mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-17 04:34:25 +00:00
252 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Kerry Lu
|
44e94eb985
|
fix(cost): split xai spend rows across input and output instead of booking the total as output (#46320)
* fix(cost): keep the input/output split on streamed xai spend rows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(cost): split xAI's reported total across input and output by token math Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Mateo Wang
|
dba46c0513
|
fix(responses): keep the provider code and message on top-level stream error events (#46438)
* fix(responses): keep the provider code and message on top-level stream error events Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): log a mid-stream failure before the router falls back CustomStreamWrapper now waits for failure logging before it raises the error the router falls back on, so the cooldown lands on the deployment that failed instead of the fallback that replaced it. Also keeps numeric error codes and the top-level message on the WebSocket and ChatGPT paths. * fix(streaming): run sync failure callbacks before a failed stream falls back to another deployment The router cools a deployment down from a sync failure callback that reads the request's model_info. A failed stream submitted that callback to the logging executor without waiting, so it often ran after the router's fallback had overwritten model_info and cooled down the healthy fallback deployment instead, leaving the model group with no deployments * test(responses): cover top-level OpenAI stream error events end to end * test(streaming): read live worker pids so the second SIGKILL chaos variant sees two workers * fix(streaming): run waited sync failure logging off the shared logging pool * revert(streaming): keep failed-stream failure logging in the background Waiting for sync failure callbacks before a failed stream raises fixed the router cooldown race, but it slowed healthy calls under many failing streams with a slow callback, since the wait shares a thread pool with every call's start. The race is pre-existing on main and is tracked separately, so this PR goes back to main's logging timing and keeps only the top-level error event changes --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Tobias Mayr
|
d03923e6a9
|
fix(responses): propagate cache_control through responses->chat completion bridge (#32511)
* fix(responses): propagate cache_control through responses->chat completion bridge User/assistant messages, tool call outputs, and function calls built from Responses API input items were dropping cache_control, breaking prompt caching for Bedrock/Anthropic when routed through the litellm_completion transform. Also propagate cache_control onto the last content element of user/assistant messages, since Anthropic/Bedrock read it from the content block rather than (or in addition to) the message level. Adds the missing cache_control field to ChatCompletionToolMessage and ChatCompletionResponseMessage TypedDicts to keep the assignments type-safe. * chore(ui): regenerate schema.d.ts for ChatCompletionToolMessage.cache_control Adding cache_control to the ChatCompletionToolMessage TypedDict changed the proxy's OpenAPI spec; regenerated via `npm run gen:api`. * fix(responses): don't overwrite existing content-block cache_control; add list-content test Per Greptile review on the PR: - The message-level cache_control was unconditionally overwriting the last content block's cache_control when that block already carried its own (preserved by _transform_responses_api_content_to_chat_completion_content). Now only propagates onto the last block when it doesn't already have one. - Added the missing test coverage for the content-block propagation path with list content, which no existing test exercised (all used plain string content, so the isinstance(content, list) branch was never hit). * style(responses): extract cache_control into a named variable, trim comment Per style review: the message-building branch read cache_control 3 different ways in 5 lines (.get() twice, then [] indexing once), unlike the sibling tool-call-output/function-call functions this PR touches, which each extract it into a named variable up front (output_cache_control, function_call_cache_control). Matched that convention here too. Also trimmed the 3-line inline comment to one line, matching the file's usual comment length for similarly subtle behavior. * chore: refresh lazy OpenAPI snapshot * fix: type cache control propagation * fix: place cache control type suppressions * style: format cache control type conversion * refactor(responses): build bridged cache_control messages in one shot * fix(responses): keep cache_control marks on bridged tool calls and within the provider cap A function_call item's mark now rides on the tool call the bridge builds, an assistant text item merged behind a function_call keeps its own mark, a developer item keeps its mark when it is mapped to a system message, and a previous_response_id replay yields its stale marks to the newest ones so the provider cap holds. The Responses layer counts the marks on function_call and function_call_output items before it places an ordinal injection point, and the chat pass replaces that count with its own instead of adding to it. * fix(responses): count each cache_control mark once and keep the bridge within the provider's limits List content carries an item-level cache_control on its last block only, so the provider sees one cache point and the breakpoint census counts one. Marked function tools and SDK-typed input items are handled by the Responses-layer reserve, assistant text merged into a function call turn keeps its mark on its own block, and the previous_response_id replay budget drops marks per turn, newest kept, instead of stripping every older turn once one overshoots. The request's own marks now fall under the same budget, newest kept, so five marked items no longer answer the provider's 400. A cache_control value that is not an ephemeral mark with an optional ttl is left off the bridged message instead of reaching the provider as sent, and a developer message maps to the system role with its content, name, and cache_control only, so unknown keys never reach a strict provider. * fix(responses): send item cache_control only to cache-point targets and follow drop_params Item marks reach the provider only when the target turns them into cache points, and every other target keeps main's behavior of stripping them. Without drop_params a mark the provider would refuse reaches it as sent, so the client gets the same 400 as on /v1/chat/completions. With drop_params a malformed mark is dropped and only the newest 4 are kept. The shared input-to-messages helper and the developer mapping in base_utils go back to main, and a marked developer item reaches a cache-point target as a system message in the bridge. * fix(responses): budget top-level marks, follow drop_params on Nova tool marks, and match chat-keeping providers * fix(responses): validate replayed marks and count input tokens without item marks * fix(responses): leave unknown Bedrock ARNs unmarked under drop_params, match OpenRouter's list, and reserve only forwarded marks * test(responses): cover item cache_control parity per chat route, drop_params trimming, and replay budgets * fix(responses): keep item marks off inspection paths and match each chat route's keep rule Only the request the bridge sends gets item marks now. Guardrails, token counting, rate limiting, and input_tokens read the input with no item marks, as on main, so an off-spec mark cannot fail a guardrail call. Tool message and tool call marks are typed inside the bridge, leaving the shared chat types and guardrail schemas as on main. Databricks keeps marks only for Claude, Snowflake uses its chat route's Claude check, and every Anthropic deployment keeps them whatever its model name. The injection census skips SDK-typed tools, and the owned-proxy test expects the marked messages on /v1/responses. * test(responses): cover guardrail reads without item marks, Snowflake name parity, and SDK-typed tools in the census * fix(responses): leave a non-list input untouched when stripping item marks * test(responses): cover string, list, object and tuple input with and without item marks kept Each input shape now answers the same whether the unmapped Bedrock ARN keeps item marks or strips them under drop_params, through the proxy and the SDK. Object input also runs through the OpenAI-compatible chat bridge, /v1/responses/input_tokens and the project input-token limiter * test(cache): derive owned-proxy cell timeouts from the harness boot budget The capped-burst cells and the uncapped response-cache cells boot their own two-worker proxy, and a fixed 240 or 360 second timeout cut them during boot on a slow runner before the harness readiness budget could decide. They now carry the same derived budget as the sibling chaos and guardrail files, with four boot and stop budgets for the restart cell that boots twice --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
058c84476a
|
fix(mcp): leave out tool texts too long to embed instead of failing tool search (#43554)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
47e4ed88c2
|
fix(anthropic): keep refusal stop_reason and stop_details on the logged response (#46104)
* fix(anthropic): keep refusal stop_reason and stop_details on the logged response * fix(anthropic): keep the refusal stop-fields boundary tolerant of a non-dict upstream body * test(anthropic): use Anthropic's documented refusal example as the unit-test fixture * fix(streaming): keep provider fields on async stream cache hits and received_model_id on synthesized finish chunks * fix(caching): replay cached completion_tokens_details on stream cache hits and skip non-object cached provider fields * test(integration): cover Anthropic-family refusal stop_details on the wire, the cache and under chaos * fix(caching): skip a cached completion_tokens_details that fails validation on stream replay * fix(anthropic): keep refusal stop fields on a JSON-mode non-stream response Also adds the round 3 audit cells for JSON-mode refusals, the proxy response serialization, and wrong-typed cached usage details on both stream replays * test(anthropic): expect content_filter on streamed JSON tool refusals after main's stream change --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Kerry Lu
|
83980c9d63
|
fix(router): read the first stream chunk before returning so a failure before any token runs through the retry and fallback budget (#46493)
* fix(router): read the first stream chunk before returning so a failure before any token runs through the retry and fallback budget Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(router): keep only the raising call inside pytest.raises for the pre-content stream tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(router): yield the primed first chunk from a helper generator so the stream iterators keep their complexity Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(bedrock): expect the empty invoke stream to be reported from router.completion now that the first chunk is read there Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: give router stream mocks a first chunk or an ending so the eager first read neither hangs nor retries Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(router): name the first-chunk helpers after what they do (_read_first_chunk, _FirstChunk, _chunks_with_first) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(router): drop the string annotation on _FirstChunk.chunk, ModelResponseStream is imported at runtime --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Kerry Lu
|
542b254ca2
|
fix(anthropic): forward service_tier on /v1/messages for anthropic, azure_ai and bedrock_mantle (#46370)
* test(integration): add known-bug translation cases for request fields LiteLLM drops service_tier on /v1/messages, conversation on /v1/responses and metadata on /v1/chat/completions never reach the provider. Each gets a TranslationTestCase with the correct provider body, marked xfail(strict=True) through the new TranslationTestCase.known_bug field, plus a passing service_tier case for /v1/messages on the openai route Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(integration): widen the known-bug cases to azure_ai, bedrock_mantle, openai/responses and azure deployments Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(anthropic): forward service_tier on /v1/messages for anthropic, azure_ai and bedrock_mantle Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
2d4472efc1
|
fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733)
* fix(vllm): write spend log rows for /vllm passthrough calls to router models The vLLM passthrough config never built a logged response for relayed calls, so stream and non-stream calls through /vllm with a router model wrote no spend row and never charged the key. vLLM now shares the OpenAI-shaped relay logging that Azure already had, moved into an openai_like helper both configs call. * ci: run the vllm passthrough unit tests in the llms-providers shard * fix(proxy): log /vllm text completions and ask router models for stream usage A chat stream relayed to a router model without stream_options now gets include_usage added on the way out, and the usage chunk vLLM appends is removed before the client sees it, so the spend row carries vLLM's own token counts instead of a local estimate. /vllm/completions calls now write a row too, stream and non-stream. * fix(vllm): keep usage, fingerprints, and disconnect rows correct on /vllm streams Inject and strip stream usage on /vllm/completions too, hold every finish frame for the fingerprint when n > 1, pass a forced-usage server's stream through untouched, stop turning continuous_usage_stats alone into per-chunk usage, close the upstream when the client hangs up so the row is written, and assemble text choices with one sort instead of a scan per choice * fix(vllm): keep n>1 stream order when holding finish chunks for the fingerprint A held finish chunk now goes out as soon as any other chunk arrives, so a choice that finishes while another still streams keeps its place. Only the finish chunks right before the usage chunk get vLLM's system_fingerprint. * fix(vllm): keep caller stream_options and log both success handlers Forward a stream_options the proxy cannot read, or a non-boolean include_usage, to vLLM as the caller sent it. Only a false always_include_stream_usage changes the /vllm relay, so clients get the same stream bytes under every setting. Record the passthrough origin when logging starts so the sync and async success handlers both parse the relayed body, hand callbacks a parsed text completion, and read relayed messages and prompt separately so a stray field no longer drops the local count. Add the audit's integration tests for the relay, the settings, and the Azure spend row. * test(vllm): expect the caller's stream under always_include_stream_usage true * fix(vllm): relay long SSE frames in linear time * test(vllm): time the relay's usage and finish_reason prefilter on one large frame --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Kerry Lu
|
6bd5580425
|
fix(streaming): add CustomStreamWrapper.close() and release the connection when a sync stream ends (#46354)
* fix(streaming): close sync streams so the connection goes back to the pool CustomStreamWrapper gets a sync close() (plus context manager support) that closes the wrapped provider stream, and both the sync and async wrappers close the provider stream when the stream reaches its end. The Anthropic stream iterator keeps the httpx response it reads so close()/aclose() can release the socket after message_stop instead of leaving it checked out of the pool Co-authored-by: Blair Jordan <blair.j.jordan@gmail.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(streaming): keep the basedpyright ceiling flat in CustomStreamWrapper.close() Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(streaming): close the response on the shared sync stream path too BaseModelResponseIterator gets a sync close() next to its aclose(), and the sync branch of BaseLLMHTTPHandler hands it the httpx response the way the async branch already does, so providers built on it release the socket on close() instead of waiting for garbage collection Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(streaming): unit tests for CustomStreamWrapper.close() and the shared iterator close() Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(streaming): close the provider stream before re-raising a mid-stream error Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Blair Jordan <blair.j.jordan@gmail.com> |
||
|
Mateo Wang
|
457b5d26c7
|
fix(anthropic): stream json_schema answers as content on Bedrock Mantle and Claude Platform, and join split answers (#46331)
* fix(vertex_ai): unwrap tool-emulated json_schema envelopes and send output_config.format for Claude
Vertex AI Claude deployments that emulate response_format through a forced
tool sometimes nest the schema object under an extra key such as
`parameters` or `input`, and that envelope reached message.content with a
200. The converter now unwraps exactly one nested object that matches the
schema, leaving a payload that is itself schema-shaped alone.
