CodeQL flagged two module-level cyclic imports introduced by defining
CachedTokensDetails in litellm.types.llms.openai and importing it from
litellm.types.utils and litellm.cost_calculator. The class now lives in
litellm.types.llms.base, which imports nothing from litellm, and every
user imports it from there.
Also pins that combining realtime usages where only one response.done
carries cached_tokens_details keeps the earlier modality split in both
orders, and commits the regenerated dashboard API types.
A guardrail that rewrites text per chat message now returns the rewritten
rows as structured_messages instead of only texts, so the Responses and
chat handlers write the rewrite back through the structured path. The
generic guardrail API response accepts an optional structured_messages
list, Prompt Security modify builds one from modified_messages, and rows a
server echoes back exactly as shown are restored to the original row
objects because the request model drops undeclared keys. Texts-only
per-message answers keep the named rejection on both endpoints.
get_listed_tool now applies tool_name_to_description so the guardrail evaluates the description clients saw, with a regression test. The listed-tools cache and tool_input_schema fields use Mapping annotations so the change adds no LIT001 findings, and schema.d.ts is regenerated with npm run gen:api
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
JWT auth validated Entra app tokens but never carried an agent identity
into the authenticated principal, so agent policies (trace id
requirement, per-agent MCP restrictions, agent spend attribution) only
applied to virtual keys bound to an agent. A new litellm_jwtauth field,
agent_id_jwt_field, names the claim (dot notation supported) that is
matched against a registered agent's id, then name; the canonical
agent_id flows through the standard and proxy-admin JWT paths, and a
configured claim naming no registered agent fails closed with 403
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
CredentialLiteLLMParams omitted tenant_id, client_id, client_secret,
azure_scope, azure_username and azure_password, so the strict dump used
by credential reuse and Azure client init dropped them and the reused
credential ended with no auth at all
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The e2e harness exists to prove product features end to end against a live
proxy. The prior Hard Rule carved out an exception for "tests that cover the
harness itself" and pointed at coverage_registry/test_collector.py, which in
practice invited unit tests of harness helpers to be staged alongside e2e
work. That is the wrong tool: harness logic that is worth locking down does
not need a mock-driven unit test living under tests/e2e.
Drop the carve-out. The Hard Rule now reads that no unit tests of any kind
belong under tests/e2e, and the passing mention of unmarked harness coverage
in the transport section is removed so the doc no longer contradicts itself.
coverage_registry/test_collector.py still exists on disk and is left in place
for now; whether to relocate or remove it is a separate decision.
Keeps the base's rule that a non-admin id lookup matching no spend-log row answers 403, so the detail route never consults cold storage without an owner row
A guardrail that answers one rewritten text per message it saw no longer
matches the texts the Responses handler extracted once the request carries
instructions or tool items, so the rewrite was rejected with a 500. Spread
such an answer over the structured messages' text slots and write it back
through the structured path, have Prompt Security modify return
structured_messages directly, and give the chat completions pairing the same
named rejection instead of a silent misalignment when the counts differ.
A run over MAX_BASE64_LENGTH_STDOUT_LOG now stays in the log line only when it is hex or decimal with at least two distinct characters. Collapsing only mixed-case runs let every constant-byte payload through: 0x00 encodes to AAAA, 0x01 to AQEB, 0x55 to VVVV, 0xAA to qqqq, so a zero-filled upload still paid the full secret regex.
The two traceback tests that raised a 100,000-character run of one letter now raise the same text the other length-cap tests use, since a single-letter run is exactly the shape the collapse treats as a constant-byte payload
Only mixed-case runs of the base64 alphabet collapse now, so a long hex digest,
numeric id, or padding run stays in the debug line. The truncation filter also
formats the traceback at every level and collapses base64 runs in it before the
secret regex sees it, instead of only capping its length at INFO and above
Since #37391 every log record went through the secret-redaction regex twice, once in the
filter and again in the formatter, and the formatter pass ran on the whole formatted line. At
DEBUG level a multi-megabyte request body (a multi-page PDF upload to /v1/ocr) turned each of
those lines into ten seconds of synchronous regex work on the event loop, long enough for a
Kubernetes liveness probe to restart the pod mid-request.
The filter is now the complete scrubber (message, exception text, stack info, and extras) and
stamps the record, so the formatters skip records that are already clean. The stdout
truncation filter also collapses base64 runs longer than MAX_BASE64_LENGTH_STDOUT_LOG (4096
by default) at every level before the secret regex sees them, so a debug line carrying a
request body costs milliseconds instead of seconds.
* fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets
One flush drains up to MAX_LOGS_PER_INTERVAL source transactions or logs, but a
transaction fans out to one LiteLLM_SpendLogToolIndex row per tool and a log
to one LiteLLM_SpendLogGuardrailIndex row per guardrail, so the index
create_many payload was unbounded. Both index writes now go through
spend_log_write_batches(SPEND_LOG_WRITE_BATCH_MAX_BYTES, SPEND_LOG_WRITE_BATCH_MAX_ROWS).
The tool index write moves out of the rollup batch_() so the split reduces
the query-engine payload; replayed index rows are no-ops under
skip_duplicates, and the daily rollup upserts stay in one transaction
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): pin the row budget in the index fan-out tests
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>
Router.log_retry used to copy the failed attempt's kwargs and metadata into
metadata.previous_models. Nothing downstream read those copies, but they carried
client credentials into spend logs and grew the payload on every retry. Each
attempt now leaves a flat record (model group, deployment id, exception type and
string, attempt number), which drops RETRY_BREADCRUMB_EXCLUDED_KWARGS and the
per-retry credential masking.
num_retries_per_request was enforced from len(previous_models), which only
looked at the metadata bucket and never exceeded four records. The sync and
async client wrappers and the Rust lifecycle guard now read attempted_retries
from whichever metadata bucket the call carries.
Resolves LIT-7505
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
