Two cleanups from the /simplify review pass:
* ``Response`` was imported inside the ``except OSError`` branch in
``/get_image`` and at the top of ``/get_favicon``. Per the project's
no-inline-imports rule (CLAUDE.md), hoisted to the existing
``from fastapi.responses import (...)`` block at the top of
``proxy_server.py``.
* The test class's ``_patches()`` helper returned a 2-element list of
patch context managers and tests indexed into them via
``self._patches(...)[0], self._patches()[1]`` — two distinct calls
with confusing aliasing semantics. Restructured to:
- module-level ``_patch_async_safe_get(...)`` that returns a single
patch context manager
- autouse fixture that patches ``get_async_httpx_client`` for every
test in the file (it's the same patch in every case)
- small ``_image_response(...)`` factory to deduplicate Mock setup
Tests now read as ``with _patch_async_safe_get(return_value=...):``
with no list-indexing or duplicate Mock construction.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three review items addressed:
* **Veria (Medium): SSRF via redirect.** ``fetch_validated_image_bytes``
was calling ``validate_url(url)`` once and then fetching with the
default httpx client, so a 3xx to an internal IP would have been
followed unvalidated. Switched to ``async_safe_get`` (the existing
SSRF primitive used elsewhere in the codebase) which walks each
redirect hop, re-validates, and rejects redirects to blocked
networks. Default ``litellm.user_url_validation`` is True so
protection is on out of the box.
* **Greptile (P2): SVG can embed JS.** Removed ``image/svg+xml`` from
the allowed-Content-Type set. The hardcoded response media type
(``image/jpeg`` / ``image/x-icon``) means a real SVG body wouldn't
render as SVG anyway in modern browsers — the allowlist entry was
giving up XSS surface for no actual SVG-rendering benefit. If real
SVG support is wanted later, that's a deliberate feature PR with CSP
/ nosniff bundled.
* **Greptile (P2): cache-write OSError drops validated bytes.** When
the upstream fetch succeeded but ``open(cache_path, "wb")`` raised
(read-only assets dir), the bytes were discarded and the default
logo was served — a silent regression for that deployment. Now
serve the validated bytes inline via ``Response(...)`` as a fallback
before falling back to default.
Tests:
- Replaced low-level mocks of ``validate_url`` with mocks of
``async_safe_get`` directly, exercising the helper's contract
rather than the SSRF primitive's internals.
- New ``test_rejects_svg_content_type`` confirms SVG is blocked.
- ``test_get_image_cache_logic`` fixture now sets
``mock_response.is_redirect = False`` so ``async_safe_get`` doesn't
treat the Mock's truthy attribute as a redirect.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The unauthenticated ``/get_image`` and ``/get_favicon`` endpoints accept
the admin-set env vars ``UI_LOGO_PATH`` and ``LITELLM_FAVICON_URL`` and
return whatever bytes they resolve to, with a hard-coded ``image/jpeg``
or ``image/x-icon`` content-type. Two attack shapes:
* ``UI_LOGO_PATH=/etc/passwd`` (or any other readable file path) — any
unauthenticated caller exfiltrates the file via ``GET /get_image``.
The previous gate was ``os.path.exists(logo_path)`` which fires on
every readable file. Same shape for the favicon endpoint.
* ``UI_LOGO_PATH=http://169.254.169.254/iam`` (or any internal HTTP
service the admin pointed at) — the proxy fetches it server-side
and streams the response body to the unauthenticated caller. No
URL validation, no Content-Type validation; ``application/json``
AWS metadata gets tunneled out under the ``image/jpeg`` wrapper.
New helper module ``litellm/proxy/common_utils/static_asset_utils.py``:
* ``resolve_local_asset_path(candidate, allowed_roots)`` — returns the
resolved absolute path only if it lives within one of the allowed
asset roots. Uses ``realpath`` so symlinks pointing outside the roots
are caught.
* ``fetch_validated_image_bytes(url)`` — runs the URL through
``validate_url`` (rejecting private / cloud-metadata / loopback
targets) and only returns the response body if the upstream
Content-Type is in a small allowlist of image MIME types.
Both ``/get_image`` and ``/get_favicon`` are wired through the helpers.
The SSRF gate is enforced unconditionally — these endpoints are
unauthenticated, so the admin-facing ``litellm.user_url_validation``
toggle does not apply (an admin who opted out of URL validation for
LLM provider paths shouldn't also expose ``/get_image`` to SSRF).
