* fix(anthropic): send /v1/messages PDF documents to OpenAI-shaped providers as file parts
* refactor(anthropic): hold the chat completions document change for a later commit
* fix(anthropic): send /v1/messages PDFs as file parts and keep file parts on azure_ai
* fix(snowflake): turn file parts into document blocks for Cortex Claude
* fix(prompt_security): sanitize chat file parts that carry file_data
* fix: answer 400 or drop PDFs for models that cannot read them
Models whose model_info or cost map entry sets supports_pdf_input to
false, and Ollama, now get the PDF dropped under drop_params and a 400
from litellm without it. GigaChat uploads file parts, SAP keeps sending
them as image_url data URLs, azure_ai passes dict content through, and
annotations other than url_citation move to provider_specific_fields
instead of failing the response.
* fix(router): scope supports_pdf_input to its deployment and keep provider annotation keys
Mark the azure_ai chat models in the cost map that cannot read PDFs, so drop_params drops the PDF and
litellm answers its own 400 without it. Keep url_citation annotations whole, move only typed provider
annotations to provider_specific_fields, and split them the same way when a stream is rebuilt.
* fix(vertex_ai): send PDF file parts to Vertex partner models as image_url
Vertex AI's OpenAI-compatible partner endpoint rejects the chat `file` part, so PDFs from /v1/messages
reach those models as the image_url data URL they took before. Mark native DeepSeek chat models as
unable to read PDFs, and treat a file part as a PDF by its format or filename when it has no data URL.
* fix(cost-map): leave native DeepSeek PDF support unset
/v1/messages reaches native DeepSeek through its own Anthropic endpoint, so the marks never applied there
and would only change chat completions, which this PR does not otherwise touch.
* fix(main): drop a user turn that held only a PDF under drop_params
Dropping the PDF from a PDF-only user turn left an empty content list, which
Foundry and OpenAI-shaped providers reject with a 400, so drop_params still
failed for that request. The emptied user turn is now removed.
* fix: read OCI PDFs, gate deployment base models, and stop empty drops
OCI generic chat sends file parts as image data URLs again, so OCI Gemini
keeps reading PDFs from /v1/messages and chat file parts.
The PDF gate now reads model_info.base_model, drops PDFs under drop_params
for azure_ai deployments that never declared PDF support (the old flattening
behavior), and answers 400 when dropping the PDF leaves no user message.
The cost map marks the Vertex partner text models that a live probe showed
answering without reading the PDF.
* test(integration): cover the PDF input gate, messages PDF file parts and provider annotations
Wire cells for the supports_pdf_input check on chat, chat streaming, /v1/messages and the Responses bridge, its model_info, base_model, cost map and Ollama sources, drop_params at deployment and request level, azure_ai file parts, sibling deployment isolation, Anthropic SDK PDFs reaching azure as titled file parts, Gemini and Bedrock document controls, Prompt Security sanitizing a /v1/messages PDF, and OpenRouter file annotations live, cached and streamed
* test(integration): cover Snowflake Claude and SAP in the messages PDF wire cells
* fix(azure_ai): flatten non-PDF file parts to text as before and cover the GigaChat PDF upload
* fix(main): PDF check reads the deployment's top-level base_model
* fix(main): keep roles alternating after drop_params removes a PDF-only turn
When ensure_alternating_roles is set, re-run role normalization on the messages left after the PDF check drops a turn, so two assistant turns never end up next to each other
* test: type the PDF and annotation tests the PR added
* test: type the GigaChat, SAP and Snowflake PDF tests
* fix(github_copilot): treat a malformed api-key.json like a missing one
* fix(github_copilot): read the key and the endpoints of api-key.json as separate strict views
* fix(github_copilot): ignore a non-UTF-8 api-key.json like any other malformed file
Read the cached key file as bytes so a UTF-16 file, which Windows
PowerShell 5.1 writes with >, fails JSON validation instead of raising
the decoder's error, and the request gets the refresh or the login hint
* fix(github_copilot): decode UTF-16 key files and refresh over a malformed endpoints field
* fix(github_copilot): decode a UTF-16 access-token file and refuse an undecodable one like a missing one
* fix(github_copilot): use the refreshed key when api-key.json cannot be written
* fix(github_copilot): keep a refreshed key that cannot be saved in memory
* fix(github_copilot): serve a kept key and its endpoint together after the key file is repaired
A key held in memory is now checked before api-key.json, so the token and the endpoint come from the same source, and the map holds one entry per key file with the access token beside it
* test(github_copilot): type the authenticator test fixture and the tests this branch adds
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(gemini): use collection endpoint for custom context cache
* fix(vertex_ai): build the cachedContents collection URL under a custom api_base
* fix(vertex_ai): keep a gateway prefix that contains /publishers/
* test(integration): expect the cachedContents collection URL on a custom Gemini api_base
* fix(vertex_ai): cut cache collection URLs at the base's location, graft a mount prefix
* fix(vertex_ai): cache under a publisher model api_base in that model's location
A Vertex AI api_base that names an endpoint or no model keeps its old cache URL, so
no cache is created that the chat call cannot use. The cache body takes its project and
location from the api_base model, matching the collection URL.
* fix(vertex_ai): cache for the api_base's model and skip caching on a Gemini v1 base
A Vertex api_base naming a publisher model now gives the cache its model as well as its project and location, so the cache matches the model generateContent calls. A Gemini api_base ending in /v1 skips context caching, since the v1 API has no cachedContents and rejects the cachedContent field.
* fix(vertex_ai): check the cache token minimum against the api_base's model
The cache is created for the model a publisher-model api_base names, so the minimum prompt size now comes from that model too. A prompt below its minimum is sent uncached instead of failing at cache create.
