* feat: add Straiker guardrail integration
Implements LLM security guardrails via Straiker with prompt and response inspection, multi-mode execution (pre_call, post_call), and configurable blocking or redaction of flagged content across providers, streaming, images, and tool calls.
* fix(guardrails): harden straiker source attribution and error-path consistency
Use the operator-configured source for Straiker application attribution instead of a caller-supplied agent_id metadata value, so a caller cannot spoof which application a detection is attributed to. Make _fail reuse _block so a post_call error raises ModifyResponseException like a deliberate post_call block rather than GuardrailRaisedException, and type the blocking helper as NoReturn so the type checker enforces that execution never falls through the BLOCKED branch. Serialize the webhook payload once and send it as raw content to avoid re-serializing on the size check and on every retry.
* fix(guardrails): read straiker config and metadata from all supported shapes
Handle a dict optional_params in _get_config_value so nested guardrail
settings loaded from YAML or the DB (timeout, unreachable_fallback, and
the rest) are applied instead of silently falling back to defaults;
previously only attribute-style access was supported. Build the webhook
metadata bag from the merged metadata so client tags stored under
litellm_metadata on routes like /v1/messages reach Straiker the same way
identity and application fields already do, and widen the internal-key
skip prefix to user_api so proxy-injected budget values are not
forwarded.
* fix(guardrails): fail safe on straiker interventions without redactions
Block instead of passing content through when Straiker returns
GUARDRAIL_INTERVENED without replacement texts, so a positive
intervention verdict can never silently forward the original flagged
content. Fix the streamed-request detection to read the request body
from proxy_server_request.body, where the proxy stores it, instead of a
top-level body key that is never populated; the previous fallback was
dead, so a streamed response whose stream flag was not lifted to the top
level would have been redacted rather than blocked while buffering
replayed the original chunks.
* revert(guardrails): restore straiker caller agent_id application attribution
Restore the original behavior where a request-scoped agent_id in metadata
sets the Straiker application source, falling back to the configured
source. This is the integration's intended per-application attribution;
litellm already resolves a key-owned agent_id ahead of any caller-supplied
value, so a configured key cannot be spoofed.
* revert(guardrails): restore straiker webhook metadata scoping
Restore the original behavior where the Straiker webhook metadata bag is
built from request-scoped metadata only. Forwarding litellm_metadata was
a scope change to what the integration sends to Straiker; keep the
author's intended scoping.
* fix(guardrails): keep proxy key material out of straiker webhook metadata
Widen the internal-key skip prefix from user_api_key_ to user_api so the
proxy-injected user_api_key hash and user_api_end_user_max_budget are not
copied into the Straiker webhook metadata bag. The narrower prefix missed
the bare user_api_key name, leaking the hashed key to the vendor. Keeps
the request-scoped metadata source unchanged.
---------
Co-authored-by: cs-mehta <chandra@straiker.ai>
The proxy already returns x-litellm-model-id (the deployment id) and x-litellm-model-group (the requested model-group alias), but never surfaces the concrete underlying model that served the request; the router rewrites the response model field to the group alias, so callers had no way to read the actual deployment model like anthropic/claude-haiku-4-5. Expose it as x-litellm-model-name, sourced from the deployment recorded in litellm_params metadata.
Co-authored-by: Krrish Dholakia <krrishdholakia@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): source /v1/models token limits from cost map instead of Router.get_model_group_info
Resolves the per-model get_model_group_info fan-out on GET /v1/models
(and /models) that pegged the event loop on wildcard listings (#33636).
