* fix(router): preserve native baseline identity and accounting
* fix(router): preserve injected system caches in native baselines
* fix(router): prepare native baselines through shared request owners
* fix(router): capture native baseline fields from the provider schema
* refactor(router): reuse native provider parameter discovery
* fix(router): keep long native baselines and abstain after compaction
Message history no longer counts against the settings snapshot budget, so long
and non-ASCII native sessions keep modeled baselines. Selected-tier compaction
now abstains because the baseline would otherwise inherit the compacted history.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(router): judge implicit caching against the selected request
The implicit-cache guard compared the selected response's cache usage with the
projected baseline's breakpoints, so selected-tier cache markers made a usable
unmarked baseline plan look like unexplained caching. The guard now checks the
selected wire request. Also removes a stamp-reuse branch that could never run
because routing clears the stamp first; every pass already captures caller
settings from fresh kwargs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* test: delete unconditionally skipped legacy tests
* test: move whole-unit legacy test files into tests/unit
* test: keep moved legacy tests free of import-time global state
* test: keep the module-level invocation scan pointed at tests/local_testing
* ci: drop the agent_testing CircleCI job emptied by the move
* test: fix moved-test isolation and router coverage
* test: add Tinyfish search package marker
* test: isolate moved tests from logger state leaks
* test: isolate Helicone logging fixture state
* test: isolate Vertex pass-through credentials between moved tests
* test: cancel S3 periodic flush tasks started by moved tests
* ci: restore CircleCI assistant test selection after move
* test: prevent Datadog datetime import shadowing
* ci: drop the litellm_assistants_api_testing CircleCI job emptied by the move
* test: deduplicate imports in rebased unit tests
* test: remove duplicate passthrough router patch import
* test: remove moved legacy source files after rebase
* test: align moved tests with rebased main
* test: carry main's legacy-file edits into moved destinations
* test: make the moved cost map fallback tests assert the fetch and the backup
The four fallback cases only checked the result was non-empty, so they still
passed with integrity validation disabled. They now inject a mock client, assert
one fetch happened, and assert the result is exactly the local backup with the
fallback reason recorded.
---------
Co-authored-by: yuneng <yuneng@berri.ai>
* test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata
* docs(e2e): name every markerless harness test file that carries no Subject
* test(e2e): keep the step discovery comprehensions to one for clause
* fix(ui): show Projects nav to team and org admins
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): satisfy frontend lint budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(ui): format leftnav regression tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(projects): let org admins see projects of every team in their orgs
/project/list and /project/info only knew proxy admins and team members, so an
org admin saw projects only for teams they had personally joined. Both now use
the same team access check as /team/info.
* fix(ui): one shared Projects access rule for nav, data and actions
The Projects query skipped global org_admin users, the page-visibility picker
could never offer Projects, and New/Edit showed to users the backend would
reject. Nav and queries now share one rule, Projects is selectable in the
allowlist, New/Edit follow team_admin_editable_team_fields, and the project
modal only lists teams the user administers.
* fix(projects): record IN-list bounds for project visibility filters
Both filters are bounded by one caller's team memberships and admin orgs. Also
cover a project whose team was deleted.
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
* fix(router): price a model group from the deployments that serve it
A model group's info read composed the group's own model_group_alias
entry into its deployments, a hop the router never takes: an alias is
resolved exactly once at request time, so a group reached as an alias
target is served by its own deployments. For the chain X -> T -> U the
price read for X included U's deployments too, and the free-model
budget waiver refused a free request to X on an over-budget key, while
GET /model_group/info reported U's providers and price for X.
The group info read now prices a group from the deployments routing
serves it with: the ones named after it, the routing group of that
name, or the wildcard route matching it when neither exists. The
budget waiver, GET /model_group/info, the rate limiters, and the
response headers all read the same set as routing. get_model_list
keeps its behavior for every other caller.
* test(router): give the paid fixtures explicit per-token prices
* test(router): call the routed-group read by name so the router coverage gate sees it
* test(integration): audit the alias chain budget waiver on every route, shape, and outage
Thirty-four cells under the management group prove an over-budget key is served through an alias chain entry at the price of the deployment that serves it, on chat, responses, and messages, sync and streamed, through the OpenAI and Anthropic SDKs and raw httpx on both replicas, with the chain middle, the reverse chain, a cost-map priced middle, a ghost middle, wildcard and routing-group targets, malformed and hostile inputs, a cached reply, a repointed alias, a provider failure, and two chaos bursts (a killed worker, a scripted outage)
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(router): retry a /v1/messages stream the provider drops before the first content chunk
A /v1/messages stream that the upstream closed before any content reached the
client answered an error event after a single attempt, so the router's
num_retries never applied to that drop. The pre-content failure is now retried
within the model group before the fallback chain runs, with the budget resolved
the way a failure raised before the stream opened resolves it: a retry policy
that names the error class, then the request's num_retries, then the
deployment's, then the router's. A drop after content reached the client keeps
surfacing the provider's error after one attempt.
