Skip to content

feat(proxy): add option to disable server-side prepared statements for DB lookups - #29984

Merged
yassin-berriai merged 1 commit into
litellm_internal_stagingfrom
litellm_fix/disable-prepared-statements-option
Jun 10, 2026
Merged

yassin-berriai merged 1 commit into
litellm_internal_stagingfrom
litellm_fix/disable-prepared-statements-option

Conversation

@yassin-berriai

@yassin-berriai yassin-berriai commented Jun 8, 2026 •

Copy link
Copy Markdown
Contributor

Relevant issues

Preventative complement to the cached-plan retry fix. During rolling deployments, pooled Postgres connections can hold prepared-statement plans that a concurrent schema migration invalidates, producing cached plan must not change result type. The retry path recovers after the fact; this PR lets operators turn the failure mode off entirely for deployments where it is a known problem (pgbouncer transaction pooling, frequent migrations)

Linear ticket

Pre-Submission checklist

  • I have added meaningful tests
  • My PR passes all unit tests on make test-unit
  • My PR's scope is as isolated as possible; it only solves 1 specific problem
  • I have requested a Greptile review by commenting @greptileai and received a Confidence Score of at least 4/5 before requesting a maintainer review

Screenshots / Proof of Fix

Verified live against a real Postgres 16 instance with the new flag enabled, making real requests to the OpenAI API. Every database read and write went through the connection that has pgbouncer=true appended.

Config used (/tmp/pr29984_live_config.yaml):

model_list:
  - model_name: gpt-4.1-mini
    litellm_params:
      model: openai/gpt-4.1-mini
      api_key: os.environ/OPENAI_API_KEY

general_settings:
  master_key: sk-1234
  database_url: postgresql://litellm:litellm@localhost:5433/litellm
  database_disable_prepared_statements: true
  1. Start a dedicated Postgres and the proxy on port 4010
docker run -d --name litellm-pr29984-live -e POSTGRES_USER=litellm -e POSTGRES_PASSWORD=litellm -e POSTGRES_DB=litellm -p 5433:5432 postgres:16

python litellm/proxy/proxy_cli.py --config /tmp/pr29984_live_config.yaml --port 4010 --detailed_debug

The proxy boots, runs migrations against the real DB, and starts serving:

INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:4010 (Press CTRL+C to quit)
  1. Health check
curl -s http://localhost:4010/health/liveliness
"I'm alive!"
  1. Real chat completion through the proxy (hits the live OpenAI API)
curl -s http://localhost:4010/v1/chat/completions \
  -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" \
  -d '{"model": "gpt-4.1-mini", "messages": [{"role": "user", "content": "Say hello in 5 words"}]}'
{"id":"chatcmpl-DpKWjfc1NfZMK7IqjKhJfCu0wQkvV","model":"gpt-4.1-mini","object":"chat.completion","choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello! Hope you’re doing well!","role":"assistant"}}],"usage":{"completion_tokens":8,"prompt_tokens":13,"total_tokens":21}}
  1. Generate a virtual key (a DB write through the pgbouncer-mode connection)
curl -s http://localhost:4010/key/generate \
  -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" \
  -d '{"models": ["gpt-4.1-mini"], "key_alias": "pr29984-live-test"}'
{"key_alias":"pr29984-live-test","key":"sk-lDmw_pCGLtgS7jL-pCglog","token_id":"ea5e107a0b6a35427b05598677c29ae165bcd51aff3e0da1500f6c646aad8ee0","created_at":"2026-06-10T21:13:33.407000Z"}
  1. Use the generated key (a DB read; auth lookup resolves the key from Postgres, then the request hits OpenAI)
curl -s http://localhost:4010/v1/chat/completions \
  -H "Authorization: Bearer sk-lDmw_pCGLtgS7jL-pCglog" -H "Content-Type: application/json" \
  -d '{"model": "gpt-4.1-mini", "messages": [{"role": "user", "content": "Reply with the single word: pong"}]}'
{"id":"chatcmpl-DpKWr7W1YFLKA62gu2dVN7XaXXHeH","model":"gpt-4.1-mini","choices":[{"finish_reason":"stop","message":{"content":"pong","role":"assistant"}}],"usage":{"completion_tokens":1,"prompt_tokens":14,"total_tokens":15}}
  1. Confirm the key was actually persisted in the real Postgres
docker exec litellm-pr29984-live psql -U litellm -d litellm -t -A \
  -c "SELECT key_alias, key_name FROM \"LiteLLM_VerificationToken\" WHERE key_alias='pr29984-live-test';"
pr29984-live-test|sk-...glog
  1. Confirm the flag actually appends pgbouncer=true to the Prisma DATABASE_URL, using the exact functions the proxy runs at startup
python3 - <<'PY'
import yaml
from litellm.proxy.proxy_cli import _build_db_connection_url_params, append_query_params
from litellm.secret_managers.main import str_to_bool
gs = yaml.safe_load(open("/tmp/pr29984_live_config.yaml"))["general_settings"]
raw = gs.get("database_disable_prepared_statements", False)
flag = (str_to_bool(raw) is True) if isinstance(raw, str) else bool(raw)
params = _build_db_connection_url_params(connection_limit=10, pool_timeout=60, disable_prepared_statements=flag)
print("resolved flag:", flag)
print("params:", params)
print("flag ON  ->", append_query_params(gs["database_url"], params))
off = _build_db_connection_url_params(connection_limit=10, pool_timeout=60, disable_prepared_statements=False)
print("flag OFF ->", append_query_params(gs["database_url"], off))
PY
resolved flag: True
params: {'connection_limit': 10, 'pool_timeout': 60, 'pgbouncer': 'true'}
flag ON  -> postgresql://litellm:litellm@localhost:5433/litellm?connection_limit=10&pool_timeout=60&pgbouncer=true
flag OFF -> postgresql://litellm:litellm@localhost:5433/litellm?connection_limit=10&pool_timeout=60

With the flag on, pgbouncer=true is appended; with it off, it is absent. The live proxy above ran with the flag on and successfully served completions and performed DB reads and writes against the real database, confirming the assembled URL is valid and fully functional.

Migration scenario: reproducing and eliminating "cached plan must not change result type"

This demonstrates, on a live proxy against a real Postgres, the behavioral difference the flag introduces. The flag-off runs double as the before baseline: database_disable_prepared_statements does not exist on litellm_internal_staging, and with the flag off (the default) this branch builds the exact same DATABASE_URL and exhibits the exact same prepared-statement behavior as staging. The same schema migration that takes a proxy down with the flag off is harmless with it on.