create_model_info_response now reads max_input_tokens/max_output_tokens
from litellm.get_model_info (the static cost map) rather than the router,
which aggregated and deepcopied every deployment in a group per listed
model.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): inject model-info lookup into create_model_info_response for deterministic coverage
Inject the cost-map lookup (defaulting to litellm.get_model_info) so the
except and max_output_tokens branches are exercised deterministically and
the token-limit tests no longer hardcode mutable cost-map values.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(proxy): surface custom deployment token limits on /v1/models via cheap index lookup
Add Router.get_configured_token_limits, an O(1) model-name index lookup that
reads a concrete deployment's configured max_input_tokens/max_output_tokens
without triggering pattern matching or deep copies. create_model_info_response
layers this over the cost map so custom deployments absent from the cost map
still surface their limits, and admin-configured limits override cost-map
defaults, while wildcard-expanded names stay on the fast path.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
test_get_model_info_reports_realtime_mode resolved gpt-realtime-mini through
litellm.get_model_info, which reads the cost map litellm fetches at import from
raw.githubusercontent.com/BerriAI/litellm/main. The mode=realtime retag from
#33728 is in this repo's json and its bundled backup but has not reached main
yet, so the test failed whenever the fetch succeeded and passed whenever the
runner was rate limited and litellm fell back to the backup, flapping the
Unit Tests: MCP, Secrets, Containers & Misc job on unrelated PRs
Resolve the lookup against the bundled backup instead, the way
tests/test_litellm/test_cost_calculator.py already does: force
LITELLM_LOCAL_MODEL_COST_MAP, rebind litellm.model_cost, and clear the
get_model_info lru cache before asserting so a remote-backed entry cached
earlier in the same worker cannot leak through, then clear it again afterwards
so no locally-backed entry outlives the test
PR #33736 made the shielded streaming cleanup await
proxy_logging_obj._arelease_max_parallel_requests_on_disconnect on the
client-disconnect path. The four streaming cancel and disconnect tests in
test_budget_reservation.py drive the generator with a bare MagicMock as
proxy_logging_obj, so the cleanup crashed with TypeError: object MagicMock
can't be used in 'await' expression, breaking proxy-infra CI on every PR
Give the mocks an AsyncMock for the release method and assert it is awaited
exactly once on each disconnect path, pinning the single-owner slot release
contract that PR #33736 introduced without test coverage
glm-5p2 (and its fireworks_ai/glm-5p2 alias) carried cache_read_input_token_cost
of 2.6e-07, the GLM 5.1 rate; the entry was seeded from the wrong row. Fireworks'
standard serverless rate for GLM 5.2 is $0.14/1M = 1.4e-07, so every prompt-cache
hit was billed at nearly double the real rate.
Corrects the value in both the canonical map and the bundled backup. The existing
fireworks cost-calculator test now reads the cached rate from the map instead of
hardcoding it, so it tracks the shipped value.
* fix(embeddings): accept encoding_format='float' for vertex_ai/gemini embeddings (#33617)
OpenAI SDKs (and litellm's own client since ~1.84) send
encoding_format='float' by default, but the vertex embedding config only
supports ['dimensions'], so get_optional_params_embeddings raised
UnsupportedParamsError at the provider default value. Any
OpenAI-compatible client talking to a litellm proxy with vertex
embedding models got a 400 unless the operator set proxy-wide
drop_params: true.
Float lists are exactly what the vertex API returns, so the param is a
no-op: pop it before validation. Other values (e.g. 'base64') keep the
existing unsupported-param behavior (dropped with drop_params, raise
otherwise).
Fixes#33173
Co-authored-by: Mihidum Hettiyahandi <55163074+mihidumh@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): add Singulr guardrail integration for LiteLLM gateway (#31302)
* singulr guardrail support for litellm gateway
* Update litellm/proxy/guardrails/guardrail_hooks/singulr/singulr.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix comments
* improvement
* fix: resolve review comments and implement requested improvements
* fix:Guardrail bypass through uninspected messages
* fix:tool text scanning
* fix: Legacy function definitions bypass scanning by adding indirect message scaning
* chore: remove unintended basedpyright budget file
* fix:Response schema bypasses guardrail scanning (response_format.json_schema)
* chore: restore basedpyright-code-budget.json and update lint baselines
Restores the file deleted in c698b88686 to match upstream litellm_internal_staging.
Regenerates basedpyright and ruff-strict budget baselines via make lint-budget-update.
