Terminal batch retrieve could return the raw provider output_file_id, which
skips managed-file ownership checks on /v1/files/{id}/content and lets any key
on the proxy download another user's batch output.
Retrieve now registers the missing managed-file row before responding, and
attributes ownership to the durable batch owner rather than the retrieving
caller, so output and error ids always come back as unified managed ids.
Fixes#33989
* fix: rebuild models_by_provider in add_known_models so cost map reloads reach wildcard expansion
* fix: refresh models_by_provider in place so captured references survive reloads
A connection test that redirects the destination already leaves the configured
credentials behind. It kept litellm_credential_name, which names the same stored
secrets and is resolved further down the call, so the reference is now dropped
with them. A request that sets no connection fields of its own is unaffected,
which is how the Admin UI tests a configured model.
The proxy-wide opt-in that already governs callers supplying their own
connection parameters now also governs whether a connection test may pair a
request-supplied endpoint with the configured deployment's credentials. Off by
default, which keeps configured credentials scoped to the endpoint the
configuration names; on, the previous merge behaviour is available unchanged.
A request that supplies its own connection fields describes a connection of its
own, so the configured deployment's credentials are no longer merged underneath
it. Anything the request leaves unset still comes from the configuration, so
naming a configured model and testing it as configured is unchanged, and adding
a second deployment for an already-configured name works as before.
Replaces the earlier outright rejection, which also refused requests that
supplied a complete connection of their own.
When a connection test names a model that resolves to a configured deployment,
that deployment's routing and credential parameters are authoritative. A request
supplying a complete connection of its own is unaffected.
BREAKING CHANGE: /health/test_connection no longer lets a request replace the
routing or credential parameters of a configured model it names. Supply the full
connection parameters instead of naming a configured model.
Multipart callers express nested metadata as flat bracket-notation keys, which
reach the request-body check as literal keys rather than as a metadata dict.
The check now rebuilds them with the same helper the endpoints use, so both
encodings are handled identically and cannot drift apart.
BREAKING CHANGE: a multipart field such as `litellm_metadata[api_base]` is now
subject to the same request-body parameter rules as its JSON equivalent. Set
`general_settings.allow_client_side_credentials`, or the deployment's
`configurable_clientside_auth_params`, to keep passing these.
The URL-destination check previously ran over request-body fields only. The
per-field logic moves into reject_url_valued_destination(field, value) so a
deployment name resolved from the request path runs the same check against the
same admin allowlist.
BREAKING CHANGE: a deployment name supplied in the request path that parses as
an http/https destination is now refused. Add the host to
`provider_url_destination_allowed_hosts` in litellm_settings to keep it working.
* feat(pre-commit): save full lint output to a per-worktree log file
* docs(claude): point agents at the pre-commit log instead of rerunning
* fix(pre-commit): warn when the log cannot be created or fully written
An SSE stream that cannot be positively identified as Anthropic (no
parseable message_start event) now blocks instead of passing through
unscanned, closing the bypass where any raw-SSE backend skipped tool
permission checks entirely. Buffered chunks are joined back into one
stream before parsing, so events split across network chunk boundaries
assemble correctly instead of being silently dropped. Rewrite mode now
resets finish_reason to stop when no tool call survives, so the
re-encoded Anthropic stream reports stop_reason end_turn and clients do
not wait for a tool result that never comes
A cached HTTPHandler hands its raw httpx.Client out to consumers that keep it
for the process lifetime. When the shared client cache expires the entry on its
TTL or evicts it under the 200-entry cap, nothing references the handler, so it
is collected and its finalizer closed the client those consumers still hold.
Langfuse ingestion then failed silently on the SDK's background flush thread
until the process restarted.
A finalizer running proves only that nothing references the handler; it proves
nothing about the client. Both handlers now close the client during finalization
only when they built it and are still its sole referrer, so an unshared client is
still released promptly and a handed-out one is left alone. That keeps the
pooled-socket reclamation the finalizer was providing, which measures identical
to base over 2000 handler create-and-drop cycles.
Explicit close() stays, now gated on _owns_client so the wrapper never closes a
caller-injected client, and __aexit__ routes through it.
