* fix(mcp): key discovery caches per caller correctly and drop stale caches on server updates
Discovery-list cache identity now uses the hashed token instead of the raw
api_key and treats MCPJWTSigner-signed servers as per caller. Server
definition changes also drop the cached upstream OAuth metadata. OpenAPI
listings look tools up under the normalized registry prefix with the
separator, so an overlapping sibling prefix no longer leaks into the list.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): keep the discovery cache digest call unchanged so CodeQL matches the existing alert
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): guard OAuth metadata cache writes with a per-server generation and drop unproven per-caller discovery keys
An upstream metadata fetch that started before a server edit could store its stale reply after
invalidate_oauth_metadata_cache ran. Invalidation now bumps a per-server generation and the fetch
only stores when the generation it captured before I/O is unchanged.
The MCPJWTSigner-based per-caller discovery classification and the api_key to token key change had no
reproduction (the signer only injects on tools/list, and UserAPIKeyAuth hashes api_key in place), so
both go back to the merge-base behavior.
Integration coverage under tests/integration/mcp: overlapping OpenAPI aliases, a config-declared
server name with a space, OAuth metadata refetch after a save, and the in-flight stale-write race
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): keep OAuth metadata generations only while a fetch is in flight
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): count queued OAuth metadata fetchers so invalidation survives lock handoff
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): keep a held OAuth metadata lock registered even when no fetcher slot claims it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(mcp): prove a peer worker drops stale upstream OAuth metadata after a save elsewhere
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>
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(proxy): recover daily spend key owners
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): simplify daily spend owner recovery
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): format daily activity metadata
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): cover recovered owner metadata merge
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): bound the daily spend owner lookup with the statement timeout
* test(integration): audit the daily activity key owner fallback on every usage route
Thirty five integration cells under tests/integration/spend cover the daily
spend owner fallback on all nine daily activity routes and /usage/ai/chat:
the happy path per route, the unanimity rules (two users, blank and null
rows, an owner the user table lacks, live and deleted keys with and without
their own user, a spend log alias), a non admin reader, an invalid key, a 5 KB
key, a locked LiteLLM_DailyUserSpend, 300 keys of one team, repeated reads, a
second user landing between reads, a concurrent burst across the unified
endpoints, a killed worker, and a proxy restart
The traffic cells ignore the GET /v1/models call the proxy's five minute token
limit refresh makes to every registered OpenAI compatible deployment, since it
lands on a test's provider wire whenever the refresh instant falls inside the
test
---------
Co-authored-by: jesus <jesus@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Claude Code background sessions (claude --bg) stamp x-app: cli-bg on every
request, including main-loop turns. The session router binding only
accepted x-app: cli, so a background session never bound and its
subagents' concrete-model calls bypassed the router.
The binding write already requires the requested model to resolve to a
pre-routing strategy, so background side calls naming plain models still
never bind. Since f6eff1bde0 removed the clear path, the x-app check
guarded nothing else.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* perf(responses): run aresponses through the async wrapper so the cache is read once
aresponses() sets kwargs["aresponses"] = True and runs the decorated sync
responses() on an executor, but _is_async_request() did not recognise that
flag, so the sync wrapper did a second cache lookup on the executor thread
with a differently ordered cache-key input. Every /v1/responses request paid
two cache GETs against two different keys. Recognising aresponses in
_is_async_request() leaves the async wrapper as the only cache reader and
writer for the async path, one GET per request, same key on read and write
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): let a responses cache entry cover aresponses so responses-only configs keep caching
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Auth's spend counter MGET scope spans common checks, model budget check and reservation;
reservation increments go out as one pipeline; post-call reconcile adjustments ride the ordinary
increment pipeline and update_cache uses one batched read. Over-budget reservation counters are
charged one at a time so a rejection never touches the counters after it; post-call counter keys are
derived from ids without validating a UserAPIKeyAuth.