Native structured-output rows sent the deprecated top-level `output_format`,
which Vertex rejects with a 400. The Vertex request now carries it as
`output_config.format`, with an explicit caller value winning.
* fix(anthropic): unwrap tool-emulated json_schema envelopes on streams and tool-name wrappers
* test(anthropic): expect the json tool description through a shared constant
* fix(anthropic): drop the json tool description that makes sonnet-5 omit required keys
* fix(anthropic): keep schema-accepted answers whole and decide held streams at the second key
An answer the json_schema accepts is returned as is before any envelope rule runs, the tool-name
wrapper is unwrapped only when the schema rejects it, a malformed schema turns the unwrap off, a
streamed answer whose first key is a schema property named name or tool_name waits for its second
key before streaming, the held fragments go through a StringIO, and a prefix that stays undecided
past 4 KB is held to the end
* test(anthropic): keep the stream family cells to providers whose stream iterator gets the schema
* fix(vertex_ai): unwrap claude json_schema answers nested under up to three wrapper keys
A tool-emulated json_schema answer was unwrapped only when the real object sat one key down. In live QA, 1 of 58 answers (/v1/responses, claude-sonnet-5) came back as {"parameter": {"value": {...}}} and reached the client still wrapped
The unwrap now follows single-key wrappers up to three levels down and stops at the first object that has a key the schema declares. That object is returned only when it has every required key. A payload wrapped deeper than three levels, a level with more than one key, and a level whose key is one of the schema's own property names all come back exactly as they arrived
The streamed path needs no change because the buffered answer goes through the same unwrap when the tool block closes, and a test now pins that both paths agree
* fix(bedrock): unwrap streamed claude json_schema answers on claude platform and mantle
A streamed json_schema answer on bedrock/claude_platform and Bedrock Mantle Claude reached the client as tool_calls deltas holding the json_tool_call wrapper, with finish_reason tool_calls and no content. The shared HTTP handler built the async stream iterator without json_mode, and neither stream path passed the response_format schema
The handler now asks the provider config for the iterator through get_model_response_iterator_for_request, which carries json_mode and the request's optional params on both the sync and async paths. Claude Platform and Mantle override it to hand the json tool schema to the Anthropic stream iterator, so the streamed answer is the bare schema object with finish_reason stop, the same as the non-streamed one
Databricks is the only other provider on this handler whose iterator reads json_mode, so its async Claude json mode stream now returns the answer as content like its sync stream already did
The stream family integration test covers claude_platform_unmapped and bedrock_mantle again
* fix(anthropic): unwrap json tool envelopes by structure instead of schema validation
The unwrap now reads only the schema's top-level property names. A lone
undeclared key holding an object, alone or beside a name equal to the json
tool's own name, is the envelope, and the unwrap repeats while the inner
object shares no key with the schema. jsonschema and referencing are no
longer imported on the request path. The stream holds only an answer that
opens with the tool's name or with an undeclared key holding an object, and a
schema without top-level properties streams as it arrives.
* fix(llms): keep other providers' async streams as they were
The request-aware iterator hook passed json_mode on async streams to every provider on the shared HTTP handler, which changed Databricks and any other provider whose iterator reads it. The default hook now makes the same two calls the handler made before, so only Claude Platform and Bedrock Mantle change, and the Databricks test that pinned the wider change is removed
* fix(anthropic): walk json tool envelopes iteratively
* test(llms): pin which stream iterators get json_mode from the shared handler
A provider config that does not override the request-aware iterator hook still gets json_mode on a sync stream and still does not get it on an async stream, the same as before the hook existed
* fix(anthropic): keep json tool arguments too deep to decode instead of raising
* fix(anthropic): unwrap json tool envelopes beside undeclared string labels
* fix(anthropic): keep json answers whole on schemas that allow extra keys and stream held text as sent
A schema that allows undeclared keys and requires none now keeps an undeclared wrapper key on both the stream and non-stream paths. When no envelope is found, the held stream text is now sent exactly as the model wrote it. On Vertex /v1/messages, output_format now wins over output_config.format when both are set, which matches the Anthropic adapter.
* fix(anthropic): join a json_schema answer the model splits into one tool block per field
With tool emulation the model sometimes answers with one json_tool_call block per schema field, each naming the field and holding its value. The non-stream path returned only the first block and the stream sent every block's text back to back, so the client got one field or invalid JSON. Both paths now build one schema object from those blocks, and any other set of blocks keeps today's output
* refactor(anthropic): set the streamed finish reason in one expression
* test(anthropic): cover label envelopes, dynamic-key schemas, as-written held streams and output_format precedence
* fix(anthropic): unwrap a streamed values wrapper like the non-stream answer
* fix(anthropic): join streamed split answers on schemas without required keys, keep client tool calls and length on json_schema streams
* fix(anthropic): join streamed split answers that carry text labels on schemas without required keys
* test(bedrock): script the wrapped json_schema stream with the wrapper Bedrock Mantle sends
* test(bedrock): script the wrapped json_schema stream with the wrapper Bedrock Mantle sent raw
* fix(anthropic): join a split json_schema answer whose fields all hold the same string
* fix(anthropic): join a split json_schema answer sent as one partial object per field
* fix(anthropic): join field blocks after an empty streamed answer without a leading comma
|
||
|
ryan-crabbe-berri
|
b5aa827067
|
fix(anthropic): forward service_tier on chat completions to Anthropic and Azure (#46461)
* fix(anthropic): forward service_tier on chat completions to Anthropic and Azure Chat completions calls to Claude with service_tier were rejected client-side (or dropped with drop_params), so the tier never reached Anthropic. Map auto and standard_only through, send OpenAI's default as standard_only, and raise a 400 with a drop_params hint for values Anthropic has no equivalent for. Bedrock Invoke and Vertex reject the field upstream, so they keep rejecting it. * fix(anthropic): keep the caller's service_tier value out of the drop warning log |
||
|
Rick
|
4f3cb48dc1
|
feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706)
* feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos
DashScopeVideoConfig maps litellm's OpenAI Videos API onto Alibaba Model
Studio's async task API: create hits
/api/v1/services/aigc/video-generation/video-synthesis and status and content
poll /api/v1/tasks/{task_id}. It is registered for dashscope and for the
qwencloud and qwen_ai_platform brand aliases, following the same
get_dashscope_family_*_config pattern image generation uses. Unlike the
Sora-shaped providers the request body is nested, so prompt and media go under
input and everything else goes under parameters. X-DashScope-Async is always
sent, because DashScope rejects the call outright without it
OpenAI params translate to DashScope's contract. seconds becomes duration, and
size yields both a ratio and a named resolution tier (1280x720 gives 16:9 plus
720P), since sending only the ratio leaves the request on the default 1080P and
silently bills at that rate. input_reference becomes a single media entry,
base64 encoded into a data URI for file inputs. Which media type a model takes
(first_frame or, on the reference-to-video models, reference_image) is read
from provider_specific_entry.dashscope_video_reference_input via
get_model_info rather than hardcoded; models without it predate the media
array and get the flat img_url field. A caller-supplied media array always
wins, as that is the only way to express multi-role combinations
The create call is the only billed call, so it bills what DashScope will
deliver: the requested duration and tier, or the documented 5 second and 1080P
defaults when they are omitted. Smart duration (duration -1) lets the service
pick the length after that call, so it is rejected rather than recorded at
zero, with a 400. Task creation and task lookup both report failures as a 200 carrying
top-level code and message with no output, so that shape is raised instead of
surfacing as a queued video with an empty id. Status responses re-encode the
deployment model from the polled id, so follow-up polls and downloads route to
the same deployment. Timestamps parse as UTC+8. DashScope publishes no list,
delete or remix endpoint, so those raise rather than guess at a URL
The end-to-end tests drive the real avideo_generation() entrypoint through an
httpx MockTransport and assert on the JSON body httpx actually encoded. That is
what catches a mapper that drops input_reference before the request is built,
or a body fragment json cannot serialize, neither of which a test calling the
transform directly would see
Both model_prices maps gain wan3.0-video, wan3.0-video-prime, wan2.7-t2v,
wan2.7-i2v, wan2.7-r2v and the HappyHorse 1.0 and 1.1 t2v, i2v and r2v models,
for dashscope and the qwencloud and qwen_ai_platform aliases, priced per output
second by resolution tier from Model Studio's USD rate cards. dashscope and
qwen_ai_platform default to the Beijing host and use its rate card; qwencloud
defaults to the international host and uses Singapore's. The three
*_API_BASE_VIDEO overrides are documented in BerriAI/litellm-docs#1920
Co-authored-by: AaronHowell <237895480@qq.com>
* fix(dashscope): fail loudly on video responses that cannot be read
Addresses the review on the video generation PR. A body that is not the
documented task shape, an output block missing task_id or task_status, an
undocumented task_status and a missing output all raise DashScopeVideoError
now, instead of defaulting into a queued video with an empty id that callers
poll forever. A JSONDecodeError from a gateway response no longer escapes as
a generic connection error.
task_id and task_status are required on _TaskOutput, and a missing output
raises even when the body carries no code or message.