Fixes#44238
* fix(router): hand a retry's non-retriable error to the fallback chain and type the retry helpers
A retry that failed before its stream opened with an error no retry covers raised straight to the
client, skipping a fallback the first attempt would have used. assert_never now comes from
typing_extensions so the router imports on Python 3.10, and the retry helpers read their kwargs
through typed narrowing instead of Mapping[str, Any]
* fix(router): cast the untyped router fallback defaults the stream retry gate reads
The retry gate passed the router's fallback attributes, declared without element types, to the
typed request override helper, which basedpyright counted as new unknown-argument errors
* fix(router): consult context_window_fallbacks when a retried /v1/messages stream overflows
A retry attempt raising ContextWindowExceededError reached the fallback chain inside its
mid-stream envelope, so only the regular fallbacks list matched. The fallback attempt now
unwraps it the way it unwraps a content policy error. The new router helpers are covered for
the router code coverage check with two direct-call tests and named covering tests
* fix(router): retry a 408 raised by a /v1/messages retry and honor deployment num_retries before the stream opens
* fix(router): attribute a retried /v1/messages stream to the deployment that served it and bound the retry-policy hold
* fix(router): retry /v1/messages error frames under their retry-policy class and keep the first drop's committed budget
An `event: error` frame that arrives before the first content delta now raises the exception class the pre-stream mapping gives an HTTP answer with the same status (429 RateLimitError, 500 and 529 InternalServerError, 503 ServiceUnavailableError, 504 Timeout), so a retry policy's per-class budget governs it the way it governs the error before the stream opened. The status the client sees is unchanged
A retry that lands on a sibling deployment keeps the budget the first drop committed to, read back from the request's attempted_retries and max_retries, instead of recomputing it from the new deployment's num_retries, matching the pre-stream retry loop
* refactor(anthropic): keep the error-frame exception mapping under llms and type the retry test helper
The status-to-exception mapping an `event: error` frame gets before the retry policy is consulted now lives next to the Anthropic error status map in llms/anthropic/common_utils.py, with its own unit test, and the two-deployment retry test helper takes explicit typed parameters instead of a bare dict and untyped kwargs
* refactor(anthropic): map an error frame's status with explicit returns on every path
* fix(router): map stream error frames through the pre-stream exception mapping
An overloaded `event: error` frame on a /v1/messages stream now raises the InternalServerError a 529 answer maps to, built by exception_type from the frame's own body, so one retry policy class governs the error before and after the first byte; a failed fallback after such a frame answers 500 like every other litellm path instead of the frame map's 503
A model_group_retry_policy that does not parse (a non-integer budget, an entry that is not a mapping) no longer fails every healthy stream of that group before its first attempt: the stream runs with no policy and the plain num_retries budget, with a warning naming the group
* fix(router): forward an error frame nothing can take over for as the provider sent it
A pre-content error frame whose class the retry policy grants no retry, with no fallback configured, raised an HTTP error only on the first attempt while the same frame after exhausted retries reached the client verbatim. Both now pass through as sent, the way the merge base forwarded every frame.
* test(integration): audit /v1/messages pre-content retry across routes and budgets
Adds the /audit cells for the pre-content stream retry: the native Anthropic route
(drops and error frames before content, HTTP rejections before the stream opens, SDK
sync and async, after-content and non-retriable controls, budget exhaustion, cache
twin, spend row and headers), the chat and responses bridges, the generic routes
(responses, chat, vllm pass-through, Gemini generateContent, fine-tuning jobs list),
owned two-worker proxies for router-level budgets, retry policies and fallbacks, and
two chaos cells (a worker killed mid burst, an outage on every first attempt). Shared
helpers for scripted Anthropic SSE upstreams and OpenAI-compatible wire replies live
in tests/integration/_support
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* ci: move Postgres, MCP and Redis suites to CircleCI integration
* ci: throwaway, drop tests/proxy_behavior from its CircleCI job to show assert-ci-coverage fails
* ci: revert throwaway assert-ci-coverage check
* ci: keep the e2e helpers the gate tests still use
* ci: move the roi-database Postgres shard to CircleCI integration
* ci: run redis-compat without CircleCI's Azure and cassette env, cover postgres_suite test_path
* ci: match the GitHub env for the moved Postgres and Redis jobs
* ci: unset provider keys in the CircleCI MCP job and drop unused e2e-stack helpers
---------
Co-authored-by: yuneng <yuneng@berri.ai>
* feat(proxy): serve a Codex-native model catalog with per-model service_tiers from /v1/models
GET /v1/models and /models answer Codex CLI's catalog fetch (the request
carrying its client_version query parameter) with Codex's own
{"models": [...]} shape: a model Codex knows keeps the metadata of its
bundled 0.159.3 catalog (vendored), any other model gets Codex's fallback
entry, and model_info.service_tiers becomes each entry's service tiers so
Codex offers them as slash commands that send service_tier upstream.
