Fixes SyntaxError at pytest collection time caused by leftover
<<<<<<<, =======, >>>>>>> markers in test_bedrock_common_utils.py.
Keeps the assertion matching the model under test
(claude-haiku-4-5-20251001-v1:0).
Project-level model rpm/tpm limits stored in project_metadata were never
checked during rate limit enforcement — only model-level limits applied.
Adds _add_project_model_rate_limit_descriptor_from_metadata() to the v3
limiter (mirrors the existing team metadata path) and calls it in
async_pre_call_hook, creating a model_per_project descriptor keyed as
"{project_id}:{model}" with the project's configured limits.
Also extends get_model_rate_limit_from_metadata's Literal to accept
"project_metadata" and adds get_project_model_rpm/tpm_limit helpers.
Fixes: LIT-2317
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Guard empty recipients in _handle_multi_threshold_max_budget_alert:
log warning and skip instead of falling through to old path error loop
- Widen max_budget_alert_emails type to Dict[str, Union[str, List[str]]]
to match _parse_email_list runtime behavior (accepts comma-separated strings)
- Pre-filter asyncio.create_task with min threshold check to avoid
unnecessary task allocation on every request when spend is below
all configured thresholds
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>
- Add `default_key_max_budget_alert_emails` litellm_settings config as
global fallback for all virtual keys (per-key metadata takes priority)
- Fix crash when key has no user_id/user_email by passing recipient email
to _get_email_params (same pattern as team soft budget path)
- Use owner email for greeting, falling back to key_alias or token
- Rename setting from default_max_budget_alert_emails to
default_key_max_budget_alert_emails for clarity
Previously, _apply_default_budget_to_end_user() only set the budget in-memory,
leaving budget_id NULL in the database. This caused the budget reset job to skip
these users since it filters by budget_id. Now the function also persists
budget_id via a Prisma update call (non-fatal on failure).
Fixes#22019
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
_virtual_key_max_budget_check raises BudgetExceededError when spend
crosses max_budget, which meant the 100% threshold in the multi-threshold
email config never got a chance to fire — the request that pushes spend
over 100% was rejected before the alert check ran. Reorder so the alert
check runs first; enforcement still raises right after.
Users can set metadata.max_budget_alert_emails as a JSON map of threshold
percentages to email recipients on virtual keys. When configured, the email
handler loops over each threshold, checks per-threshold dedup cache, and
sends to the configured recipients (auto-including the key owner's email).
When no map is set, the existing single 80% threshold behavior is preserved
unchanged. Teams support is out of scope for this v0.
async_post_call_failure_hook passed only supported_enum_labels to
prometheus_label_factory; enum_values is required. The call was unused
because _inc_labeled_counter builds labels internally.
Reformat Prometheus-related modules and passthrough/copilot helpers for CI.
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) 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, 30, 8) (push) Waiting to run
When prisma migrate deploy reports 'No pending migrations to apply' the DB
already matches schema — running _resolve_all_migrations (migrate diff +
prisma db execute) adds 25+ seconds unnecessarily, causing the proxy to
miss the 90-second startup timeout in test_litellm_proxy_server_config_no_general_settings.
page_utils.test.ts enforces that every menuGroups entry has a matching
description and vice versa. The left nav uses 'skills' but page_metadata.ts
still had 'claude-code-plugins', causing two test failures.
When DIRECT_URL is not set and DATABASE_URL is a Neon pooler URL, prisma migrate diff
fails (pooler doesn't support extended query protocol for schema introspection). Previously
_resolve_all_migrations returned early without applying any migrations, leaving the
budget_limits column missing and causing test_auth_callback_new_user to fail.
Now falls back to running each migration SQL file via prisma db execute --file, which
works with pooler URLs and is safe to re-run due to IF NOT EXISTS guards.
- url_utils.py: narrow sockaddr[0] from str|int to str via a helper with a
fail-closed isinstance check. Fixes the two mypy errors introduced by
the SSRF hardening without masking unexpected stdlib behavior.
- key_management_endpoints.py: restore the documented team member_permissions
path for /key/update. The cross-key admin check added to close the
cross-org rewrite attack was over-broad: it rejected non-admin team
members even when can_team_member_execute_key_management_endpoint had
already validated their team membership and /key/update grant. Now skip
the admin check when the key has a team_id and the change is non-budget
(membership + permission already enforced above). Budget/spend changes
still require team/org admin. The cross-org attack remains blocked:
an outside org admin fails the earlier team membership check.
- test_logging_redaction_e2e_test.py: rename and rewrite two parametrized
tests to assert that request-body turn_off_message_logging has no effect.
Reflects the intentional removal of turn_off_message_logging from
_supported_callback_params so the caller cannot override admin logging
policy via the request body.
- test_key_management_endpoints.py: add two tests covering the restored
team member permission path — one positive (non-budget update succeeds
for a team member with /key/update grant), one negative (max_budget
change still rejected without admin role).
* docs: add copy-page-as-markdown button + llms.txt generation
Adds the signalwire llms-txt Docusaurus plugin + theme so every
docs page gets:
- A "Copy Page" dropdown in the breadcrumbs (Copy, View Markdown,
Ask ChatGPT, Ask Claude) — defaults from the theme hook, no
extra config required.
- A raw `.md` companion at `<page>.md` for LLM consumption.
- Site-wide `/llms.txt` index and `/llms-full.txt` corpus.
The signalwire plugin README documents a `copyPageButton` option
that the v1.2.2 Joi schema actually rejects; the theme's defaults
cover the same feature set, so only `content.enableMarkdownFiles`
and `enableLlmsFullTxt` are set. Theme is pinned to `1.0.0-alpha.9`
because the floating version resolves to a broken canary whose
`main` points at a missing file.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* docs: pin exact versions for signalwire llms-txt deps
Drop the caret ranges on the two packages added in the prior
commit so the docs site pulls byte-identical npm tarballs on
every install. Matches the existing convention in this
package.json (everything else is already exact) and protects
against supply-chain substitution if a malicious patch version
is published under the same minor.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* docs: upgrade signalwire llms-txt plugin to v2 alpha + enable copy button
The stable v1.2.2 plugin we first pinned does not call setGlobalData
during contentLoaded, so the theme's CopyPageContent component always
returned null (its `!siteConfig` bailout). The theme v1.0.0-alpha.9
is built against the v2-alpha plugin API, which is the version that
actually wires the copy-content JSON and plugin config into the theme
via setGlobalData.
Pins plugin to 2.0.0-alpha.7 (exact, no caret) and switches the
config to the v2 schema:
- top-level `markdown` + `llmsTxt` replace the v1 `content` block
- new `ui.copyPageContent` (off by default in v2) enables the button
with view-markdown + ChatGPT + Claude actions.
Verified end-to-end: production build serves the dropdown with
"Copy Raw Markdown", "View Markdown", "Reference in ChatGPT", and
"Reference in Claude" on /docs/routing (button mounts at ~x=960 in
the breadcrumbs row).
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Claude Opus 4 (1M context) <noreply@anthropic.com>