LangFuseLogger also keeps a reference to the handler whose client it hands the
SDK. Previously that handler was a local that went out of scope immediately,
leaving the client reachable only from the SDK. It still shares the cached
client, so no extra clients are created per logger.
test_reapply_runtime_registrations_replays_register_model_overrides asserts that
a fetched catalog value survives the replay for a key an operator override does
not mention. Any Router still alive in the process re-asserts its own deployments
first, so a router serving openai/gpt-4o writes its model_info over that catalog
value and the assertion reads the router's number instead. Routers built by
earlier tests stay in the weak set until they are collected, which made the test
depend on collection timing and fail intermittently in shards that run the router
tests alongside it.
The live-router rebuild is covered in test_router_model_cost_isolation.py, so
this test now runs with the replay callback unset and exercises the recorded
registrations it is about.
The redaction filter was attached to the handler shared by litellm's own
loggers, so it only covered records litellm emits. A litellm value can also
reach a log record through a dependency logging on its own logger, and those
records never pass through a litellm handler.
Attach the filter to each dependency logger that can carry one. The filter goes
on the emitting logger rather than on the root logger or a root handler, since
Logger.handle applies the emitting logger's filters before any handler runs, so
every downstream handler is covered regardless of who owns it.
The gate required a litellm. prefix on get_secret and get_secret_str, so any
module importing either function directly bypassed it: 335 environment variables
read under litellm/ were invisible to it. The three patterns collapse into one
with the prefix optional, a negative lookbehind so attribute calls on unrelated
objects cannot match, and litellm.utils. accepted since four call sites reach
get_secret that way.
Widening the patterns alone would demand about 320 new rows in the central
reference table, most of them provider credentials that are already documented
on their own provider pages. So the gate now looks across every page of the docs
site rather than only that one table, which leaves 143 keys genuinely
undocumented instead of 322.
* fix(auto-router): stop the embedding model's context window from failing long requests
The auto-router embeds the last user message to pick a model and sent it to the
embedding model unbounded. Embedding models carry 512 to 8k token windows while the
chat models they route to carry 200k+, so any prompt over the encoder's window failed
at the routing step with a 400 the destination model would never have raised.
Cut every doc to a character cap inside LiteLLMRouterEncoder, which is the one choke
point the auto-router, complexity-router, semantic guard and MCP tool filter all share.
Default 2000 chars, roughly 500 tokens, which fits even a 512-token self-hosted encoder,
overridable per deployment with auto_router_max_input_chars and globally with
DEFAULT_MAX_EMBEDDING_INPUT_CHARS.
Truncation alone cannot cover provider-side batch and byte limits, so any failure of
the route call now falls back to the auto-router's default model instead of propagating.
That path also fixes two latent bugs: a no-match left the auto-router alias in place as
the model name, which fails downstream with "Unmapped LLM provider" rather than reaching
default_model, and an empty route list raised IndexError.
Fixes#17869Fixes#20277
* fix(auto-router): make the embedding input cap opt-in so guards still see whole prompts
Defaulting the cap inside the shared encoder truncated every consumer, not just the
auto-router. The semantic guard builds the same encoder, so its pre-call check would
have classified only the first 2000 characters while the full message still reached the
model, which a benign opener in front of an injection payload walks straight past. The
MCP tool filter and complexity router were silently narrowed the same way.
The encoder now defaults to sending docs whole and cuts only when a caller passes
max_input_chars. The auto-router is the only caller that does, so guard, MCP filter and
complexity-router behaviour is unchanged from before this branch.
DEFAULT_MAX_EMBEDDING_INPUT_CHARS becomes DEFAULT_AUTO_ROUTER_MAX_INPUT_CHARS, since it
is now specific to the auto-router, and drops its env override: the per-deployment
auto_router_max_input_chars already covers it, and every env var in constants.py has to
be documented, which is what broke the documentation and code-quality checks.
Also drops the added comments and the redundant type: ignore that review flagged.
* test(auto-router): cover the max_input_chars wiring from litellm_params
Nothing asserted that auto_router_max_input_chars on the deployment reaches the
AutoRouter that embeds prompts. Dropping the wiring left every test green while the cap
silently reverted to the default, so an operator with a 512-token embedding model could
not lower it and every long prompt would fall back to the default model instead of
being routed.