Without the parameter the OpenAI list shape is unchanged. The CLI's
litellm agents codex catalog shares the same builder.
* fix(proxy): offer a Codex service tier only when every deployment of the model lists it
* fix(codex-catalog): an invalid service_tiers value offers no tier for the model
* fix(codex-catalog): read service tiers off the deployments the key's team can route to
A tier is offered to Codex only when every deployment of the model name a
request from the key's team can route to lists it, so another team's
deployment of the name and a deployment an admin paused via model_info.blocked
no longer withhold or add tiers for requests that never reach them
The catalog's always-null fields are annotated NoneType so the module imports
under pydantic 2.12.0 on Python 3.14, the lowest pin the MCP resolve job
installs, which rejects a None annotation with a None default
* test(codex-catalog): drop the redundant module docstring and sort the imports
* test(integration): add the Codex catalog audit cells and the multi-worker convergence note
* test(integration): clean up every catalog test model and answer the refresh GET
* fix(proxy): keep tiered models under Codex's catalog cut and resolve alias tiers
Under Codex's 1 MiB catalog limit the entries offering a service tier are kept
ahead of those offering none, each group in model_list order, with every kept
entry at its listing position, so the model an operator configured tiers for
survives a wide key's long listing. A model_group_alias row reads its target's
deployments, so it carries the target's tiers and stock metadata under the
alias name.
* fix(proxy): pick Codex catalog metadata per team and skip entries too large for the cut
The upstream model that selects Codex's stock entry was read off the first deployment of a name
without checking the key's team, so a team whose requests route to a different deployment could be
handed another team's prompt, reasoning levels, and tiers. The upstream model and the tiers now come
from the same team-aware selection routing uses, and a caller with no team reads the deployments no
team owns
The byte cut kept a prefix of the tier-first order, so one entry larger than the whole limit emptied
the catalog. An entry too large for the bytes left is now passed over and the smaller ones after it
are still kept
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Response cache reads and writes open cache.get llm_response and cache.set llm_response phase spans with their Redis spans nested underneath, on the Python path and on the native Rust path, and deployment selection runs inside a route {model_group} phase so the cooldown, usage and model-id reads the router issues nest under it before chat {model}. The autorouter classifier call nests under that route phase as well and carries its typed internal origin on litellm.request.purpose, so it is told apart from the provider attempt. Service spans are named {service}.{verb} {target} from a low-cardinality key family the producer declares (llm_response, auth_objects, spend_counters, router_cooldowns, claude_code_session_router_binding, rate_limits, pod_lock, budget_reset, ...) instead of the raw method or a per-request pipeline length; a pipeline flush is targeted by the one family its ops share or by mixed with the sorted families on litellm.redis.families, a batch op keeps the family it was declared under whichever pipeline or standalone read settles it, and the ambient family labels Redis spans only, never the DB write-back a task spawned inside that context performs later. The raw method stays on litellm.service.call_type and on the Prometheus and Datadog labels. Caller attribution is carried across asyncio task boundaries on a ContextVar so forwarder-only chains no longer surface, the raw cache key is dropped from Redis span metadata, pipeline op counts land as an integer attribute, every call_type the Redis cache layer emits maps to a verb, and a scan over litellm/ and enterprise/ fails when a Redis producer, batch reservation included, declares no key family.
A V2 logger built for a key or team logging entry while the operator's V2 logger is already registered keeps only the exporters its own preset contributed, whether or not the operator holds credentials for that backend, so every chat span no longer reaches the operator's collector twice. A span the success callback has to open itself, with no pre-call carrier, starts at the provider handoff (api_call_start_time) instead of the logging object's creation.