* fix: scan system messages as indirect prompt injection in Singulr guardrail
* chore: restore lint budget files to upstream baseline
* fix: resolve ruff UP006 and I001 violations in singulr guardrail
* Update litellm/proxy/guardrails/guardrail_hooks/singulr/singulr.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* resolve review comments on Singulr guardrail
* fix: scan tool call results as indirect prompt injection in Singulr guardrail
* Apply suggestion from @greptile-apps[bot]
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* minor
* formating fix
* refactor: shift extraction logic to singulr side
* refactor:keep precall hook only
* fix:formatting
* fix:linting
* improve config description
* Trigger CI
* fix
* fix:field description
* fix:errors due to change in field names
* style: apply ruff line-wrap formatting to singulr guardrail
* fix:exception
* fix:formatting
* fix playground
* improved
* Update litellm/proxy/guardrails/guardrail_hooks/singulr/singulr.py
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
* Update litellm/proxy/guardrails/guardrail_hooks/singulr/singulr.py
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
* fix
* fix ci issues
* remove uv.lock from pr
* fix
* fix:resolved comments
* chore: trigger CI
* remove uv.lock
* fix
* fix linting
* fix linting
* fix linting
* remove doc strings
* remove test fixes
* chore: retrigger CI
* change in singulr api contract
* remove some ut
* send litellm call_id to singulr
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: aniket-kardile <aniket.kardile@singulr.ai>
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
* Fix non-conformant UUIDv7 generation in native Opik integration (#31294)
create_uuid7() encoded the timestamp in units of 16 seconds instead of
milliseconds, so the top 48 bits came out ~4096x the real unix-ms. Opik's
backend validates the embedded UUIDv7 timestamp on ingestion (OPIK-7067);
the bad encoding decoded to ~year 2201 and every trace/span batch was
rejected with HTTP 400.
Rewrite create_uuid7() to be RFC 9562 conformant (top 48 bits = unix-ms),
using the standard library only so no new dependency is added. Add unit
tests covering UUIDv7 validity and millisecond timestamp encoding.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(proxy): expose uvicorn concurrency limit (#33077)
Expose uvicorn's limit_concurrency as a --limit_concurrency CLI flag and
LIMIT_CONCURRENCY environment variable. Uvicorn counts both active tasks and
accepted connections and returns HTTP 503 once the configured limit is reached.
Reject non-positive limits at CLI parse time and only add the setting to the
uvicorn startup arguments. Because idle connections also consume capacity,
deployments should use upstream connection/header timeouts and per-client
connection limits.
* test: reorder test_utils tail to keep the daily merge conflict-free (#33788)
The daily OSS branch and litellm_internal_staging each appended an
independent test block at the very end of tests/test_litellm/test_utils.py,
so merging the two collides on that shared end-of-file position even though
the additions are unrelated (this branch adds the vertex embedding
encoding-format tests; staging adds the per-model prompt-cache-minimum
tests). Moving this branch's new TestVertexEmbeddingEncodingFormat class
above test_gemini_image_models_do_not_support_reasoning, which both branches
share, gives the two additions different anchors, so git applies both
without a conflict and without pulling staging into this branch. Pure
reorder; no test bodies change
---------
Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Mihidum Hettiyahandi <55163074+mihidumh@users.noreply.github.com>
Co-authored-by: madan-singulr <150280287+madan-singulr@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: aniket-kardile <aniket.kardile@singulr.ai>
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
Co-authored-by: Aliaksandr Kuzmik <98702584+alexkuzmik@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Salva Madrid <50212436+salvamadrid@users.noreply.github.com>
Outcome keys in the tools/list _meta, the spend-log outcome and count maps, and the REST error
messages now all use get_server_prefix (alias, or the short prefix when that mode is enabled), the
same naming the caller already sees on tool names. Keying them by canonical server_name let an
authenticated caller enumerate internal server names and their health or auth state that the alias
and short-prefix schemes deliberately hide (Veria finding). One helper decides the key for every
surface; exception messages reaching the multi-server REST error list are mapped to their fault tag
with the display prefix instead of relaying exception text carrying canonical names. Server-side
logs keep the real names
* fix(proxy): bill partial streamed spend when the client disconnects mid-stream
* fix(router): guard FallbackStreamWrapper chunks alias for non-CSW streams
* fix(proxy): await disconnect billing dispatch instead of unrooted create_task
* fix(proxy): make disconnect slot release single-owner to avoid double release
* fix(proxy): use union syntax for disconnect cleanup params (UP045 budget)
Conflict in _list_mcp_tools: staging (#33612) moved toolset-grant expansion into the shared
permission primitives and removed the _merge_toolset_permissions call; resolution applies that
removal to this branch's AggregateToolListing structure
The gpt-realtime family (OpenAI and Azure) only serves /v1/realtime and is rejected by /v1/chat/completions with "This is not a chat model", but the cost map tagged them mode=chat. Retag them mode=realtime (a value already used by gemini-live and handled by the health-check realtime handler) and add realtime to the ModelInfoBase mode literal.