* test(auto-router): cover the populated route-choice list branch
The route layer can hand back a list, and picking its first element is where the
IndexError lived: the empty case was covered but the populated one was not, so the
branch that reads route_choice[0].name could be deleted with every test still green.
`is_database_connection_error` answered True for any `PrismaError` it did not
recognize, on the reasoning that an unclassified failure might be an outage and
the safer default was to keep serving. That default is inverted for faults that
never resolve. A query engine that is missing or version-skewed, a malformed
generated query, or a misused transaction all satisfied the predicate, so with
`allow_requests_on_db_unavailable` enabled the proxy would absorb one, boot
clean, and keep issuing fallback identities for as long as the process ran.
The predicate is now an allowlist: the httpx transport errors, prisma's
`EngineConnectionError`, and a `no_db_connection` ProxyException. That is what a
real outage produces, since the query engine is a local HTTP server and an
unreachable database surfaces as a transport failure against it, so the
high-availability path is unchanged. Anything unrecognized is now treated as
permanent and surfaces instead of being absorbed.
Deciding whether to serve without a database and deciding what to tell the
caller are different questions, so they no longer share a predicate.
`is_database_infrastructure_error` keeps the previous broad behavior and now
backs the reporting and recovery paths: service-unavailable classification, the
access-group endpoint's status mapping, and the health watchdog's reconnect
trigger. Their behavior is unchanged. Without that split, a permanently faulted
engine would have started reporting as an authentication failure, sending an
operator after a credential problem that does not exist.
The Jina key fallback chain read JINA_AI_API_KEY three times in a row
before falling through to JINA_AI_TOKEN, so two of the four slots were
dead. Jina's own documentation publishes JINA_API_KEY, and litellm's
rerank validate_environment already tells users to set that name, but
nothing ever read it: a user who set only JINA_API_KEY got no key
resolved and Jina answered AUTH_MISSING_API_KEY.
Replace one of the repeats with JINA_API_KEY and drop the other.
JINA_AI_API_KEY stays first so no install that resolves a key today
changes which key it picks.
The generated client bakes absolute query engine paths at build time, and
prisma-python scans them before it reads PRISMA_QUERY_ENGINE_BINARY. That
scan propagates EACCES rather than skipping a candidate, so a path baked
under the build user's HOME crashes client startup with a bare
PermissionError for every other uid, and the documented override cannot
recover from it.
Assert in the runtime stage that every baked query engine path sits under
the fixed, world-readable /opt/prisma bake, so a regression in the
generate step breaks the build instead of shipping an image that only
starts under the uid that built it. Adds an image-level test that runs
the same resolution as an arbitrary non-root uid.
Guardrails silently skipped three surfaces on the Anthropic Messages
path, so an agent loop driven by /v1/messages ran unguarded:
- The Anthropic input translation never walked tool_result blocks, so
content returned by a local tool (a curl, a file read, an MCP call)
reached the model unscanned in both the string and list content
shapes, images inside a tool_result included.
- tool_permission only understood ModelResponse, so an Anthropic
non-streaming response or a raw SSE stream carrying tool_use blocks
passed through with no rule ever evaluated.
- ContentFilterGuardrail scanned inputs["texts"] but never
inputs["tool_calls"], so the arguments a model proposes for a tool
call went unchecked.
Tool call arguments are parsed as JSON before filtering so a MASK
action rewrites the value and leaves the payload valid JSON; non-JSON
arguments fall back to scanning the raw string. Denied tool_use blocks
are dropped from the Anthropic content array and replaced with a text
block, and stop_reason resets to end_turn when nothing tool-shaped
survives.
get_api_key resolved the ai21 key from AI211_API_KEY, with a doubled 1. Every other
ai21 code path reads AI21_API_KEY, including the validate_environment branches that
report it as the missing one, so the name a user is told to set was ignored here.
No user path reaches this branch today, since every provider-resolution site rewrites
custom_llm_provider to ai21_chat and sets the key from a correctly spelled read first,
so this is a correctness fix rather than a bug fix. It is worth making because the
env-var documentation gate reads this call site: leaving the misspelling in place would
require a row for AI211_API_KEY in the environment variables reference table, which
would turn a typo into public API
* chore(typing): replace Any seams with real types across responses, proxy, and provider adapters
Replace Any-typed payload dicts, record shapes, and provider request/response
seams with TypedDicts, Protocols, and precise annotations in the ten litellm/
files carrying the highest combined basedpyright reportAny + reportExplicitAny
counts. No behavior changes.