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(guardrails): encrypt guardrail litellm_params secrets at rest
* fix(guardrails): keep salt-key encryption on master key rotation and retry rows edited mid-rotation
- rotate guardrail params under LITELLM_SALT_KEY when set, matching the key reads decrypt with
- re-read and retry a row whose updated_at moved during rotation, up to GUARDRAIL_ROTATION_ATTEMPTS
- build decrypted Guardrail rows and the rotation count without mutating locals
* refactor(guardrails): retry guardrail rotation by bounded recursion instead of a rebound cursor
- each attempt re-reads the row and recurses with attempts_left - 1, so no loop variable is rebound
- cover the give-up path after GUARDRAIL_ROTATION_ATTEMPTS writes
* test(guardrails): drive the real guardrail rotator from the master key rotation test
- inject an encrypted guardrail row through the prisma client instead of replacing the GuardrailRegistry method
- assert the written params decrypt under the new master key
* Annotate guardrail param encryption collections for type-discipline gate
* Type guardrail param recursion through validated JSON containers
* Type guardrail registry test helpers and drop section comment
* Reject client-supplied encrypted values in guardrail litellm_params
* Allow depth-bounded contains_encrypted_marker in the recursion detector
* Keep a loaded guardrail when its DB params do not decrypt with the current key
* Apply other DB edits while keeping loaded values that do not decrypt, including PATCH models
* Keep the loaded guardrail when an undecryptable param has no loaded value
* Drop suppressions the type discipline gate on main now reports as unused
* Assert what the reinitialized guardrail holds after an edit to an undecryptable one
* Drive the rotation sync tests through a registered guardrail instead of patching reinitialize
* Type the rotation test helpers and drop the new test docstrings
* fix(guardrails): refuse to approve a submission whose params do not decrypt
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>
* refactor(proxy): extract shared spend log read policy
* test(proxy): use named bindings for spend scope regression
* test(proxy): reuse existing spend log query harness
* test(proxy): cover spend log permission lookup adoption
* chore(proxy): relocate existing spend query baseline
* refactor(proxy): make scope query returns explicit
* refactor(proxy): inject deferred log permission lookup
* test(proxy): cover teamless management compatibility lookup
* refactor(proxy): compose user and team log grants
* refactor(proxy): share generic authorization composition
* refactor(proxy): compose trace read permissions
* refactor(proxy): centralize spend and trace authorization
* refactor(proxy): strengthen spend and trace scope types
* refactor(proxy): flatten log read scope into owned logs
Replace the AnyOf grant tree with a flat OwnedLogs(user_id, team_ids) scope,
and OwnedTraces(logs, api_key_hash) for traces, since every consumer flattened
the tree back into that shape.
A caller with no user id now gets an empty scope instead of matching ownerless
rows through Prisma's IS NULL. The dead request_id guard in ui_view_spend_logs
is removed, and the management facets inject the log team lookup and reuse
read_scope_sql instead of the list shim.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(proxy): run spend scope tests through one SQLite emulator
Replace the string-matching payload emulator and the hand-rolled Prisma where
interpreter with one SQLite helper that runs the real scope SQL. Session scope
tests now go through the endpoint, including the no-user caller that must not
match ownerless rows. Drop duplicated lookup-failure and trace mapping cases.
load_permitted_log_team_ids returns no teams without a database instead of
relying on the resolver's broad except.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(proxy): unify log and trace ownership permissions
* test(tracing): align fixtures with ownership read scopes
* refactor(tracing): align query scopes with row ownership
* refactor(spend): make ownership SQL predicates explicit
* test(spend): validate ownership SQL against PostgreSQL
* docs(traces): drop key-row visibility from query help guide
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): reach the empty-memberships branch in team lookup test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(ui): regenerate dashboard API types
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@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>
* test: remove 130 legacy tests owned by stronger unit proofs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: list router _embedding and _aembedding as covered via public embedding calls
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The shared exclusion predicate negated a PostgreSQL ANY comparison without handling NULL, so NULL entity ids evaluated to UNKNOWN and dropped out of the Unassigned bucket whenever exclude_*_ids was set. The paginated daily rows Prisma filter had the same NOT IN shape and gets the same IS NULL OR NOT IN treatment
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The two SpendLogs index migrations shipped in v1.103.0 each break one table shape: the plain CREATE INDEX holds a SHARE lock on a large unpartitioned table and the CONCURRENTLY one fails with 0A000 on a partitioned parent. Both files are now inert and the indexes are built by a table-driven, shape-aware step after migrate deploy: CONCURRENTLY on a plain table, ON ONLY the parent plus per-partition CONCURRENTLY and ATTACH PARTITION on a partitioned one. The migration job builds them synchronously and exits non-zero on failure; a serving proxy that ran migrate deploy itself builds them in the background off the readiness path. A valid index of the same definition under another name is renamed and reused, an invalid one is rebuilt, and extra copies are reported with their DROP INDEX statement instead of being dropped. The migration checker rejects any CREATE INDEX on LiteLLM_SpendLogs or LiteLLM_ErrorLogs in future migrations
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The pytest-postgresql based proxy tests moved to tests/integration on the real
Postgres harness in #43996, so nothing loads the plugin anymore. uv.lock is
edited by hand to drop the package and its now orphaned mirakuru and port-for
deps; uv lock --check passes and a full relock resolves the same package set
* chore(lens): remove deployment screenshots
* refactor(lens)!: rename internal engine package and API
* fix(lens): pin worker image for renamed API
* test(lens): cover fresh and populated rename migrations
* fix(lens): protect db-push upgrades and restore routing and CI
* fix(lens): resolve migration tables across schemas and include database driver
* feat(e2e): give e2e tests typed metadata for what they drive
@meta(Subject(domain, route, providers, models, capabilities, mode)) declares
what a test is about with closed enums, and each field lands in the JUnit report
as a property. The quota_management suites are the first to declare it.