* fix(vertex_ai): use the stricter cache minimum and send a Gemini base's 404 uncached
---------
Co-authored-by: paulo037 <paulo.h.carneiro.18@gmail.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(responses): drop a malformed prompt_cache_breakpoint under drop_params on the direct /v1/responses path
* refactor(responses): reuse the shared prompt_cache_breakpoint_for_wire helper in the chat bridge
* fix(responses): read a non-flag deployment drop_params as unset in the marker walk, like the param mapper
* fix(responses): drop every prompt_cache_breakpoint under drop_params when the model has no breakpoints
Also drop a marker set on the message item itself, sanitize before the
cache_control conversion so a client typo no longer erases that breakpoint,
and skip items that carry no marker so unmarked history costs no extra walk
* fix(responses): keep a valid prompt_cache_breakpoint unless the model is known to reject it
A deployment alias the cost map does not know (an Azure deployment name, a fine-tune, a
litellm_proxy alias) kept its valid markers before this PR and must keep them under
drop_params. base_model is read from litellm_params first, then model_info, as chat
completions does.
* fix(responses): drop a valid marker on known non-breakpoint models and keep the tool schema gate unchanged
* fix(responses): judge breakpoint support by model name so cost-map aliases keep valid markers
* fix(responses): keep the caller's request stripped of cache_control as before when a marker is copied
* fix(responses): keep valid prompt cache markers in place and let cache_control fill a dropped one
Under drop_params the marker step now hands back the caller's own objects when every marker is
already wire-safe, so a request with valid markers is no longer copied and walked a second time.
A deployment that turns cache_control into markers keeps the caller's own markers too, whatever
its base_model says, so one request never gets two answers about breakpoint support.
On /v1/messages a malformed raw marker next to cache_control is dropped before the conversion,
so the block gets the cache hint cache_control alone would give, as on /v1/responses.
* test(responses): keep a null marker and the original key order on a model that reads breakpoints
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(responses): resume background response streams with stream and starting_after
Retrieving a response with stream=true and starting_after=N now returns the
replayed event stream from OpenAI and Azure instead of one JSON object, on the
SDK (get_responses / aget_responses) and on the proxy's GET /v1/responses/{id}
Providers that cannot replay a stored stream drop the params under drop_params
and raise UnsupportedParamsError without it. Malformed values answer 400 with
the param named. A replay that reaches its terminal event settles the
background response's bill once and passes the provider's usage through
without estimating one. An empty replay (cursor at the end) ends normally
* fix(responses): encrypt replayed stream ids and resume Azure AI Foundry streams
A replayed background stream now gets the same response id encryption as a
created one, so the key that made the response can reuse the id. Azure AI
Foundry deployments resume streams like Azure ones, and the chat-bridged
Responses iterator closes its wrapped stream instead of raising.
* fix(responses): drop malformed resume params under drop_params and keep JSON answers to a streamed retrieve
A bad stream flag drops to a plain retrieve and a bad cursor to a full replay when drop_params is on, and a cursor without stream is ignored even when malformed. A streamed retrieve that the upstream answers with JSON returns the response object instead of an empty stream. get_responses forwards only the include keys from extra_query.
* fix(responses): give proxy stream resumes the deployment stream_timeout and document retrieve query params
* fix(responses): keep deployment stream off retrieves and reject oversized cursors
* fix(responses): keep router default stream off plain retrieves
* test(responses): black box coverage for resume refusals, drop_params, stream timeout and billing
* test(responses): replay a real stream in the billing test and type the fake wrapper chunks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn
* fix(responses): keep tool-call-only stream content empty and drop unreachable replay guards
* fix(responses): reject an assistant phase OpenAI does not define unless drop_params is set
* fix(responses): keep other providers' reasoning and stream output unchanged and fall back on records that do not fit
* fix(responses): label a structured output turn with its returned message's phase and keep lone surrogates from failing the checksum
* fix(responses): leave a turn without a phase when its content message cannot be read
* test(responses): add black box tests for chat turn history replay
* test(responses): expect the replay record on bridged chat replies
* test(responses): expect the replay record in bridged chat translation cases
* fix(streaming): keep the served service tier on the finish chunk the stream adds
* test(responses): read the expected chat message without JSON validation so the replay matcher stays
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(responses): cover Codex tool lists repeated across turns on the Bedrock chat bridge and Mantle
* fix(responses): keep each Codex tool once when its tool list repeats across turns
* test(responses): type the new tool list dedupe unit tests
* fix(responses): drop the null created_by OpenAI rejects when output items are replayed
* fix(responses): drop a null created_by from replayed input items too
A conversation saved from an older proxy still carries created_by: null on its compaction, apply_patch and shell items, so OpenAI keeps rejecting the replay. Drop the null from input items on the HTTP request transform and the WebSocket response.create rewrite, keeping a created_by that is not null.
* fix(responses): drop a null created_by from counted input items too
* test(responses): cover saved reasoning nulls and re-compaction of a saved conversation
* fix(responses): drop a set created_by from input under drop_params
* fix(types): type the Responses output serializer's parameters
* fix(responses): drop a set created_by on reasoning items and Perplexity presets under drop_params
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(gemini): preserve every grounding web source
* test(gemini): cover all grounding sources per passage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Zabir Raihan <zabirraihan@icloud.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(gemini): send Google's current Managed Agents fields on create and forward agent_config on interactions
* fix(gemini): accept id on managed agent get, delete, and list_versions
* fix(gemini): drop unsupported agent fields under drop_params and keep agent_config keyword-only
A model interaction drops agent_config under drop_params, agent create drops wrongly typed optional fields under drop_params and otherwise answers 400 naming the field the caller sent, and agent_config on interactions create is keyword-only so positional response settings stay in place
* fix(gemini): drop a non-object agent_config under drop_params and name the id alias the caller sent
* fix(interactions): reject agent_config on bridged providers and drop a typeless one under drop_params
Bridged providers answer 400 for agent_config without drop_params and drop it with drop_params. A Gemini agent run drops an agent_config without a string type under drop_params. The Gemini agents wire test expects Google's current upstream field names.