Adds a regression test covering the managed-id list path so a prisma client
missing the managed tables keeps returning a fail-closed empty page.
* fix(passthrough): walk scalar request bodies through managed-id rewrite again
The top-level dispatch in rewrite_body_ids only handled dict and list
bodies, so a truthy scalar JSON body (bare string, number, bool) hit
dict.items() and raised AttributeError where the merge base passed it
through, and a bare managed-ID string body lost resolution. Restore the
base behavior by dispatching through _walk, widen the implementation to
object with a catch-all overload, and pin both paths with regression
tests
S3 rebuilds the canonical request from the wire path with single
percent-encoding, which botocore models as S3SigV4Auth. Generic SigV4Auth
quotes the already encoded path a second time, so an object key holding any
character that percent-encodes was signed over %2520 while the request
carried %20, and S3 answered 403 SignatureDoesNotMatch.
The S3 logger was corrected in #35726; the Bedrock managed-files upload and
retrieval paths copied that same pre-fix pattern and were left behind, so a
configured bucket prefix with a space 403s every file upload and every file
content read.
heal_incomplete_nodeenv_cache() stats a $HOME-derived path with a bare
Path.is_dir(). pathlib only swallows ENOENT-shaped errnos, so a cache
directory the process cannot search raises PermissionError instead of
answering False. Images bake that cache under the build user's home, whose
mode is 0700, so a container started under any other uid dies there before
the Prisma CLI is ever invoked, and the migration never runs.
Tolerate OSError while inspecting the cache, matching the guard
nodeenv_cache_dir() already carries, so an unreachable cache means there is
nothing to heal rather than a crash. This restores the never-raises
contract ensure_prisma_toolchain() documents.
Folds every successful auto-routed request into LiteLLM_AutoRouterSession with one
conditional upsert at spend-write time, classifying each turn (same model, first
visit, return to tier, out of order) against the row's own columns so nothing is
read before the write. The upsert's placeholders and argument tuple both derive
from the transaction dataclass's own field order, so the SQL and the call site
cannot drift apart. GET /auto_router/benchmarks aggregates the rollup, grouped
by the full (router, type) identity, and never scans LiteLLM_SpendLogs. A turn's
cache interaction is derived once from its usage record (savings.py owns the
extraction; compute_savings_spend derives cache reads from usage_object itself),
hits are counted order-independently so the overall hit rate matches its covered
denominator, caller-chosen session ids are bounded before entering the primary
key, and a poisoned statement drops only its own session's remaining turns.
Return misses inside the recorded TTL are named for what the telemetry shows
(within_ttl) rather than a presumed cause, since a provider can evict early.
Savings ride each router's derived baseline by default, so the response carries
no deployment-wide baseline label. Rollup retention has its own
maximum_autorouter_session_retention_period setting, pattern-identical to the
spend-logs knob and running in the same cleanup job on its own cutoff. Every
drain trigger sizes the queues through one owner and the enqueue honors
disable_spend_logs beside the tool-usage queue it mirrors.
* fix(autorouter): match CJK keyword_tier_rules that regex word boundaries miss
Single-word keywords were matched with a \b...\b regex. Every CJK character is a
regex word character and CJK is written without spaces, so \b never fires between
two of them and a rule like 发票 silently missed 我需要开发票, falling through to
complexity scoring instead of the configured tier.
Keywords containing CJK now match as plain substrings, the same way multi-word
phrases already did. The gate reads the keyword rather than the prompt, so a
keyword with no CJK in it keeps word boundary matching regardless of the script
the prompt is written in.
* fix(autorouter): cover Han extensions in planes 2 and 3, not just up to U+2FA1F
The supplementary range stopped at U+2FA1F, so Extension G and H ideographs kept
the word boundary path and stayed unmatchable. Both planes are dedicated to CJK
ideographs, so covering them whole also handles later extensions without chasing
each new block.
