A model id on anthropic or bedrock that doesn't name Claude is translated only when base_model names Claude, so an
Anthropic-compatible non-Claude model keeps its old behavior. The four-mark count skips a message-level mark on list
content and a function mark under a marked tool, since neither reaches Claude. A null tool-level breakpoint no longer
hides the function breakpoint. The ttl order check finds the first 5m and last 1h mark once instead of per mark. The
router's prompt caching check reads prompt_cache_breakpoint as a cache mark and hashes blocks without it.
Drain the worker's fake-upstream request log when a test's gateway fixture starts, so traffic left by earlier tests on the same xdist worker no longer shows up in a test's first observation read
Generate the fine-tuning rig's provider file and job ids per fixture build, so a rebuilt module fixture in the same worker no longer collides on the managed object unique constraint
Wait for every wedged team_id and team_alias invalidation publish to fail before taking the recovery marker, now that team updates publish both keys
Pin the cooled-down priority scheduler request to the connection that observed the cooldown, since a sibling worker reads cooldowns from Redis on an interval
Simulate upstream outages and the held budget peer on ports the test keeps owning, instead of releasing a port another worker can bind
Start a peer proxy for the accounting group, which has a test that needs one
* 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
Under drop_params only translated breakpoints are dropped past the cap, earliest first in Claude's read order. A breakpoint with no ttl ahead of a 1h mark goes out as 1h, and under drop_params a client ttl that breaks the order is dropped. A Bedrock model id that does not name Claude is translated only when base_model names Claude.
* fix(proxy): check previous_response_id ownership on /v1/responses/compact
* test(proxy): cover the unmanaged response id escape hatches on every response id route
* test(proxy): audit compact previous_response_id ownership
Add integration cells for the native /v1/responses/compact routes covering owner,
admin, cross-tenant, unmanaged, malformed, duplicated and retained ids, provider
errors, the response cache, id-security settings, an upstream outage, a held
upstream, a worker kill and a proxy restart. Unskip the provider wire cell whose
bug this branch fixes.
* test(proxy): cover the no signing key path on every response id route
* fix: lower aiohttp keepalive timeout
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(http): restore the 15s keep-alive default and apply it to the Rust client
15s is aiohttp's own default and what every release before v1.78.0 used. The Rust HTTP client reads the same AIOHTTP_KEEPALIVE_TIMEOUT variable, so its default moves with it.
* test(integration): cover upstream connections dropped after the keep-alive idle window
---------
Co-authored-by: nate <nate@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* 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>
This PR now only carries prompt_cache_breakpoint to Claude cache_control on chat completions. The gpt-4.1 drop_params strip is #46453 and prompt_cache_options lands in a stacked follow-up
* 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
Bedrock Converse reads only a tool's top-level cache_control, so a breakpoint written under function was dropped there. It now becomes the tool's top-level mark on every Claude route, unless the client already marked the function
Replaces the per-transform census with one step in completion() for every Claude chat route.
Breakpoints become cache_control on the same block. A ttl Claude lacks is a 400 naming drop_params,
or dropped with the mark kept under drop_params. prompt_cache_options with mode implicit turns on
Claude automatic caching where the route has it and is a 400 on Converse. With drop_params, more
than four marks keep the latest four. Without it they reach Claude, which answers itself
* 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>
prompt_cache_options sent through extra_body skipped the drop_params rule on the
routes that merge extra_body into the Claude body (Bedrock Invoke, Bedrock Claude
Platform, Azure AI, Databricks Claude), so Bedrock rejected it with its own 400.
AnthropicConfig.transform_extra_body now applies the same rule, and Databricks only
applies it to Claude models.
Converse now gates the rename, the cap and the prompt_cache_options rule on whether
the model takes cachePoint blocks, so an application inference profile ARN gets
cache points, and a model without cachePoint support gets the request as written.
prompt_cache_options is now a refusal value from claude_cache_marks next to the cap
refusal, mapped to the public exception in one place. assert_never comes from
typing_extensions so the module imports on Python 3.10. is_cache_control_set is back
to main since no header depends on it, and unmarked tools reach _map_tools as on main.