* fix(interactions): honor additional_drop_params for agent_config on bridged providers
* fix(agents): drop a clashing instructions alias under drop_params
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(azure): audit #47348
Add proxy integration tests for #47348's cached Entra token providers and
off-loop token refresh, and fix the token herd the audit found: once the
fetch moved to a worker thread, concurrent cold requests each fetched their
own token. Every cached bearer token provider now serializes its calls so
the first fetch fills the cache and the rest reuse it
* fix(azure): build each cached Entra token provider once under concurrent first calls
lru_cache does not hold back concurrent misses, so worker threads that miss together each built their own credential and token provider, and each fetched its own token. A lock around each provider cache makes the first caller build it and the rest reuse it
* fix(azure): share Entra token fetches only while no valid token is held
Concurrent callers now share one result (or one error) from the cold
fetch, while callers inside the refresh window keep the still-valid
token. The oidc/azure provider build and the client-assertion exchange
are single-flighted per audience, and the shared helpers no longer call
subscripted generic aliases, which crashed on Python 3.10.
* fix(azure): refresh Entra tokens once while other requests keep the valid token
MSAL treats a token with less than five minutes left as expired, so every
request in that window fetched a new one. Now one request refreshes while
the others keep using the still-valid token.
Requests that waited on a fetch that failed retry once through a fresh
fetch instead of all failing with the first error.
Credentials that only implement get_token keep working, and OIDC token
exchanges are cached per scope.
* fix(azure): bound Entra token waits during an outage
Requests waiting on a failed token fetch now retry only when the fetch
before it succeeded, so during an Entra outage later bursts fail after one
fetch instead of two.
Requests during a refresh only get the held token while it has more than
60 seconds left, and a failed refresh falls back to that token instead of
failing its request.
* fix(azure): share one retry per failed Entra token fetch and raise on a failed refresh
Waiters of a failed fetch now retry the flight they joined, so a fast-failing Entra makes one retry instead of one per waiter. A failed refresh raises again instead of returning the held token, which Postgres token auth read as a fresh one. The DefaultAzureCredential fallback reuses one provider per scope.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(responses): audit #47363
Adds integration cells for the input token count paths #47363 changed: the provider id of a managed file and the 403 for another team's file on OpenAI, file_search and additional_tools parity plus cache-mark stripping and untranslatable tools on Claude, and the Bedrock runtime count leaving out the options it refuses.
* fix(count-tokens): reject a lone tool with no chat equivalent before the Claude count call
A Claude input token count whose only tool was mcp or computer_use_preview skipped the pre-call check and went to the provider, so the caller got the provider error instead of the 400 naming the tool. The check now runs whenever a tool would get a placeholder name.
* fix(responses): count a lone Anthropic toolset and name the uncountable tool
The lone-tool 400 now fires only for OpenAI Responses built-in tool types, so a nameless Anthropic toolset still counts. The error says LiteLLM cannot count that tool type for the model. Adds a Bedrock unit cell for the lone-tool 400 and pins the runtime wire test's tool shape per request type.
* fix(responses): take the uncountable tool types from the OpenAI SDK and keep the region hint off LiteLLM's 400
The Responses built-in tool types now come from openai's ToolParam union, so a type the SDK adds is refused before the count call too. The AWS region hint no longer lands on an error LiteLLM raised before calling the provider. Tests cover two more lone types and the hint.
* fix(responses): keep LiteLLM's own list of uncountable tool types and pass a non-string tool type through
* fix(responses): count tool_search and namespace tools the way Claude chat inference sends them
The count refused a lone tool_search with LiteLLM's 400 and sent a lone
namespace raw or squashed it into an empty tool, while Claude chat
inference maps tool_search to Anthropic's tool search tool and unpacks
a namespace into its function tools. Both now go through the
deployment's own map_openai_params, so the count sends what inference
sends, and tool_search leaves the list of uncountable types.
* fix(bedrock): count a Claude request with its deployment's own chat translation
Bedrock invoke and Mantle inference turn a chat tool_search tool into Bedrock's
tool search tool, but the Bedrock counter always translated with the Anthropic
config, so the count answered 400 for a request inference serves.
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(count_tokens): keep the framed estimate when a region-less token_count_model cannot count (audit #47441)
* fix(count_tokens): let framing stand in for a shipped token_count_model, keep a configured one's error
The framed local estimate now replaces a 400/404 from any count model the cost map ships, Mantle-pinned rows included, and an admin-set token_count_model keeps its error as the docs say.
* fix(count_tokens): warn with the region when framing stands in for a pinned count model
Test a Mantle row #47441 pinned in its own region, and keep the region hint check on an admin-set count model.
* fix(count_tokens): name the deployment in the framing stand-in warning
* fix(count_tokens): let framing stand in when a cost map count model's region denies the account
A count model the cost map pins to a region can answer 401 or 403 when the
account has not enabled that region or lacks Mantle count access there. With
framing set, the estimate now stands in, as it does for 400 and 404. An admin
set count model and a count model with no pinned region keep the error.
The warning now names the model group, the count model and its region, and
says the proxy falls back to the estimate.
