* fix(proxy): merge a key's cache controls into the request's cache settings instead of replacing them
* fix(proxy): keep a key with no-cache out of opt-in caching
A key whose cache metadata sets no-cache now drops the caller's use-cache, so on a default_off proxy its responses stay out of the shared cache as before the merge change. default_on proxies ignore use-cache, so they are unchanged
* fix(proxy): keep base handling of non-dict key cache metadata
Key cache metadata that is not a dict, such as false or a string, wipes the request's cache settings as before the merge change, so those keys stay out of opt-in caching
* fix(proxy): keep a key with use-cache false out of opt-in caching
* fix(proxy): only keep request cache settings on an allowed opt-in
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(reasoning): log the GPT-5 reasoning_effort drop warning only when the provider gets no effort
* fix(proxy): count an extra_body effort as sent and pass the drop holder through ChatGPT and Copilot
* fix(proxy): pass the drop holder to get_optional_params under the internal _litellm_ prefix
* fix(openai): keep the reasoning effort drop warning when extra_body sends another level
The held warning now stays quiet only when the request sends the level the gate dropped,
so a top-level xhigh dropped while extra_body sends none still logs. The Copilot test case
writes the access-token file the current authenticator reads.
* fix(openai): keep the reasoning effort drop warning when a request fails before reaching the provider
The drop warning holder now lives for the whole completion call, and
completion's exception handler prints whatever it still holds, since a
request that fails after mapping never reached the provider. Each flush
empties the holder, so a provider error after dispatch does not print the
warning a second time
* fix(openai): warn when extra_body's reasoning_effort carries no effort level on the Responses bridge
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(vertex_ai): bill gemini image text, thinking and priority tokens at their own rates
Co-authored-by: kerry <kerry@berri.ai>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(images): bill unitemized output as text when no images return
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost_calculator): price image calls only by the tier the provider served
---------
Co-authored-by: kenneth <kenneth@berri.ai>
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep the upgrade notice off the request path and count area-labelled release notes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(proxy): regenerate dashboard API types and read the release cache through one typed helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): respond 502 from /get/latest_release_info when no release note entry is countable
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): respond 502 when the release fetch failed and announce a release with no countable notes without counts
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): re-ask for the latest release while the proxy is still fetching it and keep fetch diagnostics out of the 502 body
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): keep the known release on screen while the proxy refetches it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): answer 202 while the release is being fetched so the dashboard polls only then
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): name the release query options to stay inside the lint budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): return the 202 as a response value instead of mutating the injected response
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): fetch the release on the background client so its 502 never reaches the error handler
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(rate-limit): settle a fallback's tokens on the model group that served it
The v3 limiter pinned post-call TPM settlement to the model reserved at
admission, so when the router fell back to another model group the
requested model's counter took the usage and the serving model's counter
stayed empty. When the served model group differs from the admitted one,
charge the served group and refund the abandoned group's per-model
reservation. Same-model retries and alias reloads keep the admission target.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(rate-limit): refund an abandoned fallback reservation only on counters the served model does not settle
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(rate-limit): wait for the primary refund and the fallback charge before reading counters
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(rate-limit): only treat a limiter-admitted fallback target as the served model at settlement
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(rate-limit): drop unrelated formatting from the v3 limiter unit test file
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(rate-limit): remove helper copies duplicated while appending the fallback settlement tests
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(router): send managed batch uploads to batch deployments when a chat deployment has a lower order
A purpose=batch upload on a mixed Azure chat and batch group was order-filtered before batch routing narrowed it, so the file landed only on the order-1 chat deployment and the batch create that followed got Azure's 400 invalid_deployment_type. The upload now runs under the same batch routing as the batch create.
* fix(router): keep a failed batch upload's cooldown and order fallback on the batch deployments
* fix(router): keep a batch upload off chat deployments while its batch deployment cools down
* fix(router): keep a refused batch upload's retry off the chat deployment
* fix(router): keep a refused batch upload's error and skip chat while the batch deployment is paused
* test(router): pin the order fallback for a batch create on a group with no batch deployment
* test(integration): expect an Azure batch upload on the batch deployment alone
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* feat(anthropic): forward message threads on native /v1/messages
Keep the thread body field on native Anthropic legs, add the
message-threads-2026-08-12 beta for it, reject it with a 400 on legs that
cannot continue a stored thread, and relay error.details of an upstream
Anthropic error so thread_not_found reaches SDK thread helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(anthropic): keep a stale thread 404 from cooling the deployment and type the thread beta ignores
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: sort the cooldown handler imports
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic): dedupe the message-threads beta map rows and annotate test finals
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic): bind message threads to the key that created them and answer unsupported continues with thread_not_found
Every virtual key on a proxy shares one Anthropic credential, so forwarding thread alone let any key
continue another key's thread by its message id. A new default proxy hook binds each thread reply id
to its virtual key, or to the signed-in identity when there is no key, and answers a continue naming
an id it did not bind with the 404 thread_not_found the SDK replays on.
Legs without message threads now serve a create without the thread and answer a continue with that
404 before any upstream call, instead of answering it with no history.
* fix(proxy): keep a cached message thread reply with the key that got it first
A response cache hit replays the original reply id, and binding it again handed the thread to the second key, so the creator's continue got thread_not_found.