Postgres 16 in Docker, with statement logging on so we can see exactly what Prisma sends:

docker run -d --name litellm-pr29984-mig -e POSTGRES_USER=litellm -e POSTGRES_PASSWORD=litellm -e POSTGRES_DB=litellm -p 5434:5432 postgres:16
docker exec litellm-pr29984-mig psql -U litellm -d litellm -c "ALTER SYSTEM SET log_statement = 'all';"
docker exec litellm-pr29984-mig psql -U litellm -d litellm -c "SELECT pg_reload_conf();"

Two configs, identical except for the flag:

# /tmp/litellm_pr29984_off.yaml
general_settings:
  master_key: sk-1234
  database_url: postgresql://litellm:litellm@localhost:5434/litellm
  database_disable_prepared_statements: false

# /tmp/litellm_pr29984_on.yaml  (only this line differs)
  database_disable_prepared_statements: true

Proxy launched on port 4020 via the CLI so the DATABASE_URL rewrite in proxy_cli.py runs:

DISABLE_SCHEMA_UPDATE=true python litellm/proxy/proxy_cli.py \
  --config /tmp/litellm_pr29984_off.yaml --port 4020 --num_workers 1 --detailed_debug

DB-backed traffic is a virtual key plus repeated authenticated reads. Key auth issues a SELECT against LiteLLM_VerificationToken on every call, which is the query Prisma keeps as a server-side prepared statement:

GEN=$(curl -s http://localhost:4020/key/generate -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" -d '{"key_alias":"pr29984"}')
NEWKEY=$(echo "$GEN" | python3 -c "import sys,json;print(json.load(sys.stdin)['key'])")
for i in $(seq 1 N); do curl -s "http://localhost:4020/key/info?key=$NEWKEY" -H "Authorization: Bearer $NEWKEY"; done

What the flag actually changes. The flag is not "prepared statements on vs off entirely". With it off, Prisma keeps one persistent named prepared statement per query and reuses it across requests on a pooled connection. With it on (pgbouncer=true), Prisma issues a fresh, uniquely named prepared statement per query and does not reuse a cached plan. The reused plan is the thing a migration invalidates, so removing the reuse removes the failure mode.

Statement names seen in the Postgres log for the same LiteLLM_VerificationToken SELECT, counted by name. Flag OFF (one plan reused):

1066 execute s25
   1 execute s30
   1 execute s28
   1 execute s27

Flag ON (every execution is a distinct, single-use statement):

   1 execute s68
   1 execute s67
   1 execute s66
   1 execute s65
   1 execute s64
   1 execute s63
   1 execute s62

A 60-request burst added 60 reused executions of s25 with the flag off, and 60 distinct one-shot statements (s62, s63, ...) with the flag on.

The migration failure (flag OFF). The error fires when the result type of a column inside a cached plan changes under DDL. LiteLLM_VerificationTokenView references the base-table columns, so it was dropped first to allow the column type change (the view is unrelated to Prisma's cached statement, which reads the base table directly):

docker exec litellm-pr29984-mig psql -U litellm -d litellm -c 'DROP VIEW IF EXISTS "LiteLLM_VerificationTokenView";'
# warm the reused cached plan
for i in $(seq 1 120); do curl -s "http://localhost:4020/key/info?key=$NEWKEY" -H "Authorization: Bearer $NEWKEY" -o /dev/null; done
# the migration: a column inside the cached SELECT changes result type
docker exec litellm-pr29984-mig psql -U litellm -d litellm -c 'ALTER TABLE "LiteLLM_VerificationToken" ALTER COLUMN rotation_count TYPE BIGINT;'
# subsequent traffic on the same pooled connections
for i in $(seq 1 200); do curl -s -o /dev/null -w "%{http_code}\n" "http://localhost:4020/key/info?key=$NEWKEY" -H "Authorization: Bearer $NEWKEY"; done

Result with the flag off:

post-migration hammer: ok=0 fail=200        # every request returns HTTP 500
NEW cached-plan errors in POSTGRES log: 200
proxy log: ConnectorError(... QueryError(PostgresError { code: "0A000",
           message: "cached plan must not change result type", severity: "ERROR" ...

Every request after the migration fails until the stale plans are gone (connection recycling). This is the production symptom during a rolling deploy: old pods hold cached plans, a migration lands, and their pooled connections start returning errors.

Same migration, flag ON. Identical sequence (drop view, warm traffic, ALTER COLUMN rotation_count TYPE BIGINT, 200 follow-up requests), against the proxy started with database_disable_prepared_statements: true:

post-migration hammer (flag ON): ok=200 fail=0
NEW cached-plan errors in POSTGRES log: 0
NEW cached-plan errors in PROXY log: 0

No request fails, and Postgres logs no error. Because each query re-prepares against the current schema, there is no stale cached plan to break.

A note on migration shapes: a plain ALTER TABLE ADD COLUMN of an unrelated column did not trigger the error here, because Prisma selects an explicit column list rather than SELECT *, so adding a trailing column does not change the result type of those cached plans. The error needs the result type of a selected column to change (for example INT to BIGINT), or it bites raw SELECT * style queries and views. The flag protects the general case by never reusing a cached plan, so any of these migration shapes becomes safe.

Cleanup:

docker rm -f litellm-pr29984-mig

Type

🆕 New Feature

Changes

Adds database_disable_prepared_statements to general_settings. When true it appends Prisma's pgbouncer=true param to the proxy's DATABASE_URL / DIRECT_URL, which puts Prisma in pgbouncer transaction-pool compatible mode and stops the query engine from using server-side prepared statements. That also sidesteps the cached plan must not change result type error during rolling schema migrations.

The flag is threaded through _build_db_connection_url_params alongside the existing connection_limit / pool_timeout / connect_timeout / socket_timeout knobs, so it follows the same path every other DB connection setting already uses. An explicit pgbouncer value in database_extra_connection_params still wins, preserving the existing override precedence. String values for the flag (e.g. from os.environ/ substitution) are coerced through str_to_bool, so "false" resolves to disabled rather than silently enabling; non-boolean strings also resolve to disabled, covered by a regression test.

Tests cover the param builder in isolation (flag on sets pgbouncer=true, flag off leaves it out, operator pgbouncer=false override wins) and a parametrized end-to-end assertion that database_disable_prepared_statements reaches the URL params during proxy startup for boolean, string, and non-boolean string config values.

@yassin-berriai

Copy link
Copy Markdown
Contributor Author

@greptileai

@CLAassistant

Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

@greptile-apps

greptile-apps Bot commented Jun 8, 2026 •

Copy link
Copy Markdown
Contributor

Greptile Summary

This PR adds a database_disable_prepared_statements opt-in flag to general_settings that appends Prisma's pgbouncer=true query parameter to DATABASE_URL / DIRECT_URL at startup, causing Prisma to issue fresh single-use prepared statements rather than reusing cached plans — eliminating the cached plan must not change result type error that pooled connections encounter during rolling schema migrations.

  • The flag is threaded through _build_db_connection_url_params alongside existing connection-pool knobs; extra_params still wins, preserving operator override precedence.
  • String values (e.g. from os.environ/ substitution) are coerced through str_to_bool, so "false" and unrecognised strings correctly resolve to disabled.
  • New tests cover the param builder in isolation (flag on/off, extra_params override) and a parametrized end-to-end startup test for bool, "true", "false", and "not-a-bool" config values; no real network calls are made.

Confidence Score: 5/5

The change is purely additive and opt-in; existing deployments that do not set the flag are completely unaffected.

The implementation follows existing patterns exactly (same coercion logic as should_update_prisma_schema, same extra_params override precedence), both DATABASE_URL and DIRECT_URL are updated correctly, the default is False so no existing deployment is touched, and the test suite covers the full matrix of config value types including the previously-flagged 'false' string edge case.

No files require special attention.

