* fix(model-info): include reasoning effort support fields in get_model_info
_get_model_info_helper constructs ModelInfoBase explicitly but never
reads supports_xhigh/minimal/none_reasoning_effort from the cost map
JSON. Add the three fields so get_model_info() returns them correctly.
Also add supports_minimal_reasoning_effort to the ModelInfo TypedDict
(xhigh and none were already declared, minimal was missing).
* fix(model-registry): add missing reasoning effort fields for claude 4.6/4.7
Claude Opus 4.7 supports max reasoning effort (above xhigh).
The field was present for Opus 4.6 but missing for all Opus 4.7
entries (base, dated, Bedrock, Vertex AI, Azure AI).
All Claude 4.6/4.7 models (Opus 4.6, Sonnet 4.6, Opus 4.7) support
minimal reasoning effort via adaptive thinking. Add the field to all
provider variants.
* fix(adapter): map output_config.effort to reasoning_effort (#25079)
Anthropic's adaptive thinking (thinking.type="adaptive") and
output_config.effort were silently dropped when translating to
OpenAI format, resulting in no reasoning_effort on the outgoing
request.
Adapter changes (format translation):
- adapters/transformation.py: add "adaptive" branch to
translate_anthropic_thinking_to_reasoning_effort(); pass through
output_config.effort as-is in _translate_thinking_to_openai();
add "output_config" to translatable_anthropic_params
- adapters/handler.py: extract output_config from extra_kwargs into
request_data so it reaches the translation layer
- responses_adapters/transformation.py: add "adaptive" branch and
output_config param to translate_thinking_to_reasoning()
Handler changes (model-aware normalization):
- utils.py: add normalize_reasoning_effort_value() that uses
get_model_info() to map "max" → "xhigh"/"high" and
"minimal" → "minimal"/"low" based on model capabilities
- adapters/handler.py: call normalization before responses routing
- responses_adapters/handler.py: call normalization after translation
Relates to BerriAI/litellm#25079
* test(reasoning-effort): add tests for effort capability fields and normalize logic
Test coverage for:
- get_model_info returning supports_minimal/max_reasoning_effort fields
- JSON registry entries for claude 4.6/4.7 across all providers
- normalize_reasoning_effort_value degradation chains and exception fallback
- Adapter translation of adaptive thinking + output_config.effort
* fix: forward custom_llm_provider to normalize_reasoning_effort_value in responses adapter
* fix(mcp_semantic_tool_filter): match canonical tools that arrive with
a client-side namespace prefix.
`SemanticMCPToolFilter._get_tools_by_names` matched by exact equality
between the canonical name stored in the router
(`<server><MCP_TOOL_PREFIX_SEPARATOR><tool>`) and the name in the
incoming `tools[]` list. MCP clients such as opencode wrap every tool
name with their own additive alias prefix
(`<client_alias>_<canonical>`), so the two never matched, the filter
dropped every tool to zero, and the proxy forwarded `tools: []` with
`tool_choice: auto` — which strict upstream providers reject with a 400.
The fix adds anchored suffix matching with a separator check: the
canonical must form the complete tail of the incoming name and be
preceded by `_` or `-`. Exact matches still win over suffix matches,
incoming tools are returned at most once, and the original tool object
is passed through unchanged so the client-facing name survives for
tool-call round-trips.
Seven unit tests in a new TestGetToolsByNames class cover exact
match, underscore- and dash-prefixed variants, non-separator-anchored
suffixes (which must not match), exact-wins-over-prefixed precedence,
deduplication when two canonicals suffix-match the same incoming tool,
and ordering-follows-router-output.
Fixes#26078
* review: strengthen the suffix-fallback tie-breaker and the
deduplication regression test (Greptile comments on #26117)
- test_same_tool_not_returned_twice now passes two distinct canonicals
("read_file" and "file") that both suffix-match the same incoming
tool, rather than the same canonical twice, so the assertion
actually exercises the used_ids dedup path instead of the
duplicate-input-list path.
- The suffix fallback in _get_tools_by_names now prefers the shortest
incoming name that still qualifies under the separator-anchored
match. In the one-prefix-per-client opencode scenario this is a
no-op, but in multi-namespace configurations the shortest qualifying
name is the least-wrapped one and is the most defensible deterministic
choice, replacing the dict-insertion-order fallback.
- Adds test_suffix_fallback_prefers_shortest_candidate covering the
new tie-breaker directly.
Still 15 tests passing locally (was 14).
* review(#26117): gate suffix-matching on canonical containing MCP_TOOL_PREFIX_SEPARATOR
@krrish-berri-2 flagged a possible collision in the suffix fallback:
a local user function whose name happens to end in a bare canonical
substring (e.g. my_firecrawl_scrape vs canonical firecrawl_scrape)
would be spuriously selected.