Tests:
- ``TestResolveLocalAssetPath``: 10 cases covering legitimate paths,
``/etc/passwd``, ``/proc/self/environ``, symlink-out, ``..``
traversal, directories, missing files, and root list edge cases.
- ``TestFetchValidatedImageBytes``: 7 cases covering SSRF block, non-
image content-type rejection, valid image passthrough, non-200
response, fetch exception, empty URL, and parametrized coverage of
every allowed image MIME type.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three issues surfaced in review of the previous commit:
1. **Veria — Medium**: ``litellm_params`` carries a nested
``litellm_embedding_config`` dict (auto-resolved from the model
registry on create / update) which itself holds ``api_key`` /
``aws_*`` / ``vertex_credentials``. The previous redactor only
inspected top-level keys, so the nested values passed through
unredacted. Recurse into nested dicts.
2. **Greptile — P2**: when ``litellm_params`` is a JSON-serialized
string (the in-memory registry occasionally stores it that way), the
previous redactor silently no-op'd via the ``isinstance(..., dict)``
guard and echoed the raw payload back. Now: parse, redact, re-serialize.
If the string is not valid JSON, replace it with the redaction
sentinel rather than echo it.
3. **mypy** flagged ``_redact_sensitive_litellm_params``'s
``Optional[Dict[str, Any]]`` signature as incompatible with the
``object``-typed call site. Widened to ``Any -> Any`` to reflect the
actual contract (the function now handles dict / str / None / other).
Also fixes a related test regression in
``test_remove_sensitive_info_from_deployment_with_excluded_keys``: the
``"credentials"`` plural addition to ``SensitiveDataMasker`` defaults
caused the first call (without ``excluded_keys``) to mutate the input
dict's ``litellm_credentials_name`` to a masked value. The second call
(with ``excluded_keys``) then saw the already-masked value rather than
the original. Construct fresh input for each call.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Updated instances of DualCache to UserApiKeyCache across multiple files to enhance cache handling for user API keys.
- Adjusted cache retrieval and storage methods to ensure proper serialization and deserialization of cached objects.
- Introduced a new UserApiKeyCache class to streamline caching logic and improve type safety.
- Updated relevant tests to reflect changes in caching behavior and ensure compatibility with the new cache implementation.
Mirrors the existing vertex_credentials handling for the newer
vertex_ai_credentials field, and extends the dynamic masker's sensitive
pattern set to recognize the plural form so other plural-named credential
fields are also covered.
The periodic budget-window reset job filtered keys/teams with
`where={"budget_limits": {"not": None}}`. The prisma-client-python
library does not support null-filtering on `Json?` columns (no
DbNull/JsonNull sentinel — upstream issue #714). The client drops the
`None` value during serialization and the engine rejects the query with
`MissingRequiredValueError: where.budget_limits.not: A value is
required but not set`, so neither the key nor team reset path runs.
Switch those two `find_many` calls to `query_raw` with
`WHERE budget_limits IS NOT NULL`, selecting only the PK and the
`budget_limits` column. Writes still go through the ORM. Add unit tests
covering the expired/unexpired paths for keys and teams, string-encoded
JSON payloads, empty payloads, error isolation between the two paths,
and a regression guard asserting the query still uses `IS NOT NULL`.
Previously, members added to a team without an explicit per-member budget were
all linked to the same `litellm_budgettable` row referenced by the team's
`metadata.team_member_budget_id`. Updating one member's budget via
`/team/member_update` mutated the shared row and silently changed every other
member's budget too.
Now both write paths produce a private, per-member budget:
- `add_new_member` clones the team's default budget into a fresh row when a
member is added without `max_budget_in_team`/`allowed_models`. If no team
default exists, the membership is created with no budget.
- `_upsert_budget_and_membership` detects when an existing membership still
points at the team's default budget id and clones-on-write, relinking the
membership to the new private budget before applying the update.
- `team_member_update` reads `team_member_budget_id` from team metadata and
passes it through so the helper can make this distinction.
Adds unit tests for clone-on-write, in-place update of a private budget, and
the no-default-no-budget add path.