Download failures move into the 4xx range, since a 5xx has the proxy retry
them: 409 while the task is still running, 400 for a task that failed, 404
for an id that expired. The status a provider reported is kept when it
reported one, so an in-body failure that arrives on a 200 is billed as the
400 it is rather than as a retryable connection error.
characters and image are only dropped when drop_params is set; the params
that are rebuilt into the body or consumed by the caller (model, prompt,
user, extra_*) stay silently skipped, since the proxy stamps user from the
caller's end-user header.
Co-authored-by: AaronHowell <237895480@qq.com>
* fix(dashscope): clear the lint gates after merging main
* fix(dashscope): accept file tuples and paths as video input_reference
video_generation() types input_reference as FileTypes, which includes
(filename, content[, content_type[, headers]]) tuples and pathlib paths,
but the DashScope encoder only read bytes and file objects, so those
image-to-video calls raised before reaching DashScope. Bare strings stay
URLs and are never opened as paths.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(dashscope): snap size to a supported ratio and read file tuples and paths
* test(dashscope): assert whole mapped values and bill against hand-written rates
The tier pricing test read its expected rate from the same map the cost
calculator uses, so a wrong rate passed. Billing is now checked against
fixed rates driven through the status response usage, while the map test
only asserts every supported tier has its own rate. Size mapping tests
compare the full mapped dict, and the single-test wiring class is a
plain function.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(videos): download content through the caller's client and stop retrying dead tasks
Two Cursor Bugbot findings on the DashScope video PR.
The DashScope artifact lives on OSS, so transform_video_content_response makes a
second request. It built its own cached client, discarding an injected client and
its ssl_verify. Thread the client through the content response the way
transform_video_status_retrieve_response already does, and use it in the three
providers that fetch from a second URL (DashScope, RunwayML, fal.ai). The
remaining providers accept it and read the response body, matching how they
already accept an unused client on status retrieve.
A FAILED or CANCELED task reported without a code or message fell past the
in-flight check into the 502 branch, so the proxy retried a task that can never
produce a video. Raise 400 for a terminal status instead.
* fix(dashscope): answer 404, not 409, when a Wan video is downloaded before it finishes
A download that lands while the task is still PENDING or RUNNING answered 409. That
reads as a client error, which was the intent, but litellm's retry predicate counts 409
as retryable, so the proxy polled DashScope twice more before giving up and then counted
the caller's own early download against the model's error rate
404 is what the OpenAI videos API documents for content that is not ready, and it is the
one status in that family the retry predicate leaves alone. The rest of the mapping is
unchanged: 400 for a task the provider reported as failed, 404 for an expired task id,
502 when a succeeded task carries no artifact
The download tests now drive avideo_content and assert the caller sees NotFoundError
rather than an internal server error
* fix(dashscope): route a video poll back to the model group that created the task
The create response encoded the upstream model name into the returned id. Both the
dashscope and qwen_ai_platform prefixes serve the same model names from their own hosts,
so a proxy with a deployment per region had deployments that only the model group told
apart. Encoding the bare model name resolved a poll to whichever deployment the router
lists first, which sent it to the other region's host with that region's key and a task
id that region never issued. That is the reroute the earlier proof records as the
dashscope and qwen_ai_platform poll ids coming back tagged qwencloud
The id now carries the model group the create was routed to, which is what the proxy
resolves a poll back to, and falls back to the model name for a direct SDK call that has
no router
The regression test drives a real router with one deployment per region, under a
different prefix and under the same one, and asserts the poll carries the key of the
region that created the task
* fix(dashscope): read the routed model group from litellm_metadata
The router stamps the model group it picked into litellm_metadata. metadata only
carries a copy when the caller sent no metadata of its own, and every proxy request
sends some, so a proxied create still encoded the bare model name and the poll
resolved to whichever region's deployment the router lists first
The regression test now also creates the video with caller metadata, which fails
without this change
* fix(dashscope): reject unbillable video requests and keep fal and runway on their own clients
* fix(dashscope): show the caller why a video task is gone or not ready instead of the bare upstream body
* fix(dashscope): check video request values before the billed create and honor per-call drop_params
Type check documented DashScope parameters so a bad seed answers 400 instead of a billed failed task,
pass the call's and deployment's drop_params into the video mapping, answer 400 for an expired task id so
the deployment is not cooled down, read DASHSCOPE_API_BASE for video, keep polling SUSPENDED tasks, and
refuse to map size onto models litellm has no price for.
* fix(dashscope): carry the requested model name in video ids so alias and wildcard keys can poll
A key scoped to an alias or to a name a wildcard serves could create a
video and then got a 403 on the poll and the download, because the id
carried the group that served the call (wan3, qwencloud/*) and the key
was never given that name. The id now carries the name the router was
asked for on that hop, and the router resolves an alias, routing group
or wildcard name in an id back to itself when no deployment name or
provider model matches it first
* fix(dashscope): keep a routing group's video polls on the member that created the task
A routing group spans several model groups, so an id carrying the group's name
load-balanced its polls, and some left for another region's host and key with a
task id that region never issued. The id now carries the member that served the
task when the request named a routing group, and keeps the requested name for a
model group, an alias, or a wildcard match.
* fix(dashscope): carry the requested and served model in video ids so group-scoped keys poll in the creating region
* fix(proxy): pin a video's served group only after key and team aliases resolve
* test(integration): audit DashScope video create, poll, download, routing and chaos paths
* fix(proxy): keep catch-all video polls on their provider and count served polls against the requested group
* test(routing): expect a forged served group to be dropped from the polled video id
* test(integration): cover rate-limited routing group polls and catch-all polls of DashScope videos
---------
Co-authored-by: AaronHowell <237895480@qq.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
||
|
ryan-crabbe-berri
|
12cce6c372
|
fix(anthropic): check Vertex forced-tool support on the real model, skip non-string user ids, drop speed where unsupported (#46337)
* fix(anthropic): check Vertex and Bedrock forced-tool support on the real model The Vertex and Bedrock invoke Claude transforms swapped the model for a claude-3-sonnet stand-in before calling the shared Anthropic mapping so response_format would take the tool-based path. Every model-keyed check in that mapping then ran against the stand-in, so the synthetic json tool was forced on models whose map entry says forced tool use is unsupported and the request 400ed upstream. Bedrock patched the one symptom with a backstop, Vertex had nothing. The shared mapping now asks a uses_native_structured_output hook for the structured-output decision and the two overrides answer it with their provider-scoped lookup, so the real model reaches every check and the stand-in, the restore dance and the Bedrock backstop go away. * fix(anthropic): skip non-string metadata user ids instead of raising _valid_user_id ran re.match straight on litellm_params metadata.user_id, so an integer id raised TypeError and the proxy answered 500. The user param path already skips non-strings, so the validator now does the same for any caller: a non-string id is simply not forwarded. * fix(utils): drop speed on every provider without fast mode speed rides into get_optional_params as a provider-specific kwarg, so the only gate for it lived in the Anthropic transform and Bedrock converse, OpenAI, Azure and the extra_body legs forwarded it to a 400. The gate now runs once in get_optional_params before provider-specific kwargs are copied, so every provider drops it with drop_params or rejects it with a clean 400, and a direct Anthropic fast-mode model keeps it. * fix(utils): gate speed only under drop_params and keep it for litellm_proxy Raising on speed when drop_params is off would turn requests that tolerant OpenAI-compatible backends accept into 400s, and dropping it for litellm_proxy would disable fast mode on a downstream proxy that supports it * test(anthropic): derive the forced-tool regression model from the cost map and drop new docstrings * test(utils): pin that speed is untouched without drop_params and annotate new test locals * test(integration): lock the Vertex and Bedrock invoke json tool to the real model's forced-tool support Vertex sends tool_choice only when the model accepts forced tools, reasoning_effort maps the same with and without response_format, and Bedrock invoke keeps sending the json tool unforced |
||
|
devin-ai-integration[bot]
|
a93fee9f6c
|
feat(decisions): add Laya and Bespoke providers to the Add Model form (#45260)
* feat(ui): add decisions and classifier providers to the Add Model form Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(cost): use literal upstream decisions paths Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix: drop duplicate TYPESAFE provider fields entry superseded by main's TypeSafe Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * style(ui): drop stray blank line in provider_info_helpers test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): type the OSS decisions provider fields test * fix(decisions): keep Laya and Bespoke env keys on their configured server Route laya and bespoke Decisions deployments through the same oss_connection and validate_oss_model rules the pass-through and the classifier router use, so LAYA_API_KEY and BESPOKE_API_KEY only go to LAYA_API_BASE and BESPOKE_API_BASE, an api_base with credentials, a query, or a non-HTTP scheme answers 400, and an unknown checkpoint name answers 400 before any upstream call * fix(decisions): send the Laya and Bespoke env key to a form-added model on the env server A deployment added through Add Model always carries an API base, so the env key only reached deployments with no base. The env key now goes to a deployment whose base matches LAYA_API_BASE or BESPOKE_API_BASE, an empty deployment key counts as no key, and the Bespoke placeholder is the name Ollama serves. * test(decisions): cover the env-base classifier case in the complexity router test * fix(decisions): match the env server with or without /v1 and point Ollama users at bespoke/nimble * fix(decisions): call /v1/systemone once from classifiers and pass-through on a /v1 base * fix(decisions): strip /v1 from the API base path only, so a host named v1 still works --------- Co-authored-by: kerry <kerry@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> |
||
|
Mateo Wang
|
ccc656873d
|
fix(http_handler): only replay POST and PATCH when the request never reached the upstream (#46336)
* fix: narrow async HTTP retries Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(http_handler): keep disconnect resend for idempotent PUT and DELETE Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: nate <nate@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
aa0279e0a2
|
feat(anthropic): generate auto mode safeguard_results with a classifier model on the /v1/messages chat bridge (#45600)