Co-authored-by: Krrish Dholakia <krrishdholakia@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(complexity-router): user-triggered escalation keywords
Add an escalation_keywords config option to the complexity router so a user
can force a bump to the next-higher complexity tier by including a phrase in
their message (a stronger model, but not one they get to choose). Defaults to
['LITELLM ESCALATE'] when unset, case-sensitive so it only fires on the
deliberate shouted form; admins can override the list or set [] to disable.
Escalation applies across every routing path: heuristic/LLM classification,
literal and semantic keyword_tier_rules overrides, adaptive routing, and
session affinity (where it bumps relative to the pinned model and persists the
higher tier for the rest of the session). Capped at the highest configured
tier and skips unconfigured intermediate tiers.
Expose it in the Auto-Router v2 UI as an Escalation Keywords field wired into
the complexity_router_config payload.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(complexity-router): validate escalation keywords and pin at tier ceiling
Strip blank/whitespace escalation keywords so an empty phrase can't match every message and escalate all traffic. Keep the exact pinned model when a session escalates at the highest configured tier instead of randomly hopping to a peer in a multi-model pool.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Append-append conflict at the end of test_mcp_server.py between this branch's aggregate-outcome
tests and the mode-aware preemptive-401 tests from staging; both kept
* fix(proxy): stop treating upstream model body field as a LiteLLM model on auth-enforced pass-through routes
An auth: true user-defined pass-through endpoint runs full virtual-key auth, and get_model_from_request unconditionally extracted the request body model field, so key/team/user/project model allowlist checks rejected requests whose model only exists upstream (key_model_access_denied), even when the key was explicitly granted the route via allowed_passthrough_routes.
The pass-through route registry moves to a leaf module (route_registry.py) that the auth layer can import without re-entering the pass_through_endpoints -> user_api_key_auth -> auth_utils import cycle. get_model_from_request now returns None for routes registered as user-defined pass-through endpoints (exact and subpath), which skips model allowlist and per-model budget enforcement on those routes while key auth, allowed_passthrough_routes, and spend/budget checks stay intact. Built-in provider passthrough routes (/vertex_ai, /gemini, ...) keep model enforcement.
Resolves LIT-4299
* fix(proxy): key pass-through model-access skip on the dispatched endpoint, not the request path
Addresses a model-authorization bypass: the first version decided whether to skip
model-allowlist extraction by matching the request path against the pass-through
route registry. That ignored the HTTP method and, more importantly, whether the
request was actually dispatched to a pass-through handler. A custom pass-through
whose path collides with a built-in route (e.g. /v1/chat/completions, or an
include_subpath prefix of one) still writes a registry entry even though FastAPI
serves the built-in handler, so a normal request to that route had its model checks
skipped and could reach a model outside the key/team/user/project allowlist.
The skip is now keyed off the FastAPI-resolved endpoint. create_pass_through_route
tags its handler with LITELLM_PASS_THROUGH_ENDPOINT_MARKER, and get_model_from_request
returns None only when request.scope["endpoint"] carries that marker. Because routing
runs before auth dependencies, this reflects the handler that actually serves the
request: on a collision the built-in handler is dispatched and carries no marker, so
model enforcement stays on. This also removes the need for the separate route_registry
module, so that extraction is reverted.
Regression tests cover a pass-through-dispatched request (model suppressed), a
built-in-dispatched request on the same path (model still enforced), and the no-request
budget path.