* 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>
* 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>
* 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>
* test(integration): cover assistants_evals endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(tests): replace exception assertions flagged by ruff
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(openai): type assistant run options
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(unit): cover assistant and eval contract paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(openai): keep assistant run options unvalidated
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): pin assistants and evals wire contracts as BUG skips
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover every eval route, full responses, image parts and full SDK stream payloads
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): relay upstream eval run model, send reasoning_effort, cover SDK root alias, done frame and client disconnect
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): name reasoning_effort in the run BUG skip
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): use a non-null marker thread and name the eval run model restamp in its BUG skip
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): mark disconnect cases with a messages.create the proxy relays on main
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(assistants_evals): cover thread message shapes, raw run options, header leaks and /v1 eval bases
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): expect the OpenAI /cancel path for eval run cancel
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
* test(integration): cover responses endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): tighten responses contract tests per review
Isolate team-only response-id ownership with a same-user different-team key,
send every denial through the OpenAI SDK on all three aliases, make the
previous_response_id affinity check deterministic, assert the whole cancel
response, prove the Cursor stream text, -fast suffixes and include_obfuscation
strip, add SDK compact cases, restore router pre-call checks after the
affinity test, and inline the root-level responses_test_support helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): wait for every proxy worker before routing to new deployments
Restore the cross-worker convergence wait dropped when the shared helper was
inlined, so the affinity and retrieve-routing tests cannot pass before the
alternative deployment is loaded on a multi-worker gateway
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover Responses ownership and wire contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): address responses contract review
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): expect the provider model in the conversation passthrough body
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): expand responses endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): restore streamed response retrieval
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): wait for proxy workers after deployment setup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): track readiness per proxy worker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
* test(integration): cover files_batches endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): split raw cloud-storage delete test by caller
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop mutable polling state in content download test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): dispatch request spellings without rebinding
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): import assert_never from typing_extensions for python 3.10
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): tighten files_batches wire and access assertions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): tidy files_batches access tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover repeated target models, upload expiry, batch aliases
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): prove files streaming path, SDK model denial and admin GCS delete
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): give the streaming head the wire barrier's full budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: strengthen files and batches wire coverage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: drop duplicate parametrize from the model-routed upload helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: pass the SDK base url in the skipped repeated-plain upload test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): allow batch output metadata lookup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: avoid draining file content requests before wait
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
Converse emits one cachePoint per tool message and ignores a cache_control under a tool's function, so the
Claude 4-check now counts sites per wire and a dropped tool-message slot clears every mark on that message.
The Converse breakpoint rename, prompt_cache_options check and cap now apply to Claude models only, so Nova
and other Converse models keep forwarding prompt_cache_options as before. Also freezes the e2e
PromptCacheBreakpoint model and covers a block carrying both keys on every Claude route.
* test(integration): cover vector_stores endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): strengthen vector store route contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): update vector store route contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop owner-update BUG skip for admin-only vector store routes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(vector_stores): cover the managed-file fallback, owner delete and per-request retries
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): probe vector store worker readiness by deployment id
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): pin vector store retry header and create routings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(integration): ruff format vector store managed file tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
* test(integration): cover realtime endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): reject duplicate multipart parts and cover the transcription_sessions alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the type ignore and check the aliased transcription response
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): pin realtime multipart part types, replayed transcription session, undeclared session fields and budget refusal path
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): move the refusal path note next to the expected message
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): assert realtime refusal status before parsing and pin the replayed transcription session whole
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): sort the realtime webrtc test imports
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): pick the transcription mint and token with one Final each
* test(integration): pin realtime transcription mint, replay, and redeem contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(integration): ruff format the realtime webrtc test
* test(integration): drop the redundant comment on the realtime SDK calls test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): type the realtime client secret refusals table
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(realtime): tighten endpoint contract assertions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
* test(integration): cover chat_completions endpoint contracts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): pin per-call prompts and both n=2 chat choices
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover mixed path-model auth, string guardrail rejection and typed text-completion forms
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the prompt-spellings cache workaround and cover Azure SDK text completions on the deployments alias
---------
Co-authored-by: mateo <mateo@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Unit tests for the block-level rename, the wire-order cap, the drop_params sources, prompt_cache_options rejection and the untouched native cache_control path on the Anthropic, Vertex AI, Bedrock invoke, Bedrock Converse and Azure AI transforms, plus a providers wire test that drives all five routes through a live proxy against scripted peers, including a proxy started with litellm_settings drop_params
* 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>
* 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.
