffered stream * fix(proxy): yield to the event loop on every streamed chunk, no hold budget or clock * docs(proxy): say why the streaming loop yields on every chunk * fix(proxy): streaming loop yields once it has held the event loop 50 ms, clock read inline * docs(proxy): streaming loop comment names the 50 ms hold * Revert "docs(proxy): streaming loop comment names the 50 ms hold" This reverts commit cbf1371873. * refactor(proxy): streaming loop hold budget is _STREAM_LOOP_HOLD_MS = 50 * Revert "refactor(proxy): streaming loop hold budget is _STREAM_LOOP_HOLD_MS = 50" This reverts commit 356454def6. * docs(proxy): streaming loop comment notes the yield is a floor, not a count of releases --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-10-16 11:33:01 -07:00
Mateo Wang	f8217d2a03	fix(count_tokens): apply context_management edits in the Gemini /v1/messages/count_tokens count (#46843) ... * fix(count_tokens): apply context_management edits in the Gemini /v1/messages/count_tokens count /v1/messages runs clear_tool_uses context edits before it sends an Anthropic body to a Gemini or Vertex AI deployment, but /v1/messages/count_tokens counted the body unedited, so a request with older tool results cleared counted about 2.8x what inference bills. The count now runs the same history and context-edit step inference runs, honors additional_drop_params on the deployment, and skips compact edits so a count never makes a paid summary call. * fix(count_tokens): match the Gemini count to inference for compact edits and drop opt-outs Run compact edits in the count without the summary call so trigger checks and history slicing match /v1/messages, honor a request-level additional_drop_params, keep the full body when any deployment in the model group drops context_management, and answer 400 naming a block Gemini cannot count when an edit trigger fails on it * fix(count_tokens): count the unedited body when an edit fails and honor deployment ids in the drop check * fix(count_tokens): log a failed edit in the count at debug, since the send already logs it * fix(count_tokens): resolve a deployment id before wildcard routes in the drop check, as the router does * fix(count_tokens): honor the router-wide additional_drop_params opt-out in the drop check The router merges default_litellm_params between the deployment and the request, so a router-wide context_management opt-out makes /v1/messages send the full history. The count now reads it in the same order. Adds the audit's wire tests for the count's context edits. * fix(count_tokens): read the opt-out of a deployment the router serves by its litellm model name * fix(count_tokens): read the opt-out and drop_params from the deployments the router and completion_model send to * fix(messages): drop an invalid context_management spec under drop_params so the send matches the count * fix(count_tokens): give Claude Code and Codex counts the drop_params default /v1/messages gives them The proxy turns on drop_params for Claude Code and Codex user agents on /v1/messages. The count now applies the same default, so an invalid context_management spec drops on both endpoints instead of the count answering 400 while the send answers 200. The wire test also covers default_fallbacks, model_group_alias, and completion_model routes. * test(count_tokens): cover a coding agent that turns drop_params off and stop two count tests running as Claude Code	2026-10-16 17:53:06 +00:00