* docs(e2e): say e2e_metadata avoids litellm, not that it is stdlib-only
It already imports pydantic and pytest, both of which the suite needs to collect. The rule that matters is no litellm import
* test(e2e): declare models through the constant each test drives
43 @meta declarations in quota_management typed the model name out again, so changing the call would leave the coverage report naming the old model. Each file now has one constant used by both, and a guard fails on any model written as a string literal in @meta
* refactor(e2e): set route only when the endpoint is what the test checks
A budget or rate-limit test whose chat call only triggers the block now leaves route unset, since its steps already name the call. Tests of an endpoint keep it: budget CRUD, key creation, spend reporting reads, and the per-endpoint spend tests for chat, messages, embeddings, batches and health. The two /spend/logs tests tagged chat_completions are now spend_reporting
* refactor(e2e): build the declared properties without mutating a list
subject_properties seeded a list and grew it with append and extend. It now flattens one tuple per field, and the plural-name table is a read-only mapping
* fix(e2e): tag each spend-route probe with the endpoint it checks
The breadth test gave all 33 probes spend_reporting, so /key/list, /user/list, /team/list, /organization/list and /customer/list counted as spend reporting. Each case now carries its own route, with organization and customer management added to Route
* feat(e2e): record each e2e test's steps, starting with ProxyClient
@step on a harness method records a plain-English line for every call, in
order, as repeated JUnit step properties. Labels are templates filled from the
call's parameters, like "Generate a virtual key with models: claude-haiku-4-5
and rpm limit: 3", and secret request fields are marked Field(repr=False) so
they never print. ProxyClient and the rate-limit QuotaClient carry steps first;
the other harnesses follow one area at a time. The recorder and JUnit tests run
in the Code Quality workflow's test_e2e_metadata step.
* docs(e2e): rewrite the recorded test steps guide in plain language
* fix(e2e): keep logging callback credentials out of recorded steps
* fix(e2e): mask the run's credentials in every recorded step
* fix(e2e): attach steps before the oauth failure snapshot
The failed setup or call report of an mcp_oauth_live test copied user_properties before the steps were attached, so it carried no steps. Every setup and call report now takes its properties after the steps attach
* fix(e2e): name the saved credential in its recorded step
The create_credential label read credential_info, which defaults to {} and is never set by the live callers, so the step printed nothing after 'for'. It now reads the required credential_name, and a guard fails on any label that reads a field with a default
* feat(tracing): bring current ingestion prerequisite onto main
Port the prerequisite implementation from BerriAI/litellm#43915 at 5aacd57455 so Lens does not depend on the retired tracing stack.
* feat(lens): add trace analysis and standalone worker
* fix(lens): clarify review limits and finalize main integration
* fix(lens): simplify worker setup and show the next check
* fix(lens): simplify analyzer setup and resolve integration failures
* fix(lens): preserve durations and evidence from later trace reads
* fix(lens): trust server context for internal analysis exclusion
* fix(lens): pin reviewed analyzer image and verify request inclusion
* test(lens): select time units before entering custom duration
* test(lens): allow the standalone analyzer lifetime HTTP client
* test(lens): run analyzer tests in active proxy coverage shard
RedisBatch: one pipeline per Redis backend for independently declared operations (MGET, GET, Lua
scripts, INCRBYFLOAT, SET, DEL), a future per operation so each owner keeps its own fallback, Redis
Cluster hash-slot fallback. A request-scoped batch middleware shares that pipeline across the auth
identity reads and write-back, the spend counter MGET, the rate limiter Lua groups and the routing
read. A rate-limit denial stands when another pipelined group fails; every pipelined group is refunded
on rejection; local cooldowns win over the prefetch.