* 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
Each test below passed or failed on the same commit depending on test order
or port timing in the CircleCI integration workflow
- readiness probe only polls a port the launched proxy owns, so a stolen
port no longer sends GET /health/integration-readiness to another test's
wire server
- team update tests seed fresh member users, since a proxy admin relocation
adds team members to the destination org and leaked org_b membership into
the shared INTERNAL_USER
- realtime whisper tests wait until every proxy worker serves only the new
gpt-realtime-whisper deployment, via a per-worker deployment id route
- configured fallbacks test runs on its own proxy and database, because
/config/update persists router settings and cannot unset fallbacks, which
left [] and changed the no-fallback error text other tests assert
- otel excluded services tests each get a private Redis so a sibling proxy
cannot warm the budget registry cache the tenant span depends on
- Langfuse audit upstream uses unique response ids instead of len(targets),
which could repeat under concurrency and drop SpendLogs rows
* test(responses): pin bridged commentary plus final answer as one chat choice
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(responses): pin reasoning, two-message and two-tool-call bridge shapes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): number bridged chat tool calls 0, 1 instead of all 0
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>
* fix(responses): fold bridged Responses output into one chat choice
A Chat Completions request bridged to /responses got one choice per
Responses message item, so a reply shaped [message, message,
function_call] put the tool call on choices[1] and clients reading
only choices[0] never saw it. Fold every message text, annotation,
reasoning item and tool call into choices[0]
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): drop mutable annotations and the extra cast in the choice fold
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): remove a cast-ok marker that suppressed nothing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): join folded message texts with a newline
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* revert(responses): join folded message texts with no separator so stream and non-stream match
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>
* 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>
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
* 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>
* 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>
* 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>
* 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>
* feat(fireworks_ai): add Decisions support for accounts/fireworks/routers/rune on /v1/systemone and /v1/decisions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(fireworks_ai): point the rune cost row at the public Fireworks docs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(decisions): patch litellm.callbacks with monkeypatch in the Fireworks cached-cost test
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>
* test(integration): give chaos and timing tests a harness API and gate raw signals
Chaos tests killed and suspended proxy workers with raw os.kill and psutil
calls and bounded elapsed time with fixed literals, so they raced the uvicorn
worker healthcheck and failed on slow CI boxes
OwnedProxy now offers kill_worker and replacing_worker, which return only once
a replacement answers readiness with its own pid, and suspended, which is
refused unless the proxy was launched with a lenient worker healthcheck.
timing.py bounds durations against a measured control or the injected delay.
run.py measures the proxy import time once and derives readiness deadlines and
the per-test timeout from it, writing boot-calibration.json
check_test_quality.py adds TQ010 (raw process signals) and TQ011 (elapsed time
asserted under a numeric literal) for tests/integration outside _support, and
every call site is migrated so both report zero with no suppressions
* test(integration): steer the assistants wire burst onto both workers
The mixed-status burst assumed the OS would spread 48 connections across both workers and failed when one worker took them all. Each half is now sent while the other worker is suspended, and the test asserts an exact 24 and 24 split
* test(integration): restore product-enforced timing bounds lost in the migration
Some TQ011 migrations dropped or loosened a bound whose time is the behaviour
under test. The websocket session cap only kept its floor, so a cap closing at
300 s would have passed, and several timeouts were bounded by the injected stall
instead of the configured product value
assert_enforced_within bounds an elapsed time by the configured value plus
explicit slack, with an optional floor. The websocket cap, the MCP validation
timeout, the guardrail litellm_params timeout, the prisma command timeouts, the
baseline projection lock timeout and the key metadata statement timeout use it.
The device code refusal keeps its 15 s margin, and the langfuse retried prompt
fetch is now bounded by a cold fetch of a steady prompt as well as by the
ignored retry-after
* fix(tests): wait for the supervisor to reap killed workers and fix real-kill migrations
The lenient worker healthcheck was the whole case budget, so uvicorn's supervisor sat
in a ping on the killed worker for up to that long before respawning it. It now uses
the graceful stop budget, and a worker kill returns only after the victim is reaped,
so pooled connections no longer race the dead worker's socket.
Several tests on main picked the multiprocessing resource tracker as their victim and
never killed a worker. Now that they kill a real one, presidio counts streams cut by
the death, delete_model waits for the config reload that removes a deleted model from
a replacement worker, and the wedged coordination Redis test kills before the wedge
and waits for every parked publish to fail before resuming Redis.
The redis cluster test imports the harness through the tests package so it collects
in the unit job, and the per-model fallback rig exposes the owned proxy it now needs.
* test(observability): only require S3 deliveries the killed worker could not have buffered
A real SIGKILL drops the victim's unflushed batch, so requests it already answered can't be expected to land. The test now requires every request served after the replacement to land, some of the surviving worker's burst share to land, and nothing unsent to land
---------
Co-authored-by: Yuneng Jiang <yuneng@berri.ai>
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.
