Addresses review. Promotion copies a trace control field from `metadata` into
`litellm_metadata` only when the key is absent, so a key that is present but
empty in `litellm_metadata` wins and the `metadata` value is never used. The
check still looked at `metadata` in that case, which let
`missing_session_id: reject` accept a request that ends up with an empty
session id, and let an empty trace_id or session_id block the headers
The check now follows the same rule as promotion. If the active container has
the key, its value decides. Only when the key is absent does the promoted
`metadata` value count. This makes the conflicting-bucket cases behave exactly
as on main
Addresses review. On LITELLM_METADATA_ROUTES the proxy promotes the caller's
trace control fields (trace_id, session_id, ...) from `metadata` into
`litellm_metadata`, but only after the header fallback runs. Checking only
`litellm_metadata` let traceparent and baggage fill those fields first, and the
promotion then skipped them because they were already set, so the trace was
recorded under the header ids
The check now also reads `metadata` for fields in
LITELLM_TRACE_CONTROL_METADATA_FIELDS on those routes, and
apply_missing_session_id_policy uses the same check, so `reject` no longer
refuses a request whose session id is about to be promoted
The earlier test asserting that a session_id in `metadata` must not block
baggage on /v1/responses had the premise wrong, since that value is promoted.
It is replaced by tests that assert the promoted caller ids win on
/v1/responses and /v1/messages, with no policy, reject, and generate
Addresses review. The first version treated any value in either `metadata` or
`litellm_metadata` as caller steering. On LITELLM_METADATA_ROUTES the body
`metadata` is provider-facing and is only promoted later, so a session_id there
suppressed baggage before apply_missing_session_id_policy ran, and a request
with a usable baggage session id got a 400 under `missing_session_id: reject`.
An empty session_id did the same, since the policy treats "" as absent
Now only the active metadata container counts, and only a truthy value, which
matches how apply_missing_session_id_policy decides a session id is present.
The helper takes a typed `object` rather than a bare dict
Adds regression tests for both cases, including the end to end reject path,
and drops the test docstrings
The W3C traceparent/baggage fallback in
add_litellm_metadata_from_request_headers documents itself as last-resort:
Lower priority than everything above - only fires when neither the
explicit litellm headers nor the Anthropic-metadata path found anything
But it guards on the top-level `litellm_trace_id` / `litellm_session_id` body
keys and never checks `metadata`, which is the documented way callers set
trace_id / session_id (`metadata: {"trace_id": ...}` on /chat/completions).
A caller that explicitly sets metadata.trace_id has it silently replaced by the
header value, so the implementation contradicts its own stated precedence.
This is not a corner case on managed platforms: GCP's front end injects a
traceparent into every inbound request, so the fallback fires on traffic whose
caller never sent the header. The request still returns 200 and the trace still
reaches the logging backend, just under an id the caller never chose, so any
caller correlating by its own id silently fails to find its trace.
Guard both fallbacks on the caller's request-body metadata as well.
Deliberately narrow:
- x-litellm-trace-id still outranks the body (documented priority #1)
- a request that steers neither field still adopts traceparent/baggage exactly
as before
- steering is per-field: setting only trace_id still lets session_id come from
baggage
- litellm_metadata is checked too, for LITELLM_METADATA_ROUTES (/v1/responses,
/v1/messages, batches, files)
Also corrects the comment, which understated the guard.
4 new tests; each fails without the source change. The existing traceparent and
baggage tests are unchanged and still pass.
* feat(azure): add gpt-audio and gpt-realtime alias rows from the Azure model list
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(azure): keep existing catalog formatting untouched
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Non-streaming responses served by the Rust core already carry
x-litellm-rust: true through _hidden_params.additional_headers, which the
SDK exposes and the gateway renders as a response header. Native streams
did not, because the lifecycle Stream and SyncStream objects had nowhere
to hold hidden params and the marker writer skips objects without them.
Give both stream classes the same _hidden_params bag every other litellm
response has, so the existing marker attaches without wrapping the stream
or changing its identity.