The routing prefetch failure log line strips request line breaks (CodeQL py/log-injection)
Resolves LIT-8882
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): keep the provider's served service_tier on streamed chunks and spend rows
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): satisfy type-discipline and strict ruff budgets
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): stamp the served service_tier on every Responses bridge chunk
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-adapter): expose streamed chunks so disconnects bill partial spend
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(service-tier): cover anthropic and responses served-tier billing paths
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-adapter): return a chunks-exposing stream so disconnects bill partial spend
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(service-tier): bill disconnects through the router's anthropic stream wrapper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: apply ruff format to the anthropic stream changes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(coverage): ignore delegating properties the ast scan cannot see
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: keep the cast-ok reasons on the cast call line
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover served service_tier billing for streamed chat and messages, complete and disconnected
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic-cache): delegate chunks/messages/model through the messages stream cache writer
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(streaming): keep service_tier on OpenAI-compatible parsed chunks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(streaming): parameterize delegated chunks and messages types
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(tests): follow the anthropic pass_through rename after merging main
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(anthropic): drain the logging worker between response cache tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): cover azure, databricks, responses bridge and gemini served tiers in the stream billing integration test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(databricks): keep the served service_tier on streamed chunks and bill it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(databricks): type the served service_tier chunk without a loose kwargs dict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost): bill the served service_tier over the requested one
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost): drop explanatory comment from the tier resolution
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: kerry <kerry@berri.ai>
* ci: warn on SQL IN lists with no written bound
Postgres caps a prepared statement at 32,767 bind parameters and a
membership filter binds one per value, so an IN list built from table
data breaks once the table outgrows the cap. That is how the budget reset
job froze every due budget (LIT-7535, #40564).
check_unbounded_in_lists.py reports every Prisma "in" / "not_in" filter
whose value has no fixed size and every raw SQL literal that splices a
list in after "IN (", unless the line carries "# bounded-ok: <reason>".
It only warns for now: the output is the inventory for RCA action item
AI-1, and it exits 0.
* ci: decide a constant IN list by its module binding, not its casing
An ALL_CAPS name imported or filled at runtime is as unbounded as any
other, so a name now passes only when the module binds it once to a
value of fixed size. Adds Final to the locals a loop does not forbid.
* ci: only a frozen module value makes an IN list constant
A module list bound once could still grow through append or extend, so
a name now counts as fixed only when it is bound to a tuple, frozenset
or constant. Trims the module docstring to what a reader needs.
* ci: chunk Prisma IN lists with a shared helper and fail on new unbounded ones
Add litellm.repositories.bounded_in: find_many_in, count_in, update_many_in
and delete_many_in split a deduplicated value list into 5,000-value chunks,
AND each chunk with the caller's where, run them in order (a transaction
handle works) and combine the results. Writes take a required atomicity
argument, and a where that already filters the chunked field is refused.
check_unbounded_in_lists.py now fails CI on any finding missing from
unbounded_in_baseline.txt and on any stale baseline entry, so the baseline
only shrinks. Entries are keyed by path, enclosing scope, kind, field and
occurrence, not line numbers. The helper module is exempt, a constant
spread into a frozen tuple counts as fixed, and messages point at the
helper for "in" and at an array parameter for "not_in" and raw SQL.
A real-Postgres integration test shows a raw 40,000-value filter rejected
for too many bind variables while the helpers handle it.
* refactor: rename bounded_in to chunked_in and let callers pick a chunk size
The helper module is litellm.repositories.chunked_in, and its unit and
integration tests, the checker's exemption path and its finding messages
follow the new name. The `# bounded-ok` marker is unchanged.
find_many_in, count_in, update_many_in and delete_many_in take a
keyword-only chunk_size, defaulting to IN_LIST_CHUNK_SIZE (5,000). A value
below 1 or above MAX_IN_LIST_CHUNK_SIZE (30,000) raises ValueError before
any query, which leaves the rest of the filter headroom under Postgres's
32,767 bind-parameter cap.
* refactor: flatten chunked_in's stacked comprehensions with chain.from_iterable
LIT014 (#42650) caps a comprehension at one for and one if clause. The four nested walks in the helper now chain their iterables instead, with the same order and results.
* refactor: recover user details with find_many_in, sending chunks as lists
_details_for_user_ids reads users through find_many_in instead of a raw
"in" filter, so its lookup stays under the bind-parameter cap for any
number of recovered keys. Up to 5,000 ids it still sends one find_many
with the same where dict, and a PrismaError from any chunk is still
logged and treated as no details.
The helper now sends each chunk as a list, so a chunked filter equals
the dict a hand-written call would send and a migrated call site's
existing assertions keep passing.
The site's baseline entry is gone.
