Add an aws_textract OCR provider on the Rust route, with no Python path. The
detect-document-text model returns plain lines and analyze-document renders
layout and tables as markdown. Both use Textract's synchronous API, so a
multi-page PDF or TIFF is rejected with an error that names the single-page
limit. A call with no region fails instead of falling back to Bedrock's default
SigV4 covers the request body, and host hooks can rewrite that body before it
is sent. litellm-http now has OutboundRequest, which serializes the body once,
shows those bytes to a RequestSigner and is the only thing a route can send.
Chat, audio transcription and OCR build it after their hooks ran, so a callback
that redacts the body still produces a valid Bedrock or Textract signature
ChatCompletionsAuth and AudioTranscriptionAuth are replaced by
litellm_auth::RequestAuth, and one helper in core turns it into a signed or
unsigned request. Audio transcription now signs only the AWS header set and
rejects a forwarded header that SigV4 computes, the same as chat
The OCR catalog routes aws_textract as Rust required, and the dispatch context
reads the provider from the model prefix so a provider scoped rule can match
On a fresh database where the migrations run in a separate job while the
proxy boots with DISABLE_SCHEMA_UPDATE=true, the startup view check ran
as a fire-and-forget task, used up its three 10 second retries before
LiteLLM_SpendLogs existed, and died with an unretrieved exception. The
spend views were never created, so the /global/spend routes returned 500
until the pod was restarted
PrismaClient now holds a view setup task. It polls to_regclass for the
spend-log table every 5 seconds, creates the views and loads the spend
log row count once the table is there, keeps polling if an attempt raises
while the schema is still settling, and logs an ERROR with the last
failure if nothing worked after 15 minutes. Proxy shutdown cancels the
task
The spend route e2e tests for the five view-backed routes are no longer
skipped and wait for the views through the harness convergence helper
The OCR route called back into Python's get_secret_str for every env
fallback. With no secret manager configured that is os.environ behind a GIL
hop, and with one configured it blocked a tokio worker on vault I/O and also
sent the Azure and GCP identity variables, which Python reads with os.getenv,
to the vault. The other Rust routes already read the process environment.
Read the process environment here too. When litellm would read secrets from
a secret manager, decline the Rust route so the Python route serves the call
with the vault-backed keys
A completed batch reports its whole cost on every retrieve, and the
per-model budget limiter added that cost to the key, user, team, and
end-user counters on each poll. Stamping model_group on plain-id
retrieves widened this from model-encoded batch ids to every poll, so
a key ran out of a budget it never spent. A marker per counter and
batch id now lets the first poll charge and later polls skip.
The azure row of test_get_model_info_falls_back_from_dated_snapshot_to_undated_entry used gpt-5.6-luna-2026-07-09, which main's cost map carries as an exact azure key, so the lookup returned the dated key and the required misc test job failed on main. All three dated snapshot tests now use a 2099-01-01 snapshot date, so they keep exercising the strip path whatever real snapshots the map gains
DeepSeek charges half the listed rate outside 01:00-04:00 and 06:00-10:00 UTC
Monday to Friday, so every deepseek-flash, deepseek-v4-flash,
deepseek-v4-flash-vision-exp, and deepseek-v4-pro entry now carries an
off_peak_pricing block with those windows and the halved input, output, and
cache-hit rates. The generated cost map schema picks up the block, and the
regression tests pin the peak and off-peak cost of one call at fixed moments.
The S3 Vectors ingestion embedded every chunk with the request's
embedding.model or the default, never the embedding_model the store was
registered with, while search on the same store embeds with the
registered model. A registered store uploaded to by id alone therefore
embedded with the wrong model and AWS rejected the vectors on the
dimension mismatch. The store's embedding model now wins for S3 Vectors
ingestion through a helper next to the one search already uses
Configured injection points were dropped whenever the request already
carried a client-set cache_control anywhere, so an operator's rolling
tail checkpoint silently never landed once a caller marked its own
system prompt. Only the automatic defaults stand down now. Configured
points skip a target the client already marked and stay under the
provider's 4-block cap, counting the client's marks on messages, system,
tools and the root cache_control first. The chat path carries the tool
count as a stamp on the points because the prompt-management hook never
receives tools.
Fixes#40675
Hosted Responses API tools with no Chat Completions equivalent were forwarded
verbatim, so Codex 0.140+ got a 400 from the provider on every turn. The bridge
now drops tool_search and local_shell the same way it drops computer_use,
image_generation, and shell, and also drops parallel_tool_calls when no chat
tools remain, since chat completions only accepts it alongside tools
A "bucket:" or ":index" id split into an empty name, so ingestion silently
generated a fresh index and search sent the empty name to AWS. Both sides now
raise the existing format error through the shared helper.
A registered S3 Vectors store usually carries only its "bucket:index" id,
and the previous commit stopped forwarding the caller's bucket and index for
a managed store, so ingesting into one raised KeyError 'vector_bucket_name'.
The ingestion now derives both from vector_store_id with the rule the search
side already uses, explicit keys still winning. The caller's
litellm_credential_name is dropped for a managed store too, since it expands
into api_key and api_base, and max_embedding_requests_per_min joins the
per-upload options a caller may still set.
