* fix(auto_router): bill the routing embedding to the caller's key and team
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(auto_router): validate the forwarded caller metadata with a pydantic model
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>
Without the auto_router feature in the signed enterprise license a proxy may hold
one complexity router with classifier_type heuristic_v2 across config.yaml and the
DB; with it the limit is lifted. The ceiling is derived once from LicenseCheck and
handed to the Router, which refuses the extra router at registration. config.yaml
over the limit refuses to start, and /model/new, /model/update and
PATCH /model/{id}/update refuse the write with a 403 before touching the DB.
Expiry follows the existing max_users/max_teams pattern: judged when the
license is verified, not on every call, and a verify that rejects the license
(expired or unreadable) leaves no signed payload behind. The rollback after a
failed upsert re-admits state that was already serving, so it is exempt from the
ceiling: an edit that fails, including one refused by a ceiling that has since
tightened, leaves the router serving its previous configuration.
A write that leaves a row on heuristic_v2 under a limited license runs in one
transaction that takes a Postgres advisory lock before counting the DB rows plus
this proxy's config.yaml routers, so concurrent writes on any pod cannot both
claim the sole slot and no surplus row is ever persisted.
Only the row insert runs under that lock: the team model bookkeeping, which
needs a second pool connection, runs after the transaction has committed.
PATCH /model/{id}/update follows the same order as create: the row is written
through the slot first and the team's model list is updated only afterwards, so
a refused write leaves the team as it was.
The slot transaction bypasses the repository's publish-on-write, so it
publishes the config change once after commit, as delete_team_models does.
425e3069b9 added Router.get_configured_mode but only exercised it
through create_model_info_response, which the router coverage gate does
not count. The code-quality workflow has been failing on staging and on
every open PR since.
* fix(vector_stores): only list vector stores the caller was granted
/vector_store/list returned every managed vector store with no team_id to any
key, and let a dashboard session see stores created from the dashboard because
every session shares the litellm-dashboard team id. Non-admin listings now show
a store only when the key or one of the caller's real teams is allowlisted for
it via object_permission.vector_stores, or the team owns it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(vector_stores): keep a dashboard session key's own grants when the user has no teams
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>
CI unit shards load the price map from main at import, so a model that only
exists on the branch never reaches open_ai_chat_completion_models and
cost_per_token cannot infer its provider. Refresh the sets after swapping in
the local map so the tier pricing cases resolve gpt-6-astra before merge
OpenAI documents low, medium, high, xhigh, and max for gpt-6-astra, with no none level, so the entry stops advertising none and starts advertising max.
Adds the OpenAI gpt-6-astra entry to both price files with standard, flex, priority (fast mode), batch, and above-272K long-context rates, and regression tests covering each tier and the batch rates.
A five-token response can complete before the cancel lands, which put the
test back on the "Cannot cancel a completed response" path it used to
swallow. Ask for a long generation so the cancel always beats completion,
and assert the cancelled status unconditionally
test_cancel_streaming_response drained the whole background stream before
cancelling, so an OpenAI keepalive stall held the e2e_openai_endpoints job for
301s and failed it on a generic APIError, and on a healthy day it cancelled an
already completed response and swallowed the 400 without verifying a cancel.
Cancel at the first event carrying a response id, bound admission to 90s, skip
naming the stall when only keepalives arrived, and assert status == cancelled
* fix: stop a cleared Organization field from failing key creation
Clearing the Organization combobox in the Create Key modal left organization_id set to an empty string, so /key/generate looked up an organization named "" and failed with "Organization doesn't exist in db. Organization=".
OrganizationDropdown now emits null on clear, and GenerateKeyRequest normalizes an empty organization_id or project_id to None the same way it already does for team_id.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test: drop customer-specific docstring from key request normalization test
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: yassin <yassin@berri.ai>
* fix(spend_tracking): leave SpendLogs.session_id null when no client session id was established
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(lint): ratchet basedpyright budget after session_id fix
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend_tracking): ignore trace ids as session ids
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend_tracking): gate null SpendLogs.session_id behind missing_session_id: omit
Unset, generate and reject keep the legacy trace id fallback. omit records only
metadata.session_id, the key Langfuse reads, so a trace id copied into
litellm_session_id by get_litellm_params never becomes a session.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend_tracking): stamp the omit decision on the request so a config reload cannot fabricate a session
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend_tracking): keep omit covering requests the pre-call stamp never reaches
Router-model provider pass-through calls allm_passthrough_route directly and
skips add_litellm_data_to_request, so those requests never run the pre-call
helper and carry no omit stamp. Reading only the stamp made POST
/anthropic/v1/messages write a fabricated uuid into SpendLogs.session_id under
missing_session_id: omit while its Langfuse trace had no session, the exact
divergence the policy exists to remove.
The stamp now only pins omit on, and an unstamped request falls back to the
configured policy, so a config reload still cannot fabricate a session for a
request that was decided pre-call.
* fix(spend_tracking): make the session-omission marker proxy-owned so clients cannot forge it
* fix(spend_tracking): strip the client-sent omission marker from both metadata buckets before they merge
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(spend_tracking): strip the session-omission marker from both metadata buckets
The pre-call policy ran before litellm_metadata is merged into metadata, so a
client that planted the marker in litellm_metadata had it copied back into the
route's own bucket after the strip and still got a null SpendLogs.session_id.
---------
Co-authored-by: yassin <yassin@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>
* fix(proxy): return persisted team memberships from /user/new
new_user attached default teams after building its response from the
pre-membership snapshot, so NewUserResponse.teams was always empty for
users created with default_internal_user_params.teams. The CLI SSO flow
reads that response on a user's first login and minted a teamless JWT,
which skipped the default team's model allowlist.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): return team ids as a tuple to satisfy LIT001
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>
Bedrock retired cohere.command-r-plus-v1:0 on 2026-08-19 and lists no
Cohere command chat model anymore, so the three local_testing cases that
pinned it fail with a 404 end-of-life error on every pipeline. Drop the
case from test_completion_bedrock_httpx_models and move the
parallel-streaming Bedrock entry to mistral.mistral-7b-instruct-v0:2,
which still takes the invoke route and is ACTIVE in the CI account.
GET /user/list gains an optional search query param that ORs a case-insensitive contains match over user_id and user_email. The Users page search box now sends that param and reads "Search by email or ID…", the way the Teams page already searches by name or ID. Every existing /user/list param keeps its meaning and the Filters drawer is untouched
Claude-Session: https://claude.ai/code/session_018yW93iDaEMhoQUXcYjus7D
The logs table already rolled up cost per session but the Tokens column only showed the representative call's usage. The per-session aggregate query now also sums prompt, completion and total tokens, and the Tokens cell switches to those sums for multi-call sessions the same way the Cost cell does.
Claude-Session: https://claude.ai/code/session_01CNasFqyjnLN3Rqman25vde