* fix(anthropic): keep message threads bound on every route and stable across turns
Check the thread binding on every route that carries thread except pass-through,
keep bindings in their own cache so they never evict rate-limit counters, add no
tool or message derived betas on thread turns, answer a create on a leg without
threads with a 400 thread_unsupported_request unless drop_params is set, and
forward threads on Claude Platform on AWS
* fix(anthropic): reject message threads on /v1/messages passthrough deployments
A deployment that forwards /v1/messages untranslated to an OpenAI-compatible
server inherited the native config's thread support, so `thread` reached a
server that keeps no thread state. It now answers the same 400
thread_unsupported_request on create and 404 thread_not_found on continue as
a translated leg
* fix(anthropic): resend a thread's create betas on continues and check bound ids on pass-through
A thread create now gets the betas LiteLLM derives from its tools and
messages again, so an advisor tool create that answered 400 on the previous
commit answers 200. Anthropic fingerprints the beta set, so the proxy keeps
the anthropic-beta header the create sent upstream in the thread binding and
adds it to every continue on /v1/messages. It reads that header from the
upstream request, since success logging overwrites the logged request
details before the success hook runs
A continue on the /anthropic pass-through route of a thread the proxy bound
to another key now gets the 404 thread_not_found. Ids the proxy never bound
still pass through, as before
* fix(anthropic): continue unbound threads off /v1/messages and keep every anthropic-beta on chat and Responses
* fix(anthropic): skip non-string anthropic-beta list entries instead of raising
* test(anthropic): keep the header merge regression test clear of main's appended tests
* fix(anthropic): add a thread's create betas to the client's own on continues and keep base header merging on chat and Responses
* fix(anthropic): answer an unbound thread id on chat and Responses with the 404 and drop the stale beta-join tests
* fix(proxy): check a thread continue sent inside extra_body against its owner
Azure AI promotes extra_body into the request body, so another key could continue a thread by putting thread there, past the ownership hook that read only the top-level field
* fix(proxy): write a thread's first owner atomically and bind creates sent inside extra_body
Two workers that both miss a reply's binding now agree on the first key stored in Redis, since the claim uses SET NX and each worker caches the stored winner. A create sent inside extra_body now binds its reply like a top-level create. The redundant Claude Platform supports_message_threads override is removed, since the provider already resolves to the native Anthropic beta list
* fix(proxy): include agent_id in the key-less message thread owner
* fix(proxy): tag message thread ownership Redis calls with their key family
---------
Co-authored-by: mateo <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): judge the zero-cost budget waiver by the model a key or team alias serves
The zero-cost budget waiver judged the name the client sent, but key `aliases` and team
`model_aliases` are applied later during request preparation. An over-budget key got a 422
for an alias of a $0 model, and an alias named like a $0 group that points at a paid model
was waived and served past the budget.
For a string body `model` on chat, completions, responses and messages, the key-path,
centralized and custom-auth waivers now judge the model request preparation serves. That
model comes from the same team, key, global and router alias functions that request
preparation uses, so the two cannot drift. Other routes and the JWT path keep judging the
requested model. common_checks no longer overrides a caller's explicit decision not to skip
budgets, and proxy-made sub-calls are judged by their own model.
Resolves LIT-10283
* fix(proxy): waive only once auth has applied the router aliases, and keep empty team alias targets
The served-model waiver now applies only after auth's router-alias rewrite has run on the
request body. Custom auth without common checks runs its waiver before that rewrite, so it
keeps judging the requested model instead of a key or team alias of a name the router
rewrites elsewhere. The waiver also keeps an empty-string team alias target, matching
request preparation.
Resolves LIT-10283
* fix(proxy): waive by the served model only for a client's own body-model request
The waiver resolved aliases for any request on a chat, completions, responses or messages
path, including the HTTP request the Responses WebSocket builds for first-frame admission.
That session dispatches the model as an endpoint model, which skips the team alias, so a
team alias of a paid model to a free one waived the paid model's budget.
The waiver now resolves aliases only when FastAPI matched the request to one of the body
model routes, which requests built inside the proxy and path model routes never are. The
waiver tests are folded into one table, share a priced router fixture, and cover the
stale team alias flag cache.