Server-registered MCP tools are always emitted as
<server_name><MCP_TOOL_PREFIX_SEPARATOR><tool_name> via
add_server_prefix_to_name, so a canonical without the separator is
not a namespaced MCP tool and does not warrant suffix matching.
Added that guard to _name_matches_canonical with a regression test
(test_does_not_collide_with_local_function_on_unprefixed_canonical)
that reproduces the collision before the fix and is pinned after.
Pre-existing TestGetToolsByNames fixtures that relied on bare
canonicals (get_weather, search, read_file, write/delete/read) were
switched to realistic server-prefixed ones so they continue to
exercise the suffix-fallback path under the new guard. The opencode
scenario (client prefix on already-server-prefixed canonical) is
unchanged.
---------
Co-authored-by: sakenuGOD <sakenuGOD@users.noreply.github.com>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
Two changes, both test-only:
- Configure the aiohttp session with TCPConnector(force_close=True) and an
explicit ClientTimeout(total=30, connect=10). Prevents reuse of idle TCP
connections that the proxy/kernel may have closed during the long window
between setup POSTs and the later poll loop, and surfaces a blocked proxy
event loop quickly instead of hanging on aiohttp's 5-minute default.
- In poll_key_spend_until, catch aiohttp.ClientError and asyncio.TimeoutError
around the single /key/info call. A transient transport hiccup now logs and
retries on the next tick instead of failing the entire polling loop.
Addresses the ConnectionTimeoutError observed on the first /key/info call
after the 20 chat completions.
- Narrow _team_obj_from_token to require non-None team_id so mypy
passes.
- Preserve the no-auth dev-mode contract for deployments with
master_key unset AND no JWT/OAuth2 configured — the gate
short-circuits only in that specific combination. JWT or OAuth2
deployments without master_key still run the centralized authz.
- is_database_connection_error now enumerates data-layer PrismaError
subclasses (DataError, UniqueViolationError, ForeignKeyViolationError,
MissingRequiredValueError, RawQueryError, TableNotFoundError,
RecordNotFoundError) as False, and maps everything else (bare
PrismaError, connectivity subclasses, DB_CONNECTION_ERROR_TYPES) to
True. Known-safe-to-propagate errors don't trigger HA fallback;
unknown / generic PrismaError still falls back to preserve legacy
503 behavior.
- Update test_handle_authentication_error_db_unavailable_connectivity
to include PrismaError in the fallback list.
Multiple paths through _user_api_key_auth_builder returned a
UserAPIKeyAuth without running common_checks(): OAuth2 token validation,
OAuth2 proxy header hook, JWT admin shortcut, master_key path,
pass-through custom headers, the /user/auth route, and the
allow_requests_on_db_unavailable fallback. An operator-configured key
model-access list, max_budget, team_blocked flag, or team model scope
was therefore silently skipped on those paths. The HA-fallback token
was worse: it was a full proxy-admin synthetic, so a DB outage granted
full admin to every caller.
Fix three root causes (VERIA-18):
1. Centralize common_checks in the user_api_key_auth wrapper. The
builder paths no longer call it; the wrapper runs it once after the
builder returns, for every path. Introduces _run_centralized_common_checks
which gathers team/user/project/end_user/global_spend context in
parallel via asyncio.gather. Preserves the existing
custom_auth_run_common_checks opt-out for custom-auth deployments.
2. Narrow is_database_connection_error — drop the blanket PrismaError
catch that routed data-layer errors (UniqueViolationError, etc.)
into the HA fallback. Only real connectivity failures plus the
no_db_connection marker now qualify.
3. DB-unavailable fallback issues an INTERNAL_USER token with user_id
DB_UNAVAILABLE_FALLBACK_USER_ID instead of proxy-admin. An outage
can no longer escalate an anonymous caller.
JWT admin / master_key tokens still grant admin via a synthesized
admin user_object (so non_proxy_admin_allowed_routes_check in
common_checks recognizes them); other common_checks branches
(team_blocked, team_model_access) now apply uniformly.
Two model-access gates run per request in `common_checks` and they're
asymmetric: `can_key_call_model` falls back to the key's
`access_group_ids`, but `can_team_access_model` only looks at
`team.models` + `team.access_group_ids`. A key granted a model via its
own access group on a model-restricted team is silently denied at the
team gate.
Wrap `can_team_access_model` in try/except in `common_checks`: on
`team_model_access_denied`, consult a new `_key_access_group_grants_model`
helper that expands `valid_token.access_group_ids` via the existing
`_get_models_from_access_groups` and checks via `_can_object_call_model`.
Re-raise if the key's access groups don't grant the model. Any other
exception propagates unchanged.
Effect: request allowed if `team allows X` OR `key's access group
grants X`, making the two gates symmetric.