Resolves LIT-4299
* fix(proxy): enforce max_parallel_requests as a per-slot concurrency gauge
The v3 rate limiter tracked max_parallel_requests with the same
sliding-window machinery as RPM/TPM. A concurrency gauge cannot live on a
windowed counter: every window roll reset the counter to 1 while requests
were still in flight, the completion decrements for those forgotten
requests then drove the counter negative, and rejected requests left
stranded increments that nothing released. Under sustained load a key with
max_parallel_requests=5 let backend concurrency climb to the full client
concurrency (observed 60 on a live proxy) while the proxy kept returning
429s for everyone else
Replace the windowed counter with a per-slot registry (Redis sorted set of
slot ids scored by acquire time, with an asyncio-locked in-memory fallback):
admission atomically prunes expired slots and registers a new slot id only
when in_flight + 1 <= limit, so rejected requests never occupy a slot;
success, failure, and client-disconnect paths release exactly the slot id
this request acquired (stashed in the request metadata channels), so a
release without a matching acquire or a double-fired callback can never
free another request's slot; and a slot leaked by a crashed worker is
pruned individually after its TTL even under continuous traffic
Resolves LIT-4259
Fixes#16011
* fix(proxy): release every acquired gauge and respect mirrored counts in the in-memory fallback
Address review findings on the slot-registry gauge: the acquisition stash
now carries the gauge counter keys alongside the slot id, so the release
paths free the slot from every gauge it was registered under instead of
hardcoding the api_key scope, and the disconnect release keys off the
stashed acquisition instead of the key object's current
max_parallel_requests configuration (which can change mid-request). The
in-memory fallback now treats a cached integer (the count mirrored from
the last successful Redis script call) as real occupancy, carrying it
forward as a floored counter during a Redis outage instead of restarting
from an empty registry
* fix(proxy): release the parallel slot on proxy-level rejections
async_post_call_failure_hook is the only callback that fires when a
downstream hook (guardrail, budget check) rejects a request after the rate
limiter's pre-call hook acquired a slot; async_log_failure_event is a
completion-level callback and never runs for proxy-side rejections.
Release the stashed acquisition at the top of the hook, before the TPM
reservation guard, so those slots do not linger for the full slot TTL and
wedge the key at its limit under moderate rejection rates. Clearing the
acquisition marker keeps the release idempotent when a later failure
callback runs in the same flow
* test(proxy): cover success release, read-only count, Redis release mirror, and TPM rejection release
Four behaviors of the slot-registry gauge had no direct test: a successful
completion releasing exactly its acquired slot, read_only callers counting
in-flight slots through the count script (and degrading to the local
mirror when the script fails) without acquiring, the Redis release script
mirroring returned counts into the local cache, and the TPM reservation
rejection releasing the already-acquired slot before raising
* style(proxy): use builtin generics and union syntax in new rate limiter annotations
The slot-gauge code added Tuple/List/Dict and Optional[...] annotations, pushing
the UP006 and UP045 strict-rule totals past their ceilings in ruff-strict-budget.json.
Convert only the annotations this branch introduces to builtin generics and PEP 604
unions, leaving the rest of the module untouched.
* fix(router): tag-aware pre-routing strategy selection for shared model_name
Complexity/auto/adaptive/quality router registries were keyed by model_name
alone, so a second deployment sharing a model_name but carrying different tags
was rejected and every request used the first config. This made tag-based
routing to distinct provider configs behind one alias impossible, surfacing as
401 'Not allowed to access model due to tags configuration' for the second tag.
Each registry now holds a list of tag-scoped strategies and async_pre_routing_hook
selects the entry whose tags match the request before classification, falling
back to a default-tagged then first-registered entry. A repeat of the same
(model_name, tags) pair is still rejected.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(router): cover tag-scoped pre-routing strategy registry helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore: re-trigger CI
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The consolidation regressed the pre-existing walker semantics: _extract_upstream_auth_failure used
to keep scanning until it found a 401/403, while the consolidated helper took the first response of
any status and then tested it, so a causal 401 sitting behind an unrelated 5xx (retry attempts,
multi-stream task groups) was misclassified as upstream_error and its challenge lost on the listing,
tool-call, and probe paths. The traversal is now an iterator in deliberate order and each consumer
applies its predicate over the stream: the auth scan takes the first 401/403 even behind non-auth
responses, generic classification takes the first response, and classify_list_exception derives its
auth arm from the same scan so the carrier choice and the classification can never disagree
* fix(mistral-ocr): forward the complete public parameter contract
The Rust OCR path already lists id in the supported Mistral parameters, but litellm/ocr/main.py ran filter_out_litellm_params before handing optional_params to the bridge. That generic filter drops every key in all_litellm_params, which includes id, so the supported public Mistral OCR field id was silently stripped and never reached the provider while the rest of the contract went through.
Restore id after the generic filter via an OCR-specific reserved set, keeping genuine internal params filtered. Add Rust core and ai-gateway contract tests that pin the exact serialized request body for the full supported contract and prove internal canaries are dropped, a Python regression test that id survives while internal params do not, and a deterministic capture E2E plus a live Mistral param test.