Resolves LIT-10283
---------
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(passthrough): bill a background response once however many times it is read
* fix(passthrough): keep the background response flag on spend events sent to the collector
* test(spend): type the background response test helper and its settlement parameter
* fix(proxy): keep a background response's settling read in-process instead of adding a spend event field
An older collector refuses a spend event with a field it does not know and drops the whole charge, so a newer
gateway sending to an older collector lost the background response's cost. The read that settles a background
response now stays in-process, the same way video status polls do, and the spend event keeps its shape
* fix(proxy): keep a batch retrieve in-process when message redaction hides the logged batch
* refactor(proxy): split the is_offloadable_success docstring into one line per reason
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* refactor(rust_bridge): route every Rust-to-Python call through host modules
Rust now reaches Python only through litellm/rust_bridge/host/ (plus the
execution driver), and no Python module outside host/ imports it. Library
calls that reproduce Python behavior (httpx and OSError error text,
huggingface_hub downloads, the random generator, os.environ) go through
host functions too. The rule is written into host/AGENTS.md
The live litellm.model_cost table, its version and every Python writer move
to litellm_core_utils/model_cost_table.py, and host/model_cost.py keeps only
the functions Rust calls. The cost map fetch passes use_http_settings instead
of handing Rust an http_settings() snapshot
* refactor(rust_bridge): read REDIS_USERNAME from the process environment in Rust
The Redis bridge asked Python for all of os.environ to read one key. CPython's
os.environ writes through to the process environment, so Rust reads it with
ProcessEnvironment like the rest of the module. Also drops doc comments that
restated their code.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci(rust): raise the native extension size cap to 55 MB
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(auto_router): report a session's whole spend on /auto_router/session
Claude Code sends its background calls straight to Haiku under the same session id, so those requests never
reached the auto-router session rollup and the status line under-reported the session. Every billed spend
row in a caller-supplied session now increments a key-scoped Redis counter whose one-hour expiry each write
resets, and the endpoint reports it as total_spend, with spend unchanged. The increment runs where the spend
row is accepted, so it counts each row exactly as often as the key's spend counters do. It reads as no total
without a shared Redis
* fix(auto_router): name the unsupported provider when a turn routes off Anthropic
A turn routed to a non-Anthropic tier with no native wire response, such as a Cloudflare DeepSeek model,
failed strict native validation and was logged as observation_unavailable, which reads like a broken
capture. It now reports unsupported_selected_provider. Turns with a native wire response keep their
existing reasons, and no estimate is added, so savings for these turns stay unknown
* docs(auto_router): explain when session savings stay unestimated
saved_spend on /auto_router/session now says a turn inside the longest prompt-cache TTL of the session's
first observed turn, or of its last incomplete observation, is not estimated, so a null there is expected
for that window
* fix(auto_router): say why a system-only cache prefix has no savings estimate
Claude Code puts its cache breakpoint on the system prompt, so the baseline prefix count sends Anthropic a
body with no messages, which it rejects, and every turn read as token_count_unavailable. A count that fails
only on system or tools prefixes now reports uncountable_system_or_tools_prefix. Gateways that accept the
empty body still count it. A live check against claude-opus-5-5 showed a differential count with a
placeholder message is off by -2 tokens for system-only and +68 for tools, so these turns stay unestimated
and the savings gap for Claude Code is not fixed here
* fix(auto_router): declare the session total's Redis key family and test its expiry
The session total read and wrote Redis without a service target, so its calls showed up as bare redis
spans. Both now run under session_spend_totals. The key no longer hashes the api key, which is already a
hashed token, and only digests the session id. A new test drives Redis expiry on a test clock to show an
active session keeps its total and an idle one restarts
* docs(auto_router): note which turns are still estimated inside the history window
Turns that took the identical baseline path, and turns whose whole cached prefix the session had already
written, are estimated even inside the first cache TTL window, so saved_spend now says so
---------
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(router): re-check and reserve per-model rate limits on fallback targets
A provider error fallback handed the caller the fallback model group without
its per-model TPM/RPM limits ever being checked. The router gets a
fallback_rate_limit_check hook next to fallback_budget_check, the proxy wires
it to the v3 limiter, which reserves the target model's per-model descriptors
before each fallback hop and skips targets that are over their limit.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(router): dedupe a repeated fallback target before the reserving rate limit check
Both walks now consult the attempted set before the rate limit check, so a
chain like ["B", "B"] reserves B once. The deprecated settings parity test
also learns the new setting.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(router): a bidirectional fallback chain never re-reserves the requested model group
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(router): match the surfaced failure in the fallback reservation tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(rate-limit): keep the admission stash untouched while building fallback descriptors
Building the fallback target's descriptors could rewrite the request stash's
PTU ceiling, which post-call settlement reads for the model the caller named.
The fallback check now hides the stash while it builds, like the frame check.
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>
The PATCH model update endpoint was missing from the management_routes group, so virtual keys restricted to management_routes got a 403 on it while the legacy POST /model/update worked. Fixes#50918.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(guardrails/rubrik): moderate text-completion prompts and forward rac_agent_id
_moderate_prompt synthesized a user message from texts for /v1/completions
requests but built the payload from structured_messages, so the webhook
received an empty messages list and the prompt went unmoderated. Pass the
resolved messages into _build_prompt_moderation_payload.
Forward metadata.rac_agent_id to the before_prompt and after_completion
webhooks so agent-scoped policies apply. Only that key is forwarded; the
rest of request_data metadata carries non-serializable objects and inbound
headers
* fix(guardrails/rubrik): also read rac_agent_id from litellm_metadata
/v1/messages, /v1/responses and other LITELLM_METADATA_ROUTES keep proxy
metadata under litellm_metadata, so a caller on those routes may set
rac_agent_id there. Read metadata first, then litellm_metadata, forwarding
only a non-empty string
* fix(guardrails/rubrik): take rac_agent_id from key or team metadata only
The Rubrik webhooks use rac_agent_id to choose which agent-scoped
policies apply. Forwarding it from the request body let a caller pick any
agent's policies, including one a policy exempts. Read it from the
caller's admin-configured key metadata, falling back to team metadata,
via CustomGuardrail._get_admin_metadata. The proxy writes those from the
authenticated key and strips client-supplied user_api_key_* fields from
both metadata dicts, so a caller cannot set or override the value
---------
Co-authored-by: yucheng-berri <yucheng@berri.ai>
* perf(spend): narrow user and team spend log reads to the owner's api_keys so the (api_key, startTime) index is used
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend): satisfy the type discipline gate for the api_key scope helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend): run the api_key lookup under the statement timeout, skip it for search and empty key lists
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>
langfuse_otel, weave_otel and langtrace now encode litellm.Message objects, and any value JSON cannot encode, when they write the prompt, so spans keep their token usage and model parameters. Under LITELLM_OTEL_V2 the payload builder dumps Message objects instead of dropping them
* feat(search): add Microsoft Web IQ provider
* fix(search): require HTTPS for Web IQ credentials
* fix(search): include Web IQ in the packaged endpoint catalog
* fix(search): register Microsoft Web IQ query pricing
* test(search): fix Web IQ exception assertion lint
* fix(search): type Web IQ response passthrough and search error headers
The type-check gate failed on 8 new unknown-type errors in the Web IQ
transformation. Build passthrough fields from a typed helper and validate
the response models directly, and type the base search error headers as
dict[str, str] so subclasses no longer inherit an unknown parameter.