Resolves LIT-8881
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* perf(router): fetch cooldown state and usage counters in one Redis round trip
The cooldown filter (CooldownCache) and usage-based-routing-v2 selection
(LowestTPMLoggingHandler_v2) each issued their own MGET on every request
because they live in different objects. RoutingReadBatch fetches both key
sets through DualCache.async_batch_get_cache_shared while the healthy
deployments are resolved and hands the usage slice to the strategy, so
selection does not read again. Each cache keeps its own memory tier,
throttling, reservation rollback and circuit-breaker handling, and the
strategy falls back to its own read when the prefetch does not cover its
keys. simple-shuffle keeps reading only cooldowns.
aresponses no longer issues a second, blocking response-cache read from
the worker thread that runs the sync wrapper.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(caching): keep per-cache tier failures inside the shared batch read
Wrap the memory-tier prepare and backfill steps of DualCache.async_batch_get_cache_shared
so a failing tier degrades that cache's read to None the way async_batch_get_cache does,
instead of escaping into routing. Drop the aresponses sync-cache guard: for native
Responses models the worker-thread read is the one whose key matches the write, so
skipping it broke cached /v1/responses replays.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(router): rename usage key builder so the async cache-call check reads it as a key helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(alerting): narrow daily-report cache values before numeric comparison
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(caching): type the shared batch-read helpers and merge Redis results without mutation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style: fix import sort in test_dual_cache
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(caching): flatten shared batch read keys without a stacked comprehension
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
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>
* fix(model-prices): correct azure/eu/gpt-6-astra to Data Zone rates
Co-authored-by: rain <1504569896@qq.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(model-prices): align groq, gemini and openai entries with official docs
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(model-prices): roll in verified Vertex, Gemini, OpenRouter and Azure AI registry fixes
Absorbs the fields from #43609, #43666, #43671 and #43644 that match the provider's own docs or price API today, and adds a cost test for the azure/eu/gpt-6-astra Data Zone tiers
Co-authored-by: bunnysayzz <stfuazzo@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(model-prices): add Copilot, Bedrock Kimi K3, Gemini Robotics and OpenRouter values from official sources
Co-authored-by: Michal Formanek <michal.formanek@generaliceska.cz>
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: rain <1504569896@qq.com>
Co-authored-by: bunnysayzz <stfuazzo@gmail.com>
Co-authored-by: Michal Formanek <michal.formanek@generaliceska.cz>
* feat(cost_calculator): add cost_per_second for chat per-second pricing
Keep legacy input_cost_per_second and output_cost_per_second as aliases for chat, completion, embedding and responses. When both legacy fields are set, input_cost_per_second wins
Move Bedrock commitment rows to cost_per_second so they bill once
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost_calculator): drop legacy per-second fields from chat paths
Keep Azure chat token pricing generic and update inert Voxtral rates and SageMaker examples
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost_calculator): recognize output-only per-second rates
Include output_cost_per_second when checking whether a deployment cost entry has pricing so output-only legacy aliases remain attached to the deployment during cost selection
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(pricing): cover cost_per_second and legacy per-second aliases through the proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(cost_calculator): drop output_cost_per_second as a chat per-second alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(cost_calculator): restore output_cost_per_second as a chat per-second fallback
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(cost-map): keep input_cost_per_second on bedrock commitment rows for older clients
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): classify every credential-bearing param for the canary suite
* test(proxy): classify gcs_path_service_account as secret, run registry in auth-checks shard, check slot ids at import
* test(proxy): use one generic slot id for callback and request-body credential params
* test(proxy): name a canary slot only for params an integration test plants
* test(proxy): classify the SigNoz callback params
* test(proxy): move the slot sync note into the module docstring
* test(proxy): model unplanted credential params as their own classification
* test(security): classify request-body api_key as unplanted until D1 exists; check registry slots against the harness
* test(security): classify request-body api_key under slot D1
* test(security): classify Langfuse and Datadog callback secrets under slots C1 and C3
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): sweep proxy logs, metrics, a gzip Datadog intake and the Logs drawer for credential canaries
* test(e2e): treat an unset prompt-storage setting as unset and restore it
* test(integration): name the Datadog sink slot G1d
* test(e2e): search the Logs page for base64 forms of the deployment key
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): pass the resolved deployment id to the Datadog route sweep
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): request-path credential canary slots D1-D4
* test(integration): read the Logs drawer and spend-log filter for failed request rows
* test(integration): check the marker in each failed row's spend-log filter; run header slots on chat-family routes
* test(integration): run D2 on embeddings again; only the client-header slot runs on chat-family routes
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): pass the slot deployment's model_info id to the route sweep
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* test(integration): callback credential canary slots C1-C3 and D5
Team callback, team callback_settings, config default_team_settings and key metadata.logging Langfuse secrets, a team Datadog dd_api_key, and request-body Langfuse keys (allow_client_side_credentials) must reach only their sink. Each scenario checks its sink received the canary as auth and that the marker is visible at the stored body, the Logs drawer route and the sink. Adds a unit test that the stored request body snapshot carries no callback parameter.