Important Files Changed

Filename Overview
litellm/proxy/_types.py Adds database_disable_prepared_statements: Optional[bool] field to ConfigGeneralSettings with clear documentation; no logic changes, purely additive.
litellm/proxy/proxy_cli.py Threads disable_prepared_statements through _build_db_connection_url_params and run_server; string coercion via str_to_bool is correct and matches existing patterns; both DATABASE_URL and DIRECT_URL are updated; extra_params override precedence is preserved.
tests/test_litellm/proxy/test_proxy_cli.py Adds unit tests for the param builder in isolation and a parametrized end-to-end startup test covering bool/string/not-a-bool config values; all tests use mocks and make no real network calls.
ui/litellm-dashboard/src/lib/http/schema.d.ts Generated TypeScript schema updated to include database_disable_prepared_statements?: boolean

Reviews (6): Last reviewed commit: "test(proxy): add regression case for non..." | Re-trigger Greptile

@greptile-apps

greptile-apps Bot commented Jun 8, 2026

Copy link
Copy Markdown
Contributor

Greptile Summary

Adds a database_disable_prepared_statements config flag to general_settings. When set to true, it appends pgbouncer=true to the Prisma DATABASE_URL / DIRECT_URL query params, preventing server-side prepared statements — useful for pgbouncer transaction-pool deployments and for avoiding the cached plan must not change result type error during rolling migrations.

  • The new parameter follows the exact same threading path as the existing database_connect_timeout, database_socket_timeout, and database_extra_connection_params knobs through _build_db_connection_url_params → append_query_params.
  • An explicit pgbouncer key in database_extra_connection_params still overrides the flag, preserving existing precedence.
  • Four new tests cover the flag-on, flag-off, explicit-override, and end-to-end forwarding cases; all are fully mocked.

Confidence Score: 4/5

Safe to merge; the change is additive and off-by-default, touching only the DB connection URL assembly path that runs at startup.

The implementation is minimal and follows established patterns. The one notable gap is the raw bool() cast on the config value, which would silently activate the flag if the value is the string "false" — an unlikely but possible edge case when env-var substitution or non-standard YAML encoding is involved.

The bool() coercion in proxy_cli.py around the new database_disable_prepared_statements read is worth a quick look.

Important Files Changed

Filename Overview
litellm/proxy/_types.py Adds database_disable_prepared_statements: Optional[bool] to ConfigGeneralSettings, matching the existing pattern for other DB connection knobs.
litellm/proxy/proxy_cli.py Adds disable_prepared_statements to _build_db_connection_url_params and wires it through run_server; uses bool() to coerce the raw config dict value, which silently enables the flag for string "false".
tests/test_litellm/proxy/test_proxy_cli.py Adds four new unit/integration tests covering the flag-on, flag-off, extra-params-override, and end-to-end forwarding cases; all tests are properly mocked with no real network calls.

Reviews (2): Last reviewed commit: "feat(proxy): add option to disable serve..." | Re-trigger Greptile

Comment thread litellm/proxy/proxy_cli.py Resolved
@codecov

codecov Bot commented Jun 8, 2026 •

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

ðŸ“Ē Thoughts on this report? Let us know!

@yassin-berriai

Copy link
Copy Markdown
Contributor Author

@greptileai I've addressed the prepared-statements string coercion. Could you re-review?

@yassin-berriai

Copy link
Copy Markdown
Contributor Author

@greptileai

1 similar comment
@yassin-berriai

Copy link
Copy Markdown
Contributor Author

@greptileai

@yassin-berriai

Copy link
Copy Markdown
Contributor Author

@greptileai review

@yassin-berriai
yassin-berriai force-pushed the litellm_fix/disable-prepared-statements-option branch from 8b9b0df to 539fe9d Compare June 10, 2026 22:53
@yassin-berriai
yassin-berriai merged commit dff25fe into litellm_internal_staging Jun 10, 2026
119 checks passed
@yassin-berriai
yassin-berriai deleted the litellm_fix/disable-prepared-statements-option branch June 10, 2026 23:06
mateo-berri added a commit that referenced this pull request Jun 13, 2026
yuneng-berri added a commit that referenced this pull request Jun 14, 2026
mrgizmo212 pushed a commit to ttgaillc/ttginf that referenced this pull request Jun 16, 2026
michaelxer pushed a commit to michaelxer/litellm that referenced this pull request Jun 17, 2026
michaelxer pushed a commit to michaelxer/litellm that referenced this pull request Jun 17, 2026
koladefaj pushed a commit to koladefaj/litellm that referenced this pull request Jun 17, 2026
factnn pushed a commit to factnn/litellm that referenced this pull request Jun 18, 2026
marioleonardo pushed a commit to marioleonardo/litellm-mongodb-patched that referenced this pull request Jun 19, 2026
fzowl pushed a commit to fzowl/litellm that referenced this pull request Jun 24, 2026
@ghost ghost mentioned this pull request Jun 25, 2026
9 of 13 tasks
blake-hamm added a commit to blake-hamm/bhamm-lab that referenced this pull request Jun 28, 2026
â€Ķto v1.90.0 (#232)

This PR contains the following updates:

| Package | Update | Change |
|---|---|---|
| [https://github.com/BerriAI/litellm.git](https://github.com/BerriAI/litellm) | minor | `v1.89.4` → `v1.90.0` |

---

### Release Notes

<details>
<summary>BerriAI/litellm (https://github.com/BerriAI/litellm.git)</summary>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](BerriAI/litellm@v1.89.4...v1.90.0-rc.1)

#### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](BerriAI/litellm@0112e53).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

#### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](BerriAI/litellm#29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](BerriAI/litellm#29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](BerriAI/litellm#29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](BerriAI/litellm#29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](BerriAI/litellm#29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](BerriAI/litellm#27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](BerriAI/litellm#29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](BerriAI/litellm#29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](BerriAI/litellm#29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](BerriAI/litellm#29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](BerriAI/litellm#29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](BerriAI/litellm#29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](BerriAI/litellm#29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](BerriAI/litellm#29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](BerriAI/litellm#29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](BerriAI/litellm#29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](BerriAI/litellm#29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](BerriAI/litellm#29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](BerriAI/litellm#29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](BerriAI/litellm#29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](BerriAI/litellm#29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](BerriAI/litellm#28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](BerriAI/litellm#29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](BerriAI/litellm#29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](BerriAI/litellm#29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](BerriAI/litellm#28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](BerriAI/litellm#29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](BerriAI/litellm#29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](BerriAI/litellm#28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](BerriAI/litellm#29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](BerriAI/litellm#29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](BerriAI/litellm#29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](BerriAI/litellm#29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](BerriAI/litellm#30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](BerriAI/litellm#29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](BerriAI/litellm#24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](BerriAI/litellm#30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](BerriAI/litellm#30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](BerriAI/litellm#30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](BerriAI/litellm#30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](BerriAI/litellm#29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](BerriAI/litellm#30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](BerriAI/litellm#30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](BerriAI/litellm#30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](BerriAI/litellm#30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](BerriAI/litellm#30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](BerriAI/litellm#30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](BerriAI/litellm#28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](BerriAI/litellm#30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](BerriAI/litellm#30044)
- \[internal copy of [#&#8203;28007](BerriAI/litellm#28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](BerriAI/litellm#28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](BerriAI/litellm#29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](BerriAI/litellm#30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](BerriAI/litellm#30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](BerriAI/litellm#29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](BerriAI/litellm#29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](BerriAI/litellm#30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](BerriAI/litellm#30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](BerriAI/litellm#29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](BerriAI/litellm#30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](BerriAI/litellm#30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](BerriAI/litellm#30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](BerriAI/litellm#26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](BerriAI/litellm#27346)
- \[internal copy of [#&#8203;30137](BerriAI/litellm#30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](BerriAI/litellm#30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](BerriAI/litellm#30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](BerriAI/litellm#30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](BerriAI/litellm#30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](BerriAI/litellm#29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](BerriAI/litellm#30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](BerriAI/litellm#30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](BerriAI/litellm#30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](BerriAI/litellm#30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](BerriAI/litellm#30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](BerriAI/litellm#30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](BerriAI/litellm#28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](BerriAI/litellm#29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](BerriAI/litellm#30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](BerriAI/litellm#30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](BerriAI/litellm#30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](BerriAI/litellm#30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](BerriAI/litellm#30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](BerriAI/litellm#30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](BerriAI/litellm#30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](BerriAI/litellm#30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](BerriAI/litellm#30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](BerriAI/litellm#30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](BerriAI/litellm#30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](BerriAI/litellm#30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](BerriAI/litellm#30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](BerriAI/litellm#30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](BerriAI/litellm#30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](BerriAI/litellm#30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](BerriAI/litellm#30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](BerriAI/litellm#30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](BerriAI/litellm#30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](BerriAI/litellm#30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](BerriAI/litellm#30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](BerriAI/litellm#30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](BerriAI/litellm#30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](BerriAI/litellm#30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](BerriAI/litellm#30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](BerriAI/litellm#28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](BerriAI/litellm#30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](BerriAI/litellm#30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](BerriAI/litellm#30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](BerriAI/litellm#30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](BerriAI/litellm#30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](BerriAI/litellm#30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](BerriAI/litellm#30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](BerriAI/litellm#30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](BerriAI/litellm#30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](BerriAI/litellm#30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](BerriAI/litellm#30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](BerriAI/litellm#30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](BerriAI/litellm#30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](BerriAI/litellm#30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](BerriAI/litellm#30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](BerriAI/litellm#30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](BerriAI/litellm#30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](BerriAI/litellm#30543)
- fix(guardrails): stop re-initializing DB guardrails on every poll by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30542](BerriAI/litellm#30542)
- chore(oss): litellm oss staging 150626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30463](BerriAI/litellm#30463)
- ci(lint): add blanket-noqa, dataclass-default, and unused-noqa Ruff rules by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30516](BerriAI/litellm#30516)
- ci: ratchet lint and type-check gates (ruff preview, ANN, mypy, basedpyright) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30379](BerriAI/litellm#30379)
- fix(proxy): allow internal roles to access vector store CRUD routes by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30503](BerriAI/litellm#30503)
- fix(otel): stamp gen\_ai.input/output.messages on v2 spans by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30548](BerriAI/litellm#30548)
- fix(otel): export v2 gen\_ai client metrics to the configured meter provider by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30549](BerriAI/litellm#30549)
- fix(bedrock): preserve cache\_control for ARN models in /v1/messages adapter by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29823](BerriAI/litellm#29823)
- fix: greatly increase basedpyright slack by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30563](BerriAI/litellm#30563)
- fix(budget): recompute budget\_reset\_at when budget\_duration changes on /budget/update by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30555](BerriAI/litellm#30555)
- fix(otel): accept UPPER\_SNAKE\_CASE OTEL\_INSTRUMENTATION\_GENAI\_CAPTURE\_MESSAGE\_CONTENT in v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30562](BerriAI/litellm#30562)
- chore(lint): remove PLR0915 too-many-statements ruff rule by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30574](BerriAI/litellm#30574)
- ci(lint): ratcheted type-discipline gate (mutable collections, casts, guards, kwargs, suppressions) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30500](BerriAI/litellm#30500)
- feat(proxy): add verification\_uri\_complete to CLI SSO device flow by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30571](BerriAI/litellm#30571)
- chore: litellm oss staging160626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30527](BerriAI/litellm#30527)
- fix(guardrails): return 400 not 500 when AIM blocks a request by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30573](BerriAI/litellm#30573)
- ci(lint): grandfather any-discipline with a per-file ratchet budget (50% headroom) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30582](BerriAI/litellm#30582)
- fix(audio): don't override explicit response\_format with verbose\_json by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30599](BerriAI/litellm#30599)
- fix(anthropic): price and surface response service\_tier in cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30558](BerriAI/litellm#30558)
- feat: add dev and wildcard proxy configs for local testing by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30556](BerriAI/litellm#30556)
- fix(proxy): list public team model name in /v1/models by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;30588](BerriAI/litellm#30588)
- ci: drop mypy entirely, standardize type checking on basedpyright by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30648](BerriAI/litellm#30648)
- feat(guardrails): surface OpenAI moderation violation\_categories on guardrail traces by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30659](BerriAI/litellm#30659)
- fix(proxy): resolve list files credentials from team BYOK deployments by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30495](BerriAI/litellm#30495)
- feat(proxy): add --max\_requests\_before\_restart\_jitter to stagger worker restarts by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30601](BerriAI/litellm#30601)
- fix(health): correct bedrock embedding health checks by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30583](BerriAI/litellm#30583)
- test: harden remaining pass-through CI flakes (image-gen spend poll, ruby assistants timeout) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30685](BerriAI/litellm#30685)
- test(pass\_through): harden vertex spendlog poll against transient empty reads by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30683](BerriAI/litellm#30683)
- fix(cost): stop non-string service\_tier from silently dropping cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30690](BerriAI/litellm#30690)
- feat(proxy): warn at startup when custom\_auth skips common\_checks enforcement by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30665](BerriAI/litellm#30665)
- fix(pod\_lock): release cron lock by matching async\_set\_cache JSON encoding by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30600](BerriAI/litellm#30600)
- ci: run a local fake OpenAI endpoint instead of the shared Railway mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30695](BerriAI/litellm#30695)
- ci(windows): pin uv to Python 3.11 so it ignores the preinstalled 3.14 by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30704](BerriAI/litellm#30704)
- feat(ui): migrate models page to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30677](BerriAI/litellm#30677)
- refactor(ui): remove orphaned pass-through-settings route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30692](BerriAI/litellm#30692)
- fix(cost): stop non-string response service\_tier from dropping cost tracking by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30706](BerriAI/litellm#30706)
- feat(agent-shin): automated PR/issue triage, low-quality auto-close, and review-gate label lifecycle by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30433](BerriAI/litellm#30433)
- chore: litellm oss 170626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30637](BerriAI/litellm#30637)
- fix(bedrock\_mantle): add SigV4 fallback to chat completions auth by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30714](BerriAI/litellm#30714)
- feat(search): add TinyFish as search provider by [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) in [#&#8203;30634](BerriAI/litellm#30634)
- feat(ui): migrate old usage report to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30694](BerriAI/litellm#30694)
- fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is stale by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30684](BerriAI/litellm#30684)
- chore(ci): remove Agent Shin pull\_request\_target workflows by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30784](BerriAI/litellm#30784)
- chore: litellm oss staging by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30745](BerriAI/litellm#30745)
- ci(zizmor): also run on litellm\_internal\_staging by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30789](BerriAI/litellm#30789)
- fix(test): drop references to removed Agent Shin workflows by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30791](https://github.com/BerriAI/litellm/pull/30791)
- chore: remove in-product survey and Claude Code feedback nudges by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30773](https://github.com/BerriAI/litellm/pull/30773)
- feat(ui): migrate api-keys landing to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30699](https://github.com/BerriAI/litellm/pull/30699)
- feat(proxy): configurable response headers and login-page hint by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30792](https://github.com/BerriAI/litellm/pull/30792)
- ci(zizmor): gate PRs on medium+ findings and clear existing ones by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30797](https://github.com/BerriAI/litellm/pull/30797)
- fix(proxy): use e.request\_data for logging\_obj in ModifyResponseException streaming passthrough by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30800](https://github.com/BerriAI/litellm/pull/30800)
- chore: make pr template linear portion clearer by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30766](https://github.com/BerriAI/litellm/pull/30766)
- chore(typing): add boto3/botocore stubs so basedpyright resolves the AWS SDK by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30815](https://github.com/BerriAI/litellm/pull/30815)
- fix(otel): one v2 logger owns the global provider; scope tenant OTLP creds per exporter by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30590](https://github.com/BerriAI/litellm/pull/30590)
- fix(passthrough): recover output tokens for interrupted anthropic streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30787](https://github.com/BerriAI/litellm/pull/30787)
- fix(proxy): record partial spend on the failure row for interrupted streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30788](https://github.com/BerriAI/litellm/pull/30788)
- fix(ui): repoint dead usage guide link to cost tracking docs by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30859](https://github.com/BerriAI/litellm/pull/30859)
- fix(ui): warn that team models are deleted in the delete-team modal by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29990](https://github.com/BerriAI/litellm/pull/29990)
- feat(caching): add valkey-semantic cache backend and fix semantic cache scope keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30675](https://github.com/BerriAI/litellm/pull/30675)
- test(ui): isolate OldTeams delete-warning tests from leaked mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30871](https://github.com/BerriAI/litellm/pull/30871)
- feat: add lint-gate target and truncation-proof summary to the strict ruff gate by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30877](https://github.com/BerriAI/litellm/pull/30877)
- chore(ui): rebuild ui for release by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30894](https://github.com/BerriAI/litellm/pull/30894)
- chore(ci): bump deps by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30899](https://github.com/BerriAI/litellm/pull/30899)
- fix(watsonx): wrap string embedding input in array for WatsonX API by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30897](https://github.com/BerriAI/litellm/pull/30897)
- test: point router/completion/triton tests at the local fake OpenAI endpoint by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30900](https://github.com/BerriAI/litellm/pull/30900)
- feat(sandbox): e2b code execution primitive by [@&#8203;krrish-berri-2](https://github.com/krrish-berri-2) in [#&#8203;30898](https://github.com/BerriAI/litellm/pull/30898)
- fix(ui): source api-keys identity from useAuthorized to stop "User ID is not set" by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30903](https://github.com/BerriAI/litellm/pull/30903)
- chore(ui): rebuild ui by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30906](https://github.com/BerriAI/litellm/pull/30906)
- chore(ci): promote internal staging to main by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30907](https://github.com/BerriAI/litellm/pull/30907)
- fix(redis): prevent forcing SSLConnection when ssl=False in connection pool by [@&#8203;Jacopos311](https://github.com/Jacopos311) in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- fix(proxy): log UI setup failures instead of silently swallowing by [@&#8203;sarvesh1327](https://github.com/sarvesh1327) in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