* fix(search): raise Web IQ parse errors without widening the base header type
Typing the base search error headers as dict[str, str] made the shared
HTTP handler report one more argument-type error. Restore the base
signature and raise the same BaseLLMException directly from Web IQ.
---------
Co-authored-by: Gilad Katz <29776916+giladk1221@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
* chore(cost-map): add fal_ai image and video rows priced from the fal.ai model pages (first fal-ai sync)
* chore(cost-map): add 18 more fal_ai rows whose page states a per-image, per-megapixel or per-second price despite a generic API unit
* chore(cost-map): add 11 promotional fal_ai video rows at the rate live on 2026-11-10 (promotional rates apply until the promotion ends)
* test: exempt the three fal_ai seedance-2.5/us rows whose 1080p rate is above $1 per second from the cost ceiling check
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): keep the namespace == name shape for deferred top-level tools
The OpenAI Agents SDK matches a call to a deferred top-level function
(defer_loading=True) only when the function_call carries namespace == name,
the shape it reserves for deferred top-level tools. The Responses bridge
returned no namespace, so after a native tool search the SDK failed with
"Tool <name> not found". A client that adds namespace == name then hit the
echo path, which joined it into "<name>__<name>" for the provider.
- namespace_tool_name_map maps deferred top-level functions to (name, name),
so non-streaming and streaming replies carry namespace == name
- the function_call echo does not qualify a name whose namespace equals it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(responses): keep the qualified name for a namespace member that shares its namespace's name
A namespace "search" with a member "search" is advertised as the chat tool
"search__search" and comes back as name == namespace == "search". The echo
rule from the previous commit skipped the join for every namespace == name,
so that replay reached the provider as "search", a tool it was never given.
The bare-name echo now applies only to the request's deferred top-level
tools (deferred_top_level_names), and the reply map uses the same set. A
deferred top-level name that a self-named namespace member also uses is left
out of both directions, so the namespace member keeps its round trip.
The lookup reads defer_loading is True instead of validating it, so
callers that only read the input (token counting under drop_params) do not
raise on a malformed flag.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(responses): keep the bare name for a namespace == name echo replayed without request tools
Stored history (previous_response_id) is rebuilt with no request tools, so the echo of a deferred
call carrying namespace == name used to join to name__name. Only a namespace that holds a member of
its own name still joins. The lookup also tolerates a tools value that is not a list, and the
comprehensions stay within one for and one if clause.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): read request tools through one validated accessor
The deferred-name lookup and the response-side tool maps take the request's tools from one
TypeAdapter-backed accessor, so a tools value that is not a list of objects reads as no tools and
the type gate does not grow.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): type the request mapping handed to the input transformer
transform_responses_api_input_to_messages takes dict[str, object] instead of a bare dict, so the
tools accessor's argument is known to the type gate and the instructions value is narrowed to str.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): build the namespace tool map from the validated member names
namespace_tool_name_map reads each namespace's members through the same validated accessor as the
self-named check, which keeps the type gate's per-rule counts at their merge-base values.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): replay stored turns with the tools they were sent with
Stored previous_response_id history is rebuilt with each turn's own tools, so a namespace member
that shares its namespace's name keeps the joined name__name form on replay, while a deferred
top-level call keeps the bare name. Adds the session handler regression.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): keep the object entries of a tools list and read them on the streaming path too
One accessor hands the request's tools to the request path and the streaming iterator, dropping only
the entries that are not objects instead of the whole list, so both paths see the same custom, namespace
and deferred tools. Trims the explanatory comments.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): count input tokens with the request's tools in hand
/v1/responses/input_tokens hands the request params, tools included, to the input transformer, so an
echoed call for a namespace member named after its namespace counts as name__name there too.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): hand the request tools to every input conversion that reads an echoed call
The guardrail provenance pass, the prompt caching pre-call check and the Rust precall token count convert
Responses input with the request's tools, so a namespace member named after its namespace keeps name__name
there as it does on the request path.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): keep namespace == name for deferred tools loaded by a client-side tool search
A tool the client's own tool search loaded is still a deferred top-level tool to the Agents SDK, so the bridge keeps its deferral for the response-side name map and the route strips it again before the provider sees the request.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Homen Shum <317650355+homenshum-cheiron@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(cli): connect a per-user GitHub Copilot credential from the command line
lite credentials connect runs the GitHub device login with the caller's own key,
so users can connect Copilot without opening the LiteLLM UI.