* feat(anthropic): generate auto mode safeguard_results with a classifier model on the /v1/messages chat bridge * fix(anthropic): check caller limits for the safeguards classifier, mark truncated tool calls, and keep pre-compaction context * fix(anthropic): log classifier spend under the caller's key hash and read list-shaped classifier replies * feat(anthropic): generate safeguard_results on the Responses bridge and native non-Claude /v1/messages providers * fix(messages): keep safeguards requests on Python under the Rust opt-in * fix(anthropic): keep non-ASCII text unescaped in the safeguards classifier prompt * test(anthropic): build the text-parts classifier reply without openai's construct path Message.model_construct goes through openai's construct_type, which caches discriminated unions in a weak-key map. On Python 3.12 a PEP 604 union cannot be weak-referenced, so the fixture raised inside the fake classifier and the test read an unavailable verdict. model_copy sets the list content without that path. * fix(anthropic): scan only new bytes for SSE frame ends on safeguarded native streams * fix(anthropic): answer safeguards on web search short circuits and widen the classifier reply cap * fix(anthropic): answer unsupported when the proxy serves no deployment for the safeguards classifier * fix(anthropic): keep a backend's stream verdicts and join split SSE data lines before stamping * fix(anthropic): map only the router's no-healthy-deployments refusal to unsupported * fix(anthropic): answer unavailable for the turn on a transient caller denial and let the classifier deployment's timeout apply * fix(anthropic): keep the user's whole opening message in the classifier transcript past its budget * fix(anthropic): run the proxy's own access checks for the safeguards classifier call The classifier and compaction sub-calls now pass through the same model access checks as the parent request (key, team, team member, user, project, end user, managed agent grants), with budgets left to the per-model budget check so nothing is reserved. They also carry the parent's logging params and headers, so a redaction header or per-request callback params apply to their own rows. Only per-model RPM limits count against a sub-call now, since a key-wide or team-wide RPM window is already spent by the parent request. The MCP auto-execute loop classifies only its final response, a chat-bridge stream without safeguards yields frames directly, and a classifier provider failure logs one warning line instead of a traceback * fix(anthropic): keep safeguards sub-calls off the parent's session routing and carry a body trace id The classifier and compaction summary calls no longer get the parent's proxy_server_request, so a Claude Code session bound to a router no longer pulls them off their configured model. Redaction still reads the headers carried in metadata. Their access checks now use the parent's resolved litellm_trace_id when the parent metadata has no trace_id, so a team that requires a trace id accepts a sub-call whose parent sent it in the body. * fix(anthropic): keep the disable-callbacks header on safeguards sub-calls * fix(proxy): charge per-model budgets from litellm_metadata when metadata holds only routing keys * test(integration): add safeguard_results cells for the bridges, native routes, caller checks, and classifier failures * fix(proxy): check the caller's budgets on the classifier call and keep failed access reads retryable --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
2f3ccbe7c7
|
feat(decisions)!: send images to Cloudflare Clef through its images field (#45734)
* feat(decisions): send images to Cloudflare Clef OpenAI-format input_image parts and the System One images field now reach Cloudflare clef and clef-flash in its images field, with remote URLs downloaded and inlined first. Providers that cannot take images drop them under drop_params and answer 400 otherwise. * fix(decisions): follow drop_params for images and use the call timeout for image downloads * fix(decisions): drop a malformed images entry on its own under drop_params * fix(decisions): refuse images next to input whatever drop_params says * fix(decisions): bound clef image fetches, honor drop_params for images, and log caller URLs Refuse more than 4 images for Cloudflare clef before any download, keep the caller's timeout as one deadline across image fetch retries, accept images next to input under drop_params, validate image strings and objects, and pass the caller's image URLs (not inlined bytes) to logging callbacks. * fix(decisions): check input_image URLs and clef image sizes * fix(decisions): accept data URL media type parameters and check clef image types * fix(decisions): count clef images after dropping unsupported types and flag clef vision --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
mrinal-berri
|
1aee1a21ed
|
fix(databricks): send a single plain text block as a string for non-Claude models (#45686)
* fix(databricks): send a single plain text block as a string for non-Claude models Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): simplify single-text-block helper Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * docs(databricks): clarify json_object validation wording Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(databricks): integration cells for single text block content shape Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(databricks): rename list-content cells to stays_list Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(responses): expect plain string content for bridged Databricks messages Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(databricks): cover the customer's Unity Catalog model from #45617 and #45618 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(databricks): drop casts from _collapse_single_text_block Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(databricks): assert the whole outgoing messages list in the collapse unit test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(databricks): cover system joins, fallback, SDK clients, and outage burst for one-block content --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
ryan-crabbe-berri
|
b37eac29f0
|
fix(anthropic): cache tool result screenshots on the /v1/messages to Responses bridge (#46324)
* fix(anthropic): put a tool_result cache breakpoint on its hoisted images on the Responses bridge A marked tool_result whose images get moved into a trailing user message now carries the breakpoint on the last moved image instead of the function_call_output, so the prefix OpenAI caches includes the images * test(anthropic): cover a marked tool_result with two screenshots on the Responses bridge * fix(anthropic): keep every tool result screenshot inside the breakpoint that covers it on the Responses bridge A marked tool_result's screenshots now go right after its output, so earlier unmarked screenshots land inside the breakpoint and later tool outputs stay after it. A cache_control mark on a block inside a tool_result is read too. * fix(anthropic): cover only the screenshots up to a mark inside a tool result, and drop raw breakpoints under drop_params A cache mark on a text block inside a tool result now covers that result only up to the marked block, the way Anthropic caches it, so screenshots after the marked text stay outside the breakpoint. A mark on the tool result itself still covers every screenshot in it A deployment that reads no prompt cache breakpoints now drops raw prompt_cache_breakpoint marks, top-level and inside tool results, when drop_params is on, and still forwards them as sent without it * fix(anthropic): keep raw breakpoints under drop_params for models that take them * docs(anthropic): say a mark inside a tool result covers its whole text and documents --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: yuneng-jiang <yuneng@berri.ai> |
||
|
devin-ai-integration[bot]
|
c581c85559
|
fix(vertex_ai): unwrap tool-emulated json_schema envelopes and send output_config.format for Claude (#45871)
* fix(vertex_ai): unwrap tool-emulated json_schema envelopes and send output_config.format for Claude Vertex AI Claude deployments that emulate response_format through a forced tool sometimes nest the schema object under an extra key such as `parameters` or `input`, and that envelope reached message.content with a 200. The converter now unwraps exactly one nested object that matches the schema, leaving a payload that is itself schema-shaped alone. Native structured-output rows sent the deprecated top-level `output_format`, which Vertex rejects with a 400. The Vertex request now carries it as `output_config.format`, with an explicit caller value winning. * fix(anthropic): unwrap tool-emulated json_schema envelopes on streams and tool-name wrappers * test(anthropic): expect the json tool description through a shared constant * fix(anthropic): drop the json tool description that makes sonnet-5 omit required keys * fix(anthropic): keep schema-accepted answers whole and decide held streams at the second key An answer the json_schema accepts is returned as is before any envelope rule runs, the tool-name wrapper is unwrapped only when the schema rejects it, a malformed schema turns the unwrap off, a streamed answer whose first key is a schema property named name or tool_name waits for its second key before streaming, the held fragments go through a StringIO, and a prefix that stays undecided past 4 KB is held to the end * test(anthropic): keep the stream family cells to providers whose stream iterator gets the schema * fix(anthropic): unwrap json tool envelopes by structure instead of schema validation The unwrap now reads only the schema's top-level property names. A lone undeclared key holding an object, alone or beside a name equal to the json tool's own name, is the envelope, and the unwrap repeats while the inner object shares no key with the schema. jsonschema and referencing are no longer imported on the request path. The stream holds only an answer that opens with the tool's name or with an undeclared key holding an object, and a schema without top-level properties streams as it arrives. * fix(anthropic): walk json tool envelopes iteratively * fix(anthropic): keep json tool arguments too deep to decode instead of raising * fix(anthropic): unwrap json tool envelopes beside undeclared string labels * fix(anthropic): keep json answers whole on schemas that allow extra keys and stream held text as sent A schema that allows undeclared keys and requires none now keeps an undeclared wrapper key on both the stream and non-stream paths. When no envelope is found, the held stream text is now sent exactly as the model wrote it. On Vertex /v1/messages, output_format now wins over output_config.format when both are set, which matches the Anthropic adapter. * test(anthropic): cover label envelopes, dynamic-key schemas, as-written held streams and output_format precedence --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
ryan-crabbe-berri
|
365c4885de
|
fix(openai): carry cache_control to prompt_cache_breakpoint on chat completions to gpt-5.6 (#46101)
* fix(openai): carry cache_control to prompt_cache_breakpoint on chat completions to gpt-5.6 A cache_control mark on a system, developer, user or tool message sent to /v1/chat/completions now reaches an OpenAI deployment that reads prompt_cache_breakpoint (gpt-5.6+ on api.openai.com, or one opted in through prompt_cache_options) as a prompt_cache_breakpoint on the same content part, instead of being stripped. Marks on assistant turns and tool definitions are still dropped, and deployments that do not read breakpoints keep today's behavior. * test(openai): rewrite chat prompt_cache_breakpoint wire test as sent-vs-received literals Each test now shows the request the caller sends and the exact body OpenAI receives as plain JSON, with one helper that returns the upstream body. Drops the per-test marker plumbing and the spend-log check, which did not test the cache mark translation. * test(openai): cover a marked chat message with null content on the breakpoint path A system, developer, user or tool message that carries cache_control but whose content is neither a string nor a list of parts is handed to the existing strip untouched instead of raising inside the transform. The new case pins that the request still goes out with the mark stripped and no breakpoint added. * refactor(openai): reuse the cache control hook's breakpoint placement on chat completions The chat transform had its own copy of how a message-level cache_control lands on a part for OpenAI's prompt_cache_breakpoint. It now calls one hook helper that the injection path also uses, so which roles and part types can carry a breakpoint is decided in one place. A message-level mark on list content now lands on the last part OpenAI accepts a breakpoint on, matching injection. * test(e2e): cover cache_control reaching gpt-5.6 explicit prompt caching on chat completions Four live cases through the proxy: a marked system part, a marked string system message, a marked user part and a marked tool result. Each must write the cache on the first call and read it on the second. * fix(openai): parse content parts instead of a banned TypeGuard when renaming cache marks The strict ruff gate bans typing.TypeGuard as unverified narrowing. The part rename now validates an accepted part with pydantic before handing it to the shared rename helper. |
||
|
Mateo Wang
|
0ebec123fd
|
chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388)
