A body with large token-id lists and any s3:// string or file_id key made
the full walk build a node per number, taking seconds per request. The walk
and its prefilter now skip int, float, bool and None values.
(cherry picked from commit 57e73a8f7d)
A client AWS identity field does not prove that the caller can read the bucket. A
role or profile name picks credentials the proxy holds, and Bedrock reads the object
with them. So the bucket list now applies to every non-admin s3 media part, whatever
AWS identity fields the request sends. allow_client_side_credentials: true still
turns it off
This removes BaseAWSLLM.identity_choosing_params and the router lookup that only the
skip needed
Ported to lts/1.108.x
An admitted aws_role_name, aws_web_identity_token or aws_profile_name now skips the
bucket list only when it decides the credentials get_credentials picks, on every
deployment of the model group. A web identity token without a role and a session
name does not, since get_credentials then ignores it. A profile does not when the
deployment or the environment sets a role, since the role branch runs first. In
those cases Bedrock still reads with the proxy's credentials, so the bucket list
applies
BaseAWSLLM.identity_choosing_params mirrors the branch order of get_credentials, and
both read the same AWS_* environment fallbacks through one helper
Ported to lts/1.108.x, where the model group is read with Router.get_model_list
A tool result forwards a video to Bedrock only when it is an s3Location. An inline
base64 video is dropped with a warning, as it was before this change, since Converse
rejects video in a toolResult block
A non-admin key that sends an AWS identity its deployment admits through
configurable_clientside_auth_params (aws_role_name, aws_web_identity_token or
aws_profile_name) skips the bucket list, because Bedrock then reads the object with
that identity. The managed-prefix 403 still applies
The check now skips the body walk when no string starts with s3:// and no file_id or
model_file_id_mapping key is present, which keeps large image bodies cheap
Adapted for lts/1.108.x. The per-frame check on WS /v1/responses is not ported,
because this line has no Responses WebSocket frame guard to hook it into. The gate
keeps this line's admits_s3_bucket allowlist and its order of walking the body
before the admin role check
(cherry picked from commit 6662cb34d768bd68a7dc34ea27c363a1bd7f6578)
The s3 media gate refused every LiteLLM managed file id whose upload sits under the
managed prefix, even when the key's own user or team created it. It now asks the
managed files hook which unified ids the key may read and skips only the objects
those ids embed. A forged or unowned id, or a proxy without the hook, still gets a 403.
The gate also reads the provider file ids in a client-supplied model_file_id_mapping,
so an alias can no longer point a non-admin request at an unlisted or managed object.
Markdown documents (.md, .markdown) now map to Bedrock's md document format, so an
s3 Markdown source without an explicit format no longer fails with an unknown media type.
On lts/1.108.x the gate still walks the body before it reads the key role, so callers that pass a
specced UserAPIKeyAuth mock keep working, and it reads self.data and general_settings directly
since the line has no raw_request_fields.
(cherry picked from commit 37f085c966)
The s3:// bucket check now reads URL fields only inside the content parts
that a Bedrock transform turns into an S3 source, and it uses the same
s3:// test as the prompt factory. Values in metadata, annotations, tool
arguments and other fields pass as before. Each URL is named once in the
403 and 400 messages
Bedrock batch files refuse s3:// media only on the lines that go through
the Converse transform, so passthrough-provider lines upload unchanged
Backport to lts/1.108.x, adapted to the line. The line has no per-line
batch parser, so the per-record loop turns the Converse refusal into the
line error, and the old body check is gone
Cherry-picked from 2c23d2253a (litellm_bedrock_converse_s3_image_sources)
The s3:// media check now reads the whole request body instead of a fixed
list of fields, and it also reads the Gemini file_uri and fileUri keys. A
Bedrock batch input line with an s3:// media URL is a 400 before upload
that says "LiteLLM does not accept s3:// media URLs in Bedrock batch
files", since Bedrock batch files do not take s3:// media URLs yet.
Backport to lts/1.108.x, adapted to the line. The line has no per-line
batch parser, so the batch check runs at the top of the per-record loop
that every Bedrock batch entry point shares.
Cherry-picked from d437577e3d and b089fb9f90 (litellm_bedrock_converse_s3_image_sources).
A non-admin key may only send an s3:// media URL whose bucket is listed in
general_settings.allowed_client_side_s3_buckets (or when client-side
credentials are allowed), and never one under litellm's managed prefixes.
Proxy admins are not limited. A bucket_owner on an s3:// URL that is not a
non-empty string is a 400, the Responses bridge forwards the owner only for
s3:// URLs, audio on S3 is a 400, and video in a tool result is sent to Bedrock.