#### New Contributors

- [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) made their first contribution in [#&#8203;30634](BerriAI/litellm#30634)
- [@&#8203;Jacopos311](https://github.com/Jacopos311) made their first contribution in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- [@&#8203;sarvesh1327](https://github.com/sarvesh1327) made their first contribution in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

**Full Changelog**: <BerriAI/litellm@v1.89.0...v1.90.0>

</details>

---

### Configuration

📅 **Schedule**: (UTC)

- Branch creation
  - At any time (no schedule defined)
- Automerge
  - At any time (no schedule defined)

ðŸšĶ **Automerge**: Disabled by config. Please merge this manually once you are satisfied.

â™ŧ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update again.

---

 - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box

---

This PR has been generated by [Mend Renovate](https://github.com/renovatebot/renovate).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4yMjAuMCIsInVwZGF0ZWRJblZlciI6IjQzLjIyMC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6WyJkZXBlbmRlbmNpZXMiXX0=-->

Co-authored-by: Renovate Bot <renovate@bhamm-lab.com>
Reviewed-on: https://codeberg.org/blake-hamm/bhamm-lab/pulls/232
blake-hamm added a commit to blake-hamm/bhamm-lab that referenced this pull request Jun 28, 2026
This PR contains the following updates:

| Package | Type | Update | Change |
|---|---|---|---|
| [ghcr.io/berriai/litellm](https://images.chainguard.dev/directory/image/wolfi-base/overview) ([source](https://github.com/BerriAI/litellm)) | final | minor | `v1.85.1` → `v1.90.0` |

---

### Release Notes

<details>
<summary>BerriAI/litellm (ghcr.io/berriai/litellm)</summary>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](https://github.com/BerriAI/litellm/compare/v1.90.0...v1.90.0)