* chore(typing): validate provider payloads at the boundary to clear 464 basedpyright Any errors Replaces untyped reads of decoded JSON in 48 provider, guardrail and proxy modules with one pydantic validation at the point the payload enters the module, so every value read afterwards carries a real type. reportAny 6111 -> 5663 and reportExplicitAny 1416 -> 1400. No basedpyright, ruff-strict or type-discipline rule is higher repo-wide or in any single file, and no cast, ignore or suppression marker was added. * chore(typing): replace 47 Any annotations that every caller already satisfies with object Each annotation here is a parameter or return type whose value is only stored, compared, logged or forwarded, so object describes it exactly and no function body changes. A site was kept only if no basedpyright, ruff-strict or type-discipline rule rose in any file that references it. reportExplicitAny 1400 -> 1353 and reportAny 5663 -> 5655. * chore(typing): type upstream responses and loose annotations across providers, proxy and integrations Second pass of the Any reduction. Decoded upstream JSON is validated once at the provider boundary and read through typed views afterwards, annotations that every caller already satisfies move from Any to a concrete type, and the nine search transformations validate each result item on its own so error text no longer carries the item index. No cast, no type: ignore, no suppression marker and no budget file edit * ci(unit): run the brave, google_pse, nlp_cloud and opensandbox tests in the providers shard |
||
|
ryan-crabbe-berri
|
7bd108139f
|
fix(openai): carry cache_control to prompt_cache_breakpoint on /v1/responses to gpt-5.6 (#46105)
* fix(openai): carry cache_control to prompt_cache_breakpoint on /v1/responses to gpt-5.6 Native /v1/responses used to strip every Anthropic cache_control mark, so a gpt-5.6 deployment in explicit mode never wrote a cache. Marks on system, developer and user parts and on function_call_output now become prompt_cache_breakpoint on the same block when the deployment reads breakpoints, and are stripped exactly as before everywhere else * fix(openai): read str providers and base_url in the prompt cache breakpoint gate Responses configs generated from a provider JSON file, and openai_like itself, name their provider as a plain str, so .value crashed every native Responses request through them. The gate also only read api_base, while responses() keeps a caller's base_url as an extra field on the params, so an injected mark on a custom host was rewritten to a breakpoint * test(openai): cover the pass-through branches of the prompt cache breakpoint swap A part type OpenAI does not cache keeps no breakpoint and an item mark skips it, and an item or content of a shape OpenAI will reject reaches the strip untouched instead of failing inside the proxy * fix(prompt_caching): keep a client-written prompt_cache_breakpoint when a cache_control mark lands on the same block |
||
|
devin-ai-integration[bot]
|
d9123f4595
|
feat(realtime): proxy OpenAI Live sessions on /v1/live/sessions (#43621)
Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
74e5dc9747
|
fix(proxy): keep provider refusal, logprobs and system_fingerprint in chat completions (#44788)
* fix(proxy): keep provider refusal, logprobs and system_fingerprint in chat completions Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): handle missing chat completion roles Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(types): restore throwaway Usage skip in ModelResponse Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): handle explicit fields on custom response dumps Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: update refusal expectations for LIT-9235 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(lint): suppress type discipline violations with reasons Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * style: ruff format proxy utils Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(types): keep basedpyright counts at merge-base for azure dump and ModelResponse Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(types): keep an explicit null system_fingerprint passed to ModelResponse Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry <kerry@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
yuneng-jiang
|
1587faeeb9
|
test(unit): wait on the work itself instead of fixed sleeps (#46261)
* test(unit): wait on the work itself instead of fixed sleeps in 21 flaky files Replace sleeps that raced background logging, cache writes, refreshes and thread work with either awaiting that work directly (logging worker flush, the batch logger's flush_queue, the tasks the call spawned, thread joins) or an Event the test's own fake sets when it runs. Each wait keeps a 5s hang guard that never decides pass or fail. Tests that need a fake clock, real sockets, or measure latency are left unchanged, and no production code moves * test(unit): await the tasks each completion spawns instead of yielding once The logging tests yielded once with asyncio.sleep(0) so the task that enqueues the success log could run before the worker flush. That relied on the enqueue happening before the task's first await. Snapshot the running tasks around each acompletion call and await the ones it spawned, so the guarantee holds however many steps sit before the enqueue |
||
|
yucheng-berri
|
784581bace
|
fix(proxy)!: return provider-matching 4xx for the LIT-8062 status code follow-ups (#45537)
* fix(proxy): return provider-matching 4xx for the LIT-8062 status code follow-ups
- OCR multipart errors are 400 invalid_request_error on the file param
- a missing model is a 400 on chat, responses and messages even with a wildcard deployment
- responses max_output_tokens <= 0 reaches the provider instead of being raised to 16
- daily activity rejects end_date before start_date with a 400
- vector store file attributes are sent in full so the provider enforces its key limit
- router-wide defaults no longer satisfy a param the Router takes positionally, or a model the router does not serve
- a JSON null user_config is treated as absent
* chore: keep the type gates at their merge-base counts
* fix(proxy): keep fixed-target wildcards serving a missing model and close router-default gaps
- a missing model is rejected only when the wildcard would forward it into the target
- moderation only counts router defaults for models get_model_list lists
- user_config defaults and deployment params never satisfy a positionally bound param
* test(integration): pin the fixed-target wildcard path and no provider call on positional-param 400s
* chore: validate pattern-matched deployments instead of reading untyped dicts
* fix(proxy): keep router defaults counting for a2a agent models
* test: drop the signature-walk test and type the new test helpers
* test(integration): audit matrix for the status-code follow-ups
Drives every mode the fix branches on through a real proxy, Postgres, Redis and
the scripted upstream: positional params against router, deployment and
user_config defaults; moderation listed vs unlisted; unknown and a2a models;
every user_config shape on chat, responses and messages, streaming and SDK
clients; forwarding vs fixed-target wildcards for missing, null and empty
models; Responses max_output_tokens edges; OCR parse errors; vector store file
attributes; every daily activity route; and a provider outage mid burst plus a
killed worker on a two-worker proxy. Product gaps found are skipped as BUG.
* style: ruff format the audit test files
* test: name the auth pre-check as the source of the JSON array 500
* test: build the audit helpers without mutation and share one sentinel
* test: build every audit request body as one literal
* fix(proxy): keep router defaults and model-less dispatch for requests a fallback chain serves
* fix(proxy): count request, key and team fallbacks when an unlisted model inherits router defaults
* fix(proxy): skip key and team fallbacks on the client-credential dispatch path
* fix(proxy): keep router defaults when the router's own * fallback serves an unlisted model
* fix(proxy): count client-style fallbacks, forward an empty model, report invalid usage chat dates
- The router-default pre-check now treats client-style request, key and team fallbacks
([{"model": ...}]) as serving an unlisted model, as the router does
- The forwarding-wildcard gate only rejects a missing or null model; an empty model
reaches the provider as before (vLLM serves its loaded model for it)
- The /usage/ai/chat tools hand the model the date-range error instead of an empty
dataset or a generic fetch error
* test(usage): type the invalid-date tool test
* fix(proxy): keep rejecting an empty model behind a forwarding wildcard
Key and team model checks skip an empty model, so forwarding it let a key
restricted to another model reach a server's default model (vLLM serves
its loaded model for ""). Pin that with a restricted-key integration cell.
* fix(usage): report the query layer's date 400 to the usage chat model
Checking dates before the fetch refused formats the global usage tool's query
accepts (2026/10/01 returned spend on main). Catch the daily activity query's
own 400 instead, so each tool rejects exactly what it rejected before and only
the message changes.
* fix(proxy): restore three model-less and unlisted-model paths main served
An empty model is looked up as sent, so next to a forwarding */* wildcard it
still reaches the fixed * deployment it matches. A null model with a prompt_id
is left to the prompt manager, which may pick the model. A Claude Code
subagent turn on a session-bound auto/complexity router counts as served, so
the router default max_tokens still applies.
* fix(proxy): only skip the model check for a prompt_id when a prompt manager is registered
Without a callback prompt manager nothing can pick the model, so a null model
with a prompt_id behind a forwarding wildcard gets the same 400 as any other
null model.
* fix(proxy): leave a model-less Claude Code subagent turn to its session router
A subagent turn on a session bound to an auto, complexity, adaptive or
quality router is answered by that router whatever model it names, so a
null or missing model behind a forwarding wildcard is no longer rejected.
An empty model stays rejected.
* fix(proxy): skip the wildcard model check only for a bound Claude Code session
Read the session's router binding, as the router does, instead of only
checking that the request could resume one, so a subagent turn without a
model on an unbound session is still rejected before a forwarding
wildcard sends it upstream.
* refactor(proxy): stop predicting routing in the proxy pre-checks
- drop the wildcard missing-model gate: a model-less request behind a forwarding wildcard goes to the router and gets the provider's own status, as on main
- drop the "model the router serves" check: router defaults count for any named model again, except moderation, where the Router merges them only for listed models
- keep the positional-param, moderation and null user_config fixes
* test(ocr): cover the form, size, empty body, invalid JSON and file-document 400s
---------
Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
|
||
|
devin-ai-integration[bot]
|
fdab308646
|
fix(vertex_ai): keep Gemini cache creation token count out of request kwargs (#46152) | ||
|
Kerry Lu
|
0eff31ae4e
|
fix(gemini): bill context cache creation tokens from cachedContents responses (#46144)
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
bfb4f4b2c3
|
fix(databricks): accept service_tier on requests and carry the served tier on responses (#46111)
* fix(databricks): accept service_tier on requests and carry the served tier on responses Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): mark the in-place service_tier store as rebind-ok Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * style(databricks): wrap the service_tier store to the line limit Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): keep the rebind-ok suppression on the service_tier line Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): only set service_tier on responses when the upstream returned one Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): name the B010 suppression on the service_tier setattr Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(databricks): shorten the service_tier suppression to the line limit Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(responses): read service_tier from the Responses request only Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Delweng
|
b24b68e576
|
fix(gemini): price tool-use prompt tokens as input (#46021)
* test(gemini): tool-use prompt tokens must be priced as input Signed-off-by: Delweng <delweng@gmail.com> * fix(gemini): price tool-use prompt tokens as input toolUsePromptTokenCount was folded into usage.prompt_tokens but left out of prompt_tokens_details.text_tokens, and generic_cost_per_token bills input from text_tokens, so URL context / code execution / File Search tool tokens were counted but never charged. Search-grounded responses keep adding zero via the grounding-aware billable count, and promptTokensDetails absent still leaves text_tokens None so billing falls back to the full prompt_tokens Signed-off-by: Delweng <delweng@gmail.com> --------- Signed-off-by: Delweng <delweng@gmail.com> |
||
|
devin-ai-integration[bot]
|
4fae3c64bb
|
feat(sagemaker)!: inference components and OpenAI-compatible embeddings (#44985)
* feat(sagemaker): inference components and OpenAI-compatible embeddings
Send model_id on a SageMaker embedding deployment as the invoke call's
InferenceComponentName, sync and async, and keep it out of the request body.