Backport to lts/1.108.x, adapted to the line.
Cherry-picked from 2c7b965ff4 (litellm_bedrock_converse_s3_image_sources).
* fix(proxy): bill partial Responses API streams when the client disconnects
Streamed /v1/responses requests and the default-route OpenAI and Azure /v1/messages requests behind them logged a 499 with zero spend when the client went away mid-stream, while /v1/chat/completions already billed the chunks it had sent. The Responses API iterator now keeps the response.created payload and can hand the disconnect cleanup a response.incomplete event with counted usage and the served service_tier, and the messages-route byte stream and router wrappers delegate to it.
* fix(proxy): satisfy lint gates for partial Responses API disconnect billing
Make the disconnect helper public so the proxy, router and messages adapter can import it without reportPrivateUsage, type the SSE byte stream as an AsyncGenerator so aclose is known, read litellm_call_id off the logging object, and keep the new tests on Final locals with the recorder injected through dynamic_async_success_callbacks instead of litellm.callbacks.
* fix(router): bill the primary stream's tokens after a mid-stream hop and chat-bridge Responses streams on disconnect
The router's fallback wrapper now folds the primary Responses stream's relayed tokens into the fallback's disconnect event the way _combine_responses_fallback_usage does for a natural end of stream, and LiteLLMCompletionStreamingIterator (chat-only providers served through /v1/responses) builds its disconnect event from the chat completion chunks it collected. stamp_responses_usage_cost is now public so the bridge module can price that event.
* Potential fix for pull request finding 'CodeQL / Log Injection'
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
(cherry picked from commit f0ae445cc4)
* fix(bedrock)!: stream Converse passthrough frames through post_call guardrails instead of buffering (#46307)
* test(integration): Converse stream post_call guardrail relays frames as they arrive (LIT-9515)
* fix(bedrock): stream Converse passthrough frames through post_call guardrails instead of buffering (LIT-9515)
A post_call guardrail that scans through apply_guardrail now runs on
/bedrock/.../converse-stream the way it runs on /v1/messages: frames reach the
caller as the upstream sends them, every fifth frame and the end of the stream
are scanned, and a block after the first frame ends the stream with an AWS
exception frame. streaming_buffer_until_moderated still holds the stream and
applies masks per content block. Guardrails that need the whole response
(own async_post_call_success_hook, mask_response_content, native hooks, policy
pipelines) keep the buffered path.
* fix(bedrock): apply held Converse stream masks when the upstream ends with an exception frame (LIT-9515)
* fix(proxy): log a relayed passthrough stream's spend before its mid-stream failure hook (LIT-9515)
* fix(bedrock): close and report every way a relayed Converse stream ends (LIT-9515)
- The framer ends the stream with an empty item once the upstream closes, so held masks are applied whether the
upstream ends with messageStop, an exception or error frame, or a dropped connection
- A guardrail HTTPException after the first frame reaches the relay, which logs the stream's spend, runs the
failure hook and ends the stream with the exception frame, instead of ending inside the guardrail with no
failure row
- A failure before the first frame waits for the stream's spend to be logged, as a mid-stream failure does
- Closing the response before its body starts closes the guardrail layers and the upstream
- Each stacked guardrail layer gets its own copy of every frame, so an earlier layer's end-of-stream rewrite never
reaches frames a later layer still holds
- Deltas whose text ends in half a surrogate pair are decoded with the standard JSON parser
* fix(bedrock): relay a Converse frame whose payload is not UTF-8 instead of ending the stream (LIT-9515)
* test(integration): cover Converse stream relay failure, end-of-stream-only, stacked, disconnect and burst cells (LIT-9515)
* fix(bedrock): estimate prompt tokens for a passthrough stream cut before Bedrock reports usage (LIT-9515)
Bedrock sends usage only in the last frame of a stream, so a stream ended by a guardrail block or a client
disconnect logged 0 prompt tokens while AWS still charges for the prompt. The stream collector now estimates them
from the request the way chat completions streams do
* fix(bedrock): read tool result blocks without recursion in the passthrough prompt estimate (LIT-9515)
* fix(passthrough): keep the spend flush running when the wait for it is cancelled (LIT-9515)
* fix(bedrock): keep a converse-stream buffered when its guardrail releases a held stream on scan (LIT-9515)
A held post_call guardrail with streaming_buffer_release_on_scan releases each
window as received once its scan passes, so the relay delivered the original
text instead of the guardrail's masks. Such a stream keeps the buffered path,
which applies masks per content block as on main.