Made-with: Cursor
Adds total_spend column to LiteLLM_TeamMembership that accumulates
continuously and is not zeroed by the budget cycle reset job. This
enables UI surfaces to distinguish current-cycle spend (the existing
spend column, which resets) from lifetime spend per team member.
Also exposes budget_reset_at on LiteLLM_BudgetTable so /team/info
callers can see when a member's budget window next resets. The field
was already stored in the DB but stripped by the response Pydantic
model.
Includes regression tests that:
- Guard the reset job against ever writing total_spend: 0
- Verify the spend writer increments both spend and total_spend in
one UPDATE statement.
* refactor: new agentic loop event hook
simplifies how to create logic for tool based multi llm calls
* fix: compress - make it work on anthropic input as well
* fix(compress.py): working prompt compression for claude code
ensures claude code messages can run through proxy easily
* docs: add agentic loop hook guide
* docs: add agentic_loop_hook to sidebar
* fix: fix multiple arguments error
* fix: fix tool call loop for compression on streaming /v1/messages
* fix: fix linting errors
* fix: fix ci/cd errors
* feat(litellm_pre_call_utils.py): use claude code session for litellm session id
allows claude code logs to be stitched together, making it easy to know they were all part of the same conversation
* fix: suppress incorrect mypy warning rE: module
* revert: drop PR's changes to litellm/proxy/_experimental/out/
Restores the 34 HTML files under _experimental/out/ to their pre-PR
paths (X/index.html -> X.html). All renames are R100 (content
unchanged); no other files are touched.
* fix: address greptile review comments on PR #25729
- Skip ``kwargs["tools"] = []`` injection when compression is a no-op —
Anthropic Messages rejects empty tool arrays on requests that did not
originally declare tools.
- Move agentic-loop safety guards (fingerprint cycle / max depth) out of
the per-callback try/except so they propagate instead of being swallowed
by the generic exception handler. Extracted _check_agentic_loop_safety.
- Gate generic ``x-<vendor>-session-id`` capture behind the
LITELLM_CAPTURE_VENDOR_SESSION_HEADERS env var (off by default) to
preserve backwards compatibility; explicit x-litellm-* headers are
unaffected.
- Fix monkeypatch target in pre-call-hook test to patch the actual
module-level binding
(litellm.integrations.compression_interception.handler.compress).
- Add regression tests for empty-tools skip and opt-in session capture.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* revert: drop LITELLM_CAPTURE_VENDOR_SESSION_HEADERS flag
Generic x-<vendor>-session-id header capture is a new feature and only
runs *after* the explicit x-litellm-trace-id / x-litellm-session-id
checks, so it does not change behavior for any existing caller that was
already using the LiteLLM headers — no backwards-incompatibility to gate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(compress): replace input_type with CallTypes call_type
Drop the bespoke ``CompressionInputType`` literal and use the existing
``litellm.types.utils.CallTypes`` enum instead. ``litellm.compress()``
now takes ``call_type: Union[CallTypes, str]`` (default
``CallTypes.completion``) — no new concept to learn, and the enum is
already the way the rest of the codebase talks about request shapes.
Supported values: ``completion`` / ``acompletion`` (OpenAI chat-completions
shape) and ``anthropic_messages`` (Anthropic structured content blocks).
Updated: compress(), the compression_interception handler, tests, docs,
and the two eval scripts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When litellm.max_end_user_budget_id is configured, implicitly-created end users
(via /chat/completions) have budget_id=NULL in the DB since the default budget
is only applied in-memory. The budget reset job filtered by budget_id, so these
users were never reset and eventually permanently blocked.
Fix: when the default budget is in the reset list, also query for and reset
end users with budget_id=NULL and spend > 0. This keeps the hot auth path
unchanged (no DB writes on every request).
Fixes#22019
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Post-merge audit found 6 adjacent variants of the VERIA-28 class. All
fixed here with regression tests:
1. Strip widened from 3 named keys to the full user_api_key_* prefix.
The proxy writes a dozen user_api_key_* fields (user_id, alias,
spend, team_id, request_route, end_user_id, …) into
data[_metadata_variable_name]; the 3-key strip left the rest
exploitable for identity/spend forgery in audit logs and guardrails.
2. proxy_server_request['body'] snapshot moved to AFTER the strip.
Was captured at line ~990 before the strip ran, so
standard_logging_object, lago, and spend_tracking readers saw the
attacker-forged payload even though the live data dict was clean.