Co-authored-by: Yujong Lee <yujong@berri.ai>
* refactor(types): replace Any with proven types in 13 files
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(types): drop unused executor import from utils type-checking block
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(realtime): keep reserved-key filtering on azure realtime health params
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(realtime): pin reserved-key filtering in azure realtime health auth params
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(realtime): exercise the real azure header builder in the reserved-key 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>
* fix(proxy): fail parked DB lookups at a deadline and flip readiness while they stall
Under a load burst with a slow authentication database every request parked inside
the pod with no deadline while /health/readiness kept answering 200 (its own ping
gets a fresh connection), so the load balancer kept sending traffic until the pod hit
its memory limit, and the parked requests completed against the provider minutes
after every client had hung up
Every pre-request read (key, team, user, end user, budget, membership, organization,
object permission, jwt mapping, project, proxy budget, spend counter reseed) now runs
under one deadline, PROXY_DB_LOOKUP_DEADLINE_SECONDS (default 10 s). A lookup that
hits it fails the request with the existing 503 "authentication database is
temporarily unreachable" answer, honours allow_requests_on_db_unavailable, and never
triggers the transport reconnect (the transport is fine, the query is slow), which is
what turned the repro's stall into "too many clients". Writes stay unbounded
A deadline hit marks the pod stalled for PROXY_DB_LOOKUP_STALL_WINDOW_SECONDS
(default 30 s, 0 disables), during which /health/readiness answers 503 with
"db": "stalled" behind the same fail-open gate, so the pod leaves rotation before it
fills its memory. The existing litellm_in_flight_requests gauge already exposes the
parked set on /metrics
The deadline is enforced on the wall clock: bounded_db_lookup waits on the lookup
task with asyncio.wait and raises DBLookupDeadlineExceeded when the deadline passes
even if the lookup absorbs its cancellation, where asyncio.wait_for on 3.12+ would
sit on the cancelled task for as long as it takes
The failure spend-log row no longer re-runs the key and team lookups when the
failure itself is a database connection or deadline error, so a request that hit
the deadline is answered after one deadline instead of two
* fix(proxy): bound the spend counter gate wait and narrow the stalled lookup shortcut
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep the global spend lookup on the prisma client handle
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>
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): list key and team model aliases in GET /v1/models
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep alias listing helpers within the type discipline budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): cover alias rows on GET /v1/models and /v1/models/{id}
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply team then key aliases like chat completions and keep the alias as the retrieved id
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply key aliases twice like chat completions and skip only malformed alias entries
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): apply the global model_alias_map between the key alias passes like chat completions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): list only the caller's own aliases and never rewrite a listed model id on retrieval
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(proxy): ruff format model_info alias lookup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): hide undiscoverable names from model retrieval so an alias named like one resolves to its target
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): keep undiscoverable models retrievable by id while excluding them from the alias guard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): pass an immutable name sequence into the model_info alias guard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): type the model list alias test helpers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): annotate the new alias listing test fixtures and helpers
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>
* feat(bedrock): add gpt-5.4 and gpt-5.5 us and global inference profile pricing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(bedrock): drop supports_max_reasoning_effort from gpt-5.4 and gpt-5.5 rows
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-05, 2026-09-06)
Drop the TID251 cast import and both cast-ok casts from the refusal
message_delta rebuild by narrowing the TypedDict union on its type literal,
drop the redundant Mapping cast after the isinstance check in
_mapping_field, and type the Lyria predict read-only helpers as
Mapping[str, object] instead of a bare dict with mutable-ok.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-09)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-10)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: keep the pre-existing cost-estimate comment and usage cost read out of the cleanup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-13)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: keep the model info pricing helper out of the cleanup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: drop suppressions that no longer suppress anything (2026-09-16)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: keep the rebind-ok reason inside the line limit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(anthropic): rebuild the refusal message_delta by spreading the chunk
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-17)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-18)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-19)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: keep the pre-existing protected-resource return type out of the cleanup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: clear fresh tech debt from the last 24 hours (2026-09-20)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: type fresh getattr, Any, and bare dict debt from 2026-09-22
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(mcp): keep the string guard on tools/list next_cursor
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(vercel_ai_gateway): type the embedding error headers dict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(techdebt): fix inert suppressions and missing Final in 2026-09-22 changes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(techdebt): shorten suppression reason to fit line length
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(techdebt): format provider spread so its suppression sits on the literal
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(techdebt): drop the logger extras suppression that LIT013 now flags as inert
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(techdebt): clear fresh suppressions, Any aliases and slop from the 24h window
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(vercel): take a read-only headers mapping in get_error_class
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mateo <mateo@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): edge-case matrices for malformed token limits and callback_settings shapes
Extends the integration suite so two classes of issues found by gauntlet
reviews are caught end to end against a real proxy:
- non-numeric or odd model_info token limits (from /model/new and from
config YAML) must be listed as absent on /v1/models, /models,
/v1/models/{id} and /model/info, keep sibling models listed, and still
serve chat
- every callback_settings shape (top level and per consumer) must let
the proxy boot, register the configured callbacks and serve chat
Four product bugs on main surfaced by the matrices are recorded as
BUG skips per the suite convention: chat 500 and /model_group/info 500
on non-numeric token limits, a startup crash on a non-object
callback_settings, and otel silently dropped on a non-object
callback_settings.otel
* test(integration): pin the exact coerced value for numeric-edge token limits
Addresses review feedback: the numeric-edge matrix only asserted
'int or absent'. It now asserts the listed value for each case on
/v1/models, /models and /v1/models/{id}, which also lets the listing
helper drop its optional-expectation branch.