* test(count_tokens): cover framed 401 and 403 from a shipped count model region on the wire
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(images): cover SDK retry budgets and router ownership
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(images): forward max_retries to the OpenAI image generation client
Per-call, deployment and default_litellm_params max_retries were filtered
out before reaching the OpenAI-compatible image handler, which then always
used 2 SDK retries. Forward the caller's value, and pin it to 0 for routed
calls so the Router stays the only retry owner, matching completion()
Co-authored-by: Ericz <yonglzh@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(images): read image max_retries through a typed kwargs view
Co-authored-by: Ericz <yonglzh@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(images): assert the public invalid retry error mapping
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(images): preserve the invalid retry status code
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(images): group the proxy test imports
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(images): discard proxy retry test routers
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>
Co-authored-by: Ericz <yonglzh@gmail.com>
* test(huggingface): cover TEI rerank truncate passthrough and server default
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(huggingface): stop forcing truncate=false on TEI rerank and pass truncate params through
Co-authored-by: Luke Schaefer <225965040+luke-e-schaefer@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(huggingface): keep TEI truncate options provider-specific
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(huggingface): use MockTransport for rerank truncation
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>
Co-authored-by: Luke Schaefer <225965040+luke-e-schaefer@users.noreply.github.com>
* test(nvidia_riva): audit #41021
Adds an owned Riva ASR gRPC server and provider integration cells for the riva_offline request-body ban, the offline and streaming paths, the per-deployment caller opt-in, and the 413 and 408 error mappings
* test(nvidia_riva): check word timing requests and audio samples in the Riva double
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Covers the json_schema envelope edge cases #47478 fixed on the Anthropic json tool path: a key listed only in
`required`, a tool-named wrapper on a stream, non-ASCII and lone-surrogate answers, a stream cut before the tool
block closes (proxy and sync SDK, Anthropic and Bedrock Invoke), and a string `output_format` with and without
`drop_params` on Anthropic and Vertex chat and /v1/messages. The scripted Anthropic peer now refuses a non-object
`output_format` the way Anthropic does
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(anthropic, bedrock): audit #47489 thinking replay across Claude routes and Bedrock Converse
* test(bedrock): compare the whole replayed Converse turn in the merged-message and cache point cells
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(proxy): audit #46815
Add integration tests for every count route #46815 changed, and count a Claude
subscription caller's tokens with their forwarded token when the deployment has
no configured key, which #46815 turned into a 401
* test(proxy): accept the forwarded subscription token in the count endpoint mocks
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* test(gemini): audit #47542
Proxy integration cells for the Gemini and Vertex default output budget: the env budget reaches Google on chat and responses, turns on long decode, yields to the caller's own limit, caps per deployment, skips resumes, and a camelCase two-candidate request is never continued
* test(gemini): annotate the budget wire module's pytestmark as Final
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Checks that a SageMaker stream failing after its first chunks reaches /v1/chat/completions, /v1/messages and /v1/responses callers as an error with no success end event, and that each writes a failed spend log row
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(tavily): return raw_content, score, favicon and the response envelope from Tavily search
Tavily search dropped every field except title, url and content, so
include_raw_content, include_answer, include_images and include_favicon
reached Tavily but their output never reached the caller. Each result now
carries raw_content, score and favicon when Tavily returned them, and the
top-level fields (answer, images, request_id, usage, ...) come back as
provider_metadata, same as the Exa fix in #47423
* test(tavily): move the Tavily search wire test's sample data to module constants, like the Exa test
* test(integration): update stale expectations to intended provider behavior
Each expectation moved because a merged PR changed behavior on purpose.
- chatgpt string input is wrapped as one user message (#41522)
- Gemini 2.5 tool media sits beside function_response (#48428)
- sampling knobs move to Gemini 3.5 Flash, which keeps them (#47645)
- a body base_model is stripped without allow_client_pricing_override (#47639)
- ai_decide answers without usage return usage null (#48261)
- azure_ai forwards mapped client anthropic-beta values (#48033)
- the OpenCode scripted upstream mints a fresh id per request
* test(e2e-ui): type the guardrail name before deleting it
GuardrailDeleteModal requires the exact name before Delete enables since
#45893. All three guardrail delete flows now go through one helper.
* test(observability): accept any sampled traceresponse flags and expect a 400 for a non-object body
OpenTelemetry 1.45 (#48055) sets the W3C random trace id flag on new traces,
so the gateway's traceresponse now ends in -03. The producer copies the server
span's own trace flags, so the tests now accept any two-digit flags with the
sampled bit set instead of pinning -01
#48438 made a non-object JSON body a 400 "Invalid JSON payload: expected an
object" on purpose, so the [1] body case is renamed non_object_body and
expects that 400
* test(observability): stop waiting on OpenTelemetry's export log line in the langtrace outage test
The outage test waited for "Exception while exporting Span batch" in the proxy
log, which is OpenTelemetry's wording and no longer appears with 1.45. The test
keeps asserting what the gateway guarantees, callers unaffected during the
outage, a live gateway, and every span after recovery delivered once with no
outage span duplicated
* test(guardrails): count the Responses disconnect spend rows #47611 added
Since #47611 a streamed /v1/responses disconnect writes its own spend row, so
the concurrent disconnect test saw 20 rows where it counted 10 by model group.
It now reads each row's call type and expects ten acompletion rows with the
outage verdict and ten aresponses rows with success. /v1/messages disconnects
still write no row on main, so they are left out of the count rather than
pinned as absent
The responses-httpx case of the single disconnect test no longer needs its
LIT-8603 skip and passes
* test(observability): size K4's timeout from the harness boot budget
K4 boots three two-worker proxies in a row. On CircleCI each boot takes 43 to
58 seconds, so a passing run took 179.97s against its fixed 180s cap and 6 of
30 runs hit pytest-timeout. The cap and the restart gate wait now come from
readiness_seconds and graceful_stop_seconds, like other multi-boot tests
* feat(bedrock): price native guardrailConfig trace usage into spend and x-litellm-response-cost
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bill native Bedrock guardrail trace usage on chat, responses and pass-through
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): record the Bedrock guardrail trace of a streamed metadata chunk on the logging object
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(bedrock): apply guardrailConfig on /v1/messages and price its trace, record the stream trace on both builder paths, redact the native guardrail_response
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(bedrock): validate the guardrail trace with one pydantic model
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(bedrock): record the native guardrail entry when litellm_params metadata is None
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(bedrock): import the renamed messages invoke transformation module
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(bedrock): skip native guardrail billing on cache hits and redact the trace with message logging off
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(bedrock): walk the guardrail trace iteratively when redacting it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(bedrock): record the native guardrail trace where the Bedrock response is parsed
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(bedrock): type the native guardrail trace fixtures and locals
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(responses): round-trip Anthropic compaction blocks as compaction items
/v1/responses on Anthropic routes now returns Claude's compaction block as a
compaction output item (and streams it as output_item.added/done), and a
compaction input item is replayed to Claude as its native compaction block,
so the next turn reuses the summary instead of compacting again. Other routes
receive the summary as assistant text. The Anthropic stream handler now keeps
the summary text that arrives in compaction_delta.