* fix(cli): stop connect before the GitHub code expires and explain lost connections
The connect command kept polling until the proxy rejected the expired code with a raw HTTP 400, so it now stops one interval before expiry and prints its own expired message. A dropped connection or timeout while waiting now prints a short rerun message instead of a traceback.
* fix(cli): keep checking for approval until the GitHub code actually expires
Connect stopped one interval early, so an approval in the last seconds was missed. The countdown now starts when the code is requested, which is never later than the proxy's own cutoff, and polling continues while another poll fits.
* fix(proxy): send the streamed Responses fallback metadata as a typed Responses event
With expose_fallback_errors_to_caller on and include_fallback_errors set, a streamed /v1/responses
call that fell back sent its fallback metadata as a chat.completion.chunk with no type, so the OpenAI
SDK read it as an audio delta event with type None. On the Responses route the frame is now
{"type": "litellm.fallback_metadata", "litellm_fallback": {...}} and goes through the same Responses
framing as every other event, so it gets an event: line whenever its neighbours do. The chat route
keeps its chat chunk unchanged
* test(proxy): stop pinning the Responses stream terminator in the fallback metadata test
Main ends Responses streams without data: [DONE] since #47980, so the test reads the event frames whether or not a terminator follows them, and passes both before and after that change merges
* fix(proxy): keep the top-level model on the Responses fallback metadata event
* fix(proxy): keep the fallback metadata id on the Responses event and omit an empty model
* fix(proxy): leave the top-level model off the Responses fallback event when raw model names are on
The complexity router's return_raw_model_name leaves every other event unstamped, so the fallback event now matches. A new test streams a raw upstream frame before the event to cover how main names it.
* chore: push again after GitHub dropped the previous push event
* fix(proxy): send the Responses fallback event without an event line so older OpenAI SDKs read it
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(bedrock): forward x-pass- headers on the /bedrock/model pass-through routes
The /bedrock/model/{model}/invoke, invoke-with-response-stream, converse and
converse-stream routes built the pass-through call from the request body, so
x-pass- headers never reached Bedrock. The processor now hands the caller's
x-pass- headers to the pass-through route, keeps them out of the logged body
snapshot, and on Converse drops the invoke-only guardrail headers when the
deployment sets guardrailConfig and the request metadata header when the proxy
owns request metadata
* fix(bedrock): bill the served service tier on invoke pass-through and scope x-pass- forwarding to the Bedrock routes
* test(bedrock): assert forwarded x-pass- headers on the request Bedrock receives
* test(bedrock): gate the router-model x-pass- forwarding on the request Bedrock receives
* fix(bedrock): bill a caller's forwarded invoke guardrail and keep x-pass- headers out of guardrail vendor payloads
* fix(bedrock): bill a caller guardrail on every invoke model and replace a trace value Bedrock rejects
* fix(bedrock): keep guardrail traces out of chat responses, forward the trace header as sent, and drop credential x-pass- headers
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(tool_choice): accept the Responses API's flat allowed_tools layout on chat completions
An allowed_tools tool_choice in the flat Responses layout ({"type": "allowed_tools", "mode": ..., "tools": [...]})
answered 400 on litellm.completion, acompletion, Router and the proxy's chat and /v1/responses-to-chat routes. One
parser now reads both layouts into the nested Chat layout, and the existing Responses bridge flattens it back for
/v1/responses, so either layout reaches OpenAI in the shape each endpoint expects
* fix(tool_choice): drop an allowed_tools choice under drop_params and refuse conflicting flat entries
An allowed_tools tool_choice a provider can't enforce, or a malformed one, now drops under drop_params and answers 400 without it, the same rule LiteLLM uses for other unsupported values. That covers providers outside OpenAI and Azure, malformed choices on every provider, and Azure api versions older than 2023-12-01
A flat allowed_tools entry that carries both name and a nested function or custom key answers 400, since the two names can disagree, matching what flattening already refuses
* fix(tool-choice): keep the 400 when LiteLLM runs the tools, report auto after a drop
Under drop_params an allowed_tools choice a provider can't enforce was dropped, so on MCP gateway tools and in
run_tool_loop and arun_tool_loop LiteLLM could run a tool the allow list excluded. Those paths now keep the 400 they
answered before the flat layout was accepted, and a malformed choice stays a 400 on MCP gateway tools.
/v1/responses served through chat echoed a choice it had dropped, on sync, async and streamed responses. It now
reports auto, and a choice the provider received is still echoed as sent.
* fix(tool-choice): refuse an excluded tool right before LiteLLM runs it
Checking the provider up front missed a model alias, an old Azure api_version,
a litellm_proxy hop, and SDK fallbacks. The tool loop and the MCP gateway now
check the allowed_tools list right before they run a tool call, so an excluded
call answers 400 and never runs.
Under drop_params the choice now drops only when the caller runs every tool,
so a provider-run MCP server or built-in keeps the 400. The Azure checks read
the request's api_version, which also fixes the /v1/responses echo there.
* fix(tool-choice): drop the choice under drop_params and hand an excluded MCP call back unrun
The drop now applies to every provider that cannot take an allowed_tools
tool_choice, whatever the request's tools hold. LiteLLM never runs a call the
choice excludes: on MCP paths the whole round goes back to the caller in a 200,
the same shape as require_approval, and the tool loop keeps its 400 because it
only returns final content. A malformed choice stays a 400 before any request
on the tool loop and on chat with MCP gateway tools.