3. get_tags_from_request_body (auth-time) now coerces JSON-string
metadata via safe_json_loads. Previously crashed with
AttributeError on string metadata (DoS; potential RBAC bypass if
a caller swallowed the exception).
4. get_end_user_id_from_request_body coerces JSON-string
metadata/litellm_metadata. Previously isinstance(dict) guard
caused end-user budget attribution to be silently skipped when
the caller sent metadata as a JSON string.
5. Four hand-rolled 'if data.get("metadata") is None: data["metadata"] = {}'
blocks in proxy_server.py (7160, 7341, 7590, 11375) now guard on
isinstance(dict). They crashed with TypeError when metadata was a
JSON string (DoS).
6. _get_admin_metadata defensively guards with isinstance(dict);
previously AttributeError'd on any leaked string metadata.
Also hoists the inline safe_json_loads import in _guardrail_modification_check
to module level per CLAUDE.md style.
Budget table entries (team members, end-users) used duration_in_seconds()
for a sliding-window reset, while keys/users/teams used calendar-aligned
get_budget_reset_time(). This made "30d" and "1mo" mean different things
depending on entity type. Now both paths use get_budget_reset_time() for
consistent calendar-aligned resets (e.g. "30d" → 1st of next month).
Fixes#25432
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(router): integrate allowed_fails_policy into health check failures (#24988)
* feat(router): integrate allowed_fails_policy into health check failures
Health check failures now increment the same per-deployment failure
counters used by allowed_fails_policy, so users can control how many
health check failures of each error type are required before a
deployment enters cooldown.
- ahealth_check() preserves the original exception in its return dict
- run_with_timeout() returns a litellm.Timeout on health check timeout
- _perform_health_check() propagates exceptions to unhealthy endpoints
- _write_health_state_to_router_cache() calls _set_cooldown_deployments
for each unhealthy endpoint that has an exception
- When allowed_fails_policy is set, the binary health check filter is
bypassed so cooldown is the sole routing exclusion mechanism
- Safety net: if all deployments are in cooldown with
enable_health_check_routing=True, the cooldown filter is bypassed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(router): add health_check_ignore_transient_errors flag
When enabled, health check failures with 429 (rate limit) or 408 (timeout)
status codes are skipped from the cooldown pipeline. These are transient
load issues, not broken deployments. Auth errors (401), 404, and 5xx errors
still increment counters and trigger cooldown as before.
Config (general_settings):
health_check_ignore_transient_errors: true
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(router): also exclude 429/408 from health state cache when ignore_transient_errors set
The previous fix only skipped cooldown counter increments. The health state
cache was still marking 429/408 endpoints as is_healthy=False, causing the
binary health check filter to exclude them from routing.
Now, when health_check_ignore_transient_errors=True, 429/408 endpoints are
also excluded from the unhealthy list passed to build_deployment_health_states(),
so the binary filter treats them as unaffected (not unhealthy).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(router): add health check driven routing guide
New standalone page covering the full health check routing feature:
allowed_fails_policy integration, health_check_ignore_transient_errors,
architecture SVG, step-by-step setup, and gotchas (TTL, AllowedFails semantics).
Replaces the inline section in health.md with a link to the new page.
Added to the Routing & Load Balancing sidebar.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(health-check-routing): fix three CI failures
- Add "exception" to ILLEGAL_DISPLAY_PARAMS in health_check.py so the
exception object is stripped before the health endpoint serializes
results to JSON (fixes TypeError: 'URL' object is not iterable)
- Add allowed_fails_policy = None to FakeRouter stubs in
test_router_health_check_routing.py (fixes AttributeError)
- Add health_check_ignore_transient_errors to config_settings.md router
settings reference table (fixes documentation test)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Fix litellm/tests/proxy_unit_tests/test_proxy_server.py
* fix(router): address greptile review comments
- Narrow cooldown safety-net bypass: only fires when allowed_fails_policy
is set (cooldown is health-check driven). Without a policy, cooldowns
are from real request failures and must not be bypassed.
- Restore cooldown deployments DEBUG log that was accidentally removed.