Fixes#41456
* fix(responses): replay compaction blocks natively only when the request compacts
* fix(responses): carry compaction through dict-form edits, SDK replay, affinity, and guardrails
Read Anthropic's dict-form context_management, accept SDK ResponseCompactionItem
objects on replay, strip the encrypted_content affinity wrap before decoding,
scan and rewrite compaction summaries in Responses guardrails, drop the history
a summary replay replaces, send the summary as a user message so thinking
ordering holds, and send the streamed compaction .done with the newest block.
* fix(responses): count, route, guard, and redact compaction items consistently
A compaction item now reads as its summary everywhere the proxy counts or routes
a Responses request: pre-call context checks, the TPM limiter, the input token
endpoint, the stream usage estimate, and the previous_response_id session rebuild
all drop the history the item replaces. A Claude compaction item sent to a
non-Anthropic model (including a fallback) becomes a user summary message instead
of an encrypted blob the provider rejects, and Claude on Bedrock Claude Platform
takes the summary path. Output guardrails see the summary of a returned
compaction item, and logging redaction hides it.
* fix(responses): start previous_response_id replay at a stored compaction and count reservations from it
* fix(responses): keep a stored compaction summary whole in spend logs
* fix(responses): keep stored compaction items summary-only, redact compaction_delta, and finish compaction before reasoning
A spend-log row now stores a top-level compaction input item as its summary alone, so extra keys in a
client-built item no longer reach the database whole. Message redaction also nulls the streamed
compaction_delta, and the streaming bridge sends the compaction item's done event before the reasoning
item that follows it. Adds the audit's integration tests for compaction items on the wire.
* test(responses): cover stored compaction items, compaction_delta redaction, and compaction done order
Adds integration cells for the summary-only spend row of a caller-sent compaction item and its previous_response_id replay, a redacted chat stream row that holds no streamed compaction_delta, and a compaction then thinking stream whose done events follow output order.
* fix(spend_logs): honor the redaction header on failure rows for litellm_metadata routes
A failed /v1/responses or /v1/messages call keeps its proxy request headers in
litellm_metadata, but the failure row read redaction headers from metadata only,
so x-litellm-enable-message-redaction never redacted those rows.
* fix(spend_logs): lift only the redaction opt-in header into failure rows
The failure hook on litellm_metadata routes copied every real request header into the caller's own metadata dict, so the stored request body gained the headers, a caller's metadata.headers was replaced, and a disable header loosened global redaction on failed calls. It now copies only the enable headers into a new litellm_params metadata dict, and only when the caller sent no metadata.headers, so no failure row is less redacted than on main
* test(responses): cover failure-row redaction headers and caller metadata on litellm_metadata routes
* fix(responses): keep earlier-turn instructions after compaction and count compaction items by their summary
A previous_response_id rebuild that starts at a compaction now keeps the system and developer
messages of every earlier turn. Token estimates for raw Responses input count a compaction item
as its summary text instead of the serialized item.
* fix(responses): drop the stored history a caller-sent compaction item replaces on previous_response_id
* fix(responses): count only message items with a string role as compaction instructions
* test(responses): flatten the last two-for comprehension in the compaction wire test
* fix(responses): replay from a compaction in stored Responses output and SDK compaction items
A previous_response_id whose stored row is a Responses output holding a compaction item now starts its replay at that compaction, and the handler dumps SDK compaction objects before checking for a summary. Adds tests for the uncovered compaction paths.
* fix(responses): keep the stored tool call a function_call_output answers when a compaction item replaces history
* fix(responses): keep a stored tool call on every turn after a compaction item and bound the stored summary
A previous_response_id rebuild that starts at a turn holding a compaction item now sends again each stored call a
replayed tool output answers, so a retry or a later turn no longer loses the turn-1 call. The start is picked only from
rows up to the referenced response. A spend row keeps a compaction summary up to the larger of 64K chars and
MAX_STRING_LENGTH_PROMPT_IN_DB instead of with no bound.
* fix(responses): replay a compacted session only through the referenced response
A later sibling turn that sent a compaction item put its summary between a stored tool call and its tool output, so Claude answered 400 on a turn that continued the first of two retried turns, and on a retry sent without the item
* fix(spend-logs): keep main's stored value for a prompt length limit under 2
At a MAX_STRING_LENGTH_PROMPT_IN_DB of 0 or 1 the shared truncation helper stored only the truncation marker, where
main stores the marker followed by the whole value
* fix(spend-logs): keep main's stored tail for a negative prompt length limit
At a negative MAX_STRING_LENGTH_PROMPT_IN_DB the shared truncation helper stored one more character of each value than main, since it dropped main's clamp of the end slice to the limit minus the start
* fix(responses): keep a compaction item when a guardrail rewrites its summary through structured_messages
* test(responses): run the compaction wire tests on the worker database under isolated workers
* fix(router): keep the encrypted content affinity pin out of provider requests
* fix(proxy): inspect compaction summaries in guardrails, strip a client-sent affinity pin, and price failures from the newest compaction
* fix(proxy): count a failed chat or /v1/messages call on its whole history, not from a compaction-typed message
* fix(proxy): trim a failed call's input at the newest compaction only when the client called /v1/responses
* fix(proxy): trim a failed call's input at the newest compaction when the proxy dispatched it as a Responses call
* test(proxy): run the dispatched-call-type failure test through the real request setup
* fix(proxy): count a failed Cursor stream's input from the newest compaction item
The Cursor route maps to no call type, so the stream generator's failure hook fell
back to the route and counted the whole history. Pass the processor's route_type.