* fix(tool-choice): refuse an allowed_tools entry whose name is not a string
An mcp or other non-function entry with a list or dict name passed the
parser and crashed when the allow list was hashed. The parser now treats
it as malformed on both layouts, so it answers the same 400 as an empty
allow list, or drops under drop_params.
* fix(tool-choice): honor server-level and null-name mcp entries and stop hooks running excluded calls
* fix(tool-choice): match named mcp entries by server label and let built-in entries allow their interception call
* fix(tool-choice): leave a malformed allowed_tools choice unrewritten in the interception hooks
* fix(tool-choice): resolve mcp entries like the gateway and keep the choice on every hook path
Under drop_params a malformed allowed_tools choice now acts as if it was never sent, and only a choice that parses is stored and enforced. Without drop_params it answers 400 before any provider request, on /v1/responses with gateway tools before MCP listing
An mcp entry resolves its label the way the gateway picks servers to list (server name in any case, alias, access group, toolset), and a named entry matches the tool's own name or the gateway's prefixed name. The gateway rewrites mcp entries into function entries in the caller's layout and sends "none" when nothing is left
The web search follow-up keeps an allowed_tools choice, compression's litellm_content_retrieve is never excluded and joins the provider-facing choice, and the native /v1/responses hook loop applies the exclusion check and stores the choice
* fix(allowed_tools): stop web search and code interpreter follow-ups forcing another call
A kept allowed_tools choice now goes to the follow-up in mode auto, so a
required choice no longer loops to the agentic loop limit. The MCP label
scope dataclass uses a default_factory so the module imports on Python 3.11
* fix(allowed_tools): stop the Responses web search follow-up forcing another call
The Responses-shaped follow-up after a web search left tool_choice out of its patch, so the caller's required choice went out again through the chat to Responses bridge and looped to the loop limit. It now carries a kept allowed_tools choice in mode auto, like the chat follow-up
* fix(mcp): scope each MCP entry to its own allowed_tools and keep the allowlist on follow-ups
A label now covers only the tools its own allowed_tools lists, so a second label on the same server no longer widens it. Responses MCP follow-ups, streamed or not, keep an allowed_tools choice in auto mode instead of dropping it. The new Responses tests fake only the upstream MCP listing, so LiteLLM's own discovery runs
* fix(mcp): match an entry's allowed_tools against the tool name the gateway lists
A server with a display name override lists the display name, and the listing
filter matches allowed_tools against it, but the label scope only checked the
original name, so no spelling worked. The scope now also accepts the listed
name and its unprefixed part, like the listing filter. Tests now cover the
whole gateway and toolset entries and a display-named tool.
* fix(mcp): match an entry's allowed_tools only against a server's own prefix, not the first hyphen
* fix(mcp): match a tool no server resolves only by its exact listed name in an entry's allowed_tools
* fix(mcp): refuse a tool whose display name only looks like an allowed name, and let the chat follow-up answer
An MCP entry's allowed_tools now matches a tool only by its exact listed name or a spelling routing
accepts for its real name, so a display name that carries the server's own prefix no longer passes for
another tool. The chat MCP follow-up keeps an allowed_tools choice in auto mode, so the model can answer
with text after the tool ran.
* fix(mcp): match a toolset label's tools by exact native name
A toolset label served any tool whose name a routing spelling of a granted name matched, so a toolset granting the literal name "server-tool" also served the real tool "tool" that only another toolset grants. It now serves a tool only when the toolset grants its exact native name, the same check tool_is_granted uses when the gateway lists tools
* feat(spend): report guardrail spend separately in daily activity
Model and key spend in /user/daily/activity/aggregated include the cost of
guardrails like Bedrock guardrails, and nothing in the response says how much.
A customer that bills tenants per key and per model could not get model cost
alone, so tenants that pay AWS for their own guardrails were charged for them
twice
Daily spend rows now carry a guardrail_spend column next to spend, and every
breakdown in the daily activity responses exposes it, so model cost is
spend - guardrail_spend. spend keeps its meaning, so budgets still count
guardrail cost as before
The value comes from the request's cost_breakdown.guardrail_cost, capped at
the row's spend because an allowance discount or a repeat job poll can charge
less than the guardrail cost the breakdown records. The delivery ledger
freezes it into the accounting payload next to accounting_savings, since the
stored payload does not keep cost_breakdown, and the legacy daily queue writes
the same value
The migration only adds the column with a 0 default, so rows written before it
read 0
* fix(spend): count guardrail spend on rows billed without a cost breakdown
A request blocked before the LLM call is billed for its guardrails straight from
guardrail_information, so it carries no cost_breakdown and its guardrail_spend
read 0. Both writers now price guardrail_spend from guardrail_information with
guardrail_information_cost, the same function success and failure rows use to add
guardrail cost to spend
Also fills guardrail_spend in the client usage view built from request logs,
qualifies the field description for rows recorded before it existed, and adds
the lock timeout the migration checks require
* fix(ui): avoid a nested ternary when reading guardrail entries from request logs
---------
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(router): sync responses() applies the Router's num_retries and fallbacks
Sync Router.responses() made one attempt and raised, while aresponses()
retried and fell back on the same Router. The sync plan now walks retries
and fallbacks like the async one, stamps the deployment's num_retries on
the error the same way, and the SDK no longer nests its own retries under
the Router's for sync generic calls
Fixes#49938
* fix(router): sync generate_content() retries and falls back through the Router
Reading litellm_metadata in the SDK retry check left sync generate_content
with no retries at all, since its Router plan made one attempt and the inner
completion() call stopped retrying. Sync generate_content and
generate_content_stream now walk the Router's retries and fallbacks like
their async versions, so retries are neither lost nor nested
---------
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(proxy): reject client-supplied Vertex location and project unless the admin opts in
A request body could carry vertex_location, vertex_project, or their
vertex_ai_* aliases and override the region and project pinned on a
Vertex AI deployment, sending the admin's credentials to a caller-chosen
project or region. Add the four fields to the banned request params so
they need allow_client_side_credentials or configurable_clientside_auth_params.