* ci: skip functional TypedDict field maps in the unbounded IN list check
The dict passed as the field map of TypedDict("Name", {...}), or as its fields= keyword, names fields: an "in" or "notIn" key there is a type, not a filter. Only that dict is skipped, for TypedDict, typing.TypedDict and typing_extensions.TypedDict; a filter nested in a field value or passed to any other call is still reported. The two types/proxy/management_endpoints/team_endpoints.py entries leave the baseline, which is now 156.
* fix: refuse an update_many_in whose data writes the chunked field
Chunks run one after another, so an update that sets the chunked field can move a row into a later chunk, which updates it again and counts it twice: values ["old", "new"] with chunk_size=1 and data={"id": "new"} does exactly that. update_many_in now raises ChunkedFieldWriteError before any query when data has the chunked field as a top-level key, in any form, including Prisma operators such as {"set": ...}.
* docs: cut the unbounded IN list checker's docstring to what it flags and how to clear it
It now says what is reported, the three ways to clear a finding, and how the baseline and --update-baseline work, in 11 lines. The per-shape detail lives in the tests.
* ci: key an unbounded IN list finding by its filtered expression too
A baseline key of path, scope, kind, field and occurrence let a PR delete
a baselined filter and add a different unbounded one on the same field in
the same function, and the new one took over the old key. The key now
also carries the filtered expression's source, whitespace-normalized
(the Prisma value, or a raw-SQL `IN (...)` slot), so that swap reads as
one new and one stale entry and fails the run. The same expression
re-added in the same function is still the same finding.
Every baseline entry is rewritten in the new form; the 156 findings are
unchanged, and only occurrence indexes renumber where one field had
several different expressions.
* fix(sentry): scrub PII and secrets inside object reprs and nested locals, add SENTRY_SEND_DEFAULT_PII opt-in
* fix(sentry): keep the SDK denylist and filter the request headers a virtual key arrives in
* fix(sentry): leave source context lines unscrubbed
* fix(sentry): filter bracketed secret values and cap the JSON walk depth
* ci(deps): install sentry-sdk in the proxy-dev group so the unit shards import it
* fix(sentry): scrub source-context names outside real stack frames
* fix(sentry): tie the key pattern floor to the custom key minimum
* fix(sentry): keep the key pattern floor at or below a generated key's length
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* ci: run the unit_selection.sh shard files on every event instead of only fork pull requests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci: rename fork-flag to unit-flag now that it applies on every event
* test: move tests/test_litellm root and small trees into tests/unit
Pure renames, no content changes. Follow-up commits in this PR fix
references, merge the three files that already existed in tests/unit,
keep live-provider tests in tests/test_litellm and wire CI.
* test: carry tests/test_litellm conftest isolation into tests/unit
Callback lists, routing fallbacks, cached HTTP clients, logger state, AWS,
proxy-URL and keychain env, and session-end client cleanup now reset for
unit tests too. The environment isolation owns its MonkeyPatch so a test's
own monkeypatch is undone before the model-cost teardown runs.
* test: merge, split and prune the moved root and small-tree tests
Merge batches/test_batch_utils.py and the chat_completions and messages
dispatch tests into the files that already existed in tests/unit. Keep
the live Gemini interactions tests, the async image-fetch format test and
the OpenAI embedding scorer test in tests/test_litellm since they need
real network or keys. Put test_router.py under tests/unit/test_router so
the existing package no longer shadows it. Delete eight tests the audit
found superseded by stronger ones kept in this move.
* ci: run the moved root and small-tree tests under their legacy flags
Add the misc and responses-caching-types flags to unit_selection.sh and
CircleCI, extend enterprise-routing and mcp-integration, and point the
legacy GHA shards, Makefile, redis-compat workflow, merge smoke manifest
and change classifier at the new paths.
* test: make the new tests/unit directories packages
tests/unit/test_package_layout.py requires every directory to carry an
__init__.py, and without one the moved and retained
test_litellm_responses_bridge.py modules collide on import.
* test: scope the unit socket block to tests/unit in shared sessions
The GHA shards collect the legacy test-path and the unit selection in one
pytest session. The unit conftest's loopback-only block leaked into legacy
modules that reach the network at import. The legacy conftest now lifts the
restriction at collect and setup time, and the unit conftest re-applies it
when collecting its own modules.
* test: give the shard-script tests their own GITHUB_OUTPUT
They only passed where the runner set it. The CircleCI unit job's env
allowlist drops it, so the script's redirect failed there.
* test: point the router and module-deletion checks at tests/unit
router_code_coverage and code_qa_check_tests only searched tests/test_litellm,
so the moved router tests no longer counted. The two silent-experiment tests
the audit deleted were the only direct callers of those methods; they are
replaced with tests that assert the forwarded shadow request and the
recursion guard.