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

##### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](https://github.com/BerriAI/litellm/pull/29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](https://github.com/BerriAI/litellm/pull/29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](https://github.com/BerriAI/litellm/pull/29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](https://github.com/BerriAI/litellm/pull/29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](https://github.com/BerriAI/litellm/pull/29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](https://github.com/BerriAI/litellm/pull/27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](https://github.com/BerriAI/litellm/pull/29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](https://github.com/BerriAI/litellm/pull/29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](https://github.com/BerriAI/litellm/pull/29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](https://github.com/BerriAI/litellm/pull/29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](https://github.com/BerriAI/litellm/pull/29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](https://github.com/BerriAI/litellm/pull/29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](https://github.com/BerriAI/litellm/pull/29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](https://github.com/BerriAI/litellm/pull/29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](https://github.com/BerriAI/litellm/pull/29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](https://github.com/BerriAI/litellm/pull/29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](https://github.com/BerriAI/litellm/pull/29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](https://github.com/BerriAI/litellm/pull/29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](https://github.com/BerriAI/litellm/pull/29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](https://github.com/BerriAI/litellm/pull/29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](https://github.com/BerriAI/litellm/pull/29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](https://github.com/BerriAI/litellm/pull/28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](https://github.com/BerriAI/litellm/pull/29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](https://github.com/BerriAI/litellm/pull/29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](https://github.com/BerriAI/litellm/pull/29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](https://github.com/BerriAI/litellm/pull/28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](https://github.com/BerriAI/litellm/pull/29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](https://github.com/BerriAI/litellm/pull/29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](https://github.com/BerriAI/litellm/pull/28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](https://github.com/BerriAI/litellm/pull/29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](https://github.com/BerriAI/litellm/pull/29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](https://github.com/BerriAI/litellm/pull/29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](https://github.com/BerriAI/litellm/pull/29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](https://github.com/BerriAI/litellm/pull/30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](https://github.com/BerriAI/litellm/pull/29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](https://github.com/BerriAI/litellm/pull/24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](https://github.com/BerriAI/litellm/pull/30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](https://github.com/BerriAI/litellm/pull/30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](https://github.com/BerriAI/litellm/pull/30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](https://github.com/BerriAI/litellm/pull/30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](https://github.com/BerriAI/litellm/pull/29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](https://github.com/BerriAI/litellm/pull/30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](https://github.com/BerriAI/litellm/pull/30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](https://github.com/BerriAI/litellm/pull/30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](https://github.com/BerriAI/litellm/pull/30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](https://github.com/BerriAI/litellm/pull/30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](https://github.com/BerriAI/litellm/pull/30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](https://github.com/BerriAI/litellm/pull/28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](https://github.com/BerriAI/litellm/pull/30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](https://github.com/BerriAI/litellm/pull/30044)
- \[internal copy of [#&#8203;28007](https://github.com/BerriAI/litellm/issues/28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](https://github.com/BerriAI/litellm/pull/28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](https://github.com/BerriAI/litellm/pull/29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](https://github.com/BerriAI/litellm/pull/30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](https://github.com/BerriAI/litellm/pull/30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](https://github.com/BerriAI/litellm/pull/29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](https://github.com/BerriAI/litellm/pull/29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](https://github.com/BerriAI/litellm/pull/30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](https://github.com/BerriAI/litellm/pull/30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](https://github.com/BerriAI/litellm/pull/29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](https://github.com/BerriAI/litellm/pull/30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](https://github.com/BerriAI/litellm/pull/30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](https://github.com/BerriAI/litellm/pull/30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](https://github.com/BerriAI/litellm/issues/26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](https://github.com/BerriAI/litellm/pull/27346)
- \[internal copy of [#&#8203;30137](https://github.com/BerriAI/litellm/issues/30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](https://github.com/BerriAI/litellm/pull/30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](https://github.com/BerriAI/litellm/pull/30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](https://github.com/BerriAI/litellm/pull/30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](https://github.com/BerriAI/litellm/pull/30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](https://github.com/BerriAI/litellm/pull/29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](https://github.com/BerriAI/litellm/pull/30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](https://github.com/BerriAI/litellm/pull/30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](https://github.com/BerriAI/litellm/pull/30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](https://github.com/BerriAI/litellm/pull/30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](https://github.com/BerriAI/litellm/pull/30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](https://github.com/BerriAI/litellm/pull/30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](https://github.com/BerriAI/litellm/pull/28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](https://github.com/BerriAI/litellm/pull/29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](https://github.com/BerriAI/litellm/pull/30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](https://github.com/BerriAI/litellm/pull/30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](https://github.com/BerriAI/litellm/pull/30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](https://github.com/BerriAI/litellm/pull/30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](https://github.com/BerriAI/litellm/pull/30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](https://github.com/BerriAI/litellm/pull/30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](https://github.com/BerriAI/litellm/pull/30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](https://github.com/BerriAI/litellm/pull/30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](https://github.com/BerriAI/litellm/pull/30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](https://github.com/BerriAI/litellm/pull/30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](https://github.com/BerriAI/litellm/pull/30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](https://github.com/BerriAI/litellm/pull/30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](https://github.com/BerriAI/litellm/pull/30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](https://github.com/BerriAI/litellm/pull/30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](https://github.com/BerriAI/litellm/pull/30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](https://github.com/BerriAI/litellm/pull/30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](https://github.com/BerriAI/litellm/pull/30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](https://github.com/BerriAI/litellm/pull/30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](https://github.com/BerriAI/litellm/pull/30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](https://github.com/BerriAI/litellm/pull/30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](https://github.com/BerriAI/litellm/pull/30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](https://github.com/BerriAI/litellm/pull/30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](https://github.com/BerriAI/litellm/pull/30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](https://github.com/BerriAI/litellm/pull/30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](https://github.com/BerriAI/litellm/pull/30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](https://github.com/BerriAI/litellm/issues/28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](https://github.com/BerriAI/litellm/pull/30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](https://github.com/BerriAI/litellm/pull/30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](https://github.com/BerriAI/litellm/pull/30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](https://github.com/BerriAI/litellm/pull/30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](https://github.com/BerriAI/litellm/pull/30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](https://github.com/BerriAI/litellm/pull/30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](https://github.com/BerriAI/litellm/pull/30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](https://github.com/BerriAI/litellm/pull/30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](https://github.com/BerriAI/litellm/pull/30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](https://github.com/BerriAI/litellm/pull/30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](https://github.com/BerriAI/litellm/pull/30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](https://github.com/BerriAI/litellm/pull/30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](https://github.com/BerriAI/litellm/pull/30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](https://github.com/BerriAI/litellm/pull/30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](https://github.com/BerriAI/litellm/pull/30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](https://github.com/BerriAI/litellm/pull/30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](https://github.com/BerriAI/litellm/pull/30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](https://github.com/BerriAI/litellm/pull/30543)
- fix(guardrails): stop re-initializing DB guardrails on every poll by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30542](https://github.com/BerriAI/litellm/pull/30542)