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* test(mistral-ocr): drop unnecessary comments from parity tests
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* fix(mistral-ocr): only forward reserved id when set; harden capture e2e
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* refactor(mistral-ocr): typed queue-injected capture harness for e2e
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* test(mistral-ocr): fully type E2E capture models and move gateway ocr tests
Replace the remaining Any/coarse object wire types in the OCR E2E module
with concrete frozen Pydantic models for the supported-param contract,
internal canaries, upstream capture request, and normalized response, and
build every request payload immutably per call. The capture fixture now
cleans up on every failure path (terminate then always wait, kill then
always wait, shutdown plus server_close, join the server thread) and
requires an HTTP 200 liveness probe. The live Mistral test now exercises
the complete public parameter contract with valid json_schema annotation
formats. Move the ai-gateway OCR test module out of io/ocr.rs into a
focused io/ocr/tests.rs.
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* fix(mistral-ocr): drop reserved id upstream when null and type the E2E harness
Extend map_ocr_params so a null-valued reserved public id is omitted from the
serialized request, matching the Python OCR boundary for the standalone Axum
path where a caller can submit JSON id:null; add core map and serialized-body
tests for both the absent and null id cases. Extract the deterministic capture
harness into a typed ocr_capture_proxy helper module with an exception-safe
fixture that cleans up on every failure path from capture-server creation
onward (terminate then always wait, kill then always wait, shutdown plus
server_close, join the server thread, close logs after the process exits) and
requires an HTTP 200 liveness probe. Serialize wire payloads with by_alias so
the annotation schema/additionalProperties keys match the provider contract.
Replace the lambda internal canary in the Python bridge regression with a
serializable value and cover the litellm_session_id and tags internal fields.
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
The read gate cannot cause a wrong pin. A deployment is only pinned when the cache
already holds an entry for the prefix, and async_log_success_event writes entries
against the deployment's real model rather than the group alias, so a model that
will not cache a prefix never records one and there is nothing to pin it to
That makes this gate purely a cheap short-circuit deciding whether the cache lookup
is worth doing, so the threshold must be the lowest minimum in the group. Taking the
highest skipped the lookup for a prefix a lower-minimum member had genuinely cached,
losing a hit it earned, and protected against nothing. It also broke the Fable 5
direction this ticket is meant to fix: its real minimum is 512, so a group gate stuck
at a higher value would skip the lookup for a prefix Fable 5 had actually cached
* fix(ocr-errors): preserve public error and timeout contracts
Classify reqwest timeouts as a typed CoreError::Timeout and add
CoreError::public_status_code() as the single exhaustive mapping from a
typed core error to its public HTTP status. The Python bridge raises a
typed RustOcrError carrying that status instead of a generic
RuntimeError, and litellm.ocr()/aocr() translate it into the matching
public exception so AuthenticationError/401, NotFoundError/404,
BadRequestError/4xx, InternalServerError/5xx and Timeout are preserved
end to end instead of collapsing to APIConnectionError/500.
Reject empty or whitespace-only 200 bodies so they fail loudly rather
than becoming an empty OCR success; invalid JSON already fails. Upstream
error bodies stay bounded and sanitized.
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* fix(ocr-errors): map invalid OCR input to BadRequestError
Invalid caller input (bad document type, non-dict document, unusable
file input) was raised as a plain ValueError inside ocr()/aocr() and
collapsed to APIConnectionError/500 through the generic handler. Route
every OCR failure through one _map_ocr_exception host mapping: typed
RustOcrError keeps its status-based public exception, a plain ValueError
becomes BadRequestError/400, and a pydantic ValidationError (malformed
response, not client input) stays on the generic path.