* fix(s3_v2): bound concurrent S3 uploads per flush and add opt-in JSONL batch files
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(s3_v2): keep failed uploads queued, parse env-backed flags, add integration coverage
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(s3_v2): type test helpers and honor constructor bound when config value is null
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(s3): annotate required casts for the type-discipline gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(s3_v2): keep tenant prefixes, stable retries and cold storage safety in batch file mode
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): cover root-level batch file keys for codecov patch target
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): audit matrix across chat, messages and responses surfaces with sink faults
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): read sink objects under the lock in the audit cells
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(s3_v2): rebind the retry queue instead of slicing in place
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): ignore stray non-POST requests in the surface upstream
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(s3_v2): keep fake upload state on the fake client instead of nonlocal counters
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: yucheng <yucheng@berri.ai>
* test(integration): add read-replica routing harness
* refactor(integration): hoist the maintenance url imports
* fix(integration): keep per-test databases and the witness sequence readable under replica roles
* fix(integration): opt bespoke database and pool tests out of the injected read replica
* test(integration): commit recorded replica routing expectations
* fix(integration): judge routing by role containment so shrinking role sets do not fail
* fix(integration): run the pool-limit shutdown choreography on the superuser database url
* ci(integration): add the mcp group to the replica matrix
* fix(integration): judge routing by exact role sets with a named either-role allowlist
* test(integration): drop containment-era routing expectations for re-recording
* chore(integration): drop docstrings from the replica harness scripts
* docs(integration): describe exact routing matching and the either-role list
* test(integration): record exact replica routing expectations
* test(integration): allow the SELECT 1 health probe on either role
* test(integration): replace committed routing expectations with an on-demand base-vs-head parity run
* test(integration): fix parity env scope, readme wording, and seed-deterministic serialization test
* test(integration): make the sorted-role serialization test deterministic in-process
* test(integration): swap all product code in parity runs and pin role gains
* ci(integration): force tracked-file removal before parity checkout
---------
Co-authored-by: yuneng <yuneng@berri.ai>
* test(integration): reproduce passthrough upstream error body missing from logs and spend row
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): log upstream 4xx/5xx error bodies and carry them into the failure hook
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(error_normalization): let the passthrough prefix win over upstream body text
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): honor message redaction for upstream error bodies
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): bound the upstream error body read and sanitize it before logging
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(passthrough): use the Sequence import directly in the allowed-routes cast
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): rechunk the upstream error stream so the preview read stays bounded
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): audit matrix for passthrough upstream error visibility
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): drop the restating docstring on the upstream failure logger
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the retired covers markers from the passthrough error tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): keep the upstream status when the error body peek fails
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(passthrough): cover the relay aclose in the mid-read failure test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(passthrough): relay decoded partial body on mid-read failure
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>
* fix(proxy): do not requeue a daily spend batch whose commit already left for postgres
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): settle an interrupted daily spend commit from the shutdown flush instead of blocking the cancelled tick
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): burst two workers and SIGTERM during daily spend COMMIT, expect exactly once
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>
* fix(proxy): keep deployment labels on cache-hit post_call rejections
A post-call failure on a response served from the litellm cache set no first_api_call_start_time, so the failure hook flagged it as rejected before routing and dropped the model_id and provider labels
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): read the cache hit from caching_details in the failure hook
model_call_details[cache_hit] is stamped inside the enqueued success handler, so a post-call failure can observe it too early; logging_obj.caching_details is set synchronously before the cached response returns
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cover cache-hit guardrail reject deployment labels across endpoints, modes and chaos
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bound the worker-kill reject count by in-flight losses
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(proxy): assert provider and model labels on the cache-hit regression test
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>
* fix(logging): bound the exceeded budget regex so a crafted error message cannot stall the proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): audit normalized_error clustering on long messages with a real two worker proxy
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): poll for the budget denial and correlate upstream 503 bursts by request marker
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logging): replace the bounded exceeded budget regex with a linear scan that keeps the original semantics
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): compare upstream error wording against the decoded message
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): tolerate a reaped worker while listing proxy children
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>