- chore(oss): litellm oss staging 150626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30463](https://github.com/BerriAI/litellm/pull/30463)
- ci(lint): add blanket-noqa, dataclass-default, and unused-noqa Ruff rules by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30516](https://github.com/BerriAI/litellm/pull/30516)
- ci: ratchet lint and type-check gates (ruff preview, ANN, mypy, basedpyright) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30379](https://github.com/BerriAI/litellm/pull/30379)
- fix(proxy): allow internal roles to access vector store CRUD routes by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30503](https://github.com/BerriAI/litellm/pull/30503)
- fix(otel): stamp gen\_ai.input/output.messages on v2 spans by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30548](https://github.com/BerriAI/litellm/pull/30548)
- fix(otel): export v2 gen\_ai client metrics to the configured meter provider by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30549](https://github.com/BerriAI/litellm/pull/30549)
- fix(bedrock): preserve cache\_control for ARN models in /v1/messages adapter by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29823](https://github.com/BerriAI/litellm/pull/29823)
- fix: greatly increase basedpyright slack by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30563](https://github.com/BerriAI/litellm/pull/30563)
- fix(budget): recompute budget\_reset\_at when budget\_duration changes on /budget/update by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30555](https://github.com/BerriAI/litellm/pull/30555)
- fix(otel): accept UPPER\_SNAKE\_CASE OTEL\_INSTRUMENTATION\_GENAI\_CAPTURE\_MESSAGE\_CONTENT in v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30562](https://github.com/BerriAI/litellm/pull/30562)
- chore(lint): remove PLR0915 too-many-statements ruff rule by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30574](https://github.com/BerriAI/litellm/pull/30574)
- ci(lint): ratcheted type-discipline gate (mutable collections, casts, guards, kwargs, suppressions) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30500](https://github.com/BerriAI/litellm/pull/30500)
- feat(proxy): add verification\_uri\_complete to CLI SSO device flow by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30571](https://github.com/BerriAI/litellm/pull/30571)
- chore: litellm oss staging160626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30527](https://github.com/BerriAI/litellm/pull/30527)
- fix(guardrails): return 400 not 500 when AIM blocks a request by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30573](https://github.com/BerriAI/litellm/pull/30573)
- ci(lint): grandfather any-discipline with a per-file ratchet budget (50% headroom) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30582](https://github.com/BerriAI/litellm/pull/30582)
- fix(audio): don't override explicit response\_format with verbose\_json by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30599](https://github.com/BerriAI/litellm/pull/30599)
- fix(anthropic): price and surface response service\_tier in cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30558](https://github.com/BerriAI/litellm/pull/30558)
- feat: add dev and wildcard proxy configs for local testing by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30556](https://github.com/BerriAI/litellm/pull/30556)
- fix(proxy): list public team model name in /v1/models by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;30588](https://github.com/BerriAI/litellm/pull/30588)
- ci: drop mypy entirely, standardize type checking on basedpyright by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30648](https://github.com/BerriAI/litellm/pull/30648)
- feat(guardrails): surface OpenAI moderation violation\_categories on guardrail traces by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30659](https://github.com/BerriAI/litellm/pull/30659)
- fix(proxy): resolve list files credentials from team BYOK deployments by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30495](https://github.com/BerriAI/litellm/pull/30495)
- feat(proxy): add --max\_requests\_before\_restart\_jitter to stagger worker restarts by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30601](https://github.com/BerriAI/litellm/pull/30601)
- fix(health): correct bedrock embedding health checks by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30583](https://github.com/BerriAI/litellm/pull/30583)
- test: harden remaining pass-through CI flakes (image-gen spend poll, ruby assistants timeout) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30685](https://github.com/BerriAI/litellm/pull/30685)
- test(pass\_through): harden vertex spendlog poll against transient empty reads by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30683](https://github.com/BerriAI/litellm/pull/30683)
- fix(cost): stop non-string service\_tier from silently dropping cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30690](https://github.com/BerriAI/litellm/pull/30690)
- feat(proxy): warn at startup when custom\_auth skips common\_checks enforcement by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30665](https://github.com/BerriAI/litellm/pull/30665)
- fix(pod\_lock): release cron lock by matching async\_set\_cache JSON encoding by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30600](https://github.com/BerriAI/litellm/pull/30600)
- ci: run a local fake OpenAI endpoint instead of the shared Railway mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30695](https://github.com/BerriAI/litellm/pull/30695)
- ci(windows): pin uv to Python 3.11 so it ignores the preinstalled 3.14 by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30704](https://github.com/BerriAI/litellm/pull/30704)
- feat(ui): migrate models page to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30677](https://github.com/BerriAI/litellm/pull/30677)
- refactor(ui): remove orphaned pass-through-settings route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30692](https://github.com/BerriAI/litellm/pull/30692)
- fix(cost): stop non-string response service\_tier from dropping cost tracking by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30706](https://github.com/BerriAI/litellm/pull/30706)
- feat(agent-shin): automated PR/issue triage, low-quality auto-close, and review-gate label lifecycle by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30433](https://github.com/BerriAI/litellm/pull/30433)
- chore: litellm oss 170626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30637](https://github.com/BerriAI/litellm/pull/30637)
- fix(bedrock\_mantle): add SigV4 fallback to chat completions auth by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30714](https://github.com/BerriAI/litellm/pull/30714)
- feat(search): add TinyFish as search provider by [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) in [#&#8203;30634](https://github.com/BerriAI/litellm/pull/30634)
- feat(ui): migrate old usage report to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30694](https://github.com/BerriAI/litellm/pull/30694)
- fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is stale by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30684](https://github.com/BerriAI/litellm/pull/30684)
- chore(ci): remove Agent Shin pull\_request\_target workflows by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30784](https://github.com/BerriAI/litellm/pull/30784)
- chore: litellm oss staging by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30745](https://github.com/BerriAI/litellm/pull/30745)
- ci(zizmor): also run on litellm\_internal\_staging by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30789](https://github.com/BerriAI/litellm/pull/30789)
- fix(test): drop references to removed Agent Shin workflows by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30791](https://github.com/BerriAI/litellm/pull/30791)
- chore: remove in-product survey and Claude Code feedback nudges by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30773](https://github.com/BerriAI/litellm/pull/30773)
- feat(ui): migrate api-keys landing to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30699](https://github.com/BerriAI/litellm/pull/30699)
- feat(proxy): configurable response headers and login-page hint by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30792](https://github.com/BerriAI/litellm/pull/30792)
- ci(zizmor): gate PRs on medium+ findings and clear existing ones by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30797](https://github.com/BerriAI/litellm/pull/30797)
- fix(proxy): use e.request\_data for logging\_obj in ModifyResponseException streaming passthrough by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30800](https://github.com/BerriAI/litellm/pull/30800)
- chore: make pr template linear portion clearer by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30766](https://github.com/BerriAI/litellm/pull/30766)
- chore(typing): add boto3/botocore stubs so basedpyright resolves the AWS SDK by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30815](https://github.com/BerriAI/litellm/pull/30815)
- fix(otel): one v2 logger owns the global provider; scope tenant OTLP creds per exporter by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30590](https://github.com/BerriAI/litellm/pull/30590)
- fix(passthrough): recover output tokens for interrupted anthropic streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30787](https://github.com/BerriAI/litellm/pull/30787)
- fix(proxy): record partial spend on the failure row for interrupted streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30788](https://github.com/BerriAI/litellm/pull/30788)
- fix(ui): repoint dead usage guide link to cost tracking docs by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30859](https://github.com/BerriAI/litellm/pull/30859)
- fix(ui): warn that team models are deleted in the delete-team modal by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29990](https://github.com/BerriAI/litellm/pull/29990)
- feat(caching): add valkey-semantic cache backend and fix semantic cache scope keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30675](https://github.com/BerriAI/litellm/pull/30675)
- test(ui): isolate OldTeams delete-warning tests from leaked mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30871](https://github.com/BerriAI/litellm/pull/30871)
- feat: add lint-gate target and truncation-proof summary to the strict ruff gate by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30877](https://github.com/BerriAI/litellm/pull/30877)
- chore(ui): rebuild ui for release by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30894](https://github.com/BerriAI/litellm/pull/30894)
- chore(ci): bump deps by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30899](https://github.com/BerriAI/litellm/pull/30899)
- fix(watsonx): wrap string embedding input in array for WatsonX API by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30897](https://github.com/BerriAI/litellm/pull/30897)
- test: point router/completion/triton tests at the local fake OpenAI endpoint by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30900](https://github.com/BerriAI/litellm/pull/30900)
- feat(sandbox): e2b code execution primitive by [@&#8203;krrish-berri-2](https://github.com/krrish-berri-2) in [#&#8203;30898](https://github.com/BerriAI/litellm/pull/30898)
- fix(ui): source api-keys identity from useAuthorized to stop "User ID is not set" by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30903](https://github.com/BerriAI/litellm/pull/30903)
- chore(ui): rebuild ui by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30906](https://github.com/BerriAI/litellm/pull/30906)
- chore(ci): promote internal staging to main by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30907](https://github.com/BerriAI/litellm/pull/30907)
- fix(redis): prevent forcing SSLConnection when ssl=False in connection pool by [@&#8203;Jacopos311](https://github.com/Jacopos311) in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- fix(proxy): log UI setup failures instead of silently swallowing by [@&#8203;sarvesh1327](https://github.com/sarvesh1327) in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