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* refactor(ocr-errors): data-minimize public errors and preserve status-specific exceptions
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* refactor(ocr-errors): preserve exact unknown status and privatize input error
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* refactor(ocr-errors): exhaustive match mapper and typed error tests
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* fix(ocr-errors): sanitize InvalidRequest public message
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* refactor(ocr-errors): raise typed public union and drop NotFound provider miss
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
* fix(ocr-errors): map malformed provider responses to sanitized 500 and hide input-error detail
Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
get_model_info is lru_cached, so swapping litellm.model_cost is not enough on its
own. An earlier test that resolved these models against the remote map, which does
not carry prompt_cache_min_tokens yet, leaves cached entries without it, and the
stale hit resolves to the default. The assertions would then pass for the wrong
reason or fail depending on execution order
Clear on teardown as well, so entries these tests warm against the local map do not
leak into later tests, matching the fixture already used in test_utils.py
Also pin that a wildcard route resolves the underlying model's minimum. That works
only because pattern_match_deployments substitutes the real model name into
litellm_params before the deployment reaches the check; without the assertion that
claim is unpinned and the threshold would silently fall back to the default
MINIMUM_PROMPT_CACHE_TOKEN_COUNT was a flat 1024 described as "minimum number of
tokens to cache a prompt by Anthropic". Anthropic's minimum cacheable prefix is
per-model and ranges from 512 to 4096, and it can differ per platform for the same
model, so one constant is wrong in both directions
is_prompt_caching_valid_prompt gates PromptCachingDeploymentCheck, which is what
optional_pre_call_checks: ["prompt_caching"] turns on. When it believes a prompt is
cacheable, async_filter_deployments pins routing to whichever deployment previously
served that prefix. For a prompt between 1024 and 4096 tokens on Opus 4.6, Opus 4.5
or Haiku 4.5, litellm judged it cacheable and constrained routing while the provider
never cached it, so the pin cost load balancing for nothing. In the other direction
Fable 5 caches from 512 tokens, so a 512 to 1024 token prefix was refused a pin it
had earned
The minimum now resolves from prompt_cache_min_tokens in the model cost map, which
keeps it current with new models and lets the Bedrock override for Fable 5 fall out
of the existing per-entry keys with no special casing. MINIMUM_PROMPT_CACHE_TOKEN_COUNT
stays as a global escape hatch when explicitly set, and as the fallback for models the
cost map has no entry for
async_filter_deployments only ever receives the model group alias, never a model name,
so it resolves the threshold from healthy_deployments instead. A group may mix models
with different minimums, so it takes the max: a prompt is only treated as cacheable when
it clears every member's minimum, because an unnecessary pin is the defect being fixed
while a missed pin only forfeits an optimization
Gemini context caching shares this gate and has the same defect; its entries are left
unset so they keep today's behavior, tracked separately in LIT-4525
_request_has_cache_control only looked at messages and system, so a client that
marks cache_control on tools alone did not suppress auto-injection. Tool
breakpoints count toward the provider's four-block limit, so three of them plus
the two injected here is five, which Anthropic rejects. Thread tools through
both entry points and treat a client-marked tool as the stand-down signal it
already is for messages and system.
A `lite login` token 429'd with "Budget has been exceeded! Max budget:
0.25" even when no budget was configured anywhere. cli_poll_key stamped
the minted CLI session token with litellm.max_ui_session_budget ($0.25)
as a fallback whenever the user and team had no budget of their own. That
cap was designed for the Admin UI "Test Key" chat pane; the CLI reused
the same session-token machinery, so it inherited a playground-sized
budget baked into the encrypted token at login (unchangeable without
re-login), which trips fast under real CLI/agent use.
The cap is also redundant: the token already carries user_id and team_id,
so the real user/team budgets are enforced independently at request time.
Pass max_budget=None so the CLI token is governed only by those real
budgets, and drop the now-dead user/team budget lookups. The UI login
token's guard (get_experimental_ui_login_jwt_auth_token) is untouched.
Grafted from PR #33582 (closing as superseded by this PR): drives
handle_streamable_http_mcp with real MCPServer objects, parametrized over a
stamped client_credentials row and a legacy unstamped M2M-shape row; both must
reach the session manager without the per-user token store being consulted
The preemptive-401 gate for auth_type=oauth2 MCP servers keyed the challenge
on whether an Authorization header was present (not oauth2_headers). Because
the header parser classifies any Authorization bearer as an OAuth token before
the target server is resolved, a LiteLLM virtual key presented as
Authorization: Bearer sk-... suppressed the challenge on a gateway-managed
authorization_code server; the session then opened with no upstream token and
tools/list masked the failure as 200 with an empty tool list. The same gate
also wrongly challenged client_credentials (M2M) servers, which the gateway
authenticates by minting its own token at egress.
The decision is per oauth2 sub-mode, not per header. Gateway-managed modes
never receive a client-supplied upstream token: client_credentials mints at
egress so it is never challenged, and gateway-managed interactive
(authorization_code, non-delegate) is challenged whenever no stored per-user
token exists, regardless of any bearer. Only the delegate/upstream-PKCE mode,
where a present bearer genuinely is the upstream token, keeps keying on the
Authorization header. oauth2_headers itself is left untouched so the
delegate/passthrough egress paths that forward the client bearer are
unchanged.