Test: add three unit tests for `_key_access_group_grants_model`
covering: group covers model, key has no groups, group resolves but
does not cover model.
Address two Greptile P2 findings on the BYOK OAuth endpoints:
- GET /v1/mcp/oauth/authorize now runs _validate_redirect_uri up front
so a non-loopback redirect_uri is rejected before the HTML form is
rendered. Previously the user typed an API key, submitted, and got a
400 with no form state.
- POST /v1/mcp/oauth/token moves the master_key guard ahead of the
code-consumption and credential-store steps. Without this, a proxy
with master_key unset would burn the code and persist the credential
but return an error — leaving the user with no way to retrieve a
session token without restarting the whole flow.
store_in_memory_spend_updates_in_redis drained the in-memory queues
into local variables before the rpush pipeline. If rpush raised (cloud
Redis hiccup, timeout, connection blip), those already-drained
transactions were garbage-collected with the scheduler job, silently
losing all spend aggregated during that tick.
Wrap the rpush in try/except. On failure, re-enqueue the aggregated
transactions into their respective in-memory queues so the next
scheduler tick retries.
Add a unit test that seeds real queues, simulates an rpush failure,
and asserts the transactions land back in-memory.
Replace the calibration step (one request + 10-minute poll) with an
independent ground truth computed from response usage via
litellm.cost_per_token. All N requests are made up front, so a single
dropped Redis write no longer kills the test.
Add /health/readiness checks at test start and on poll timeout so the
failure message surfaces proxy state (db, cache) instead of "calibration
timed out".
Set PROXY_BATCH_WRITE_AT=2 in the spend tracking CI job to shorten the
scheduler flush window.
- POST /v1/mcp/oauth/authorize now requires an authenticated UI session
cookie. The authenticated user_id — not the OAuth client_id form
field — is stamped onto the authorization code record (RFC 6749 §2.2:
client_id identifies the client, not the user).
- redirect_uri is restricted to loopback per RFC 8252 §7.3 (localhost
plus any ipaddress.is_loopback IP, covering 127.0.0.0/8 and IPv6
loopback forms).
- POST /v1/mcp/oauth/token enforces exact-match of the redirect_uri and
client_id submitted at /authorize (RFC 6749 §4.1.3).
- /token error responses use the RFC 6749 §5.2 format ({"error":
"<code>"}), and all /token responses set Cache-Control: no-store +
Pragma: no-cache (RFC 6749 §5.1).
Restore guardrail spend/UI event_type wiring, request_data on streaming
OUTPUT paths, and centralized match redaction after the upstream revert.
Made-with: Cursor
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Has been cancelled
- Validate max effort like xhigh: Opus 4.6/4.7 id patterns or supports_max_reasoning_effort
- Set supports_max_reasoning_effort on claude-opus-4-7 entries in model cost JSON
- Update tests and add test_max_effort_accepted_for_opus_47
Made-with: Cursor
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Has been cancelled
Keep anthropic_messages as the logged call_type for non-Anthropic /v1/messages adapter paths and add a regression test to prevent fallback to completion/acompletion.
Made-with: Cursor
When the DB becomes unreachable the reconnect path calls
`prisma.disconnect()`, which ultimately invokes prisma-client-py's
synchronous `subprocess.Popen.wait()` on the query engine subprocess.
That call does not yield to asyncio, so the event loop freezes for
however long the Rust engine takes to shut down (30-120+ seconds in
production when the engine is stuck on TCP close). During the freeze
`/health/liveliness` becomes unresponsive, and in Kubernetes the
liveness probe fails and the pod is SIGKILL'd.
Replace `disconnect()` in the reconnect paths with a direct, non-blocking
kill of the engine subprocess (SIGTERM -> 0.5s asyncio-yielding sleep ->
SIGKILL) followed by a fresh Prisma client and a new `connect()`. Both
`recreate_prisma_client` and the formerly-separate "direct reconnect"
path go through the same kill-then-recreate flow.
Also validate `_get_engine_pid` returns an int (defensive; prevents a
MagicMock leak under unit-test mocking).
Tests that encoded the old blocking behavior are updated or removed;
the deleted `test_lightweight_reconnect_skips_kill_on_successful_disconnect`
invariant ("don't kill on successful disconnect") was part of the bug.
Non-streaming path required len(tool_calls)==1 to unwrap json_tool_call, so mixed user tools leaked the internal tool. Align with Bedrock converse handling: strip internal tools, merge structured JSON into content.