* fix(proxy): count a broken Cursor stream's prompt from the newest compaction item
* fix(responses): keep a tool call a later output answers when trimming before a compaction item
* fix(responses): move a compaction-split tool call's turn to right before its output on both compaction routes
* perf(responses): look up moved turn items in a set so a long compaction-split turn trims in linear time
* test(responses): measure the compaction-split turn move as a CodSpeed benchmark instead of a clock read in unit tests
* fix(responses): move only calls still open at the compaction, and bill a disconnected stream from the newest compaction item
* fix(responses): restore only the newest stored call when a reused call_id is answered after a compaction item
* fix(spend logs): bound a Responses compaction item's summary like a chat block instead of cutting its encrypted_content
* test(proxy): price a failed dispatched call through a real ProxyLogging instead of mocked hooks
* fix(responses): finish a stream whose Claude compaction failed and group answered call ids by turn once
* fix(responses): count input_tokens after a compaction item the way inference sends it
* fix(llms): sanitize trailing slashes in provider get_complete_url
* test(llms): move trailing-slash url tests into each provider's mapped unit file
* fix(llms): strip trailing slashes in Perplexity search and Ollama embedding URLs and run the Topaz tests in CI
* fix(llms): strip trailing slashes in search, DashScope, VolcEngine, GigaChat and Gradient AI URL builders
* fix(fastcrw): strip a trailing slash from api_base and expect one slash in the GigaChat tests
* fix(gigachat): strip a trailing slash from the pass-through api_base
* fix(llms): join api_base and route with one shared helper
A deployment api_base that ends in / made several get_complete_url builders emit a double slash, which Envoy and other gateways answer with 404. Add join_api_base in url_utils and use it in those builders, with a regression test that drives every get_complete_url under litellm/llms with a trailing-slash api_base
* refactor(llms): move per-provider api_base strips onto join_api_base
Use the shared join_api_base helper in the search, chat, embedding, image variation, GigaChat and VolcEngine URL builders instead of a per-provider rstrip and suffix check, so one helper owns the single-slash join
* ci: run the trailing-slash URL builder test in the llms shard
* test(integration): cover trailing-slash api_base across provider URL builders
Wire cells for chat, streaming, messages, responses, embeddings, search and pass-through with and without a trailing slash, an owned-proxy module for the flag-gated providers, env bases and a worker kill, two chaos bursts, and a Topaz SDK cell
* fix(llms): send every provider route through join_api_base
Every place under litellm/llms and litellm/main.py that joined a caller-settable api_base with a route by concatenation or f-string now goes through join_api_base, so an api_base with a trailing slash sends the same upstream path as one without it
Routes made only of a caller-supplied id, model, or passthrough path stay on a plain join over an already normalized base, because the helper's suffix dedup would turn a lookup by id into a list or create call
The sweep test now also reaches the factory-made JSON provider builders, and a new loopback test drives the public entrypoints with an api_base ending in /gw/ and checks that every request path keeps /gw/ with no double slash
* fix(llms): keep the route skip only where a builder already had it
join_api_base is a pure join again. The new ensure_api_route skips the route only when the URL path
already ends in it, and it is used only where the merge base or the trailing-slash test PR head
already skipped. Evals cancel, Predibase, and Azure AI threads append their route again, EdenAI
model listing and Gemini RAG ingestion join through join_api_base, and Azure AI Anthropic checks the
path so a host named anthropic-* builds /anthropic/v1/messages
* fix(azure_ai): read /anthropic from the URL path when building the count_tokens URL
* test(llms): run the Gemini RAG trailing-slash case through aingest
The sync ingest wrapper needs a current event loop, which an earlier async test in the same worker clears
* test(llms): cover the Azure realtime, Bedrock rerank, and oobabooga joins with a trailing-slash api_base
* test(integration): cover api_base joins across providers, query strings and named hosts
* feat(url_utils): add join_api_base and ensure_api_route helpers
* fix(url_utils): keep the scheme slashes when a stripped suffix was the whole host
join_api_base and ensure_api_route now keep the // of a base left with only a scheme,
so http://v1 with /v1 stripped joins to http://v1/files as before. The Azure v1 client
base_url goes through ensure_api_route so a base ending in /openai/v1 no longer doubles it
* fix(azure_ai): build the count_tokens URL from the messages URL
* fix(azure_ai): match anthropic as a whole path segment in the messages URL
* fix(llms): keep main's Azure AI anthropic match and non-string Bedrock endpoints
Azure AI chat and messages go back to cutting the base at the first
/anthropic, as on main, and count_tokens keeps its path check, so a
gateway path like /anthropic-proxy builds the same URLs as main. A base
that already ends in /v1/messages still gets count_tokens next to it.
A non-string aws_bedrock_runtime_endpoint (an httpx.URL VPC endpoint) is
used as its text again in AgentCore, Bedrock responses and the RAGFlow
base, instead of falling back to the default host.
get_volcengine_base_url and GigaChat's get_api_base strip a trailing
slash again for outside callers. The cache-hit wire test is skipped as a
known proxy bug, since one cache hit writes two cache_hit spend rows.
* fix(llms): drop a slash before the api_base query and tighten the route test checks
* test(llms): annotate new test locals as Final and flatten the builder generator
* fix(url_utils): keep a scheme-only api_base hostless so it fails before sending
---------
Co-authored-by: Raushankumar0720 <raushan.singh.cg@gmail.com>
* fix: Send the include_usage chunk with an empty choices array
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
* test: Skip chunks with no choices when reading streams
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
* fix: Strip usage from plain-iterator async stream chunks
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
* test: Expect empty choices on the usage chunk in the gemma tracing test
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
* fix(streaming): send the empty-choices usage chunk only to callers that asked for include_usage
The usage chunk now has choices=[] only when the caller set
stream_options.include_usage itself. When the OpenAI handler, the proxy's
always_include_stream_usage setting, or the harness added include_usage on the
caller's behalf, the chunk keeps its legacy single empty-delta choice, so
clients that read choices[0] on every chunk keep working.
The proxy and harness mark their injection with the private
_litellm_stream_usage_injected flag, and the proxy scrubs a client-sent copy.
Plain-iterator streams keep usage on their chunk when usage was not requested,
and the LLM Shield trailing flush ignores chunks with no choices.
* fix(proxy): mark the default stream usage injection so hooks keep the legacy usage chunk shape
The proxy's default strip-mode injection adds include_usage for clients that did not ask and drops the usage chunk before it reaches them, but streaming iterator hooks still saw it with choices=[]. Marking that injection with _litellm_stream_usage_injected keeps the old single empty choice for them.