* test(integration): give the callback sink waits a wider bound
* test(integration): sweep provider requests for callback credentials
* feat(guardrails): send a configured gateway_name from noma_v2 to Noma
The noma_v2 guardrail accepts a gateway_name param, falling back to the
NOMA_GATEWAY_NAME env var. The value is stripped, and when it is non-empty
it goes out as a top-level gateway_name field on /litellm/guardrail. The
param works for both guardrail: noma_v2 and guardrail: noma with use_v2,
and it is appended after the existing constructor params so positional
callers keep their meaning
* chore(ui): regenerate OpenAPI snapshot and dashboard types for gateway_name
The new noma_v2 gateway_name param shows up in the proxy OpenAPI spec, so
the lazy snapshot and the generated dashboard types need regenerating
* Update litellm/proxy/guardrails/guardrail_hooks/noma/noma_v2.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(router): stream anthropic messages lifecycle frames live when no fallback can take over
The /v1/messages streaming wrapper buffered message_start and
content_block_start until the first content_block_delta and dropped
pings behind buffered frames unconditionally, even for requests no
fallback could ever recover. With adaptive thinking on Bedrock or
Vertex the client saw no bytes for the whole thinking pass and hit
read timeouts.
Buffering now applies only while a fallback can still take over
(generic or refusal chain resolving), and a ping is always forwarded
live since it carries no lifecycle and keeps the connection alive.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(router): mirror every dispatcher fallback path in the anthropic stream gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(router): skip already-tried order levels in the anthropic stream gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(router): keep a transport-split ping behind buffered lifecycle frames instead of forwarding its head live
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(router): credit the #39566 branch this fix supersedes
Co-authored-by: Radu Swigler <radu.porumba@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mateo <mateo@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Radu Swigler <radu.porumba@gmail.com>
* docs(security): point readers to the security announcements mailing list signup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs(security): formalize the security announcements wording
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs(security): tighten the best-effort sentence
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: oliver <oliver@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clean up fresh tech debt from 2026-09-28
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: group leaderboard rows in one pass and wrap docstring at 120
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>
`_is_model_cost_zero()` reads a group's cost through `Router.get_model_group_info()`,
which resolves `model_group_alias`, and then gates that on `_is_cost_explicitly_configured()`,
which scanned `Router.model_list` for an exact `model_name` match. Alias names live only in
`Router.model_group_alias` and are never `model_name` entries, so the scan found nothing and
returned False. That False means "the zero cost was defaulted, not configured" (the sparse
auto-registration gate added for #24770), so a model priced explicitly at 0 had budget
enforced against it when requested through an alias, while the same deployment under its own
name was exempt. Both names route to the same deployment and add nothing to spend.
The two lookups in one function disagreeing is the bug, so they now share one resolution:
`_is_cost_explicitly_configured()` resolves through `Router.get_model_list()`, the same
alias-aware path `get_model_group_info()` takes. That also reaches a deployment which prices
itself through its `model_info` block, whose cost-map entry lands under the deployment id.
`_group_declares_explicit_cost()` was an alias-aware copy of this function, wired only into
`model_has_no_cost_mapping()` and never into the budget path; its body is what
`_is_cost_explicitly_configured()` now carries, and both callers share it so the two cannot
drift apart again.
`_has_ptu_flat_cost()` scanned `model_list` the same way and runs after the gate above, so
resolving one without the other would let an aliased PTU group — explicit zero per-token
price alongside a flat capacity cost — pass as free. It resolves the same way now.
Tests cover the predicate and the request path it feeds: over-budget requests through
`_should_skip_budget_checks()` into `common_checks()` for an aliased free model (allowed) and
an aliased paid model (refused), the predicate for free, paid, PTU, hidden and dangling
aliases, and `model_has_no_cost_mapping()` through an alias so the other caller of the shared
check stays covered.
Unchanged: priced groups (the predicate returns False before the gate), unmapped groups whose
zero cost was defaulted (#24770), hidden aliases and aliases pointing at a nonexistent group
(`get_model_group_info()` returns None for both, so the cost is unknown and budget is
enforced), and non-aliased PTU groups.
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude Code attaches output_config to mid-conversation system messages and
sends the per-turn-control-2026-07-01 beta with it. The Vertex beta map
dropped that beta, so Vertex rejected the body with
'messages.N.output_config: Extra inputs are not permitted'.
Forward the beta for vertex_ai, the way azure_ai already does, and add it on
the Vertex Messages path whenever a message carries output_config.
