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.
* 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>
The bridge probe asked `responses_api_bridge_check` with the summary read straight off
the Responses object, but `litellm.completion` reads it from `optional_params` via
`peek_reasoning_summary_aliases`, which the bridged request never populated. So gpt-5,
gpt-5.1 and azure/gpt-5 answered "bridging" to the probe and "not bridging" for real,
and the object still landed on Chat Completions, which only takes a string
`reasoning_effort` is now always the effort string, and `summary` rides the
`reasoning_summary` alias that main.py already reassembles into `{effort, summary}` on
the bridged path. The alias is emitted only when the probe says the model bridges, so
no chat provider ever sees it, and the probe is now asked with the exact params this
transform emits
The debug call built its message with an f-string, which
test_logging_calls_do_not_build_their_message_eagerly rejects. Pass the exception
as a %-style argument so the message is only built when the log is emitted.
The bridge probe called responses_api_bridge_check without api_base, so it
resolved the OpenAI base from globals and environment rather than from the
request, while litellm.completion runs the same check with the caller's value.
Today the two cannot disagree: this path always supplies a reasoning_effort,
which short-circuits the endpoint term in the only arm that reads it. Passing it
anyway keeps the probe a faithful mirror of the definitive check rather than one
that happens to agree.
The Responses API takes reasoning as an object, {effort, summary}. Chat
Completions takes reasoning_effort as a string enum and has no equivalent of
summary, but the completion bridge forwarded the whole object whenever summary
was set, which agentic clients set on every request.
Bedrock Converse guards its mapping with isinstance(value, str) and has no else
branch, so the object fell through, thinking was never enabled, and the caller
was billed for a non-thinking turn with nothing in the response to explain it.
The object is still forwarded for the one caller that can consume it: a model
whose cost-map mode is responses, which litellm.completion bridges back onto the
Responses API and reassembles {effort, summary} there. That decision is delegated
to responses_api_bridge_check, the same check litellm.completion runs, rather
than a second copy of the rule that could drift from it. An object carrying no
effort now yields no reasoning_effort at all.
Multi-IdP deployments can now set virtual_key_claim_field and
unregistered_jwt_client_behavior on a JWTIssuerConfig entry. Tokens from
that issuer use the issuer-specific claim path and no-match policy for the
virtual key mapping lookup; issuers that omit them keep the global values.
The auth flow now enters the mapping lookup when any issuer configures the
field, not only when the global field is set.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
/model/info fills a deployment's missing pricing in from the model cost map so the
Admin UI has a rate to display. Clients echo that whole model_info blob back on save,
and update_db_model merged it into the row, so editing an unrelated setting turned
that day's catalog price into a real per-deployment override. After that the
deployment ignored the cost map and Reload Price Data could no longer move it,
because the reload replays each deployment's stored pricing over the fresh catalog.
Drop the derived pricing from incoming model_info on the two write paths. The
drop-set is read off the same objects the read path uses, CustomPricingLiteLLMParams
plus the tiered *_above_N_tokens pattern that get_model_info passes through and no
model declares, so it cannot drift as new rates are added. output_vector_size is
exempt: it lives on the pricing model but is an embedding dimension, not a rate.
A deployment's own pricing still rides litellm_params, which is untouched, as is the
explicit-null clear, which reads the incoming model rather than the filtered dict.
The filter sits in the endpoint bodies rather than _add_model_to_db, which master-key
rotation reuses to re-serialize every stored deployment.
Codex hides catalog entries whose supported_in_api is false when it runs
with an API key, so a stock entry the proxy serves now carries
supported_in_api true alongside its list visibility.
`lite codex` now asks the installed Codex for its own model list through
`codex debug models` before writing the catalog. A proxy model whose id
matches a stock Codex slug keeps that Codex's entry (reasoning levels,
base instructions, context window and the rest) and only its picker
position, visibility and upgrade nudge come from the proxy. Unknown slugs
still get the plain entry built from the bundled base instructions. The
catalog directory is created before the stock call so a fresh CODEX_HOME
does not make Codex refuse to run
Drop the unrequested env override on LOGGING_WORKER_TIMEOUT_SUMMARY_WINDOW_SECONDS.
The constructor still accepts a value for tests, so runtime behavior is unchanged.