Add the sagemaker/openai/<endpoint> route, which sends the OpenAI embeddings
request shape ({"input": [...]} plus extra_body fields) and reads
data[].embedding and usage from the response for containers that serve the
OpenAI embeddings API. Plain sagemaker/<endpoint> deployments keep the
Hugging Face shape
* refactor(sagemaker): type validate_environment messages and cover base64 embeddings
* fix(sagemaker): name model_id in inference component errors and reject a non-string model_id on embeddings
* fix(sagemaker): fall back to the error text when SageMaker sends a null message
A ClientError whose Error.Message is null (SageMaker's InternalFailure shape) reached the
inference component hint as None and crashed with a TypeError; the message now falls back
to the error's own text on the chat and embedding paths
* test(sagemaker): audit matrix for inference-component embeddings
* fix(sagemaker): read the error status and text through one shape-checked helper
botocore's ConnectionClosedError carries response=None, so the except blocks that
read e.response.get(...) crashed with an AttributeError and the proxy answered 400
"Invalid request format" for a dropped connection. client_error_details validates
the botocore error shape with pydantic and falls back to 500 plus the error's own
text for any other shape (a missing response, an httpx Response, a plain exception).
* fix(sagemaker): drop the inference component hint from chat and derive the SDK wire expectation from the request
The chat except blocks never see SageMaker's text: HTTPHandler.post raises from
raise_for_status before the handler's own SagemakerError line, so the hint check ran
on httpx's generic "Client error '400 Bad Request' for url" line and could not match on
any chat path. The hint now names litellm.embedding only and the chat blocks keep the
status and text they had, without the dead check. The two OpenAI SDK wire tests pinned
the SDK's default encoding_format; they now expect whatever the SDK sent.
* refactor(sagemaker): meet main's per-rule lint and type ceilings
Main started gating every lint rule on its merge-base count and added LIT015
(frozen pydantic models) after this branch was cut, so the merge with main
pushed LIT001, LIT011, LIT015, BLE001 and reportArgumentType past their
ceilings. The response models are frozen with tuple fields, the OpenAI
embedding response is built with model_copy instead of writing into the
caller's object, the invoke_endpoint arguments are a TypedDict, and
optional_params and extra_body are validated into Mapping[str, object] before
they are read
* refactor(sagemaker): pick the embedding config in one place and stop pinning upstream error text
The openai/, Voyage and Cohere checks lived in both get_model_config and
get_supported_openai_params, so they now share one lookup. Tests compare error
messages against the error's own text, or against botocore's and json's own
wording, instead of copying that wording, and assert whole messages where the
text is ours
* fix(caching): key direct calls on model_id so inference components don't share cached embeddings
* test(sagemaker): name the fake-boto3 SDK test class for what it covers
* test(sagemaker): kill and stop chaos workers through the owned-proxy harness
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
|
||
|
ryan-crabbe-berri
|
c2d0726a08
|
fix(anthropic): carry cache_control to prompt_cache_breakpoint on the /v1/messages to Responses bridge (#46082)
A caller hitting /v1/messages with a cache_control mark and an OpenAI gpt-5.6 or newer deployment behind it lost the mark when the request was rebuilt as a Responses request, so OpenAI never cached at the boundary the caller chose. The bridge now rewrites each marked system, user and tool_result block to prompt_cache_breakpoint on the same block when the deployment reads breakpoints, keeps the system prompt as a developer message so its mark survives, and still strips the mark for deployments that do not read it The hook's gate becomes public so the bridge and the hook share one answer for which deployments read breakpoints, and the one-block swap lives next to the existing breakpoint helper in prompt_templates |
||
|
devin-ai-integration[bot]
|
ca4169d20a
|
feat(providers): add CoralBricks as a native provider (#44700)
* feat(providers): add CoralBricks as a native provider Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): harden cost map consistency tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): type cost helpers, read cost maps from disk, cover streaming spend Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): drop Final on loop-rebound names Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): add the provider audit cells, the Add Model browser cell and the README row * test(coralbricks): derive UI spend from model info, type browser rows, always release held upstream Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): release held upstream before the wire server joins its threads Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): number forwarded chats with itertools.count instead of a mutable list Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(coralbricks): drop retired glm-5.3-flash-fp4 and test against deepseek-v4.1-flash-fast-fp4 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(coralbricks): pin retries, await the respawned worker, read the UI rate from the catalog The retry cells now set num_retries on the deployment, since the CI rig posts router_settings.num_retries 0 after readiness and the router default of 2 no longer applies there. The SIGKILL chaos cell waits for the respawned worker's startup before the owned proxy is stopped and derives its timeout from the harness budget. The Add Model spec waits for the catalog the form loads, reads the expected rate from it, and finds the deployment through /v1/model/info, which does not paginate * fix(coralbricks): price the current model names and the new DeepSeek input rate CoralBricks renamed glm-5.3-fp4 to glm-5.3-fast and deepseek-v4.1-flash-fast-fp4 to deepseek-v4.1-flash-fast (the fp4 names stay as deprecated aliases), and cut DeepSeek V4.1 Flash input from $0.30 to $0.01 per 1M on 2026-10-08. Rates read from https://www.coralbricks.ai/api/public/models on 2026-10-10; a live cache write billed 6014 tokens at 9e-08 each, so the cache-write rate stays input plus cacheWritePerM. The test config builders now build new dicts instead of editing the parsed YAML, and the cost-map test locals carry Final. * fix(coralbricks): keep pricing for the deprecated fp4 slugs CoralBricks still serves * fix(coralbricks): list the catalog rows for wildcard deployments and derive the test's input limit from the row * fix(coralbricks): price the deprecated glm-5.3 and deepseek-v4.1-flash slugs --------- Co-authored-by: Mubashir Osmani <mubashir@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> |
||
|
mayank-affirm
|
56a1e94a31
|
fix(bedrock_mantle): map the OpenAI-shaped context overflow envelope too (#41747)
* feat(dd_span_tagger): emit litellm_user_email span tag for JWT-authenticated requests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(dd_span_tagger): use dotted litellm.user_email tag for consistency Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(model_hub): surface model_info.description in model group info and Model Hub UI Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(router): aggregate model group description without in-place mutation Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(health): skip background health check DB writes when the latest-row read fails Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(bedrock_mantle): map the OpenAI-shaped context overflow envelope too Mantle reports context overflow in two envelopes. #37862 covered the structured `validation_error` one carrying token counts ("prompt tokens (N) exceed model maximum (M)"). Mantle also returns the OpenAI-shaped body: {"error":{"code":"context_length_exceeded","message":"Your input exceeds the context window of this model. ...","param":"input", "type":"invalid_request_error"}} That passes the existing `invalid_request_error` gate but matches neither the token-count pattern nor `is_error_str_context_window_exceeded`'s substring list, so it fell through to a generic BadRequestError. Clients such as Claude Code only reactive-compact on a recognised overflow phrase, so an overflowing request surfaced as an ordinary error with no recovery. Return the same normalised "prompt is too long: ..." message for this envelope when it carries no counts, keeping the numeric wording when the provider supplies them. * fix(bedrock_mantle): map the streamed context overflow and keep its 400 on /v1/messages streams * fix(anthropic_adapter): keep only the context overflow's 400 on streamed /v1/messages so other provider 4xx still fall back * test(anthropic_adapter): wrap a parametrize line over the 120 char limit * test(integration): audit Bedrock Mantle context overflow mapping across routes, clients, and fallbacks * test(integration): move the streamed /v1/messages overflow spend row into a BUG-skipped test * test(integration): keep every chaos cell in the burst and skip only the missing spend row * fix(bedrock_mantle): answer 400 on an in-stream context overflow The Mantle overflow mapper built its ContextWindowExceededError on the original exception's response, so an overflow that Mantle reports inside a 200 stream (the chat-mode token-count envelope, which the OpenAI chunk parser wraps as a 500) kept that 500 and the streamed /v1/messages route answered HTTP 500 api_error instead of 400 invalid_request_error. The mapper now builds the error on a 400 response that keeps the original headers and request, and the mapping test covers an in-stream 500 and 503. The integration suites pin the streamed /v1/messages overflow to the pre-content 400 route under a retry budget and to the message_start plus invalid_request_error event without one, drop the chaos carve-out that expected no spend row, and give the fallbacks file a timeout mark sized to the proxy's graceful stop. * fix(bedrock_mantle): keep the provider's 400 body and match the overflow code only as error.code --------- Co-authored-by: milan <milan@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: ryan-crabbe-berri <ryan@berri.ai> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
moyai-devin-berriai[bot]
|
a86ad9ebf8
|
feat(decisions): support Clef-omni audio and video (#45811)
* feat(decisions): support Clef-omni audio and video * fix(decisions): accept Clef-omni media types with parameters and cover the proxy routes The clip patterns now mirror Cloudflare's input schema, so a data URL or content_type carrying parameters like audio/webm;codecs=opus is accepted. The four proxy routes get media tests of their own, the backup cost map is synced with the new Clef-omni rows, and the docs page moves to the docs repo as a follow-up. * fix(decisions): refuse parameterized media-type data URLs and refresh the OpenAPI snapshot Cloudflare answers 422 to a data URL whose media type carries parameters even though its schema only requires the data:audio/ prefix, so LiteLLM now refuses those with a 400 before the call. The object form keeps passing parameters through, which Cloudflare accepts. The lazy OpenAPI snapshot and the dashboard API types are regenerated for the new audio and videos fields * fix(decisions): gate media by cost-map flags, treat null clips as none, drop unsupported clips before validation * fix(decisions): keep the SDK's positional order and gate media flags on evaluation-mode models * fix(decisions): gate media on both decisions model modes and move the audit cells onto the harness helpers * test(decisions): cover the Fireworks System One router in the media refusal cells --------- Co-authored-by: moyai-devin-berriai[bot] <336287033+moyai-devin-berriai[bot]@users.noreply.github.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
Sukhdeep
|
87478c7b6d
|
fix(gemini): do not inject temperature for Gemini 3+ models when omitted (#45107)
* fix(gemini): do not inject temperature for Gemini 3+ models when omitted map_openai_params added temperature=1.0 to every Gemini 3+ request that did not set one, on both the gemini and vertex_ai routes. Google is deprecating temperature, top_p and top_k for Gemini 3+ and says upcoming models will reject them, so this default turns a request that never set temperature into one that will fail An omitted temperature now falls back to Google's own default, which their docs give as 1.0 for all Gemini 3 models. Explicit temperature, top_p and top_k are still forwarded Fixes #38663 * test(gemini): annotate sampling regression tests * test(gemini): drop the injected temperature from Gemini translation cases The nine Gemini base cases for chat completions, responses and messages send no temperature, so the provider request no longer carries the removed 1.0 default. Each new body was sent to the real Gemini API for gemini-3.5-flash, gemini-3.8-flash and gemini-3.1-pro-preview and returned 200, and the stored provider responses are unchanged * test(gemini): drop the default-temperature wording from the thinking level test docstring * test(gemini): cover omitted and explicit sampling on both Gemini routes --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
249add6f0d
|
refactor(bedrock): rename is_claude_4_5_on_bedrock to supports_bedrock_prompt_cache_ttl (#46058)