/vertex_ai/live and /rag/ingest name their Vertex project and location
by design and have no deployment pin to override, so they keep those two
fields while every other banned param is still rejected there
* fix(proxy): close the remaining Vertex target overrides and keep inert fields working
/vertex_ai/live now closes with 1008 when the query names a project or location that differs from a use_in_pass_through deployment's pin, unless that deployment or the proxy opts in
A model group's opt-in now counts only when every deployment in it carries it, and Google-style routes look the opt-in up on the model named in the URL
Vertex target names inside metadata, the live route's vertex_ai_* aliases, and /health/test_connection inheritance go back to the base behavior, since nothing reads them as a target
* test(batches): give the batch FakeRouter the model-list lookup the opt-in check reads
* fix(proxy): pin default_vertex_config on /vertex_ai/live and the proxy's Vertex project on /rag/ingest
* fix(proxy): require the Vertex opt-in on alias targets and fallbacks, and pass the live rewriter flag in main's tests
* test(proxy): give the batch tests' fake router the alias and routed-group lookups
* fix(proxy): close the Vertex opt-in, RAG corpus, and live setup-frame gaps found in review
A Vertex opt-in now counts only when every group the request can reach opts in, router,
context window, and content policy fallbacks and one alias hop included, while a group
with no Google deployment never needs the fields. A model named in the route path is
checked next to the body model.
RAG ingest from a non-admin key refuses a bare or dot-segment corpus id, a
vertex_ai_project or vertex_ai_location naming another target, and a store a non-admin
saved before the upgrade, and reads a corpus named by project number on the proxy's
own project.
/vertex_ai/live closes 1008 on any caller-named project when the proxy pins none, moves
a setup frame sent as a binary message onto the session's target, and resolves the
region from default_vertex_config before the model path.
* fix(proxy): let a live caller name the proxy's configured Vertex project when nothing pins one
With default_vertex_config set but no project pinned, /vertex_ai/live closed every query that named a project,
including the one the admin set in VERTEXAI_PROJECT or DEFAULT_VERTEXAI_PROJECT. A query naming one of those
projects now connects, and any other project still closes with 1008 before a token is minted.
* fix(proxy): keep an admin-created vector store's corpus as saved on RAG ingest
A non-admin ingest into a store an admin created named by project number had its corpus moved onto
the proxy's own project before the admin-store exemption ran, so the upload went to a different
corpus than the admin saved. The exemption now runs first, and a non-admin store still gets the
project-number rewrite and the target check.
* fix(proxy): authorize a RAG corpus moved onto the proxy's project and check client-side opt-ins once per request
* fix(proxy): merge opt-in fallback groups only when their deployments share provider and opt-in list
* fix(proxy): check team public models before allowing target overrides
* fix(proxy): include team wildcard targets in opt-in checks
* fix(proxy): validate overrides against authenticated team routes
* fix(proxy): retain URL model during deferred credential checks
Lowers Together Tev1 4B input price to the pricing page value, adds Mistral Leanstral vision and reasoning flags, and absorbs #50991, #50988 and #50958.
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Kerry Lu <326648561+kerry-berri@users.noreply.github.com>
Co-authored-by: zoveki <349028329+zoveki@users.noreply.github.com>
* feat(cost): bill batch cached image input tokens for OpenAI image models
* fix(cost): bill batch cached audio and image tokens without a text cache price
* fix(cost): honor modality cache prices in the half-price batch fallback
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: kerry <kerry@berri.ai>
* fix(router): let an explicit routing tag outrank the encrypted content pin
A Responses follow-up that replays encrypted reasoning minted on one
deployment, but asks for another with a routing tag, failed with "Not
allowed to access model due to tags configuration". The affinity check
now runs the router's tag filter on the deployment it is about to pin,
and on encryption-boundary peers. When the filter would reject them, it
releases the pin and strips the reasoning the tagged deployment cannot
decrypt, so the request routes there. Requests the tag filter accepts
behave as before.
Fixes#50926
* fix(router): strip reasoning against only the boundary peers the tags keep
When tags rejected some encryption-boundary peers, reasoning was still
judged against every peer, so a blob only a rejected peer could decrypt
reached the tagged one. Pin and strip against the tag-kept peers.
* fix(router): mark the deployment TypeVar Final
* fix(router): keep every boundary peer for the router's tag check
Returning only the tag-kept peers hid tags the later tag check needs to
fail open, so a request that passed the affinity check was refused.
Return all boundary peers and judge the reasoning against the kept ones.