* fix(router): treat deployment and router-default stream_options as injected, and drop the client flag on the queue route
* refactor(router): move the stream usage injection check into router_utils
* fix(router): read stream_options from pydantic deployment params when marking injected usage
Update the mantle, openinference, and text-completion integration tests to expect the include_usage chunk with empty choices.
* fix(proxy): keep the stream usage injection marker out of stored request bodies
* test(streaming): cover who asked for stream usage on chat, queue, deployment and spend log paths
* test: type the queue flag test, pin the logging start time, and build the deployment usage config without mutation
---------
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(bedrock): apply the deployment guardrailConfig on the /bedrock pass-through routes
The router-model pass-through dropped a Bedrock deployment's guardrailConfig, so
converse, converse-stream, invoke and invoke-with-response-stream reached Bedrock
unguarded while /v1/chat/completions on the same deployment was blocked. The
signer now sends it the way Bedrock reads it, in the body for Converse and as the
X-Amzn-Bedrock-Guardrail* headers for Invoke, replacing any guardrail the caller sent
* test(bedrock): reject version-less guardrails in the scripted Bedrock and cover the 400
The mantle and fallback fixtures named a guardrail with no guardrailVersion, which real Bedrock refuses, yet the scripted Bedrock answered them as guarded successes. The fake now answers a version-less guardrail with a 400 ValidationException, the fixtures carry versions, and a new case checks a version-less deployment guardrail reaches Bedrock and the caller gets its rejection on all four actions
---------
Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
The Gemini TTS billing and text completion guardrail tests read spend rows from the owned proxy's own database, which #47213 made private. The cursor wire test derives its effort levels from the gpt-5 cost map row that #43935 now enforces, and the Azure effort check accepts the unquoted level. The pin TTL test asserts the one hour pin #46411 writes for a tool-only mark, the video callback test decodes ids with the product decoder after #44614, and the two Gemini 3.8 flash stream cost cases bill audio at the text rate their rows imply
* test(integration): stabilize auth and team delete checks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(unit): make loop-blocking and tampered-signature checks deterministic
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(unit): isolate model-cost state and synchronize loop progress
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(unit): fail loop-progress handshakes when the blocking call never starts
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(vertex_ai): send integer enums to Gemini instead of dropping them
Gemini rejects enum values that are not strings, so _fix_enum_types removed
every non-string enum. Integer enums are now sent as type INTEGER with
format "enum" and string values, which Gemini accepts and enforces.
* fix(vertex_ai): keep converted integer enums when a tool is reused
The schema is edited in place, so a tool definition passed again already
carries the converted enum. Keep an integer enum that is already in the
format "enum" form instead of dropping it, and type the new locals.
* fix(vertex_ai): use Sequence at runtime in the enum cast
* fix(vertex_ai): treat integer-string enum values as an integer enum
A reused schema already holds its integer enum as strings. Instead of
reading `format` to recognise that, accept integer strings as well as
integers on an integer-typed enum and send both in Gemini's form. This
drops the untyped `schema.get("format")` read.
* fix(vertex_ai): map Gemini tools from a copy so a fallback keeps the caller's schema
Gemini tool mapping rewrote the caller's tools in place, so a router fallback to another provider received the Gemini-converted integer enum (string values with format enum) and returned the integer as a string
* fix(vertex_ai): send integer enums only to Gemini 3 and newer, and only ones Gemini accepts
gemini-2.5-flash stalls for minutes on a larger integer enum, so Gemini 2.x
keeps main's behavior and drops it. An enum outside int64 or longer than 1000
values is dropped too, since Gemini answers 400 for those. A nullable integer
enum written as a type list now keeps its values like the anyOf form does
* fix(vertex_ai): drop integer enum strings longer than int64 instead of failing the request
* fix(vertex_ai): drop integer enums when a request's enums pass Gemini's size limit, and send int enum members as numbers
Gemini limits the total size of all enums in one request, so the per-enum 1000-value cap still let several large integer enums through to a 400. Integer enums are now sent only while every enum value in the request adds up to 2000 characters or fewer, and an (int, Enum) member goes out as its number instead of its name
* fix(vertex_ai): send only integer enums Gemini returns exactly, and count them in Gemini token counts
* fix(vertex_ai): send Gemini integer enums without format enum, which made gemini-3.8-flash think much longer
Also skip the response cache in the repeated-request integration test, since copying tools makes the second identical request a cache hit
* fix(vertex_ai): keep dropping integer enums in Vertex batch rows, which Vertex batch cannot parse
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(tests): read the stream stall cooldown spend rows from the owned proxy's database
The cooldown cells boot an owned proxy, which writes its spend logs to its
own scratch database since owned proxies went private, while the cells polled
the worker's database and never saw a row. Read each row through the gateway
that served the request, so the cells check the proxy they called.
* fix(tests): read passthrough spend rows from the owned proxy's database
The vertex regional uplift and passthrough stream pricing spend files boot
private owned proxies, then polled the worker database for spend rows that
only reach the proxy's own database. Read them through the owned proxy's
gateway instead.
Also hold the stream stall file's hold_headers peer past the longest row
wait, so a slow spend row cannot fail the peer teardown.
* fix(tests): check agent deletion on the owned proxy's database
The agent least privilege test deletes its agent through an owned proxy,
then checked the worker database for the row, which is always empty
there. Read it through the owned proxy's gateway so a delete that leaves
the row fails the test.
* fix(tests): read turn admission spend rows from the owned proxy's database
#47525 renamed _deployment to _fallback_deployment; #47363 was written against the old name and merged after it, leaving three F821 undefined-name errors that fail the python lint job on main
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(count-tokens): translate chat tool use before Claude token counts
Responses and chat tool use (function tools, function_call items, tool messages) is now converted the way Claude chat inference converts it before the Anthropic, Azure AI and Vertex partner counters call count_tokens. Translation errors answer 400 before any provider call. Anthropic-shaped requests and /v1/messages/count_tokens keep their body as sent.