- Fix test_health TypeError: move exception extraction to a separate
exceptions_by_model_id dict returned alongside endpoints, so exception
objects never appear in the endpoint dicts that get JSON-serialized
by the /health response.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(health-check-routing): properly isolate exceptions from health response
Return exceptions_by_model_id as a separate third value from
_perform_health_check / perform_health_check so exception objects
(which contain non-JSON-serializable httpx URL types) never appear
in the endpoint dicts that get serialized by the /health response.
Callers updated: _health_endpoints.py, shared_health_check_manager.py,
proxy_server.py background loop. All use the exceptions dict only for
cooldown integration, not for display.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(shared-health-check): fix remaining 2-value return sites and update type annotation
* fix(health-check-routing): fix P0 cooldown integration never firing
The cooldown loop was reading endpoint.get("exception") which is always
None because exceptions are now returned via exceptions_by_model_id, not
stored in endpoint dicts. Fixed to use _exceptions.get(model_id).
Also fixes the transient-error filter to use _exceptions instead of
endpoint.get("exception"), and fixes all remaining 2-value return sites
in shared_health_check_manager.py. Tests updated to pass exceptions via
exceptions_by_model_id parameter instead of endpoint dicts.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(health-check-routing): fix P1 transient-error filter broken on cache hits
When SharedHealthCheckManager returns cached results, exceptions_by_model_id
is always {} so the transient-error filter defaulted to status 500 for all
endpoints, incorrectly marking 429/408 endpoints as unhealthy.
Fix: store integer exception_status on each unhealthy endpoint dict in
_perform_health_check. _get_endpoint_exception_status() uses the live
exception object when available (direct path) and falls back to the stored
integer (cache-hit path). The integer is JSON-serializable and survives
the shared cache round-trip.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(health-check-routing): gate cooldown loop behind allowed_fails_policy
Without the policy, cooldown is not the routing exclusion mechanism.
Firing _set_cooldown_deployments for all enable_health_check_routing users
was a backwards-incompatible change — 401s would immediately cooldown
deployments that the binary filter would have recovered on the next cycle.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* revert: undo allowed_fails_policy gate on cooldown loop
Cooldown integration via health checks is intentional for all
enable_health_check_routing users, not just those with allowed_fails_policy.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(docs+tests): fix health_check_ignore_transient_errors doc section and test coverage
- Move health_check_ignore_transient_errors from router_settings to
general_settings in config_settings.md (code reads it from general_settings)
- Remove duplicate enable_health_check_routing / health_check_staleness_threshold
entries that were incorrectly listed under router_settings
- Replace TestHealthCheckEndpointExceptionPropagation tests with ones that
exercise the real _perform_health_check code path via mocked ahealth_check,
verifying exceptions appear in exceptions_by_model_id and NOT in endpoint dicts
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(tests+docs): fix tuple unpacking and docs test failures
- Update test mocks that return (healthy, unhealthy) to return
(healthy, unhealthy, {}) to match the new 3-value signature
- Update test unpackings of perform_shared_health_check to use
healthy, unhealthy, _ = ...
- Add health_check_ignore_transient_errors to router_settings section
in config_settings.md (it is a Router constructor param, so the doc
test requires it there; it also lives in general_settings for proxy use)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Fix CodeQL errors
* fix(tests): fix 2-value unpackings of _perform_health_check in test_health_check.py
* fix(tests): fix mock _perform_health_check returning 2-tuple instead of 3
* fix team routing
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: add distributed lock for key rotation job (#23364)
* fix: add distributed lock for key rotation job
* fix: address Greptile review feedback on key rotation lock (#23834)
* fix: address Greptile review feedback on key rotation lock
* fix req changes greptile
* feat(proxy): Optional on_error for guardrail pipeline (API / technical failures) (#24831)
* guardrails fallback
* docs
* docs: add LITELLM_KEY_ROTATION_LOCK_TTL_SECONDS to environment variables reference
* fix(mypy): accept Union[Dict, Any] in _get_deployment_order and use typed list to fix min() type error
* fix(mypy): use Optional[str] for api_base in PydanticAI provider to match superclass signature
---------
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Co-authored-by: Shivam Rawat <shivam@berri.ai>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
- Resolve merge conflict in pass_through_endpoints.py
- Add .copy() to proxy_server_request headers to prevent cache corruption
- Add test for request.state unavailable fallback path
* fix(budget): fix timezone config lookup and replace hardcoded timezone map with ZoneInfo
* fix(budget): update stale docstring on get_budget_reset_time