* fix(otel): send cache and reasoning tokens in langfuse usage_details
The OTel V2 Langfuse mapper only sent input, output and total, so cache reads, cache writes and reasoning tokens never reached Langfuse. Emit them as input_cached_tokens, input_cache_creation and output_reasoning_tokens, and send input/output net of those buckets so Langfuse does not price the same tokens twice.
Fixes#43542
* fix(otel): drop redundant comments from the usage_details change
* feat(proxy): add model leaderboard analytics
* feat: add model insights task and range constants
* feat: record task type from task tags in model usage rollup
* feat: serve 365 days of model insights by UTC date
* test: cover task tag resolution in model usage rollup
* test: update model insights range limit test to 365 days
* chore: regenerate dashboard api types for model insights
* feat: add model insights aggregation helpers
* test: cover model insights aggregation helpers
* feat: redesign model leaderboard with stacked bars, treemap and ranking
* test: update model leaderboard view test
* feat: mark model leaderboard as beta in sidebar
* chore: sync schema.prisma copies from root
* fix: only treat task: prefixed tags as model insight tasks
* feat: add metric type for model insights ranking
* fix: rank model insights by selected metric and scope detail queries to ranked deployments
* test: plain tags are not model insight tasks
* test: cover metric ranking, deployment scoping and rollup round trip
* fix: build model insights weeks and halves from the requested date range
* test: cover empty weeks and range-based change comparison
* fix: refetch by metric, show load errors and ignore stale responses
* test: cover metric refetch and error state
* feat: define model insight tasks in a JSON file
* feat: return task labels and categories from model insights
* feat: load model insight tasks from JSON
* refactor: validate rollup task tags against the JSON task list
* feat: serve the task list with model insights
* refactor: drop hardcoded task list from constants
* build: ship model insight tasks JSON in the wheel
* test: cover model insight task JSON
* refactor: take task labels and categories from the API
* test: pass task info to task tile builder
* refactor: color treemap by API-provided category
* test: include tasks in model leaderboard fixture
* fix: make daily model usage migration idempotent
* feat: bound the model insights task query size
* fix: compute task breakdown independent of the chart metric
* test: task breakdown is stable across chart metrics
* chore: regenerate lazy openapi snapshot for model insights
* chore: regenerate dashboard api types for model insights
* fix: keep previous ranking dimmed while a new metric loads
* test: cover stale metric state in model leaderboard
* refactor: drop task row cap constant
* fix: return the full task breakdown instead of a truncated one
* test: task query is not truncated
* feat: add task summary types for model insights
* feat: summarise tasks server-side on a separate model insights endpoint
* test: cover the model insights tasks endpoint
* chore: regenerate lazy openapi snapshot for model insights tasks
* chore: regenerate dashboard api types for model insights tasks
* refactor: drop client-side task aggregation
* test: remove client-side task aggregation tests
* feat: load task breakdown separately from the chart metric
* test: task breakdown is not refetched on chart metric change
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* feat(fireworks_ai): route and list the auto, auto-instant and firerouter routers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(fireworks_ai): drive the router request test through an httpx MockTransport
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(fireworks_ai): let custom firerouter/<models> IDs inherit the firerouter row's capabilities
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(fireworks_ai): integration coverage for router short names forwarding tool_choice and reasoning_effort
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(fireworks_ai): assert tool definitions reach the router upstream
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(codeowners): drop UI and migration code owners
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(codeowners): drop CODEOWNERS self-owner line
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(cost-map): add bedrock_mantle rows for claude opus 5.5 and sonnet 5.5
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* revert(cost-map): keep bedrock_mantle claude 5.5 change to cost map rows only
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(mcp): scan and pin upstream tool descriptions
Run every discovered MCP tool's description and input schema through the
pre_mcp_call guardrails before a listing reaches the client, drop the tools
a guardrail blocks, and serve the guardrail's masked text otherwise. Add
POST and DELETE /v1/mcp/server/{server_id}/pin so an admin can freeze a
server's tool names and descriptions; the gateway serves the pinned catalog
and raises a Slack alert with the diff when the upstream drifts.
* chore: sync schema.prisma copies from root
* fix(mcp): pin input schemas, scan before pinning, admin-only pin writes
* fix(mcp): apply overrides and the pin before the discovery scan, dedupe alerts before sending
The guardrail scan now runs on the text the client is about to see: description overrides are applied first, the pinned catalog next, and the scan last, so a masked pinned or override description is served masked and a pinned tool keeps serving its pinned text while the upstream's text is poisoned. The alert signature is recorded before the send and dropped only when that send fails, so a recovery during a slow send is never undone. A tool whose scan payload cannot be built is hidden alone instead of failing the listing. apply_tool_overrides shrinks to apply_display_name_overrides and the MagicMock servers in the MCP tests carry pinned_tools=None.