* fix(bedrock): keep a converse-stream buffered when a post_call guardrail runs in parallel (LIT-9515)
The relay ran every guardrail in config order, so a run_in_parallel guardrail
listed before a masking guardrail scanned the unmasked text. Main's buffered
path runs parallel guardrails after the sequential ones and discards their
rewrites, which the relay cannot reproduce, so these streams stay buffered
* fix(bedrock): mark Noma v2 relay scans like chat and stop reading Bedrock when a held stream's client leaves
- Noma v2 scans on the converse-stream relay carry stream, and the last one
carries the finished Converse response with its stopReason, as chat sends
them, so Noma keeps one record per reply. Other guardrails get the request
unchanged. When the last sampled scan already covered the whole answer, the
end-of-stream scan still runs for Noma so it gets the finished answer
- A held relay stream whose client leaves before the first frame stops
reading Bedrock and returns 499, like chat. When Bedrock sent nothing yet,
the budget reservation and the parallel-request slot are released
- A cancelled wait for the first streamed chunk now stops the upstream read
instead of leaving it running
- A Noma v2 scan cancelled before Noma answers records not_run instead of
success with an empty response
* fix(bedrock): send Noma the finished Converse reply's tool calls and reasoning as Converse blocks
* fix(bedrock): give Noma the ended scan of a Converse reply that only calls a tool without input
* test(bedrock): expect the ValidationException main now returns for a held block before the first frame
Main's AWS-shaped passthrough errors (#46522) answer a guardrail block before the first frame with x-amzn-errortype ValidationException, so boto3 reads the code and the guardrail message instead of a bare 400.
* fix(bedrock): keep held masks when an earlier sampled guardrail ends the Converse stream with its message
A sampled guardrail that blocks with disable_exception_on_block ends the stream with its message as raw
event-stream bytes. A held guardrail after it on the same key only read frame objects, so it never saw the
messageStop, skipped its write-back and released the held text without its masks. The Converse handler now
reads those bytes back into frames, so the held guardrail sees the end of the message and masks the text
* fix(proxy): free the parallel slot when a caller leaves a Converse relay holding part of the first frame
The relay skipped releasing the slot and budget reservation whenever a spend
flush was scheduled, but a flush of a partial first frame builds no response
and logs nothing, so the slot stayed held until it expired. The flush now says
whether it logged the stream.
---------
Backport of #46307 to rc/1.107.0
Cherry-picked from ef1cb19351 (main)
Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
* fix(bedrock)!: scan Claude invoke-with-response-stream passthrough output with post_call guardrails (#46524)
* fix(bedrock): scan Claude invoke-with-response-stream passthrough frames with post_call guardrails (LIT-9618)
Invoke streams of Claude models now go through the same frame-by-frame relay as
converse-stream. Each chunk frame's Anthropic event is scanned by the /v1/messages
stream translation, a block ends the stream with an AWS exception frame, and a held
stream gets its masks written back into re-encoded chunk frames. Claude is told by
its model id or, behind an application inference profile, by the anthropic_version
its request body carries. Streams of other model families stay as they were
* test(bedrock): cover invoke stream vendor outage, upstream exception and release on scan (LIT-9618)
* fix(bedrock): hold Claude invoke streams for guardrails the relay cannot run and mark each scan as streaming (LIT-9618)
A guardrail released on scan or run in parallel left a Claude invoke-with-response-stream unscanned, while
converse-stream holds the whole stream and scans it once. Claude invoke streams now take the same buffered
path, with the rewrites written back into the chunk frames that carried each text.
Each invoke scan also sends stream true and the events relayed so far as responses, as /v1/messages does,
so a vendor can tie the scans of one streamed reply together.
* refactor(bedrock): mark the request dicts the buffered stream paths hand to post_call hooks (LIT-9618)
* fix(bedrock): scan a Claude invoke stream the upstream breaks off as a finished stream (LIT-9618)
An invoke stream that ended on an upstream exception, without a message_delta stop_reason, was scanned
as still in flight, so its tool input never reached the guardrail and a held stream released it unscanned.
The scan and its scan key now close such a stream the way converse-stream treats the end of its upstream.