* test(count-tokens): compare Claude count bodies with inference for Responses tool use
* fix(responses): forward the caller's Responses body to OpenAI token counts
OpenAI deployments now get the caller's /v1/responses/input_tokens body as sent, minus LiteLLM-only fields, so OpenAI's own count and errors come back. previous_response_id is checked for ownership like inference and routes to the deployment that served it
* fix(responses)!: count Claude Responses bodies the way inference sends them
Non-native Responses counts now run the body through the inference bridge, so
text.format, tool_choice, reasoning, built-in tools, and file_search count the
way inference sends them on Anthropic, Azure AI, Vertex, and Bedrock. The
OpenAI native count body uses the drop_params-resolved tool fields.
* fix(responses): honor drop_params and replay previous turns in Claude counts
Claude input_tokens counts now read the same drop_params setting inference merges from the deployment, router defaults, and request, so a forced tool_choice downgrades to auto under drop_params. previous_response_id replays the stored turns through inference's session loader, and chat messages carrying fields beyond role and content go through the provider's chat translation
* fix(responses): keep proxy-only request keys out of OpenAI counts and map chat tools in Bedrock counts
* fix(count-tokens): import on Python 3.11 and keep stored prompts in OpenAI counts under drop_params
* fix(responses): leave tool_choice out of counts when drop_params drops every tool
* fix(count-tokens): count Mantle options, drop cache marks, and reject input inference cannot send
The Bedrock Mantle fallback now counts thinking, tool_choice and output_config
like the runtime count. Claude Responses counts leave out cache_control marks
again, so more than four marks count instead of failing. Counts answer 400
before any provider call for user blocks chat inference refuses and for
Responses tools with no Chat Completions equivalent, instead of dropping the
block or counting a placeholder tool. Adds the wire tests for these paths
* fix(count-tokens): count Responses tools the way the inference bridge sends them
A Claude count now hoists additional_tools input items into tools, strips a malformed tool flag under drop_params and rejects it without, and leaves tools out when the deployment lists tools in additional_drop_params, so the count matches the body Claude inference sends for the same request
* fix(count-tokens): keep Bedrock runtime counts option-free and send OpenAI the provider file id
* test(count-tokens): capture the Anthropic count request at the HTTP layer instead of patching the handler
* fix(count-tokens): ignore a caller-sent file id mapping and keep non-string file ids as sent
* test(integration): follow #47441 metadata-routed Mantle counting in count_tokens wire tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): build the runtime count body without mutation
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(sagemaker): parse every streamed record however SageMaker cuts the payload parts
SageMaker cuts a container's response stream into PayloadParts at arbitrary
byte offsets, so one part can hold several SSE events or JSON lines, or only
part of one. The decoder treated each part as one record, so vLLM's [DONE]
was logged at ERROR on every stream and a split at an unlucky byte dropped
the rest of the answer.
Peel records off a running buffer with JSONDecoder.raw_decode, skipping SSE
framing and [DONE] between them.
* test(sagemaker): cover streamed records cut or merged across payload parts
* fix(sagemaker): decode UTF-8 across parts, skip SSE comment lines, and log container error records
A UTF-8 character split across two PayloadParts now decodes whole through one incremental decoder per stream.
SSE comment lines (TGI's keep-alive) and event, id and retry field lines are skipped as framing.
A container error record is logged at ERROR with its message and skipped, and any other record that is not a
chunk is logged and skipped, the same way on the sync and async paths.
* fix(sagemaker): raise a container's error record and ModelStreamError on both stream paths
A record with a non-null error now raises a 500 SagemakerError carrying the record after the chunks before it, on sync and async. Async no longer swallows a non-200 event, so a ModelStreamError raises as it does on sync. A chunk with a null error field is delivered, and any other record that is not a chunk is logged and skipped on both paths.
* fix(sagemaker): answer a streamed error with the container's status and fail a stream cut mid-record
A container's error record now raises with the status the container gave it (vLLM's error.code, the older flat vLLM shape, TGI's http_status_code or error_type) instead of a fixed 500 that the router retried as a 503. A ModelStreamError raises a SagemakerError naming its ErrorCode and Message, a stream that ends inside a record raises instead of ending as a stop, and a skipped record is logged by its keys only
* fix(sagemaker): trust only 422 and 429 from a streamed error record and fail LMI generation errors
* test(sagemaker): drive an LMI failed-generation stream through the proxy on a sagemaker/ deployment
* test(sagemaker): fall back to the next model when a stream fails before any content
* test(anthropic): cover json_schema envelope edge cases on the Anthropic json tool path
* fix(anthropic): unwrap required-only keys, walk past tool-named envelopes, keep non-ASCII text, flush cut streams, check Vertex output_format
* fix(anthropic): send held json tool text on cut Bedrock Invoke streams and drop a non-object output_format under drop_params
A Bedrock Invoke stream that ends before the json tool block closes now sends the held text and closing brace, as the direct Anthropic stream already did.
A non-object output_format on the Anthropic messages route and its providers is dropped under drop_params and otherwise forwarded, so the provider answers its own 400. Vertex Claude names the proxy setting in its 400 and reads drop_params through the shared helper.
Adds integration cases for the json_schema envelope and the cut stream.
* fix(anthropic): drop a non-object output_format on chat, unwrap a whole envelope on a cut stream, escape lone surrogates
Chat completions to Anthropic, Azure AI, Bedrock Invoke and Vertex now drop a non-object output_format under drop_params, matching /v1/messages. A stream cut after a complete held envelope is unwrapped like a normal end. A json_schema answer holding a lone surrogate keeps its \u escape so the response can still be encoded
* fix(anthropic): join a split answer when the stream ends in its last block
A cut during the second json tool block now runs the held block through
the same flush as a block stop, so it joins the streamed keys or the
earlier split blocks instead of sending two objects back to back. The
Vertex output_format fold drops its unreachable drop_params branch,
since both parent configs drop a non-object value first.
* test(vertex): expect the LiteLLM 400 for a non-object output_format on /v1/messages
Local token counts for DeepSeek V3 and V4 model names now use DeepSeek's own bundled tokenizer instead of cl100k_base, and tool definitions on V4 names count with V4's chat-template tool framing