* fix(mcp): snapshot the pin through the REST module's unpinned catalog helper
* fix(mcp): pin the raw upstream catalog so an override never hides upstream description drift
* refactor(mcp): trim the tool catalog guard docstrings to one line
* test(mcp): cover guarded discovery boundaries and response definitions
* fix(mcp): bound discovery guardrail concurrency per catalog
* fix(mcp): scan tool catalogs in bounded parallel batches
* fix(mcp): hide pinned catalogs from restricted management views
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
* fix(ui): rename All Models tab to Deployed Models and view filter to All Proxy Models
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ui): use All Proxy Models label for the public model name filter
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(e2e): rename ALL_MODELS_VIEW constant to ALL_PROXY_MODELS_VIEW
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): stored-config credential canary slots
Add canary slots for credentials the proxy holds in its env, config or
database: virtual key raw value, master key, deployment api_key via
/model/new, named credentials, AWS secret key, Vertex service-account
JSON and its minted token, team model_config credential overrides,
config guardrail api_key, and sink credentials from env.
* test(integration): resolve the config guardrail id and require detail routes to return 200
* test(integration): drop repeated timeout comments
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* test(integration): sweep config-deployment routes with the real model id and use the rig admin for the master-key slot
* test(integration): mark the configure-hook config edits as intended
* test(integration): drop suppression markers that suppress nothing
* Use claude-haiku-4-5 for the Bedrock stored-credential test model
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): credential canary slots for MCP and pass-through credentials
Adds slots F1 (MCP static auth), F2 (per-user MCP OAuth token), F2E (per-user
MCP env var), F3 (x-mcp client auth header), H1 (pass-through credential header),
H2 (vector store api_key) and H2S (search tool api_key) to the credential canary
suite. The OAuth double gains an optional mint hook so a test can choose the
issued access token.
* test(integration): wait for MCP spend rows by call type
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): canary MCP and pass-through slots pass resolved ids
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* ci: sync the weekly release cycle with Linear releases
* tmp: dry-run trigger
* tmp: backfill 1.105.0 from the rc/1.104.0 cut
* ci: drop the temporary branch trigger used to verify the Linear sync
* ci: fail on a broken rc-branch lookup and never move a just-cut release back to main
* tmp: dry-run trigger
* ci: drop the temporary branch trigger again
* test(integration): credential canary suite harness
Adds tests/integration/security with canary generation and search, sweeps over the database, GET routes, client responses, sink doubles and Redis, an owned proxy rig, a sweep sensitivity self-test and the config deployment api_key slot. Registers the security group in run.py, the manifest and the CircleCI integration matrix.
* test(integration): widen canary route sweep and harden the rig
Enumerate lazily registered feature routers, call parameterized routes with placeholder ids, fail on routes that return no response, skip provider pass-through routes, add an explicit admin-only route allowance, let the sink double use a configurable token, inflate gzip members anywhere in a blob, sweep Redis before the route walk, and trap outbound connections from the owned proxy.
* test(integration): descend into any decoded value that can still hold an encoded canary
* test(integration): bound canary decoding by depth and decoded bytes
* test(integration): scope log-table and spend-log reads to the scenario window
* test(integration): sweep spend-log rows in the scenario date window
* test(integration): keep spend-log date window summarized
* test(integration): resolve deployment ids, scope paginated log lists, key allowances by slot
* test(integration): expect 404 from the caller-scoped team membership route
* test(integration): use the rig's own master key and expect 404 from submission lookups
* test(integration): check the overridden rig key without assuming the default key is unknown
* feat(providers): add Prism provider
* fix(providers): complete Prism registration
* feat(providers): expose Prism responses and messages
* feat(providers): add DeepSeek V4.1 Flash to Prism
* test(providers): exercise Prism endpoint requests
* fix(providers): align Prism pricing and limits with the live catalog
deepseek-v4.1-flash bills 0.17/0.63 USD per 1M input/output tokens and takes image input;
deepseek-v4-flash bills 0.17/0.21 and caps output at 384000 tokens, per GET /v1/models
* test(prism): assert cost-map invariants instead of pinning catalog facts
* test(prism): derive the asserted model list from the cost map instead of pinning it
* test(prism): capture requests through respx instead of appending to a list and swapping the client transport
---------
Co-authored-by: rajitkhanna <rajitskhanna@gmail.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: ryan <ryan@berri.ai>