* test(bedrock): pass the converse-stream endpoint where the tool call without input test frames its stream (LIT-9618)
* test(bedrock): expect the ValidationException main now returns when a guardrail blocks a Claude invoke stream before its first frame (LIT-9618)
* test(bedrock): type the Claude invoke event helpers in the passthrough guardrail tests
* test(bedrock): type the remaining parameters of the Claude invoke stream tests
* refactor(bedrock): bind the buffered invoke rewrite in its condition
---------
Backport of #46524 to rc/1.107.0
Cherry-picked from 9f115be88d (main)
Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
---------
Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
* fix(router): carry a 429 status on cooldown and no-deployment errors
RouterRateLimitError and RouterRateLimitErrorBasic had no status_code, so the
proxy answered an all-deployments-cooled-down request as a generic 500 class
error and logged the bug report notice for every cooldown. Both now carry
status_code 429, which the proxy maps to a rate_limit_error and which the
retry policy already treats as retryable
* fix(proxy): start Sentry at config load and never attach request bodies
Sentry only came up inside set_callbacks on the first LLM call, so boot and
background errors were never reported, and general_settings.alerting: [sentry]
always raised Missing SENTRY_DSN because the alerting path read a dead
litellm.utils pin instead of the live SDK. The proxy now initializes Sentry
once while loading the config whenever sentry is a configured callback or
alerting target, the alerting and failure handlers read the live instance, and
max_request_body_size is pinned to never so prompts and completions stay out
of Sentry events
* fix(tracing): log Lens failures at ERROR and export row counters to Prometheus
A tracing store that fails to start, or a Lens service that rejects a batch,
was only logged at WARNING, so operators running at the default ERROR level
never saw tracing silently go dark. Both now log at ERROR and name the lens
store. The exporter's rows_written and rows_dropped tallies were never
exported, so the two counts are now Prometheus counters
litellm_lens_export_rows_written_total and
litellm_lens_export_rows_dropped_total, registered lazily on the default
registry like the other proxy-level counters and charted on the all-metrics
Grafana dashboard
* test(proxy): drop the litellm import the alerting tests no longer use
* fix(proxy): start Sentry once a DSN is set, from any config source
Boot-time init used to lock Sentry in even with no SENTRY_DSN, so a DSN loaded later from DB environment_variables was never picked up. initialize_sentry now skips when no DSN is set and re-inits when the DSN changes. alerting_handler calls it too, so alerting: [sentry] set through the DB works. Drops the litellm_settings.callbacks check since that config fails to load with sentry in it
* fix(sentry): keep stack frame locals out of events unless PII is opted in
Frame locals carried prompts (messages, request bodies, provider options) into every error event. include_local_variables now follows SENTRY_SEND_DEFAULT_PII
* test(router): drop the test that only pinned the 429 class attribute
* fix(proxy): start Sentry at boot when it is only an input callback
* fix(proxy): keep Sentry init and alerting within the strict ruff and basedpyright ceilings
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
* fix(cost): price bridged /v1/messages reasoning tokens from the chat completion, not the served Anthropic body
* fix(cost): keep the type gate flat for the bridged /v1/messages billing path
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(vertex_ai): route Model Garden models through the generateContent adapter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(vertex_ai): annotate generateContent route test parameters
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(vertex_ai): type litellm_params in get_vertex_ai_model_route
* fix(vertex_ai): bill and log Model Garden generateContent calls like chat completions
Streamed Model Garden calls through the generateContent adapter now request
stream usage where the deployment supports it, keep cached-token details, and
look up the provider-relative cost key, so they bill like the non-stream call.
The adapter forwards router metadata, passes upstream errors through with their
status, countTokens falls back to local counting for non-Gemini routes, and the
native Gemini config is limited to the Gemini routes.
* fix(google_genai): keep adapter stream usage, admin opt-out, single failure count, and base_model routing
Streamed generateContent through the chat adapter now ends with the upstream usage, honors
always_include_stream_usage false and the caller's stream_options, counts one failure per
failed call, and routes Vertex deployments by their base_model like chat does
* fix(google_genai): ask for stream usage on every adapter stream so Claude streams end with usage
* test(google_genai): expect the trailing usage chunk on bridged OpenAI streams
The OpenAI bridge test now sends the usage chunk OpenAI returns for include_usage and expects it translated into usageMetadata. The response_format support helper goes back to its single-purpose form since its only other caller is gone.