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(router): match provider-prefixed fallback keys for bare model groups
* fix(router): infer the fallback key's provider the way routing does for bare model groups
A bare model group served by a wildcard deployment (claude-sonnet-4-6 routed to anthropic/*) now finds a fallback keyed <provider>/<group>. The provider is inferred through one shared helper, inferred_provider, which the pattern router already used inline, so the fallback lookup and routing agree on the prefix. The lookup only infers a provider when some fallback key ends in /<group>, so alias-style groups never hit the resolver
* fix(router): resolve context window and content policy fallback keys through the shared lookup
---------
Co-authored-by: Jason Dougherty <jasondoc3@gmail.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* ci: fix the litellm-tests unit job with sysmon coverage, an env allowlist and coverage upload on failure
* test: replace key-dependent proxy, enterprise and mcp unit tests with synthetic values and integration and e2e coverage
* test: drop key reads at the legacy proxy, enterprise and mcp paths and wire the gemini pass-through split
* ci: move caching, proxy-extras, gateway and enterprise tests into tests/unit and run them from litellm-tests under their legacy flags
* ci: move caching, proxy-extras, gateway and enterprise tests into tests/unit and run them from litellm-tests under their legacy flags
* ci: move tests/proxy_unit_tests to tests/unit/proxy and run the proxy-db shards from litellm-tests
* ci: fail the unit shard when circleci tests split errors
* test: drop restating comments from the gemini pass-through split
* build: point the local proxy unit targets at the nested tests/unit/proxy tree
* ci: exit the unit shard cleanly when circleci tests split assigns it no files
---------
Co-authored-by: yuneng <yuneng@berri.ai>
* ci: add dashboard and core smoke checks across supported Python versions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci: tighten merge smoke harness and keep mapped test diffs additive
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci: terminate proxy on readiness timeout and use contextlib.suppress in teardown
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(logger): add shared Rust diagnostics and Python logging bridge
* feat(logger): dispatch diagnostic processing through Rust
* chore: regenerate Cargo.lock after rebase
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: allowlist bounded logging tree walkers in recursive detector
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* perf(logger): skip decoding plain access arguments
* test(logger): skip embedded-python logger test when litellm deps are absent
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: cargo fmt
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: expect NativeDiagnosticProcessor in the native public surface
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(stub): export NativeDiagnosticProcessor via __new__ in _native.pyi
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(tracing): rename logger crate and document host sink contract
* test(logger): cover exc, stack, and nested extras in the diagnostic filter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logger): keep rendered redacted line when template scan flags a key pattern
The blanket REDACTED for a changed msg/color template discarded lines
whose rendered form was already redacted by the same pipeline, e.g.
'password=%s' became 'REDACTED' instead of 'password=REDACTED'. Only
fall back to REDACTED when the rendered form did not change either,
which is where interpolation can mangle the key pattern the scrub
would otherwise see.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(rust): install python deps so the logger bridge test runs
The end-to-end bridge test skipped silently when litellm's Python deps
were absent. uv sync --no-install-project installs them without a
maturin build, and PYTHONPATH makes them visible to the embedded
interpreter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(e2e-stack): print add-mask lines only under GitHub Actions
* refactor(e2e-stack): inline the add-mask lines into main
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(otel v2): map completions, images, speech, transcription and moderation output onto the generation output
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(redaction): redact text completion choices in the standard logging payload
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): compare decoded generation output text and follow the live moderation verdict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel v2): compare logged byte counts with the received media and move e2e schemas into models.py
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* ci(e2e): keep the otel_v2 Langfuse output e2e file out of the stage-mirror gate it cannot run in
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The changed-test gate booted its stage-mirror stack without files_settings
or finetune_settings, so every raw upload with a custom_llm_provider hit a
500, and it exported the whole provider env into the gateways, so the
AWS_ROLE_NAME the assume-role test needs made the GovCloud deployment run
an AssumeRole with its static keys. The gate also deleted its pytest output,
so a red run left nothing to read. The mirror config now carries the
openai, azure, and vertex_ai file settings, gateways start without
AWS_ROLE_NAME, and the workflow uploads the pass logs and junit files with
every secret value, every field of a JSON-valued secret, and their
XML-escaped forms replaced before the raw files are removed.
A string such as "*" or "..." has no base64 characters, so it decoded to no bytes and read as an empty plaintext under any key. The migration would have counted it and overwritten it with a ciphertext of the empty string. Also read from the writer database instead of a read replica, report a database error during the migration instead of crashing the boot, skip columns the connected schema lacks across every schema on the search path, cap the JSON walk depth for the recursion detector, and move the boot wiring into one tested function.