---------
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* feat(proxy): let teams send allowed S3 buckets for batch files and read them back
A team's metadata can now list allowed_s3_buckets. Keys on that team may send one
of those buckets as s3_bucket_name on POST /v1/files and as s3_output_bucket_name on
POST /v1/batches, and the upload and batch-create handlers check the bucket against
the team list plus general_settings.allowed_client_side_s3_buckets. The early auth
body check still rejects bucket fields on every other route and method
Reads of managed files now trust the bucket LiteLLM recorded in the stored s3:// uri
through an internal stored_s3_bucket_name param, so content, retrieve, delete and the
batch cost job can read files written to a request-chosen bucket. Callers can never
send that param, and files in the model bucket resolve exactly as before
* test(proxy): assert outcomes in team bucket tests and type the managed content read
Gives the admit-only tests a real assertion, has the refresh test check what the caller gets back, and narrows the provider file id before reading its bucket so the type gate stays at its base count
* fix(proxy): keep team S3 bucket lists proxy-admin only and read prefixed request buckets back
A team admin allowed to edit team metadata could add any bucket to the team's allowed_s3_buckets, so the key now sits with the other proxy-controlled team metadata keys. The stored bucket for a managed S3 file now keeps any prefix that comes before LiteLLM's own path, so a file uploaded to a request bucket like team-bucket/tenant reads, refreshes and deletes from that prefix
* fix(proxy): keep the request's approved S3 bucket when merging deployment credentials
Model-routed uploads and batch creates merge the deployment's credentials into the request, and that merge let a deployment's s3_bucket_name or s3_output_bucket_name replace the bucket the request had already been approved for, so Bedrock wrote to the deployment bucket. The merge now keeps any bucket the request carries and fills it from the deployment only when the request has none
* fix(proxy): keep the request bucket only on upload and batch create, not on reads
The previous commit let a request's S3 bucket win over the deployment's on every credential merge, which undid #47496 on reads, where the deployment's bucket bounds which buckets a model-routed file id may point at. Deployment credentials win again by default, and only model-routed and provider-only upload and batch create opt in to keep the bucket the request was approved for
* fix(proxy): only proxy admins can set a team's allowed_s3_buckets
Org admins and users allowed to create teams could put any bucket on a team's allowed_s3_buckets through /team/new or a team update, which grants that team the proxy's AWS access to the bucket. The key now goes through the same proxy-admin-only metadata check as the batch limits, so only a proxy admin can add, change or remove it, and resending the stored value still passes
The registry lock fix (#50933) makes add_deployment and set_model_list wait
for a held delete on the same lock, taken inside HostedModelList as
self._lock. The helper only knew lines spelled with
self._deployment_index_lock, so it never saw those two writes reach the lock
and timed out after 10 seconds.
The second server in this case is a plain MCP SDK server registered as
oauth_delegate. The gateway's first catalog listing waits for that server's
OAuth metadata lookup, which never resolves and runs for the full
MCP_METADATA_TIMEOUT of 10 seconds. The MCP SDK client also gives
server/discover 10 seconds, so the case passed or failed on about a tenth
of a second of head start.
Setting LITELLM_MCP_METADATA_TIMEOUT to 5 for this case keeps the lookup
well inside the client limit. The case still asserts that subscription
changes are delivered and tools are refreshed across both servers.
* fix(proxy): count a prompt-only call_endpoint request with the provider on every counter
POST /utils/token_counter?call_endpoint=true with only a prompt sent the
prompt to the provider count API on Gemini and Vertex only. Anthropic,
OpenAI, Bedrock and Azure AI (Claude) deployments answered a local
estimate instead. Every counter now gets the prompt as one user message,
so a provider error surfaces the same as the messages form, and the
framed stand-in after a failed provider count frames the prompt as one
user turn, matching the messages form
* fix(proxy): count a call_endpoint prompt like a user message on providers without a count API
* fix(proxy): count a call_endpoint prompt as a turn only on chat deployments
A prompt-only /utils/token_counter request with call_endpoint=true now goes
to the count API as one user message only when the deployment serves chat
(mode chat, responses, or unknown). Embedding rows and models with no
deployment keep the raw local count.
The Anthropic, Azure AI, and OpenAI count calls now honor the deployment's
timeout, and a count error with an empty body names its status code.
* fix(proxy): fall back to router_settings.timeout for count calls and answer 408 on a count timeout
Count calls to Anthropic, Azure AI, and OpenAI now pick their timeout the way
a chat call to the same deployment does: the deployment's timeout, else
router_settings.timeout, else request_timeout. A count call that times out
answers 408 instead of a 500 processing error.
* fix(proxy): count a prompt as a turn only where a count API exists and give count calls chat's timeout order
* fix(proxy): read the count call timeout through the router settings snapshot
The token counter now asks llm_router.settings().timeout_for() for the chat timeout order instead of a new Router member, so the router surface does not grow
* fix(router): answer timeout_for on every router settings snapshot
The proxy reads the count call timeout through llm_router.settings().timeout_for(), but only the Rust core's snapshot had that method, so a plain RouterSettings (the unit tests' router stub) raised AttributeError. timeout_for now lives on RouterSettings and reads the core's _core_deployment_call_timeout, like the snapshot's other members
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* feat(customers): reject unknown fields on customer create and update instead of dropping them
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(customers): derive the budget hint from the budget request fields and fix the create example
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>