Co-authored-by: kerry <kerry@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
c0ca4a51f7
|
fix(bedrock_mantle): send max_completion_tokens for gpt-5.6 and gpt-6 chat completions (#43982)
GPT reasoning-series models (gpt-5.x, gpt-6) on Bedrock Mantle chat completions now send max_completion_tokens, carrying a deployment or client max_tokens over with its value. Every other Mantle chat model keeps sending max_tokens. |
||
|
devin-ai-integration[bot]
|
a7a3a6b375
|
test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940)
* test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e * test: fix disk cache collection, ungate saturation check, drop RSS memory tests * test: assert one delivered log per completion in Datadog and LangSmith checks * test: drop SDK-direct e2e copies and align cost-map path filter cases --------- Co-authored-by: yuneng <yuneng@berri.ai> |
||
|
devin-ai-integration[bot]
|
e0398455d0
|
test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759)
* test: migrate selected llm translation contracts * test: migrate anthropic completion translation tests * test: migrate bedrock and cohere translation tests * test: tighten bedrock translation migration * test: migrate azure and openai model translation tests * test: migrate openai and small-provider translation tests * test: migrate gemini and vertex translation tests * test: migrate optional params and rerank translation tests * test: migrate huggingface, json and openrouter translation tests * test: fix openrouter integration expectations * test: migrate databricks, xai, cometapi and fireworks translation tests * test: migrate ovhcloud, prompt and small provider translation tests * test: split reasoning effort grid into unit and e2e * test: migrate router and realtime guardrail translation tests * test: migrate google interactions translation tests * test: migrate a2a, evals, skills and hosted vllm translation tests * test: remove remaining llm translation suite * test: tighten migrated llm translation unit tests and land missing rows Restores rows the first pass dropped or weakened (bedrock agentcore and openwebui thinking stream, anthropic prefix, citations and tool_choice, azure agents handler, huggingface bare api_base, optional params num_retries, alternating roles, rerank response type), replaces truthiness and call-count checks with whole-value assertions, and moves tests to the mirror file of the code they cover * test: move cohere, databricks, fireworks and gemini rows to mirror files over mocked HTTP Restores three TestCohereV2Transform methods the first pass nested out of collection, replaces direct transform calls with respx-backed completion calls, and drops the databricks and fireworks files that sat outside their mirror paths * test: close lost-intent gaps found in review of the llm translation migration Points the hosted-mock guard at the triton test's new integration path, restores exact rerank result assertions for infinity, drops the reasoning e2e fallback that passed for any multi-line answer, and adds the mixtral invoke system prompt variants, eval deletion, and async pdf url download that the legacy suite exercised * test: assert provider acceptance in the reasoning effort e2e The live half of the split grid proves each route accepts reasoning_effort. claude-fable-5-1 on the direct route answers without surfacing reasoning content, so a reasoning-presence check either fails on head or needs a fallback that passes for any answer. Wire shape stays covered by the unit grid * test: cover async and stream-end paths the legacy translation suite exercised Adds async variants for bedrock converse file and thinking content, bedrock embedding timeout and region resolution, interaction stream termination and success logging, xai reasoning token folding, and bytes chunks with a prefix before data:. Also scopes the vertex safety settings global in test_vertex_safety_settings with monkeypatch so it stops leaking into gemini request bodies on the same worker * test: type the new llm translation e2e calls and mark moved fixture dirs as packages * test: name the reasoning effort e2e models as module constants * test: assert reasoning content, register the new gemini coverage ids and give the guardrail config e2e a unique name * test: block the prompt the shared guardrail denies and drop the reasoning presence check * test: drop the duplicate litellm import left by the main sync --------- Co-authored-by: yuneng <yuneng@berri.ai> |
||
|
devin-ai-integration[bot]
|
1dbde0845e
|
test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758)
* test: move guardrails, image, audio, batches, search legacy tests to unit * test: restore the custom guardrail and remaining chunk 1 unit rows * test: move the ocr matrix to e2e * test: drop comments from moved tests and fix vertex ocr credentials * test: move litellm utils and unified google legacy tests to their tiers * test: move logging callback and pass-through unit legacy tests to their tiers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: move store_model_in_db legacy tests and start the admin ui migration Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: finish the proxy job rows and drop their CircleCI jobs Moves the remaining multi-instance, openai endpoint, otel, pass-through and top-level proxy tests into tests/integration with scripted upstreams, rewrites the weak replacements to assert the outbound wire and exact responses, and removes the build_and_test job group this PR owns from CircleCI * test: tighten the key generation and error log assertions, rename migrated unit files to their mapped names * test: shard the pagerduty unit tests and record the rust harness file on the coverage allowlist * test: drive the SSO sign-in tests through a scripted IdP and isolate the cost center stand-in * test: type the e2e beta header, prompt cache and secret manager values * test: assert the missing model error message on the OpenAI routes * test: drop the deleted otel base class import and restore mcp redaction and exact langfuse usage checks * test: make the langfuse fixture directory a package for the layout check * test: restore collected no-match cases, real langfuse and gcs payload checks, and gate the aws secret lane * test: keep the ocr e2e pdf fixture next to the test * test: put meta below covers on the streaming tool search e2e * test: run the OCR matrix against a scripted upstream and fix two runner-only e2e failures * test: count only OCR calls in the OCR matrix recorder * test: pin OCR parse bodies and billed cost, group new e2e cases into classes * ci: restore the python image anchor dropped in the main sync --------- Co-authored-by: yuneng <yuneng@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
ca0ff24726
|
fix(databricks): call the ai_decide AI Function route for decisions and the auto-router (#45722)
* fix(databricks): call the ai_decide AI Function route for decisions and the auto-router Databricks serves ai_decide at POST <host>/api/2.0/ai-functions/ai-decide, not on a serving endpoint's /invocations route. The decisions provider and the auto-router classifier now accept only the ai_decide model, post to that route without a model field, unwrap the response envelope, and map a noul answer's probability to the System One noul field. * test(databricks): bound the megabyte model name test by scaling, not wall time * test(databricks): assert the whole OpenAI-format decision and floor the liveliness bound * test(decisions): move the Databricks OpenAI-format wire row to the ai_decide route * fix(databricks): keep serving endpoint decisions beside the ai_decide route * test(databricks): assert the whole classifier request body in the test routing case * test(databricks): correct System One spend call type 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> Co-authored-by: mateo <mateo@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
yucheng-berri
|
c1e3d07e76
|
fix(guardrails): scan or refuse attachments in the bedrock guardrail (#43383)
* fix(guardrails): scan or refuse attachments in the bedrock guardrail * fix(guardrails): cover native pre_call and computer screenshots in the bedrock attachment scan * fix(guardrails): classify every attachment shape the bedrock guardrail can receive * test(guardrails): type the attachment-scanning test guardrail * fix(guardrails): keep base behavior for Bedrock subclasses and malformed messages - skip the attachment scan when a subclass overrides apply_guardrail - ignore non-string message role/type instead of raising - treat a null Converse document/video/audio block as absent - keep the base request-body debug log for text-only calls * fix(guardrails): let text documents, unpadded base64 images and request-override subclasses through as before * fix(guardrails): let Converse text documents through and refuse documents that carry images * fix(guardrails): scan images inside content documents instead of refusing them * fix(guardrails): scan text document content with the Bedrock guardrail * fix(guardrails): scan document title, context and nested documents * Expand nested content documents without recursion * Keep attachment scan within the type-discipline budget * Take the image format and pixel size from the image bytes * chore(guardrails): satisfy type-discipline gate after merging main * chore(guardrails): drop docstrings added by the attachment scan * fix(guardrails): scan Converse text documents and guardContent images A Converse document whose source is text (or a list of text parts) now goes through the Bedrock text scan instead of being refused as unscannable, so the pass-through request that worked before this PR keeps working. A Converse guardContent image is now scanned like any other image. Byte and S3 document sources stay unscannable. Adds the integration test that drives every scanned endpoint through a real proxy against a scripted Bedrock ApplyGuardrail stub, and retypes the touched hook signatures for the type gates. * test(guardrails): cover Bedrock checks mode in the attachment integration test Adds a checks-mode proxy to the rig: images are refused without calling Bedrock on every route, and a Converse text document is sent to InvokeGuardrailChecks. * fix(guardrails): scan a Converse document's name and context whatever its source A Converse PDF or S3 document let through by skip_unscannable_attachments now still has its name and context scanned as text, the same as the Anthropic document path. --------- Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com> |
||
|
devin-ai-integration[bot]
|
a2e334febe
|
test: migrate local_testing SDK and provider tests out of build_and_test (#45760)
* test: migrate local_testing SDK and provider tests out of build_and_test * test: cover sagemaker region, hf template and nova paths end to end Region rows now go through litellm.completion on the sagemaker/ handler that the legacy tests exercised, the prompt template test mocks the Hugging Face tokenizer config instead of switching to custom_prompt_dict, streaming tests assert role, finish reason and body, and Nova single turn and streaming run through litellm.completion with a recorded request body * test: tighten migrated integration tests for local OpenAI routes, timeouts and air-gapped boot Split the catch-all providers migration file by behavior. The fake endpoint route tests now hit the owned upstream directly, as the legacy harness tests did. LM Studio asserts the outbound key, path and stripped model. The embedding timeout test asserts the proxy maps a deployment timeout to a 408 and forwards the read timeout to the provider client, instead of timing out the test client The Azure streaming tool-call test also asserts the second identical stream is served from the Redis cache with the same reassembled tool call The Docker network test always skipped in CI because the security job has no litellm/litellm image and no egress to pull one, and it tested a published image rather than the checkout. It now boots the checkout proxy with every outbound HTTP connection refused and asserts readiness, the bundled cost map fallback and that the cost map host is the only egress attempted * test: tighten the migrated e2e rows for local_testing SDK and provider tests Drop the duplicated Anthropic covers marker and the Anthropic cell wrongly claimed by the Bedrock and Vertex cache tests. Keep the file-wide Anthropic model as it is on main. Send the 2023-06-01 version header to Anthropic through the deployment's extra_headers so the header actually reaches the provider, and mark the creation-token case 1h then 5m like the legacy test did Reuse the Bedrock file's own registration for the pydantic response test, swap the hand-built PNGs for the shared cat.jpg fixture, assert the SageMaker Nova image answer names the cat and that top_logprobs=3 is honored, and register the SageMaker Nova opt-in markers the same way as the other opt-in markers * test: restore lost assertions in migrated test_main tests Restore the role alternation check in test_completion_anthropic_hanging, the embedding and streaming response-header checks, the logit_bias drop check and the gemini system and safety settings checks. Add an azure 429 retry-after test for test_exception_with_headers, trigger the router fallback with mock_timeout like the legacy test, and stop the mock timeout tests sleeping 3s * test: restore lost legacy assertions in migrated vertex