Made-with: Cursor
* add moonshot/kimi-k2.6 to model registry
* add moonshot/kimi-k2.6 to backup model registry
* add tests for moonshot/kimi-k2.6 model registry
* fix moonshot/kimi-k2.6 pricing and add reasoning support
* fix moonshot/kimi-k2.6 pricing and add reasoning support in backup
* update kimi-k2.6 tests: fix pricing, add tool_choice and reasoning checks
* fix: load kimi-k2.6 registry tests from local backup instead of remote cost map
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Waiting to run
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Waiting to run
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Has been cancelled
P1 review: adaptive_router.py had a top-level import of
AdaptiveRouterUpdateQueue from litellm.proxy.db, which broke the
SDK/proxy boundary that every other router strategy respects. No
other router_strategy module imports from litellm.proxy at module
level.
The queue only depends on litellm._logging — it never needed to
live under litellm.proxy. Moved:
litellm/proxy/db/db_transaction_queue/adaptive_router_update_queue.py
→ litellm/router_strategy/adaptive_router/update_queue.py
tests/test_litellm/proxy/db/db_transaction_queue/
test_adaptive_router_update_queue.py
→ tests/test_litellm/router_strategy/adaptive_router/test_update_queue.py
Also switched the queue's logger from verbose_proxy_logger to
verbose_router_logger to match the new module's ownership.
P2 review: drop unused constant STAGNATION_JACCARD_EXACT from
config.py — it was defined but never referenced.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
P1: start the adaptive-router flusher loop unconditionally at proxy boot
instead of gating on 'adaptive_routers is non-empty'. Adaptive routers
added via /config/reload after boot now have their queues drained.
State is lazy-loaded per router on first flush tick (new _state_loaded
flag on AdaptiveRouter) so hot-reloaded routers still get their
persisted priors.
P2: _finalize_adaptive_router_if_configured now prunes stale
AdaptiveRouterPostCallHook callbacks from every litellm callback list
before registering new ones. Without this, every Router replacement
left the old hooks wired up in litellm.callbacks and double-fired
signal recording for every request. Uses
logging_callback_manager.remove_callbacks_by_type (same pattern as the
semantic tool filter).
CI fixes:
- black --check failure: reformatted litellm/router.py
- schema migration diff: aligned @@index with the explicit index name
('idx_adaptive_router_session_activity') from the original migration
by adding 'map:' to all three schema.prisma copies. No new migration
needed.
Tests: 1 new covering the prune-on-hot-reload path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Mark last_updated_at (AdaptiveRouterState) and last_activity_at
(AdaptiveRouterSession) with @updatedAt so Prisma refreshes the
timestamps on every write. Without this the fields stayed frozen at
INSERT time and the last_activity_at index was misleading for any
future TTL/eviction logic. Applied to all three schema.prisma copies;
no migration SQL change needed (Prisma @updatedAt is a client-side
annotation that doesn't touch DDL).
- get_state_snapshot: report cell.total_samples instead of alpha+beta
for the 'samples' field. The previous value inflated every cell by
the COLD_START_MASS prior (e.g. showed 10.0 before any real traffic
arrived), which confused operators reading /adaptive_router/.../state.
Updated docs + the snapshot test to match.
Also fixes two pre-existing merge-break syntax errors in router.py
(missing ')' on the AdaptiveRouter TYPE_CHECKING import; truncated
async_pre_routing_hook dispatch call for the adaptive router branch)
that were masking the rest of the file from the interpreter.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py --ignore=tests/proxy_unit_tests/test_p… (push) Has been cancelled
Existing tests pinned exact kwargs on `PrismaManager.setup_database`,
but the opt-in v2 resolver added `use_v2_resolver=False` to every call.
Update the three assertions to reflect the new signature.
Fixes:
- TestHealthAppFactory::test_use_prisma_db_push_flag_behavior
- TestHealthAppFactory::test_startup_fails_when_db_setup_fails
Adds end-to-end CI coverage for `--use_v2_migration_resolver` via a new
job `installing_litellm_on_python_v2_migration_resolver`:
- Clones the pytest smoke path from `installing_litellm_on_python` but
uses a local Postgres sidecar instead of the shared DB to prevent
collisions with the v1 variant.
- Runs only the new `test_litellm_proxy_server_config_no_general_settings_v2_resolver`
which spawns the proxy with `--use_v2_migration_resolver` and smoke-tests
`/health/liveliness` and `/chat/completions`.
Refactors `test_basic_python_version.py`:
- Extracts the proxy spawn + smoke-test body into `_run_proxy_server_smoke_test`
so the v1 and v2 tests share the same code path.
- The existing `test_litellm_proxy_server_config_no_general_settings` is
now a thin wrapper that passes no extra args (v1 default, unchanged).
- Adds `..._v2_resolver` variant that passes `--use_v2_migration_resolver`.
The existing `installing_litellm_on_python` / `installing_litellm_on_python_3_13`
jobs filter out the v2 variant via `-k "not v2_resolver"` so they keep
running only against their shared DB, unchanged behavior.
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.