* fix(google_genai): end adapter streams with one STOP event carrying usage, and keep upstream usage after the finish chunk
* fix(google_genai): send the held STOP event when no usage arrives, keep a caller's stream_options, and route countTokens like generateContent
* test(integration): cover the moved Vertex routes, adapter stream usage, the shared iterator and usage settings over the wire
* test(integration): add cache-hit twins for the stream usage setting and non-stream cells for every iterator member
---------
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(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>
* 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>
* 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>
(cherry picked from commit b4f9e14a44)
* 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>
(cherry picked from commit 819faa01c3)
* 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>
(cherry picked from commit b224b15b9d)
* refactor(router): aggregate model group description without in-place mutation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 342b93fe0a)
* test(dd_span_tagger): assert the user_email tag on the active span instead of on the patched setter
The two ported tests only inspected the mock that replaced the tag setter, which the test quality gate counts as two new mock-echo tests over main. They now read the tags that land on the active span
* refactor(router): read the model group description through the typed model_info reader
The ported lookup read model_info off the untyped deployment dict, which added three basedpyright errors over main. It now goes through the existing validated model_info reader
---------
Co-authored-by: milan <milan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
* fix(proxy): let admins make per-model key/team rate limits a hard 429 instead of falling back
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): sync per-model rate limit API types
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): type per-model fallback setting access
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep the per-model hard cap inside the fallback loop and test it through the real limiter
* fix(proxy): list the per-model hard cap setting on the settings page and cover every per-model descriptor
* fix(proxy): read disable_fallbacks_on_per_model_rate_limits as a boolean value and cover the team-wide per-model cap
* test(proxy): cover per-model rate limit 429s skipping fallbacks on a live proxy
---------
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(proxy): keep the mapped status on assistants and threads route errors
* test(proxy): type and annotate the assistants and threads route error tests
* fix(proxy): redact internal details from assistants and threads route error messages
* test(proxy): integration cells for assistants route error mapping
* test(proxy): drop malformed JSON cases that never reach the assistants route handler
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* refactor(proxy): expose public names for private proxy helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep original class names behind public aliases
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): preserve internal callback filtering
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep _PROXY_ class names for managed files hooks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep old private names in package exports
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): preserve recursive auth helper name
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): align MCP limiter tests with server enforcement
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): match main's MCP limiter tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep old private names bound in importing modules
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): preserve compatibility imports through strict lint
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): use exact pyright suppression in password helper test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): add reasons to compatibility import noqa comments
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): update IN-list baseline for renamed helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): run end-of-stream post_call scan when the client disconnects mid-stream
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): close the guardrail stream chain in async_data_generator on client disconnect
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): leave the raw upstream response to the shielded finalizer on client disconnect
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep disconnect cleanup going when a streaming callback cleanup raises
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): assert the refund through a recorder instead of the mock
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): inspect tool calls released before a disconnect under incremental_diff and record a failed scan marker
The incremental_diff transform stream now scans tool calls it already released when the client disconnects, and a disconnect scan whose translation raises after the guardrail recorded success also records guardrail_failed_to_respond
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): pin that a text-only disconnect scan is not handed a tool_calls finish
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): cover disconnect scans on every streaming endpoint and client, plus outage, worker-kill and cache-hit cells
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): prove the cache-hit twin is served from the cache
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): type the disconnect-close streams so basedpyright stops reporting unknown arguments
* fix(guardrails): give the guardrail metadata cast a reason so the type discipline gate accepts it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): scan released Messages and Responses tool calls on disconnect
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(guardrails): format the disconnect scan unit tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(guardrails): drop mutable-ok markers that no longer suppress a rule
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): scan released Responses output after a finished item and end only in-flight Chat choices
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): type the disconnect scan test helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(guardrails): type request_data in the disconnect scan helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): type request_data in the disconnect scan test doubles
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): pin that chat streams with no tool call in flight end as released
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): scan only released chunks on disconnect and skip it once a block owns the verdict
The disconnect scan now uses the chunks actually yielded to the client, copies them before scanning,
skips when a mid-stream block or HTTP error already settled the verdict, and the iterator wrapper
only closes hooks that are async generators so plain async iterator hooks keep working
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(guardrails): pin that a delivered guardrail error or final chunk settles the disconnect verdict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): close any hook iterator that exposes aclose when the stream ends early
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): accept a synchronous aclose on custom streaming hook iterators
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): swallow callback aclose errors at end of stream
A custom callback whose async_post_call_streaming_iterator_hook returns a
non-generator async iterator with a raising aclose() failed the finished
stream: content plus usage reached the client and then the stream surfaced
an error SSE with no [DONE], or aborted a post_call pipeline's buffering
loop into a 500 with an empty body. Wrap the aclose invocation in
_wrap_streaming_iterator_with_enrichment in try/except and log a warning
naming the callback and the cleanup error, matching close_guarded_stream
and _close_guarded_layers. Iteration-time hook exceptions still propagate.
* fix(proxy): log only the error type when a callback aclose raises
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