ai unit tests * test: tighten migrated cost, streaming and embedding tests and scope the hosted mock guard * test: strengthen migrated anthropic, azure, bedrock and cohere provider tests Assert full request bodies and usage instead of presence checks, restore the dummy-tool and custom_llm_provider assertions the legacy tests made, add the async and per-model variants the legacy parametrization covered, split streamed tool arguments across deltas, and move the Azure chat streaming tests to the azure.py mirror file * test: tighten migrated llms provider tests and cover legacy intents lost in the move Strengthen the migrated fireworks, gemini, mistral, together, openai text completion, openrouter, perplexity and openai error tests so they assert what the legacy tests proved (cost, provider tag, usage-only-on-last-chunk, function_call rebuild, reasoning param, sync/async/stream error fields). Replace the huggingface and jina tests that doubled litellm code with respx end-to-end tests. Add the tests the pre-existing mapped tests never covered: cohere 400 mapping, token-array text completion, hosted_vllm/llamafile/lm_studio env api base embeddings, watsonx embedding auth, ollama ssl_verify client and ollama vision prompt * test: cover residual legacy paths for anthropic tool streams, watsonx async stream, ollama http images and caller async embedding clients * test: restore single request assertions in the deep_infra and azure_ai embedding tests * test: drop a no-op streaming cost flag from the openai streaming cost test * test: cover residual legacy-test lines in caching, main, utils, replicate, vertex and bedrock invoke * test: cover streamed audio assembly, choice membership, untranslated responses events and the stream log guard * test: pin cost rates in unit tests, use sdk for cohere e2e, drop vertex llama e2e * test: send the vertex maps e2e request through the openai sdk * test: drop the local_testing jobs that select no tests after the migrations * test: wait for the streamed cache entry and keep custom Mistral rates test-local * test: keep untouched Mistral test lines as they were --------- Co-authored-by: yuneng <yuneng@berri.ai> |
||
|
devin-ai-integration[bot]
|
0126c8db73
|
fix(sagemaker): keep AWS credentials out of the sagemaker_chat request body (#45724)
* fix(sagemaker): keep AWS credentials out of the sagemaker_chat request body sagemaker_chat and sagemaker_nova built the container body from every optional param, so aws_access_key_id, aws_secret_access_key, aws_session_token and the other aws_* auth params, plus model_id and sagemaker_base_url, were sent in the JSON body to the endpoint container. The request is still SigV4-signed with the same credentials, which stay in optional_params for signing * fix(sagemaker): limit the sagemaker_chat body filter to aws_ params model_id and sagemaker_base_url are not credentials, so they stay in the body as before and the change sticks to what the fix is about * test(sagemaker): assert the whole sagemaker_chat request body * fix(sagemaker): filter the sagemaker_chat body with the shared AWS auth param list * test(sagemaker): cover the sagemaker_chat body on every endpoint, credential source, and outage --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> |
||
|
yucheng-berri
|
cf8bc755a7
|
fix(vertex_ai): parse Vertex timestamps as UTC so created_at is not shifted by the host timezone (#45550)
* fix(vertex_ai): parse Vertex timestamps as UTC so created_at is not shifted by the host timezone convert_vertex_datetime_to_openai_datetime parsed the trailing-Z Vertex and GCS timestamps into a naive datetime, so .timestamp() read them as host local time and every created_at it produced was off by the host UTC offset (about 7h ahead on a PDT host). Attach UTC before converting, and accept the whole-second and nanosecond forms Google's RFC 3339 timestamps also use, which used to raise. Refs LIT-9383 * test(vertex_ai): type the UTC epoch test, guard tzset, build the rig config without mutation |
||
|
devin-ai-integration[bot]
|
25d9b05386
|
feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape (#45846)
* feat(sdk): add litellm.systemone and trim litellm.decisions to the OpenAI shape Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ci: run tests/unit/systemone in the core-utils unit shard Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(sdk): keep litellm.decisions(state=...) working with a DeprecationWarning Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: make tests/unit/systemone a package Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(sdk): surface the litellm.decisions(state=...) deprecation as a UserWarning Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry <kerry@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
dean-zavad
|
000b3685ed
|
fix(guardrails): guardrail Bedrock Converse stream text per content block (#45822)
* fix(guardrails): guardrail Bedrock Converse stream text per content block The buffered converse-stream guardrail joined every text delta of the same kind across all content blocks into one string, guardrailed it, then split the result back over the frames by length. When a guardrail edit changed the length (a mask), characters moved between blocks: text spilled from one text block into the next, and parallel toolUse inputs became invalid JSON. Group fragments per (contentBlockIndex, kind) so each block is guardrailed and written back on its own. * test(guardrails): run the Bedrock stream block tests through the real post-call hook Drive de_anonymize_event_stream with a real ProxyLogging and pass-through logging object, with a fake guardrail at the boundary, and assert the texts the guardrail receives as well as the frames the client gets back * test(guardrails): pin the logging start time in the Bedrock stream tests |
||
|
Soham Chatterjee
|
38bdda9ca7
|
feat(scaledown): add native text provider support (#44168)
* Add ScaleDown model pricing Registers the five ScaleDown models in the pricing map. ScaleDown bills on input tokens only, so output_cost_per_token is zero for every entry. The classify and decisions models bill at $0.04 per million input tokens, and extract, summarize, and compress bill at $0.05 per million. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * Price all ScaleDown models at $0.04 per million and drop unverified context limits Every ScaleDown model now bills $0.04 per million input tokens. The 32000-token max_input_tokens/max_output_tokens values were not confirmed against the service, so they are removed rather than registered. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Price all ScaleDown models at $0.05 per million input tokens This is the standard rate in ScaleDown's billing and matches the usage dashboard. The Decisions usage.cost field is not used for pricing. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Add regression tests for the ScaleDown pricing entries Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Cite the source of the ScaleDown rate in the pricing tests and type them Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Add ScaleDown as a chat provider ScaleDown serves five models over two wire protocols. extract, summarize, and compress speak OpenAI chat on /v1/chat/completions, while classify and decisions implement the Jev Decisions API on /v1/scaledown, taking a state object plus a questions map and returning one typed answer per question. The provider authenticates with x-api-key rather than a bearer token, and the decisions models need a non-chat request body, so it routes through the HTTP handler instead of the OpenAI passthrough. Malformed decisions requests are rejected locally with a message naming the problem, so callers do not have to decode an opaque 422 from upstream. Decisions bills one model call per question, so the cost upstream reports is passed through rather than re-estimated from token counts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * Route ScaleDown domain models to the native API and stop trusting usage.cost The /v1/chat/completions and /v1/models routes return 403 on api.scaledown.xyz, so extract, summarize and compress now call the native /extract, /summarization/abstractive and /compress/raw/ endpoints. The default api_base is the bare host; a trailing /v1 is stripped and re-added only for decisions. The Decisions usage.cost field was about 600x the dashboard amount, so it is no longer passed through; cost is computed from input tokens at the registered rate. Native responses are returned unchanged as JSON, including the _value/_span_anchor wrappers on nested extraction. They carry no output token count, so completion_tokens is reported as 0 and documented as unmeasured. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Move ScaleDown translation into llms/ and address review findings - Dispatch moves to llms/scaledown/chat/handler.py; main.py keeps a thin call and get_llm_provider_logic.py no longer has a ScaleDown branch, since the config resolves key and base URL itself. - questions passed via extra_body are merged and validated after the shared merge (sign_request), so the documented extra_body path works. - extra_body can no longer change the upstream model, and decisions state may carry a document but not text, so guardrails always see the text. - A custom api_base requires its own api_key; the environment key is only sent to the default host or SCALEDOWN_API_BASE. - Image content parts become the decisions document; max_completion_tokens maps to max_tokens; stream is served as one chunk for every model. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Refuse prompt-bearing extra_body keys and empty-key fallback to the env credential extra_body is merged after guardrails inspect the messages, so each model now accepts only option keys there (extract threshold/top_n, compress compression_rate, decisions questions/state); text, instructions, prompt, context and model are rejected. An empty api_key no longer lets the SCALEDOWN_API_KEY from the environment go to a custom api_base. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Read compress token usage from the real response shape /compress/raw/ nests the per-prompt counts under results and reports the total as a top-level input_tokens; the provider read a top-level original_prompt_tokens that is not there, so compress reported zero tokens and zero cost. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Accept the router's max_retries and word the extra_body error clearly The proxy adds max_retries to every call, which map_openai_params rejected, so every proxied ScaleDown request failed with a 400. It is now accepted and not forwarded. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Return extracted fields from extract, follow schema refs, and meet the type-discipline gate - extract content is now the extracted fields (span anchors dropped, wrappers unwrapped), so it validates against the caller's response_format; the raw payload stays on _hidden_params['scaledown_response']. - Local $ref/$defs in the response_format schema are resolved. - The adapter is rewritten with Final locals, read-only annotations, one raising helper and a typed handler; check_type_discipline reports no violations. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Fix stream_options, schema-guided extract cleaning, document input and multi-image handling - stream_options is accepted and not sent upstream, so include_usage streams work. - Extract output is cleaned against the requested entities, so a field named _value or *_span_anchor is no longer dropped. - Extract and summarize send an image or PDF as the native document fields. - More than one image is rejected instead of silently using the first. - The cost test derives its rate from the cost map. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Cut recursive schema refs at the cycle and cap the expanded entity count A small response_format schema with a self-referencing $def expanded to 4^16 leaves before any request was sent. Refs that point back into themselves are now cut off at that point, and the total expanded entities are capped at 1000 so repeated acyclic refs are rejected with a clear error. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * Bound ref chains and schema nesting so long schemas fail cleanly Resolving a chain of thousands of distinct $refs recursed until RecursionError. Ref resolution is now an iterative walk capped at 32 hops, and nested properties are capped at 32 levels; both raise a clear 400 instead. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> * fix(scaledown): support native classify and preserve extraction results * test(scaledown): include provider regressions in CI shard * fix(scaledown): pass registry typing and bounded recursion checks * docs(scaledown): capture provider setup before and after * fix(scaledown): preserve nullable schemas and reject malformed requests * fix(scaledown): isolate provider dispatch from existing providers * fix(scaledown): preserve the shared dispatch return contract * fix(scaledown): preserve failure logging and reject lossy schemas * fix(scaledown): keep timeout typing annotation on its expression * fix(scaledown): resolve escaped extraction schema references * fix(scaledown): annotate the bounded reference walk * chore(scaledown): remove unused loop suppression --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: moe-berri <moe@berri.ai> |