##### New Contributors

- [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) made their first contribution in [#&#8203;30634](https://github.com/BerriAI/litellm/pull/30634)
- [@&#8203;Jacopos311](https://github.com/Jacopos311) made their first contribution in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- [@&#8203;sarvesh1327](https://github.com/sarvesh1327) made their first contribution in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

**Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.89.0...v1.90.0>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](https://github.com/BerriAI/litellm/compare/v1.89.4...v1.90.0)

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

##### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](https://github.com/BerriAI/litellm/pull/29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](https://github.com/BerriAI/litellm/pull/29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](https://github.com/BerriAI/litellm/pull/29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](https://github.com/BerriAI/litellm/pull/29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](https://github.com/BerriAI/litellm/pull/29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](https://github.com/BerriAI/litellm/pull/27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](https://github.com/BerriAI/litellm/pull/29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](https://github.com/BerriAI/litellm/pull/29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](https://github.com/BerriAI/litellm/pull/29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](https://github.com/BerriAI/litellm/pull/29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](https://github.com/BerriAI/litellm/pull/29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](https://github.com/BerriAI/litellm/pull/29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](https://github.com/BerriAI/litellm/pull/29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](https://github.com/BerriAI/litellm/pull/29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](https://github.com/BerriAI/litellm/pull/29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](https://github.com/BerriAI/litellm/pull/29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](https://github.com/BerriAI/litellm/pull/29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](https://github.com/BerriAI/litellm/pull/29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](https://github.com/BerriAI/litellm/pull/29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](https://github.com/BerriAI/litellm/pull/29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](https://github.com/BerriAI/litellm/pull/29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](https://github.com/BerriAI/litellm/pull/28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](https://github.com/BerriAI/litellm/pull/29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](https://github.com/BerriAI/litellm/pull/29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](https://github.com/BerriAI/litellm/pull/29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](https://github.com/BerriAI/litellm/pull/28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](https://github.com/BerriAI/litellm/pull/29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](https://github.com/BerriAI/litellm/pull/29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](https://github.com/BerriAI/litellm/pull/28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](https://github.com/BerriAI/litellm/pull/29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](https://github.com/BerriAI/litellm/pull/29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](https://github.com/BerriAI/litellm/pull/29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](https://github.com/BerriAI/litellm/pull/29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](https://github.com/BerriAI/litellm/pull/30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](https://github.com/BerriAI/litellm/pull/29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](https://github.com/BerriAI/litellm/pull/24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](https://github.com/BerriAI/litellm/pull/30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](https://github.com/BerriAI/litellm/pull/30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](https://github.com/BerriAI/litellm/pull/30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](https://github.com/BerriAI/litellm/pull/30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](https://github.com/BerriAI/litellm/pull/29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](https://github.com/BerriAI/litellm/pull/30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](https://github.com/BerriAI/litellm/pull/30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](https://github.com/BerriAI/litellm/pull/30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](https://github.com/BerriAI/litellm/pull/30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](https://github.com/BerriAI/litellm/pull/30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](https://github.com/BerriAI/litellm/pull/30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](https://github.com/BerriAI/litellm/pull/28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](https://github.com/BerriAI/litellm/pull/30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](https://github.com/BerriAI/litellm/pull/30044)
- \[internal copy of [#&#8203;28007](https://github.com/BerriAI/litellm/issues/28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](https://github.com/BerriAI/litellm/pull/28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](https://github.com/BerriAI/litellm/pull/29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](https://github.com/BerriAI/litellm/pull/30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](https://github.com/BerriAI/litellm/pull/30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](https://github.com/BerriAI/litellm/pull/29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](https://github.com/BerriAI/litellm/pull/29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](https://github.com/BerriAI/litellm/pull/30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](https://github.com/BerriAI/litellm/pull/30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](https://github.com/BerriAI/litellm/pull/29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](https://github.com/BerriAI/litellm/pull/30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](https://github.com/BerriAI/litellm/pull/30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](https://github.com/BerriAI/litellm/pull/30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](https://github.com/BerriAI/litellm/issues/26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](https://github.com/BerriAI/litellm/pull/27346)
- \[internal copy of [#&#8203;30137](https://github.com/BerriAI/litellm/issues/30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](https://github.com/BerriAI/litellm/pull/30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](https://github.com/BerriAI/litellm/pull/30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](https://github.com/BerriAI/litellm/pull/30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](https://github.com/BerriAI/litellm/pull/30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](https://github.com/BerriAI/litellm/pull/29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](https://github.com/BerriAI/litellm/pull/30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](https://github.com/BerriAI/litellm/pull/30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](https://github.com/BerriAI/litellm/pull/30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](https://github.com/BerriAI/litellm/pull/30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](https://github.com/BerriAI/litellm/pull/30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](https://github.com/BerriAI/litellm/pull/30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](https://github.com/BerriAI/litellm/pull/28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](https://github.com/BerriAI/litellm/pull/29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](https://github.com/BerriAI/litellm/pull/30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](https://github.com/BerriAI/litellm/pull/30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](https://github.com/BerriAI/litellm/pull/30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](https://github.com/BerriAI/litellm/pull/30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](https://github.com/BerriAI/litellm/pull/30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](https://github.com/BerriAI/litellm/pull/30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](https://github.com/BerriAI/litellm/pull/30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](https://github.com/BerriAI/litellm/pull/30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](https://github.com/BerriAI/litellm/pull/30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](https://github.com/BerriAI/litellm/pull/30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](https://github.com/BerriAI/litellm/pull/30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](https://github.com/BerriAI/litellm/pull/30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](https://github.com/BerriAI/litellm/pull/30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](https://github.com/BerriAI/litellm/pull/30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](https://github.com/BerriAI/litellm/pull/30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](https://github.com/BerriAI/litellm/pull/30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](https://github.com/BerriAI/litellm/pull/30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](https://github.com/BerriAI/litellm/pull/30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](https://github.com/BerriAI/litellm/pull/30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](https://github.com/BerriAI/litellm/pull/30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](https://github.com/BerriAI/litellm/pull/30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](https://github.com/BerriAI/litellm/pull/30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](https://github.com/BerriAI/litellm/pull/30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](https://github.com/BerriAI/litellm/pull/30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](https://github.com/BerriAI/litellm/pull/30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](https://github.com/BerriAI/litellm/issues/28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](https://github.com/BerriAI/litellm/pull/30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](https://github.com/BerriAI/litellm/pull/30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](https://github.com/BerriAI/litellm/pull/30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](https://github.com/BerriAI/litellm/pull/30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](https://github.com/BerriAI/litellm/pull/30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](https://github.com/BerriAI/litellm/pull/30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](https://github.com/BerriAI/litellm/pull/30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](https://github.com/BerriAI/litellm/pull/30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](https://github.com/BerriAI/litellm/pull/30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](https://github.com/BerriAI/litellm/pull/30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](https://github.com/BerriAI/litellm/pull/30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](https://github.com/BerriAI/litellm/pull/30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](https://github.com/BerriAI/litellm/pull/30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](https://github.com/BerriAI/litellm/pull/30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](https://github.com/BerriAI/litellm/pull/30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](https://github.com/BerriAI/litellm/pull/30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](https://github.com/BerriAI/litellm/pull/30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](httpâ€Ķ
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants