chore(ci): promote internal staging to main by yuneng-berri · Pull Request #35876 · BerriAI/litellm

yuneng-berri · 2026-08-05T01:45:10Z

TLDR

Problem this solves:

...

How it solves it:

...

Relevant issues

Linear ticket

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

I have added meaningful tests
My PR passes all CI/CD checks (e.g., lint, format, unit tests)
My PR's scope is as isolated as possible; it only solves 1 specific problem
I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

Screenshots / Proof of Fix

Type

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

Changes

QA runbook

Final Attestation

The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

…lease ci: add fork GHCR publish workflow for Concourse releases

…_staging

OpenAI cut Terra 20% and Luna 80% on 2026-07-30; openai and bedrock_mantle entries already match. Azure global and us/eu data-zone terra/luna rows still used the pre-cut rates, so spend tracking over-billed those Azure deployments. Sol is unchanged. Cache-read, priority, and long-context fields scale with the same multipliers already used for azure gpt-5.6.

That workflow is fork-local for Concourse and does not belong in the Azure pricing PR against BerriAI staging

…t endpoints

…d report date ranges

…itellm_/spend-reports-implementation-25a080

…nit of work Moves reset_budget_job's hand-rolled private Prisma protocols into litellm/repositories as shared seams, and replaces its three ad-hoc db.batch_() write helpers with a composed unit of work that binds typed per-table write repositories to a single batch, committing on clean exit and writing nothing when the block raises.

…itellm_budget_reset_uow

mcpTokenStore was the only OAuth path writing straight to window.sessionStorage; useMcpOAuthFlow, useToolsOAuthFlow, the callback page and the edit-screen UI state all already go through secureStorage. Align it so the OAuth surface has one storage format instead of two. The stored payload also carried a refresh_token that nothing ever read back. All three read sites take access_token only, and nothing reads the mcp-session-token: keys directly, so the field was write-only. Drop it from the store and from the four callers that populated it. The client-forwarded modes (true_passthrough and oauth_delegate) re-authorize rather than refresh, and authorization_code is unaffected because it persists through storeMCPOAuthUserCredential on the backend, which keeps its own refresh token. Entries written before this change decode to null and are treated as absent, which surfaces the normal Authorize prompt; they are session-scoped and expire in an hour. Add two regression tests that decode the stored value before asserting, so neither can pass merely because the payload is no longer plain text.

…itellm_/elated-margulis-7f300f

…itellm_budget_reset_uow # Conflicts: # litellm/proxy/common_utils/reset_budget_job.py

…ariants

refactor(ui): route MCP session tokens through the shared storage helper

…he documented 4Gi sizing (#35830) The litellm-helm values file shipped the stock helm create boilerplate for resources: an empty default plus a commented 100m/128Mi example it invites operators to uncomment. 128Mi is roughly 32x below what the proxy needs at DB-connected steady state, and it was the only sizing figure this chart ever showed, so operators who followed it were sized for OOMKills. Point the example at the documented 1 CPU / 4Gi per worker instead, link the production sizing guidance, and note why the default stays unset. The migration job's commented block carried the same trap with a 100m/100Mi example; drop those numbers rather than substitute proxy figures that do not transfer to a job that migrates and exits. The defaults are deliberately left at {} so no existing release changes shape on upgrade; rendered output is unchanged.

… restarts and fires without store_model_in_db (#35165) * fix(proxy): persist periodic reload schedule state so status survives restarts and fires without store_model_in_db The model cost map and Anthropic beta headers reload schedules kept their last-run time in a per-pod module global, so GET /schedule/*/status reported last_run null after any restart and the Admin UI showed the reload as never having run. The reload check also only ran from the add_deployment job, which is registered only when store_model_in_db is true, so config-file deployments stored a schedule that never fired. Persist last_run_at and reload_requested_at as dedicated columns on LiteLLM_Config, owned by the reload job and manual reload endpoints, while the schedule endpoints own the param_value JSON (interval_hours); no writer can clobber another's fields. Serve status entirely from the row. Register the check as its own periodic_reload_job outside the store_model_in_db gate. Replace the force_reload boolean with a reload_requested_at timestamp each pod compares against its own in-memory last reload, so a manual reload reaches every pod exactly once instead of being cleared by the first poller. Run the blocking fetches via asyncio.to_thread, and stamp last_run_at with update_many so a schedule cancelled mid-poll is not resurrected. * fix(proxy): compare reload requests against pod data age seeded at boot A pod that had never reloaded kept its in-memory clock at None, and with no interval configured nothing ever set it, so every manual reload request was ignored by every pod except the one serving the click (Greptile P1 on the previous commit). Seed the per-pod timestamp at boot as the time its data was loaded and reload whenever a request or the interval is older than that, which also removes both None special cases from the due predicate. A schedule whose row has no last_run_at fires on the next tick so the first run does not wait a full interval. * fix(proxy): scope reload persistence to the model cost map and seed the pod clock from the actual load time Revert the Anthropic beta headers reload path to its previous JSON-flag implementation so this PR only changes the price data reload; the beta headers path keeps working exactly as before and can migrate to the shared module in a follow-up. The unused columns on its config row are inert. Seed model_cost_map_loaded_at from the timestamp get_model_cost_map records at the actual import-time fetch instead of ProxyConfig construction time, closing the startup window where a manual reload request stamped between the fetch and the constructor compared as older than the pod's data and was skipped (Greptile P1 on the previous commit). * refactor(proxy): drop the legacy force_reload backfill from the reload tracking migration The backfill only carried over a manual reload clicked in the seconds before an upgrade, and every upgrade restarts the pods, which re-fetch the cost map at import and so already deliver what that request asked for. Removing it makes the migration schema-only, so prisma db push and prisma migrate deploy leave the database in the same state instead of diverging on a data statement that only one of them runs. * fix(proxy): stamp reload timestamps at the precision they are stored at Postgres stores these columns as TIMESTAMP(3) while Python stamps microseconds, so a pod comparing its in-memory clock against the persisted copy of the same instant read as newer and skipped the reload request it had just recorded. Truncate every stamp to milliseconds at the source, and floor the boot seed the same way, so the in-memory value and its persisted copy compare exactly. * fix(proxy): identify manual reloads by revision instead of comparing timestamps Comparing a request timestamp against each pod's data age made correctness depend on clock resolution: Postgres stores TIMESTAMP(3) while Python stamps microseconds, and two events inside the same millisecond are indistinguishable no matter how the comparison is written. Replace reload_requested_at with a reload_revision counter the manual reload endpoint increments atomically in the database. Each pod records the revision it last applied and reloads whenever the row's differs, so a request reaches every pod exactly once regardless of clock skew or precision, and concurrent requests publish distinct revisions instead of overwriting one another. A pod adopts the current revision on its first poll, since data it loaded at boot already satisfies any earlier request. Interval reloads still key off the pod's own data age, where hour scale comparisons make precision irrelevant. * fix(proxy): seed the applied reload revision at startup A pod adopted whatever revision it found on its first poll, so a manual reload published while the pod was starting was marked applied without ever being served and the pod kept the prices it fetched at import. Read the row once at startup instead, right after that fetch, and treat a missing row as revision 0 * style(tests): revert incidental reformatting of test_proxy_server.py An earlier ruff format run reflowed the whole file from its 88-column formatting, adding ~1150 lines of churn unrelated to this PR. Replay only the real test changes onto the original formatting * fix(proxy): serve an outstanding reload request on a booting pod Seeding the applied revision at startup left a window: a manual reload published after the import-time cost map fetch but before startup read the row was marked applied without ever being fetched, stranding that pod on stale prices when no interval was configured. A pod now starts unapplied and serves any outstanding request on its first poll, which costs one redundant fetch per boot and removes the window along with the seeding step * fix(proxy): accept a reload interval still encoded as JSON text param_value is written with safe_dumps, and a raw row read can return it decoded or as a string depending on the driver. Strict validation rejected the string, so the schedule read as disabled and an admin's configured reloads silently stopped. Mirrors the guard ConfigRepository.get_param already carries for the same column * fix(proxy): cancel a reload schedule without resetting the revision * fix(proxy): null the interval in JSON so cancelling keeps the revision prisma rejects a null literal for a Json? column, so update_many writes an interval-less object instead. The fake config table now rejects the same input the database does, which is what the live run caught and the mock did not. Also records the run before adopting the revision, so a failed status write leaves the request unserved for the next poll rather than reporting a run that never landed. * fix(ui): match the CI-generated user_role union order in schema.d.ts

…errors in _acompletion fallback path (#34627) * fix(router): eagerly fetch deferred stream to surface HTTP errors in fallback path Providers like Vertex AI and Bedrock defer their HTTP call until the first __anext__ on the returned CustomStreamWrapper (completion_stream=None, make_call set). Errors raised inside __anext__ (e.g. 429, 503) escape the _acompletion try/except block, so fail_calls is never incremented, deployment cooldown does not fire, and the standard fallback chain is bypassed. Call fetch_stream() on the wrapper before delegating to _acompletion_streaming_iterator when completion_stream is None and make_call is set. Any HTTP error now propagates through _acompletion's except block, increments fail_calls, and enters the normal retry/fallback chain. Strip Content-Length, Transfer-Encoding, Content-Encoding, and Content-Type from exception headers at the same point to prevent HTTP framing mismatches when LiteLLM builds its own error response body. Add a re-raise guard in _acompletion_streaming_iterator (async and sync paths) so MidStreamFallbackError with already-generated content re-raises to the caller instead of silently injecting a continuation prompt into a fresh request to a fallback model. Apply logging cleanup in async_function_with_fallbacks_common_utils: use %s-style formatting and exc_info=True instead of f-strings with traceback.format_exc(). * fix(router): undo success_calls on deferred-stream fetch failure; broaden header strip * fix(router): extract header-strip helper to keep _acompletion under strict C901 threshold * test(router): add unit tests for _strip_http_framing_headers to satisfy router coverage gate * test(router): add sync _completion_streaming_iterator re-raise test for mid-chunk MidStreamFallbackError * fix(router): restore Fallbacks context in no-fallback log; document update_team mcp_rpm_limit The log and debug message when no fallback model group is found was missing the Fallbacks list, making it hard to understand why routing failed. Also adds the missing mcp_rpm_limit documentation to update_team to fix the documentation_test_api_docs CI check. * fix(router): preserve original traceback in deferred stream fetch error re-raise Using bare `raise` instead of `raise fetch_err` keeps the full inner traceback from fetch_stream() intact so the error origin is visible in logs and debuggers without being anchored to this line. * style(test): restore black-style formatting in test_router.py An earlier commit on this branch collapsed the file's pre-existing multi-line formatting into single lines while adding the deferred-stream tests, producing a diff full of unrelated reformatting noise. Restores the untouched code to its original formatting; the actual new/changed test content is unaffected (verified via AST comparison). * fix(router): re-raise mid-stream fallback on any generated content, not just text The re-raise guard added for MidStreamFallbackError only checked generated_content, which tracks text deltas alone. A stream that emitted a tool-call or reasoning-only chunk before failing had generated_content="" despite already streaming to the client, so the router silently retried and the client saw duplicated/inconsistent output. The guard now also inspects the wrapper's raw chunks for tool_calls/reasoning_content. Also moves the deferred-stream HTTP-framing-header stripping out of Router._acompletion into the proxy's _handle_llm_api_exception: Router is used directly as an SDK as well as by the proxy, and stripping headers there dropped legitimate provider metadata (content-type, proxy-authenticate) for direct SDK callers who never see the proxy's own response construction. schema.d.ts regenerated via make pre-commit; unrelated to this change. * test(router): add direct coverage for _stream_chunks_have_generated_content CI's router_code_coverage check flags any router.py function never referenced by name in a test file; the new helper was only exercised indirectly through the mid-stream re-raise guard tests. * revert(ui): drop incidental schema.d.ts regeneration Committing router.py/common_request_processing.py touched pre_commit_lint.sh's litellm/proxy trigger for the API-type-sync check, which force-regenerated schema.d.ts even though neither file changes any route or model. The regenerated ordering of two unrelated Union/enum fields (stream_timeout, user_role) isn't stable across process invocations even against completely unmodified backend code (confirmed by regenerating twice against the pre-existing committed code and getting the same diff both times), so this reverts to the original committed file rather than chase non-deterministic output. * fix(proxy): strip framing headers on the pre-existing ProxyException branch too _handle_llm_api_exception filtered framing headers into a local `headers` dict, but for an exception that's already a ProxyException, it merged {**e.headers, **headers}: the original e.headers came first, so a framing header present there but absent from the filtered `headers` (because it was just stripped) was never overwritten and survived into the response unfiltered. Filters the merged result instead of relying on the merge order to do it implicitly. * chore: retrigger CI (no GitHub Actions check-suite was created for the previous two pushes) * fix(router): detect thinking_blocks as generated content in mid-stream guard Greptile flagged that a thinking-only delta (Anthropic extended thinking, Delta.thinking_blocks) wasn't recognized as already-streamed content, so a stream that emitted only thinking blocks before failing could still restart via fallback and append an unrelated response after content the client already received. * fix(proxy): strip browser-facing security headers from provider exceptions too veria-ai flagged that the framing-header denylist still let a malicious or misconfigured provider set browser-facing headers (Access-Control-Allow-Origin, Content-Security-Policy, Clear-Site-Data, etc.) on the proxy's own error response. Adds a dedicated _BROWSER_SECURITY_HEADERS set alongside the existing framing one and strips both wherever provider exception headers reach the client response. * refactor(router): address maintainer review mechanicals - List[ModelResponseStream] -> list[ModelResponseStream] in _stream_chunks_have_generated_content (ruff UP006 strict-budget gate) - drop _strip_http_framing_headers and its 3 tests: the proxy inlines the filter directly now, so the helper has had no production caller since the header-stripping was moved out of Router - move HTTP_FRAMING_HEADERS/BROWSER_SECURITY_HEADERS/ UNSAFE_PROXY_RESPONSE_HEADERS from router.py into litellm/constants.py, removing the router.py <-> proxy import path the two CodeQL cyclic-import alerts were pointing at - move the eager fetch_stream() call before success_calls/logging/ _track_deployment_metrics instead of incrementing then compensating with a manual decrement on failure - fix a dead assert message: `mock_fallback.assert_not_called(), "..."` built a tuple, not an assert-with-message; assert_not_called() already raises on its own so this just drops the inert string * revert(router): pull mid-stream continuation-removal out of this PR Removing the continuation-prompt fallback (retrying with the partial response as a prefixed assistant message) so a stream failing after partial content always re-raises instead was a scope decision beyond what this PR's title/issue (#31874) describe, and it directly conflicts with #30242/#30743, which are already fixing the same code path for Anthropic's removal of assistant-message prefill on Sonnet 4.6+/Opus 4.6+. Landing this PR's version first would delete the branch those PRs are patching; landing theirs first would have this PR undo their fix on rebase. Restores the original prefill-based continuation-resume behavior (including the is_pre_first_chunk guard already in litellm_internal_staging) in both _acompletion_streaming_iterator and _completion_streaming_iterator, and removes _stream_chunks_have_generated_content along with the tests that only existed to cover the guard. This PR now only touches the deferred-stream eager-fetch fix and the header-stripping fixes; the non-text-content re-raise idea becomes a follow-up PR built on top of whichever of #30242/#30743 lands. * fix(proxy): re-filter unsafe headers after the response-headers hook merge _handle_llm_api_exception filtered provider/framing headers once, then merged in post_call_response_headers_hook's return value afterward without re-filtering. The ProxyException branch happened to re-filter after its own header merge, but the HTTPException/httpx.HTTPStatusError/ generic-exception branches passed the post-hook headers straight through unfiltered, so a callback hook (any custom guardrail/logging plugin) returning an unsafe header would bypass the strip entirely for those paths. Filters once, right after the hook merge, so every branch gets the same guarantee. * Revert "revert(router): pull mid-stream continuation-removal out of this PR" This reverts commit c5ca101. * fix(router): detect reasoning_items as generated content in mid-stream guard Greptile flagged that a structured reasoning-only delta (Delta.reasoning_items, the OpenAI Responses-API-style reasoning item) wasn't recognized as already-streamed content by _stream_chunks_have_generated_content, alongside the existing thinking_blocks/tool_calls checks, so a stream that emitted only reasoning_items before failing could still restart via fallback. * fix(router): annotate _stream_chunks_have_generated_content with Sequence, not list The type_discipline_gate LIT001 check flags mutable-collection parameter annotations. chunks is only iterated, never mutated, so Sequence is the correct read-only annotation and clears the ratcheted budget ceiling. * fix(router): surface original provider exception, not the internal wrapper, when mid-stream fallback gives up When content has already streamed and MidStreamFallbackError carries original_exception (e.g. RateLimitError), both the async and sync streaming iterators bare-re-raised the wrapper itself, so the client lost the specific error type/code/provider_specific_fields instead of seeing the real provider error. The fallback-failure path a few lines below already unwraps to original_exception for the same reason; apply the same pattern here. Also extend _stream_chunks_have_generated_content to recognize audio, images, and annotations deltas as generated content, matching is_chunk_non_empty's existing annotations check and Delta's treatment of audio/images as first-class content fields — a stream carrying only one of these before failing was not recognized as already-streamed, so the router could still restart it via fallback after the client had received real content. * chore: retrigger CI (frontend-lint cancelled, schema.d.ts flake) frontend-lint's check-run shows conclusion=cancelled on 70e47f4 with no superseding run, and this PR touches no UI files. Verify schema.d.ts matches the proxy OpenAPI spec is on the previously diagnosed stream_timeout/user_role Union-ordering nondeterminism (e9fc5e5). Empty commit to force a fresh CI run for both rather than a manual rerun, which requires repo admin rights this fork PR doesn't have. --------- Co-authored-by: Deepanshu <deepanshu.lulla@alpha-sense.com>

… clouds (#35806) The azure_storage logging callback and the azure blob files backend built every storage URL against the hardcoded commercial host, so an Azure Government account was unreachable with no way to override it. Read AZURE_STORAGE_ENDPOINT_SUFFIX (default core.windows.net) once in AzureBlobStorageLogger and derive the Data Lake and Blob hosts from it, so all seven previously hardcoded sites follow the configured cloud. Parse stored blob URLs with urlparse instead of matching the commercial host, so URLs persisted before the suffix was configured still resolve, and pin the resulting host-validation boundary with tests.

The management route-coverage guard fires because /team/metadata_schema landed in #33353 without a behavior-suite scenario, so this adds one covering the nine seeded actors plus the unauthenticated 401 The prometheus budget-metric assertions read the log call's first positional arg, which #35703 turned into an unrendered "%s" format string when it moved logging to lazy args. They now render the message from the call args, which also pins the arg order and the exception text that the old substring check never reached GitHub Models was fully retired on 2026-07-30, so test_completion_github_api can no longer pass: the endpoint the github provider targets returns 404 and models.github.ai answers 410 "github_models_retirement_brownout". The dead live test is removed rather than skipped

…itellm_/cci-failing-tests-f73740

…ity branches (#35840) * fix(proxy): apply key_alias/key_hash filters to all /key/list visibility branches The filters previously lived only in the own-keys OR branch, so a team admin's admin-team branch matched every team key and the Key Alias filter in the Virtual Keys UI appeared broken. Both filters are now global AND conditions alongside team_id/project_id/access_group_id/agent_id, narrowing every visibility branch while leaving unfiltered visibility unchanged. * chore: drop new explanatory comments flagged by review * chore: restore schema.d.ts to base enum order

…ider The vendored provider pinned google.golang.org/grpc v1.79.2 alongside a set of golang.org/x modules that govulncheck reports as reachable from plugin.Serve. Raising grpc to v1.82.1 and golang.org/x/text to v0.39.0 pulls the remainder up through minimal version selection and leaves govulncheck reporting no findings Only go.mod and go.sum move here, no provider source is touched. gofmt, go vet, go build and go test all pass at the new versions

…itellm_/terraform-provider-dep-bump-5feb4a

…get_bypass fix(proxy): enforce per-model budgets against resolved cursor model variants

…sible detailed config (#35746) * feat(ui): add template picker to the Add Auto Router flow Add Auto Router now opens straight into name + an optional Template dropdown (Anthropic/OpenAI model-family presets or Custom). A preset prefills the full complexity-router config and collapses the Detailed Configuration section to a one-line tier summary; choosing Custom (or nothing yet) leaves it expanded, and a caller can toggle it manually at any point. A preset option greys out with the specific missing model(s) named when the caller lacks a model it needs, or while the model list is loading or failed to load. Prefill and submit-gating logic live in testable pure functions (buildPresetPrefill, getReferencedModelsError) rather than inline in the component, per the dashboard's own testing guidance. * refactor(ui): memoize presetAvailability Consistency with the other memoized derived values it closes over (availableModelSet, presets). Negligible perf impact with two presets today, but keeps the pattern uniform as more get added. * refactor(ui): drop pointless useMemo around getAllPresets() getAllPresets() already returns a stable module-level array reference; wrapping it in useMemo added React machinery for something that can't change. * refactor(ui): hoist presets to module scope getAllPresets() was still being called from inside the component body on every render even after dropping the useMemo wrapper. Resolving it once at module load, alongside PRESETS' own module-level initialization in autorouter_presets.ts, is the actually-clean version of the previous fix. * fix(ui): collapse Detailed Configuration by default It was defaulting to expanded before any template was chosen, so the modal still opened onto the full tier/classifier form instead of just Name + Template. Custom still auto-expands it, and a preset still collapses it after prefilling. * fix(ui): list Custom Configuration last in the Template dropdown Custom is the escape hatch, not the headline choice, so the bundled presets now come first with Custom listed after them. Also lets the collapsed Detailed Configuration summary wrap onto its own line(s) instead of sharing a line with the section label and truncating mid-model-name. * feat(ui): match preset models across "-"/"." version separators Admins spell version numbers inconsistently (claude-sonnet-4-5 vs claude-sonnet-4.5), so a preset's hardcoded name and a caller's registered one can refer to the same model while differing only in that punctuation. getMissingModels (and therefore presetAvailability and the submit-blocking check) now treats the two as equivalent. Applying a preset writes the caller's actual registered spelling into the tiers, not the preset's literal string, since the caller may only have the dotted (or hyphenated) form and never the other one - buildPresetPrefill now takes the available-models set for this rewrite. Two different model names never collide; only the separator within one version number does. * fix(ui): re-check referenced models inside submitRecommendedRouter submitBlockedReason disables the button for a stale/missing model reference, but Form's onFinish (wired to the same handler) fires on a real form submission regardless of the button's own disabled state. The other four blocking checks already re-validate inside submitRecommendedRouter for this exact reason; this one was missing it, so a router could still be created referencing a model no longer in availableModelSet. Found by Bugbot. * Update autorouter_presets.json

…loor e2e_ui_testing and e2e_ui_testing_server_root_path run on cimg/python:3.12-browsers, the one UI executor whose image supplies Node rather than taking it from a cimg/node tag. That image ships Node 24.14.0, which bundles npm 11.9.0, so both lanes have failed EBADENGINE against the engines floor added in #35801. Every Node 24 release through 24.14.0 bundles an npm below 11.10.0, so engines.node also rises to 24.14.1 (npm 11.11.0), the first release where the two floors agree The pinned install goes into /opt/node with /opt/node/bin prepended to PATH instead of unpacking over /usr/local. On this image /usr/local already holds npm 11.9.0, and extracting the tarball on top of it merges the two trees into an npm that reports 11.17.0 and then exits 1 on npm ci printing no error text at all, which is a worse failure than the one being fixed The install moves into a reusable install_node command so the version and its checksum have one home, shared with proxy_pass_through_endpoint_tests, and the command refuses to run when it disagrees with ui/litellm-dashboard/.nvmrc. A lane drifting off the version the rest of the toolchain uses is what produced this failure, so that mismatch now stops the job instead of surfacing later as an install error The e2e node_modules cache key moves to v4 because the saved trees were built by the old npm

… per index

…ute (LIT-4110) (#31752) * fix(claude-code): make skill registration create-only with a PUT update route POST /claude-code/plugins upserted by name, so re-registering an existing name silently overwrote the stored skill's source and metadata. The "Add New Skill" UI button posts here, so a name collision clobbered a different skill with no signal to the user. Make POST create-only: it returns 409 if the name already exists, with a unique-violation guard mapping the find-then-create race to the same 409. Add an explicit PUT /claude-code/plugins/{plugin_name} for updates (404 if the name is missing). PUT is a full replace and documents that omitted fields reset to their defaults, so UpdatePluginRequest defaults version to None instead of fabricating the create-time 1.0.0. The shared mutable fields move to a PluginSpec base; RegisterPluginRequest keeps its name and its generated schema unchanged, UpdatePluginRequest carries no name. Regenerated the dashboard types and the lazy openapi snapshot for the new route. Resolves LIT-4110 * fix(ui): surface the proxy error detail so the skill 409 conflict is legible The add-skill form rendered the raw HTTPException envelope on failure because deriveErrorMessage did not unwrap an object-shaped detail ({"detail": {"error": ...}}), so the new create-only 409 reached the user as a JSON blob. Unwrap object-shaped detail at the client layer, which covers every handler that returns detail={"error": ...}, and surface the resulting message verbatim on the form instead of burying it under a generic prefix. * refactor(claude-code): replace blind excepts in plugin mutations with typed handling Narrow register_plugin's create-conflict guard from a broad 'except Exception' + isinstance dance to a direct 'except UniqueViolationError', using an Exception subclass sentinel (not None) as the prisma-absent fallback so the sentinel can be caught directly. Drop update_plugin's outer 'except Exception -> 500' wrapper so HTTPExceptions propagate on their own and unexpected DB errors surface as FastAPI's default 500 rather than echoing str(e). Keeps the BLE001 strict-rule budget green. * fix(claude-code): restore structured 500 handling on update_plugin via typed PrismaError catch Flattening update_plugin to satisfy the no-blind-except rule dropped its error wrapper entirely, so a data-layer failure (e.g. a dropped DB connection) would skip the intentional verbose_proxy_logger.exception call and degrade the response from the endpoint's structured {"error": ...} body to FastAPI's default {"detail": "Internal Server Error"}, inconsistent with every sibling route. Wrap update_plugin in 'except PrismaError' instead of the blind 'except Exception' the other routes use: it logs and returns the structured 500 for real DB failures while letting genuine code bugs surface rather than masking them as 'Update failed', and stays off the BLE001 budget. Add a regression test that a PrismaError during the update maps to a structured 500. * fix(claude-code): import prisma error types at function level to satisfy LIT009 * refactor(claude-code): typed plugin mutation responses and lint gate fixes Return RegisterPluginResponse models from POST and PUT instead of ad-hoc dicts, declare them as response_model so the OpenAPI schema and dashboard types carry the real response shape, build the stored manifest via model_dump, and drop update_plugin's unused auth parameter (the route dependency already enforces auth). Keeps the LIT002/B008/UP045 budgets at their ratcheted ceilings after merging litellm_internal_staging

CLAassistant · 2026-08-05T01:45:20Z

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
8 out of 10 committers have signed the CLA.

✅ yuneng-berri
✅ mateo-berri
✅ mubashir1osmani
✅ deepanshululla
✅ tin-berri
✅ yucheng-berri
✅ ryan-crabbe-berri
✅ jwang-gif
❌ yassin-berriai
❌ devin-ai-integration[bot]
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

* fix(zscaler_ai_guard): return 400 on guardrail block * fix(zscaler_ai_guard): don't log error on intentional BLOCK A BLOCK is expected guardrail behavior, not a failure. Before this fix, raising HTTPException inside the try block caused the generic except to log it as "Failed to apply guardrail", producing spurious error-level noise for every normal block event. Added except HTTPException: raise before the generic handler (matching the existing pattern in make_zscaler_ai_guard_api_call), and a regression test that asserts logger.error is not called on a BLOCK. --------- Co-authored-by: yucheng-berri <yucheng@berri.ai>

greptile-apps · 2026-08-05T01:48:45Z

Greptile Summary

This PR promotes a broad set of staging changes covering proxy reload scheduling, spend reporting, client caching, provider behavior, CI, Helm guidance, and dashboard workflows.

Adds database-backed model-cost-map reload tracking and scheduling.
Adds scoped spend reports and transactional scheduled budget resets.
Updates caching, routing, provider adapters, guardrails, and response handling.
Expands dashboard auto-router, OAuth, MCP token, and HTTP client behavior.
Updates CI toolchains and associated unit and end-to-end coverage.

Confidence Score: 4/5

The PR appears safe to merge after relocating the newly added customer-facing Helm sizing guidance to the documentation repository.

The reviewed runtime changes did not yield an established blocking failure, while the remaining issue is a non-blocking documentation-placement violation.

Files Needing Attention: helm/litellm-helm/README.md, helm/litellm-helm/values.yaml

Important Files Changed

Filename	Overview
litellm/proxy/common_utils/periodic_reload_schedule.py	Adds persisted scheduling and revision-based coordination for per-pod model-cost-map reloads; no actionable correctness defect was established.
litellm/proxy/spend_tracking/spend_management_endpoints.py	Adds authenticated, scoped spend-report endpoints with date validation and organization access checks.
litellm/repositories/unit_of_work.py	Introduces a Prisma batch-backed unit of work for atomic scheduled spend resets.
litellm/caching/llm_caching_handler.py	Removes deferred client closure so eviction cannot close clients still used by in-flight requests.
litellm/proxy/proxy_server.py	Integrates periodic reload scheduling, administration routes, and related proxy lifecycle changes.
ui/litellm-dashboard/src/components/add_model/add_auto_router_tab.tsx	Expands auto-router preset selection and model configuration behavior with corresponding tests.
.circleci/config.yml	Adds a pinned Node installation command and applies it to browser-based UI jobs.
helm/litellm-helm/README.md	Adds production sizing guidance that conflicts with the repository requirement to keep customer documentation in litellm-docs.

_{Reviews (1): Last reviewed commit: "fix(claude-code): create-only skill regi..." | Re-trigger Greptile}

greptile-apps · 2026-08-05T01:48:48Z

 | `readinessProbe.*`          | Readiness probe settings for the LiteLLM container (`path`, `periodSeconds`, `timeoutSeconds`, thresholds, and initial delay).                                                                                                                 | See `values.yaml`         |
 | `startupProbe.*`            | Startup probe settings for the LiteLLM container (`path`, `periodSeconds`, `timeoutSeconds`, thresholds, and initial delay).                                                                                                                   | See `values.yaml`         |
-| `resources.*`               | CPU/memory requests and limits for the LiteLLM container.                                                                                                                                                                                       | `{}`                      |
+| `resources.*`               | CPU/memory requests and limits for the LiteLLM container. Unset by default; production deployments should set 1 CPU and 4Gi of memory per worker.                                                                                             | `{}`                      |


Chart-local production sizing guidance

This adds customer-facing production sizing guidance to the chart README, while repository policy requires product documentation to live in litellm-docs; keeping the recommendation here splits its maintenance and allows it to drift from the published documentation.

Rule Used: Prevent documentation from being added - needs to ... (source)

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

codecov · 2026-08-05T01:54:48Z

Codecov Report

❌ Patch coverage is 74.10685% with 790 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
litellm/evals/main.py	1.31%	150 Missing ⚠️
...tellm/integrations/SlackAlerting/slack_alerting.py	19.44%	87 Missing ⚠️
litellm/caching/redis_cache.py	55.28%	55 Missing ⚠️
litellm/integrations/argilla.py	2.63%	37 Missing ⚠️
litellm/experimental_mcp_client/client.py	54.66%	34 Missing ⚠️
...col/providers/pydantic_ai_agents/transformation.py	0.00%	29 Missing ⚠️
litellm/files/main.py	65.85%	28 Missing ⚠️
...itellm/integrations/azure_storage/azure_storage.py	53.06%	23 Missing ⚠️
litellm/images/main.py	71.23%	21 Missing ⚠️
litellm/caching/caching.py	65.51%	20 Missing ⚠️
... and 56 more

📢 Thoughts on this report? Let us know!

fix(lint): pick the merge-aware base so in-progress merges are not blamed for base drift

chore: bump litellm-proxy-extras 0.4.82 -> 0.4.83

…4649)" This reverts commit dcb4e50. The suites landed without the proof-of-fix and QA runbook the PR body itself flagged as outstanding, so the coverage they claim is unverified against a live proxy

* feat(ui): add Test Routing to the auto router create form Route a test prompt through the complexity-router config on screen before the router is saved, showing the model it lands on and the same decision trace the Logs page renders. Adds POST /auto_router/test_routing, which classifies with the live pre-routing hook and sends nothing to the routed model. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): reset the routing test modal on reopen and expose /auto_router on the UI backend Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): enforce caller model access and key budget on the routing test's classifier call Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: tin <tin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

…itellm_/revert-pr-34649-9f1755

The template tests hardcoded the model names the presets happened to ship with, so editing autorouter_presets.json to name newer models turned every preset red in the fixtures and hung six waitFor calls

…itellm_gate_owns_basedpyright_heap

…test_fixtures fix(ui): derive auto-router preset tests from the bundled preset JSON

revert: "test(e2e): vendor API strategy coverage across endpoints" (#34649)

…p-bump-5feb4a chore(deps): bump grpc and golang.org/x modules in the terraform provider

…8a96 test(e2e): skip view-backed global spend probes pending LIT-5211

veria-ai · 2026-08-05T02:15:18Z

+                sl.model
+        )
+        SELECT
+            api_key,


Medium: Team spend reports expose API key hashes

The shared query returns LiteLLM_SpendLogs.api_key verbatim, and /team/spend/report is reachable by every internal team member. A member can therefore enumerate other members’ key hashes and per-model usage; return a non-sensitive alias or opaque display identifier, or aggregate results without the key identifier for non-admin scopes.

veria-ai · 2026-08-05T02:15:26Z

PR overview

This PR promotes internal staging changes to main, including updates to team spend reporting and auto-router management endpoints.

Two security issues remain open. Internal team members can access other members’ API key hashes and usage details through spend reports, while team administrators may receive sensitive provider exception contents when triggering classifier or embedding failures. Both exposures require authenticated internal roles, limiting their reach but still risking credential-related information disclosure.

Open issues (2)

Medium: Team spend reports expose API key hashes — litellm/proxy/spend_tracking/spend_management_endpoints.py:1483
Medium: Provider exception disclosure — litellm/proxy/management_endpoints/auto_router_endpoints.py:231

Fixed/addressed: 0 · PR risk: 6/10

…_heap fix(lint): move the basedpyright heap flag into the type check gate

veria-ai · 2026-08-05T02:36:47Z

+        raise HTTPException(
+            status_code=400,
+            detail={  # mutable-ok: HTTPException detail must be a plain mapping
+                "error": f"Could not route this prompt: {e}"


Medium: Provider exception disclosure

A team administrator can trigger a classifier or embedding failure, and str(e) is copied directly into the HTTP response. If the provider exception contains an API key, credential-bearing URL, or request headers, the caller receives those values; redact the exception with redact_secrets() or return a fixed client-facing message while retaining the full error only in filtered server logs.

codspeed-hq · 2026-08-05T02:57:32Z

Merging this PR will not alter performance

✅ 31 untouched benchmarks

_{Comparing litellm_internal_staging (faf3c51) with main (cfe8552)¹}

No successful run was found on main (faf3c51) during the generation of this report, so cfe8552 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

…7.0) (#336) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/berriai/litellm](https://images.chainguard.dev/directory/image/wolfi-base/overview) ([source](https://github.com/BerriAI/litellm)) | minor | `v1.96.2` → `v1.97.0` | --- ### Release Notes <details> <summary>BerriAI/litellm (ghcr.io/berriai/litellm)</summary> ### [`v1.97.0`](https://github.com/BerriAI/litellm/releases/tag/v1.97.0) [Compare Source](https://github.com/BerriAI/litellm/compare/v1.97.0...v1.97.0) ##### 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:v1.97.0 ``` **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/v1.97.0/cosign.pub \ ghcr.io/berriai/litellm:v1.97.0 ``` 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 - feat(proxy): resolve Cursor thinking/fast model-name suffixes on /cursor/chat/completions by [@mateo-berri](https://github.com/mateo-berri) in [#35554](https://github.com/BerriAI/litellm/pull/35554) - fix(team-callbacks): actually stop logging when disable\_logging is called by [@yucheng-berri](https://github.com/yucheng-berri) in [#35520](https://github.com/BerriAI/litellm/pull/35520) - refactor(lint): drop redundant !s f-string conversion flags and fix displaced import-group comments by [@mateo-berri](https://github.com/mateo-berri) in [#35546](https://github.com/BerriAI/litellm/pull/35546) - fix(proxy): backfill null user\_email on existing users during JWT auth by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34588](https://github.com/BerriAI/litellm/pull/34588) - feat(playground): add non-streaming response toggle by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35560](https://github.com/BerriAI/litellm/pull/35560) - feat(teams): apply default organization to new teams from default team settings by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35540](https://github.com/BerriAI/litellm/pull/35540) - fix(ui): block Playground page for viewer roles on direct URL access by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35676](https://github.com/BerriAI/litellm/pull/35676) - fix(caching): close evicted LLM clients so their connections are reclaimed by [@yassin-berriai](https://github.com/yassin-berriai) in [#35492](https://github.com/BerriAI/litellm/pull/35492) - chore(deps): update brace-expansion, postcss, and gitpython to current patch releases by [@yuneng-berri](https://github.com/yuneng-berri) in [#35692](https://github.com/BerriAI/litellm/pull/35692) - refactor(ui): rename the create MCP server component to PascalCase by [@yuneng-berri](https://github.com/yuneng-berri) in [#35686](https://github.com/BerriAI/litellm/pull/35686) - fix(openai): drop undefined Union from owns\_wrapped\_http\_client annotation by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35706](https://github.com/BerriAI/litellm/pull/35706) - fix(openai): drop the undefined Union from owns\_wrapped\_http\_client by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35704](https://github.com/BerriAI/litellm/pull/35704) - chore(ui): note Google's Agent Platform rename in vector store setup by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#28076](https://github.com/BerriAI/litellm/pull/28076) - fix(proxy): apply key/team router\_settings.model\_group\_alias by [@yassin-berriai](https://github.com/yassin-berriai) in [#35486](https://github.com/BerriAI/litellm/pull/35486) - feat(complexity\_router): default session affinity off and expose it in the UI by [@tin-berri](https://github.com/tin-berri) in [#35714](https://github.com/BerriAI/litellm/pull/35714) - fix(datadog): read team callback dd\_\* params from kwargs instead of blocked dynamic params ([#35115](https://github.com/BerriAI/litellm/issues/35115) port) by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35687](https://github.com/BerriAI/litellm/pull/35687) - refactor(ui): extract the MCP create form's logic and field groups by [@yuneng-berri](https://github.com/yuneng-berri) in [#35694](https://github.com/BerriAI/litellm/pull/35694) - test(ui): tier the MCP create tests into unit and integration by [@yuneng-berri](https://github.com/yuneng-berri) in [#35697](https://github.com/BerriAI/litellm/pull/35697) - fix(proxy): redact credential headers from request logging copies by [@yucheng-berri](https://github.com/yucheng-berri) in [#35678](https://github.com/BerriAI/litellm/pull/35678) - feat(guardrails/rubrik): prompt moderation, response-text blocking, streaming buffer, failure logging by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35722](https://github.com/BerriAI/litellm/pull/35722) - fix(ui): render Responses API request and response in the logs drawer by [@yuneng-berri](https://github.com/yuneng-berri) in [#35718](https://github.com/BerriAI/litellm/pull/35718) - fix(ui): hide guardrail review buttons from non-admin users by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#27535](https://github.com/BerriAI/litellm/pull/27535) - feat(team): custom metadata validation hook for team create and update by [@yuneng-berri](https://github.com/yuneng-berri) in [#33353](https://github.com/BerriAI/litellm/pull/33353) - ci(circleci): install a pinned Rust toolchain on the Linux jobs by [@yuneng-berri](https://github.com/yuneng-berri) in [#35519](https://github.com/BerriAI/litellm/pull/35519) - fix(bedrock): stop forwarding no-op toolSpec.strict to Converse by [@tin-berri](https://github.com/tin-berri) in [#35688](https://github.com/BerriAI/litellm/pull/35688) - fix(ui): reject an auto-router keyword rule left empty instead of dropping it by [@tin-berri](https://github.com/tin-berri) in [#35705](https://github.com/BerriAI/litellm/pull/35705) - fix(guardrails/rubrik): attribute blocked requests to the caller that made them by [@yucheng-berri](https://github.com/yucheng-berri) in [#35734](https://github.com/BerriAI/litellm/pull/35734) - fix(responses): forward client headers to the provider on /v1/responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34531](https://github.com/BerriAI/litellm/pull/34531) - feat(spend): add net auto-router savings to the cost-optimization dashboard by [@tin-berri](https://github.com/tin-berri) in [#35521](https://github.com/BerriAI/litellm/pull/35521) - chore(typing): clear basedpyright Any errors in budget reset, access groups, and cache settings by [@mateo-berri](https://github.com/mateo-berri) in [#35719](https://github.com/BerriAI/litellm/pull/35719) - fix(spend): read what a request cost from the record instead of pricing it again by [@tin-berri](https://github.com/tin-berri) in [#35736](https://github.com/BerriAI/litellm/pull/35736) - perf: install hiredis so redis-py parses replies with its C parser by [@Classic298](https://github.com/Classic298) in [#35709](https://github.com/BerriAI/litellm/pull/35709) - feat(ui): show auto-router savings on the cost-optimization dashboard by [@tin-berri](https://github.com/tin-berri) in [#35522](https://github.com/BerriAI/litellm/pull/35522) - perf: build log messages lazily so filtered-out log records cost nothing by [@Classic298](https://github.com/Classic298) in [#35703](https://github.com/BerriAI/litellm/pull/35703) - fix(proxy): retry model cost map fetch with Retry-After-aware backoff and keep current map on reload failure by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35739](https://github.com/BerriAI/litellm/pull/35739) - feat(otel): stamp service tier attributes on inference spans by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35679](https://github.com/BerriAI/litellm/pull/35679) - fix(proxy): log the model cost map reload failure lazily by [@tin-berri](https://github.com/tin-berri) in [#35750](https://github.com/BerriAI/litellm/pull/35750) - fix(groq): translate web\_search\_options to the browser\_search tool by [@hMED22](https://github.com/hMED22) in [#34971](https://github.com/BerriAI/litellm/pull/34971) - feat(ui): add admin-configurable user banner by [@yuneng-berri](https://github.com/yuneng-berri) in [#35729](https://github.com/BerriAI/litellm/pull/35729) - fix(e2e): make spend-counter redis connection env-driven for non-cluster deployments by [@yuneng-berri](https://github.com/yuneng-berri) in [#35732](https://github.com/BerriAI/litellm/pull/35732) - fix(proxy): make /cursor/chat/completions work with Cursor agent mode by [@tin-berri](https://github.com/tin-berri) in [#34029](https://github.com/BerriAI/litellm/pull/34029) - fix(proxy): propagate user\_email and bind api\_key on JWT auth attribution paths by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34331](https://github.com/BerriAI/litellm/pull/34331) - chore(build): move the Admin UI toolchain to Node 24 by [@yuneng-berri](https://github.com/yuneng-berri) in [#35801](https://github.com/BerriAI/litellm/pull/35801) - test(e2e): vendor API strategy coverage across endpoints by [@mubashir1osmani](https://github.com/mubashir1osmani) in [#34649](https://github.com/BerriAI/litellm/pull/34649) - chore(deps): upgrade cryptography to 50.0.0 by [@yuneng-berri](https://github.com/yuneng-berri) in [#35803](https://github.com/BerriAI/litellm/pull/35803) - test(e2e): cover legacy text /completions endpoint by [@mubashir1osmani](https://github.com/mubashir1osmani) in [#34431](https://github.com/BerriAI/litellm/pull/34431) - feat(gemini): add gemini-robotics-er-2-preview and gemini-robotics-er-1.6-preview by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35555](https://github.com/BerriAI/litellm/pull/35555) - test(e2e): move load/perf testing out of the main suite and drop the vllm passthrough test by [@yuneng-berri](https://github.com/yuneng-berri) in [#35820](https://github.com/BerriAI/litellm/pull/35820) - feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) by [@mateo-berri](https://github.com/mateo-berri) in [#35807](https://github.com/BerriAI/litellm/pull/35807) - chore: bump litellm-proxy-extras 0.4.81 -> 0.4.82, litellm 1.96.0 -> 1.97.0 by [@yuneng-berri](https://github.com/yuneng-berri) in [#35810](https://github.com/BerriAI/litellm/pull/35810) - fix(bedrock): drop conflicting tool\_choice.type when toolConfig.toolChoice is set by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35738](https://github.com/BerriAI/litellm/pull/35738) - docs(CLAUDE.md): prefer commas over semicolons when replacing em dashes by [@mateo-berri](https://github.com/mateo-berri) in [#35825](https://github.com/BerriAI/litellm/pull/35825) - chore(lint): zero out basedpyright headroom for purely local rules by [@mateo-berri](https://github.com/mateo-berri) in [#35828](https://github.com/BerriAI/litellm/pull/35828) - test(e2e): retry provider-transient statuses at the transport with bounded backoff by [@yuneng-berri](https://github.com/yuneng-berri) in [#35824](https://github.com/BerriAI/litellm/pull/35824) - chore(ci): promote internal staging to main by [@yuneng-berri](https://github.com/yuneng-berri) in [#35836](https://github.com/BerriAI/litellm/pull/35836) - refactor(ui): route MCP session tokens through the shared storage helper by [@yuneng-berri](https://github.com/yuneng-berri) in [#35835](https://github.com/BerriAI/litellm/pull/35835) - docs(helm): replace the classic chart's 128Mi resource example with the documented 4Gi sizing by [@yassin-berriai](https://github.com/yassin-berriai) in [#35830](https://github.com/BerriAI/litellm/pull/35830) - fix(proxy): persist periodic reload schedule state so status survives restarts and fires without store\_model\_in\_db by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35165](https://github.com/BerriAI/litellm/pull/35165) - fix(router): eagerly fetch Vertex AI deferred stream to surface HTTP errors in \_acompletion fallback path by [@deepanshululla](https://github.com/deepanshululla) in [#34627](https://github.com/BerriAI/litellm/pull/34627) - fix(azure\_storage): honor AZURE\_STORAGE\_ENDPOINT\_SUFFIX for sovereign clouds by [@yucheng-berri](https://github.com/yucheng-berri) in [#35806](https://github.com/BerriAI/litellm/pull/35806) - fix(proxy): apply key\_alias/key\_hash filters to all /key/list visibility branches by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35840](https://github.com/BerriAI/litellm/pull/35840) - fix(proxy): enforce per-model budgets against resolved cursor model variants by [@mateo-berri](https://github.com/mateo-berri) in [#35834](https://github.com/BerriAI/litellm/pull/35834) - feat(ui): reorder Add Auto Router into name + template, with a collapsible detailed config by [@tin-berri](https://github.com/tin-berri) in [#35746](https://github.com/BerriAI/litellm/pull/35746) - test: repair three failing suites on litellm\_internal\_staging by [@yuneng-berri](https://github.com/yuneng-berri) in [#35845](https://github.com/BerriAI/litellm/pull/35845) - fix(guardrails): scan model output on the /openai/v1/responses alias by [@yucheng-berri](https://github.com/yucheng-berri) in [#35818](https://github.com/BerriAI/litellm/pull/35818) - ci: pin Node on the Playwright UI lanes so npm ci meets the engines floor by [@yuneng-berri](https://github.com/yuneng-berri) in [#35848](https://github.com/BerriAI/litellm/pull/35848) - fix(pricing): apply OpenAI's gpt-5.6 terra/luna cut to Azure cost map by [@mubashir1osmani](https://github.com/mubashir1osmani) in [#35481](https://github.com/BerriAI/litellm/pull/35481) - feat(spend): add caller-scoped key/user/team/organization spend report endpoints by [@yuneng-berri](https://github.com/yuneng-berri) in [#35725](https://github.com/BerriAI/litellm/pull/35725) - revert: "fix(caching): close evicted LLM clients so their connections are reclaimed ([#35492](https://github.com/BerriAI/litellm/issues/35492))" by [@mateo-berri](https://github.com/mateo-berri) in [#35856](https://github.com/BerriAI/litellm/pull/35856) - refactor(repositories): add prisma protocol seams and a spend-reset unit of work by [@mateo-berri](https://github.com/mateo-berri) in [#35748](https://github.com/BerriAI/litellm/pull/35748) - perf(streaming): assemble streamed tool-call arguments in linear time by [@mateo-berri](https://github.com/mateo-berri) in [#35826](https://github.com/BerriAI/litellm/pull/35826) - fix(s3\_v2): sign S3 object URLs with S3SigV4Auth so encoded paths verify by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35726](https://github.com/BerriAI/litellm/pull/35726) - test(e2e): self-seed the ui suite's password-login users in global setup by [@yuneng-berri](https://github.com/yuneng-berri) in [#35863](https://github.com/BerriAI/litellm/pull/35863) - fix(claude-code): create-only skill registration with a PUT update route (LIT-4110) by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#31752](https://github.com/BerriAI/litellm/pull/31752) - fix(proxy): fix zguard httpcode when block input by [@jwang-gif](https://github.com/jwang-gif) in [#31948](https://github.com/BerriAI/litellm/pull/31948) - fix(lint): pick the merge-aware base so in-progress merges are not blamed for base drift by [@mateo-berri](https://github.com/mateo-berri) in [#35868](https://github.com/BerriAI/litellm/pull/35868) - chore: bump litellm-proxy-extras 0.4.82 -> 0.4.83 by [@yuneng-berri](https://github.com/yuneng-berri) in [#35877](https://github.com/BerriAI/litellm/pull/35877) - feat(ui): add Test Routing to the auto router create form by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35859](https://github.com/BerriAI/litellm/pull/35859) - fix(ui): derive auto-router preset tests from the bundled preset JSON by [@tin-berri](https://github.com/tin-berri) in [#35882](https://github.com/BerriAI/litellm/pull/35882) - revert: "test(e2e): vendor API strategy coverage across endpoints" ([#34649](https://github.com/BerriAI/litellm/issues/34649)) by [@yuneng-berri](https://github.com/yuneng-berri) in [#35881](https://github.com/BerriAI/litellm/pull/35881) - chore(deps): bump grpc and golang.org/x modules in the terraform provider by [@yuneng-berri](https://github.com/yuneng-berri) in [#35844](https://github.com/BerriAI/litellm/pull/35844) - test(e2e): skip view-backed global spend probes pending LIT-5211 by [@yuneng-berri](https://github.com/yuneng-berri) in [#35875](https://github.com/BerriAI/litellm/pull/35875) - fix(lint): move the basedpyright heap flag into the type check gate by [@mateo-berri](https://github.com/mateo-berri) in [#35869](https://github.com/BerriAI/litellm/pull/35869) - chore(ci): promote internal staging to main by [@yuneng-berri](https://github.com/yuneng-berri) in [#35876](https://github.com/BerriAI/litellm/pull/35876) - feat(ui): add role capability gating, migrate Tool Policies route by [@yuneng-berri](https://github.com/yuneng-berri) in [#35812](https://github.com/BerriAI/litellm/pull/35812) - refactor(ui): inject the fetch client's base url instead of reading it at import by [@yuneng-berri](https://github.com/yuneng-berri) in [#35802](https://github.com/BerriAI/litellm/pull/35802) - chore: remove unused .flake8 config and flake8 dev dependency by [@mateo-berri](https://github.com/mateo-berri) in [#35888](https://github.com/BerriAI/litellm/pull/35888) - chore: stop advising pre-commit and bootstrap by [@mateo-berri](https://github.com/mateo-berri) in [#35884](https://github.com/BerriAI/litellm/pull/35884) - fix(auth): name enable\_jwt\_auth when a JWT-shaped key is rejected by [@yassin-berriai](https://github.com/yassin-berriai) in [#35831](https://github.com/BerriAI/litellm/pull/35831) - feat(auto-router): make reminder marker pair configurable by [@akapur99](https://github.com/akapur99) in [#35874](https://github.com/BerriAI/litellm/pull/35874) - fix(UI): update anthropic model presets by [@tin-berri](https://github.com/tin-berri) in [#35896](https://github.com/BerriAI/litellm/pull/35896) - fix(bootstrap): switch to the dashboard node floor via nvm or fnm by [@mateo-berri](https://github.com/mateo-berri) in [#35895](https://github.com/BerriAI/litellm/pull/35895) - perf(pre-commit): run python, dashboard, and gen-api checks concurrently by [@mateo-berri](https://github.com/mateo-berri) in [#35903](https://github.com/BerriAI/litellm/pull/35903) - feat(spend): derive a default auto-router savings baseline from the hardest tier by [@tin-berri](https://github.com/tin-berri) in [#35907](https://github.com/BerriAI/litellm/pull/35907) - fix(http\_handler): self-heal handler clients closed after cache eviction by [@mateo-berri](https://github.com/mateo-berri) in [#35862](https://github.com/BerriAI/litellm/pull/35862) - fix(cost\_tracking): keep OpenAI prompt cache token details through usage reassembly by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34812](https://github.com/BerriAI/litellm/pull/34812) - fix(cost): bill gpt-5.6 prompt cache reads at the cache read rate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34957](https://github.com/BerriAI/litellm/pull/34957) - fix(batches): account for Responses API usage by [@rimysore](https://github.com/rimysore) in [#35367](https://github.com/BerriAI/litellm/pull/35367) - ci: retry Codecov uploads and stop failing jobs on OIDC token flakes by [@mateo-berri](https://github.com/mateo-berri) in [#35251](https://github.com/BerriAI/litellm/pull/35251) - feat(complexity\_router): let operators rename the four complexity tiers by [@akapur99](https://github.com/akapur99) in [#35893](https://github.com/BerriAI/litellm/pull/35893) - chore(lint): zero stale ruff and LIT headroom and strip inert type: ignore comments by [@mateo-berri](https://github.com/mateo-berri) in [#35928](https://github.com/BerriAI/litellm/pull/35928) - chore(lint): zero out seven more purely local basedpyright rules by [@mateo-berri](https://github.com/mateo-berri) in [#35927](https://github.com/BerriAI/litellm/pull/35927) - chore(ui): zero stale headroom on local dashboard eslint budgets by [@mateo-berri](https://github.com/mateo-berri) in [#35929](https://github.com/BerriAI/litellm/pull/35929) - fix(managed-files): skip rows without file objects by [@rimysore](https://github.com/rimysore) in [#35365](https://github.com/BerriAI/litellm/pull/35365) - fix(router): redact fallback tracebacks at the call site and cover the sync deferred stream by [@yassin-berriai](https://github.com/yassin-berriai) in [#35843](https://github.com/BerriAI/litellm/pull/35843) - fix(migrations): recover from an interrupted Prisma toolchain install by [@yassin-berriai](https://github.com/yassin-berriai) in [#35832](https://github.com/BerriAI/litellm/pull/35832) - fix(lint): bring basedpyright rule counts back under their budget limits by [@mateo-berri](https://github.com/mateo-berri) in [#35962](https://github.com/BerriAI/litellm/pull/35962) - chore(ui): don't zero out stale headroom except no-console by [@mateo-berri](https://github.com/mateo-berri) in [#35964](https://github.com/BerriAI/litellm/pull/35964) - fix(proxy): give proxy\_admin\_viewer read parity with proxy\_admin by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35851](https://github.com/BerriAI/litellm/pull/35851) - refactor(ui): address UI lint budget issues by refactoring UI by [@tin-berri](https://github.com/tin-berri) in [#35960](https://github.com/BerriAI/litellm/pull/35960) - fix(ci): make the env-key doc gate see get\_secret\_bool reads by [@yassin-berriai](https://github.com/yassin-berriai) in [#35833](https://github.com/BerriAI/litellm/pull/35833) - fix(caching): re-land evicted LLM client closing ([#35492](https://github.com/BerriAI/litellm/issues/35492)) atop self-healing handlers by [@mateo-berri](https://github.com/mateo-berri) in [#35870](https://github.com/BerriAI/litellm/pull/35870) - fix(proxy): keep the connected DB client when a startup health check fails by [@yassin-berriai](https://github.com/yassin-berriai) in [#35837](https://github.com/BerriAI/litellm/pull/35837) - chore(lint): remove litellm/types from the ruff lint exclusion by [@mateo-berri](https://github.com/mateo-berri) in [#35926](https://github.com/BerriAI/litellm/pull/35926) - feat(sgr): make the gateway middleware the source of truth for successful requests by [@yassin-berriai](https://github.com/yassin-berriai) in [#35717](https://github.com/BerriAI/litellm/pull/35717) - feat(auto-router): let operators replace the LLM classifier's system prompt by [@akapur99](https://github.com/akapur99) in [#35855](https://github.com/BerriAI/litellm/pull/35855) - fix(docker): bake the pip image's prisma engines at a world-readable path by [@yassin-berriai](https://github.com/yassin-berriai) in [#35976](https://github.com/BerriAI/litellm/pull/35976) - fix(auth): return 403 from the OAuth2 enterprise gate by [@yassin-berriai](https://github.com/yassin-berriai) in [#35838](https://github.com/BerriAI/litellm/pull/35838) - fix(router): keep custom model\_info across a price data reload by [@yassin-berriai](https://github.com/yassin-berriai) in [#35491](https://github.com/BerriAI/litellm/pull/35491) - fix(proxy): resolve pass-through credentials live from router deployments by [@mateo-berri](https://github.com/mateo-berri) in [#35916](https://github.com/BerriAI/litellm/pull/35916) - fix(ci): fetch only head and merge-base in lint jobs instead of every branch by [@mateo-berri](https://github.com/mateo-berri) in [#35982](https://github.com/BerriAI/litellm/pull/35982) - fix(autorouter): match CJK keyword\_tier\_rules that regex word boundaries miss by [@akapur99](https://github.com/akapur99) in [#35984](https://github.com/BerriAI/litellm/pull/35984) - feat(spend): rebuild the auto-router benchmarks backend as a per-session rollup by [@tin-berri](https://github.com/tin-berri) in [#35910](https://github.com/BerriAI/litellm/pull/35910) - refactor(ui): replace hand-rolled query-param routing with nuqs by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35871](https://github.com/BerriAI/litellm/pull/35871) - fix(docker): bake the componentized prisma engines at /opt/prisma so any uid can start by [@yassin-berriai](https://github.com/yassin-berriai) in [#35989](https://github.com/BerriAI/litellm/pull/35989) - fix(migrations): keep the toolchain heal from raising on an unreadable nodeenv cache by [@yassin-berriai](https://github.com/yassin-berriai) in [#35986](https://github.com/BerriAI/litellm/pull/35986) - fix(bedrock): sign Bedrock managed-file S3 requests with S3SigV4Auth by [@yassin-berriai](https://github.com/yassin-berriai) in [#35983](https://github.com/BerriAI/litellm/pull/35983) - chore(typing): replace Any seams with real types across responses, proxy, and provider adapters by [@mateo-berri](https://github.com/mateo-berri) in [#35809](https://github.com/BerriAI/litellm/pull/35809) - fix(ai21): resolve the documented AI21\_API\_KEY instead of a misspelled name by [@yassin-berriai](https://github.com/yassin-berriai) in [#35985](https://github.com/BerriAI/litellm/pull/35985) - fix(docker): fail the image build when the generated prisma engine paths drift off /opt/prisma by [@yassin-berriai](https://github.com/yassin-berriai) in [#35979](https://github.com/BerriAI/litellm/pull/35979) - fix(jina\_ai): resolve the documented JINA\_API\_KEY as a fallback by [@yassin-berriai](https://github.com/yassin-berriai) in [#35992](https://github.com/BerriAI/litellm/pull/35992) - fix(proxy): only treat a recoverable database outage as grounds to serve without one by [@yassin-berriai](https://github.com/yassin-berriai) in [#35864](https://github.com/BerriAI/litellm/pull/35864) - fix(ci): make every remaining CI checkout shallow by [@mateo-berri](https://github.com/mateo-berri) in [#35997](https://github.com/BerriAI/litellm/pull/35997) - fix(auto-router): stop the embedding model's context window from failing long requests by [@akapur99](https://github.com/akapur99) in [#35956](https://github.com/BerriAI/litellm/pull/35956) - fix(ci): make the env-key doc gate see bare get\_secret and get\_secret\_str reads by [@yassin-berriai](https://github.com/yassin-berriai) in [#35996](https://github.com/BerriAI/litellm/pull/35996) - fix(logging): extend secret redaction to records litellm does not emit directly by [@yassin-berriai](https://github.com/yassin-berriai) in [#35977](https://github.com/BerriAI/litellm/pull/35977) - test(utils): pin the register\_model replay test to the recorded half by [@yassin-berriai](https://github.com/yassin-berriai) in [#35994](https://github.com/BerriAI/litellm/pull/35994) - fix(ci): run every helm test suite, not just the first one per file by [@yassin-berriai](https://github.com/yassin-berriai) in [#35993](https://github.com/BerriAI/litellm/pull/35993) - ci: fail the build when a test file or Dockerfile is invoked by no job by [@yassin-berriai](https://github.com/yassin-berriai) in [#35991](https://github.com/BerriAI/litellm/pull/35991) - fix(langfuse): stop a collected httpx handler from closing a shared client by [@yassin-berriai](https://github.com/yassin-berriai) in [#35981](https://github.com/BerriAI/litellm/pull/35981) - fix(bedrock): grant bedrock:CountTokens in OIDC session policy by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#33145](https://github.com/BerriAI/litellm/pull/33145) - feat(pre-commit): save full lint output to a per-worktree log file by [@mateo-berri](https://github.com/mateo-berri) in [#36004](https://github.com/BerriAI/litellm/pull/36004) - feat(ui): match auto-router preset models against deployments' underlying model IDs by [@tin-berri](https://github.com/tin-berri) in [#35972](https://github.com/BerriAI/litellm/pull/35972) - fix(core\_helpers): map generic 'error' finish\_reason to 'stop' by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#33972](https://github.com/BerriAI/litellm/pull/33972) - fix(proxy)!: apply request-parameter checks consistently across body, path and form inputs by [@yuneng-berri](https://github.com/yuneng-berri) in [#36011](https://github.com/BerriAI/litellm/pull/36011) - fix: rebuild models\_by\_provider in add\_known\_models so cost map reloads reach wildcard expansion by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36010](https://github.com/BerriAI/litellm/pull/36010) - feat(complexity\_router): report LLM classifier cost per request via routing\_decision and x-litellm-classifier-cost header by [@tin-berri](https://github.com/tin-berri) in [#36015](https://github.com/BerriAI/litellm/pull/36015) - fix(model-prices): correct replicate model key typo by [@AkashNaickar](https://github.com/AkashNaickar) in [#34800](https://github.com/BerriAI/litellm/pull/34800) - fix(proxy): register managed batch output files on terminal retrieve by [@Souravrajvi0](https://github.com/Souravrajvi0) in [#34092](https://github.com/BerriAI/litellm/pull/34092) - perf(pre-commit): fetch basedpyright base counts from CI artifacts by [@mateo-berri](https://github.com/mateo-berri) in [#35970](https://github.com/BerriAI/litellm/pull/35970) - fix(ui): sync projects list page index to ?page= so back and reload keep the page by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36003](https://github.com/BerriAI/litellm/pull/36003) - fix(ui): link project page keys to their virtual key detail by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36002](https://github.com/BerriAI/litellm/pull/36002) - refactor(ui): drop unreferenced locals from dashboard route components by [@yuneng-berri](https://github.com/yuneng-berri) in [#35819](https://github.com/BerriAI/litellm/pull/35819) - fix(ui): opening a project now pushes ?project= so back and deep links work by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36001](https://github.com/BerriAI/litellm/pull/36001) - refactor(ui): drop unreferenced locals from shared dashboard components by [@yuneng-berri](https://github.com/yuneng-berri) in [#35821](https://github.com/BerriAI/litellm/pull/35821) - refactor(ui): drop unreferenced locals from tests and narrow destructures by [@yuneng-berri](https://github.com/yuneng-berri) in [#36025](https://github.com/BerriAI/litellm/pull/36025) - fix(guardrails): allow litellm\_content\_filter to run on post\_mcp\_call by [@mateo-berri](https://github.com/mateo-berri) in [#35980](https://github.com/BerriAI/litellm/pull/35980) - fix(guardrails): scan /v1/messages tool traffic by [@mateo-berri](https://github.com/mateo-berri) in [#35999](https://github.com/BerriAI/litellm/pull/35999) - refactor(ui): drop dead locals and unused React state across the dashboard by [@yuneng-berri](https://github.com/yuneng-berri) in [#36026](https://github.com/BerriAI/litellm/pull/36026) - feat(ui): add the auto-router usage tab to cost optimization by [@tin-berri](https://github.com/tin-berri) in [#35995](https://github.com/BerriAI/litellm/pull/35995) - fix(managed\_files): derive unified output file ids deterministically so concurrent registrations converge by [@mateo-berri](https://github.com/mateo-berri) in [#36019](https://github.com/BerriAI/litellm/pull/36019) - fix(proxy): send keepalive pings on anthropic messages SSE streams during upstream silence by [@mateo-berri](https://github.com/mateo-berri) in [#36024](https://github.com/BerriAI/litellm/pull/36024) - fix(managed\_files): return unified ids from unscoped file listing by [@mateo-berri](https://github.com/mateo-berri) in [#36031](https://github.com/BerriAI/litellm/pull/36031) - fix(arize\_phoenix): lowercase OTLP/gRPC auth metadata key by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34883](https://github.com/BerriAI/litellm/pull/34883) - fix(auto-router): accept every reminder marker pair a harness emits by [@tin-berri](https://github.com/tin-berri) in [#36029](https://github.com/BerriAI/litellm/pull/36029) - fix(pricing): sync flex/priority tier keys to dated OpenAI snapshot variants by [@mateo-berri](https://github.com/mateo-berri) in [#35923](https://github.com/BerriAI/litellm/pull/35923) - fix(cost): bill reasoning tokens at the service tier output rate by [@mateo-berri](https://github.com/mateo-berri) in [#35925](https://github.com/BerriAI/litellm/pull/35925) - fix(proxy): include today's UTC bucket when a daily activity range ends at the caller's current day by [@tin-berri](https://github.com/tin-berri) in [#36051](https://github.com/BerriAI/litellm/pull/36051) - fix: expired-miss share over all measured turns + cost-optimization tab labels by [@tin-berri](https://github.com/tin-berri) in [#36037](https://github.com/BerriAI/litellm/pull/36037) - fix(router): include Bedrock batch/S3 fields and model in deployment credentials by [@mpcusack-altos](https://github.com/mpcusack-altos) in [#24548](https://github.com/BerriAI/litellm/pull/24548) - fix(batch): track cost for managed batches with no attributable key/u… by [@elinacse](https://github.com/elinacse) in [#35468](https://github.com/BerriAI/litellm/pull/35468) - feat(guardrails): add scan\_only\_tool\_results to scope unified guardrails to tool results by [@mateo-berri](https://github.com/mateo-berri) in [#36014](https://github.com/BerriAI/litellm/pull/36014) - fix(cost): stop token-pricing the placeholder input on file content calls by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35140](https://github.com/BerriAI/litellm/pull/35140) - fix(proxy): fetch background responses through the router in CheckResponsesCost by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35137](https://github.com/BerriAI/litellm/pull/35137) - fix(proxy): yaml store\_prompts\_in\_spend\_logs should take precedence over DB cached value by [@Praveena-617](https://github.com/Praveena-617) in [#35769](https://github.com/BerriAI/litellm/pull/35769) - fix(lint): measure the basedpyright budget gate in a gate-owned venv by [@mateo-berri](https://github.com/mateo-berri) in [#36050](https://github.com/BerriAI/litellm/pull/36050) - docs: cap all GitHub comments at 15-25 words, curb semicolon splices by [@mateo-berri](https://github.com/mateo-berri) in [#36059](https://github.com/BerriAI/litellm/pull/36059) - chore(lint): name MappingProxyType in the mutable-collection fix messages by [@mateo-berri](https://github.com/mateo-berri) in [#36072](https://github.com/BerriAI/litellm/pull/36072) - test: roll back runtime model registrations between tests by [@mateo-berri](https://github.com/mateo-berri) in [#36039](https://github.com/BerriAI/litellm/pull/36039) - refactor(types): cut 653 implicit and explicit Any diagnostics across 11 modules by [@mateo-berri](https://github.com/mateo-berri) in [#36054](https://github.com/BerriAI/litellm/pull/36054) - fix(proxy): stop resolving the UI session sentinel team on /search\_tools/list by [@yuneng-berri](https://github.com/yuneng-berri) in [#36061](https://github.com/BerriAI/litellm/pull/36061) - fix(batches): persist managed file ids for cancelled/failed/expired batches by [@mateo-berri](https://github.com/mateo-berri) in [#36048](https://github.com/BerriAI/litellm/pull/36048) - fix(batches): register managed output files on batch cancel by [@mateo-berri](https://github.com/mateo-berri) in [#36034](https://github.com/BerriAI/litellm/pull/36034) - fix(proxy): allow non-admins to reach /user/daily/activity/aggregated by [@yuneng-berri](https://github.com/yuneng-berri) in [#36062](https://github.com/BerriAI/litellm/pull/36062) - fix(anthropic): coerce explicit additionalProperties to false in output\_format schema by [@dkindlund](https://github.com/dkindlund) in [#35811](https://github.com/BerriAI/litellm/pull/35811) - fix(batches): prevent managed file fallbacks by [@rimysore](https://github.com/rimysore) in [#35371](https://github.com/BerriAI/litellm/pull/35371) - chore: ignore the mechanical lint and typing sweeps in git blame by [@mateo-berri](https://github.com/mateo-berri) in [#36076](https://github.com/BerriAI/litellm/pull/36076) - fix(proxy): warn at startup when max\_budget is set but no database is connected by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36041](https://github.com/BerriAI/litellm/pull/36041) - fix(proxy): promote caller metadata trace fields into litellm\_metadata by [@yucheng-berri](https://github.com/yucheng-berri) in [#35866](https://github.com/BerriAI/litellm/pull/35866) - feat(terraform): sync provider 0.3.0 from the mirror and cut 0.4.0 by [@yuneng-berri](https://github.com/yuneng-berri) in [#36098](https://github.com/BerriAI/litellm/pull/36098) - fix(guardrails): honor configured timeout in Zscaler AI Guard by [@yucheng-berri](https://github.com/yucheng-berri) in [#36110](https://github.com/BerriAI/litellm/pull/36110) - fix(logging): fall back to litellm\_metadata when metadata is empty by [@yucheng-berri](https://github.com/yucheng-berri) in [#36105](https://github.com/BerriAI/litellm/pull/36105) - fix(proxy): re-assert the authenticated identity on passthrough requests by [@yucheng-berri](https://github.com/yucheng-berri) in [#36121](https://github.com/BerriAI/litellm/pull/36121) - chore: bump litellm-enterprise 0.1.53 -> 0.1.54, litellm-proxy-extras 0.4.83 -> 0.4.84 by [@yuneng-berri](https://github.com/yuneng-berri) in [#36139](https://github.com/BerriAI/litellm/pull/36139) - fix(ui): match auto-router preset models against wildcard-expanded model groups by [@tin-berri](https://github.com/tin-berri) in [#36111](https://github.com/BerriAI/litellm/pull/36111) - test(router): assert the auto-router max\_input\_chars kwarg by [@yuneng-berri](https://github.com/yuneng-berri) in [#36109](https://github.com/BerriAI/litellm/pull/36109) - fix(ui): allow clearing a key's budget reset from the Edit Key form by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36140](https://github.com/BerriAI/litellm/pull/36140) - fix(managed\_files): skip unparseable rows when listing managed files by [@mateo-berri](https://github.com/mateo-berri) in [#36021](https://github.com/BerriAI/litellm/pull/36021) - fix(a2a): stop writing per-caller headers onto the shared cached httpx client by [@yassin-berriai](https://github.com/yassin-berriai) in [#35978](https://github.com/BerriAI/litellm/pull/35978) - build(deps): bump h2 to 4.4.1 and js-yaml to 4.3.1 by [@yuneng-berri](https://github.com/yuneng-berri) in [#36147](https://github.com/BerriAI/litellm/pull/36147) - chore: promote staging to main by [@mateo-berri](https://github.com/mateo-berri) in [#36057](https://github.com/BerriAI/litellm/pull/36057) - fix(azure\_sentinel): respect AZURE\_AUTHORITY\_HOST and derive the Azure Monitor audience per cloud by [@yucheng-berri](https://github.com/yucheng-berri) in [#36137](https://github.com/BerriAI/litellm/pull/36137) - fix(bedrock): pass SSE-KMS key through to the batch input-file S3 upload by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35148](https://github.com/BerriAI/litellm/pull/35148) - fix(anthropic adapter): stop indexing choices\[0] on choiceless streaming chunks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35314](https://github.com/BerriAI/litellm/pull/35314) - fix(bedrock): normalize /v1/completions and /v1/responses batch records by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35675](https://github.com/BerriAI/litellm/pull/35675) - fix(proxy): return the real status code when a credential update is rejected by [@yucheng-berri](https://github.com/yucheng-berri) in [#36166](https://github.com/BerriAI/litellm/pull/36166) - fix(proxy): improve Headroom /v1/compress HTTP 404 diagnostics by [@aayush598](https://github.com/aayush598) in [#35952](https://github.com/BerriAI/litellm/pull/35952) - fix(proxy): invalidate cached project object on project update and delete by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36028](https://github.com/BerriAI/litellm/pull/36028) - feat(proxy): add apply\_user\_budget\_to\_team\_keys opt-in by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36102](https://github.com/BerriAI/litellm/pull/36102) - fix(proxy): stop alerting on health probes that lose the planned engine-restart race by [@yassin-berriai](https://github.com/yassin-berriai) in [#36141](https://github.com/BerriAI/litellm/pull/36141) - test(docker): gate the componentized gateway and backend images on an arbitrary-uid offline boot by [@yassin-berriai](https://github.com/yassin-berriai) in [#36136](https://github.com/BerriAI/litellm/pull/36136) - fix(http): stop pooled clients persisting cookies on the aiohttp jar too by [@yassin-berriai](https://github.com/yassin-berriai) in [#36149](https://github.com/BerriAI/litellm/pull/36149) - fix(router): bound fallback-walk work and error-log volume by [@yassin-berriai](https://github.com/yassin-berriai) in [#36148](https://github.com/BerriAI/litellm/pull/36148) - ci: wire credential\_endpoints tests into the proxy endpoints job by [@cursor](https://github.com/cursor)\[bot] in [#36187](https://github.com/BerriAI/litellm/pull/36187) - docs(keys): document /key/info fields and clarify budget\_reset\_at is the next reset by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36127](https://github.com/BerriAI/litellm/pull/36127) - fix(azure\_sentinel): add AZURE\_SENTINEL\_AUTHORITY\_HOST as a Sentinel scoped override by [@yucheng-berri](https://github.com/yucheng-berri) in [#36165](https://github.com/BerriAI/litellm/pull/36165) - docs(pr-template): add a User Flow section with authoring instructions by [@mateo-berri](https://github.com/mateo-berri) in [#36162](https://github.com/BerriAI/litellm/pull/36162) - fix(proxy): derive config agent ids from agent\_name so grants survive secret rotation by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36020](https://github.com/BerriAI/litellm/pull/36020) - chore(ui): regenerate schema.d.ts for the /key/info docstring update by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36210](https://github.com/BerriAI/litellm/pull/36210) - build(deps): bump gitpython to 3.1.58 to clear osv-scan on staging by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36212](https://github.com/BerriAI/litellm/pull/36212) - fix(proxy): deny agent access when key and team grants resolve to nothing by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36221](https://github.com/BerriAI/litellm/pull/36221) - build(deps): defer the second pypdf advisory until the 6.15.0 bump by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36218](https://github.com/BerriAI/litellm/pull/36218) - fix(a2a): align agent list annotation and test with the tuple return type by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36217](https://github.com/BerriAI/litellm/pull/36217) - ci: always run the UI API types sync check so it can be required by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36213](https://github.com/BerriAI/litellm/pull/36213) - build(deps): bump nanoid to 3.3.17 in the dashboard lockfile by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36227](https://github.com/BerriAI/litellm/pull/36227) - feat(ui): show user email or alias in usage data export by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36232](https://github.com/BerriAI/litellm/pull/36232) - feat(auto-router): track turns per complexity tier (LIT-5302) by [@tin-berri](https://github.com/tin-berri) in [#36209](https://github.com/BerriAI/litellm/pull/36209) - fix(websearch): restore snippet text in native web\_search\_tool\_result blocks (LIT-5315) by [@tin-berri](https://github.com/tin-berri) in [#36228](https://github.com/BerriAI/litellm/pull/36228) - fix(proxy): resolve entity access groups in the model listing endpoints by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36230](https://github.com/BerriAI/litellm/pull/36230) - fix(ui): let access groups be a team's only model source, with hover provenance by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#36234](https://github.com/BerriAI/litellm/pull/36234) - fix(managed\_files): return unified output file ids from GET /batches by [@mateo-berri](https://github.com/mateo-berri) in [#36049](https://github.com/BerriAI/litellm/pull/36049) - test(proxy): compare empty agent list to the tuple get\_agent\_list returns by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36225](https://github.com/BerriAI/litellm/pull/36225) - fix(otel): name the RPC system and upstream on MCP tool-call spans by [@yucheng-berri](https://github.com/yucheng-berri) in [#35857](https://github.com/BerriAI/litellm/pull/35857) - fix(guardrails): chunk oversized Bedrock ApplyGuardrail requests instead of failing by [@yucheng-berri](https://github.com/yucheng-berri) in [#36119](https://github.com/BerriAI/litellm/pull/36119) - test(e2e): settle control-plane writes across every replica, not just one by [@yuneng-berri](https://github.com/yuneng-berri) in [#36247](https://github.com/BerriAI/litellm/pull/36247) - fix(responses): forward allowed\_openai\_params through the chat completions bridge by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35885](https://github.com/BerriAI/litellm/pull/35885) - test(proxy): assert the copy \_add\_team\_member\_budget\_table returns by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36244](https://github.com/BerriAI/litellm/pull/36244) - chore(ui): regenerate dashboard api types for tier\_turns by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36243](https://github.com/BerriAI/litellm/pull/36243) - refactor(types): declare mirrored pricing fields on ModelInfo by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36215](https://github.com/BerriAI/litellm/pull/36215) - fix(lint): make strict-gate noqas survive base ruff and flag stale ones by [@mateo-berri](https://github.com/mateo-berri) in [#36257](https://github.com/BerriAI/litellm/pull/36257) - fix(vertex\_ai): surface real error/status on vertex batch create instead of IndexError 500 by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35141](https://github.com/BerriAI/litellm/pull/35141) - ci: give the remaining pull\_request workflows a concurrency group by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36252](https://github.com/BerriAI/litellm/pull/36252) - refactor(lint): graduate zero-violation strict rules and guard the budget ratchet by [@mateo-berri](https://github.com/mateo-berri) in [#36161](https://github.com/BerriAI/litellm/pull/36161) - fix(proxy): enforce require\_managed\_files on every route that accepts a raw provider id by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35551](https://github.com/BerriAI/litellm/pull/35551) - chore(typing): clear 1.4k basedpyright Any errors across 21 hotspot files by [@mateo-berri](https://github.com/mateo-berri) in [#36282](https://github.com/BerriAI/litellm/pull/36282) - test: roll back live router replay membership between tests by [@mateo-berri](https://github.com/mateo-berri) in [#36278](https://github.com/BerriAI/litellm/pull/36278) - chore(ci): sync main into internal staging by [@yuneng-berri](https://github.com/yuneng-berri) in [#36288](https://github.com/BerriAI/litellm/pull/36288) - build(lint): rename make pre-commit to make check with a working-tree fallback by [@mateo-berri](https://github.com/mateo-berri) in [#36277](https://github.com/BerriAI/litellm/pull/36277) - fix(ui): show team BYOK models in team fallback settings by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36241](https://github.com/BerriAI/litellm/pull/36241) - fix(otel): mark v2 server spans as failed for pre-call errors by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34546](https://github.com/BerriAI/litellm/pull/34546) - fix(websearch\_interception): bill intercepted searches to the calling key by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35708](https://github.com/BerriAI/litellm/pull/35708) - chore: remove pre-commit rule by [@mateo-berri](https://github.com/mateo-berri) in [#36295](https://github.com/BerriAI/litellm/pull/36295) - docs: clarify guideline priority ordering in CLAUDE.md by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36296](https://github.com/BerriAI/litellm/pull/36296) - feat(router): independent, default-on deployment affinity for the auto-router by [@tin-berri](https://github.com/tin-berri) in [#36146](https://github.com/BerriAI/litellm/pull/36146) - test: repair stale CircleCI contracts by [@yuneng-berri](https://github.com/yuneng-berri) in [#36293](https://github.com/BerriAI/litellm/pull/36293) - chore(ci): promote internal staging to main by [@yuneng-berri](https://github.com/yuneng-berri) in [#36286](https://github.com/BerriAI/litellm/pull/36286) - chore: rebuild Admin UI bundle for the 2026-08-08 release by [@yuneng-berri](https://github.com/yuneng-berri) in [#36297](https://github.com/BerriAI/litellm/pull/36297) - chore(ci): promote internal staging to main by [@yuneng-berri](https://github.com/yuneng-berri) in [#36304](https://github.com/BerriAI/litellm/pull/36304) ##### New Contributors - [@rimysore](https://github.com/rimysore) made their first contribution in [#35367](https://github.com/BerriAI/litellm/pull/35367) - [@AkashNaickar](https://github.com/AkashNaickar) made their first contribution in [#34800](https://github.com/BerriAI/litellm/pull/34800) - [@Souravrajvi0](https://github.com/Souravrajvi0) made their first contribution in [#34092](https://github.com/BerriAI/litellm/pull/34092) - [@elinacse](https://github.com/elinacse) made their first contribution in [#35468](https://github.com/BerriAI/litellm/pull/35468) - [@aayush598](https://github.com/aayush598) made their first contribution in [#35952](https://github.com/BerriAI/litellm/pull/35952) - [@cursor](https://github.com/cursor)\[bot] made their first contribution in [#36187](https://github.com/BerriAI/litellm/pull/36187) **Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.96.0...v1.97.0> ### [`v1.97.0`](https://github.com/BerriAI/litellm/releases/tag/v1.97.0) [Compare Source](https://github.com/BerriAI/litellm/compare/v1.96.2...v1.97.0) ##### 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:v1.97.0 ``` **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/v1.97.0/cosign.pub \ ghcr.io/berriai/litellm:v1.97.0 ``` 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 - feat(proxy): resolve Cursor thinking/fast model-name suffixes on /cursor/chat/completions by [@mateo-berri](https://github.com/mateo-berri) in [#35554](https://github.com/BerriAI/litellm/pull/35554) - fix(team-callbacks): actually stop logging when disable\_logging is called by [@yucheng-berri](https://github.com/yucheng-berri) in [#35520](https://github.com/BerriAI/litellm/pull/35520) - refactor(lint): drop redundant !s f-string conversion flags and fix displaced import-group comments by [@mateo-berri](https://github.com/mateo-berri) in [#35546](https://github.com/BerriAI/litellm/pull/35546) - fix(proxy): backfill null user\_email on existing users during JWT auth by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34588](https://github.com/BerriAI/litellm/pull/34588) - feat(playground): add non-streaming response toggle by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35560](https://github.com/BerriAI/litellm/pull/35560) - feat(teams): apply default organization to new teams from default team settings by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35540](https://github.com/BerriAI/litellm/pull/35540) - fix(ui): block Playground page for viewer roles on direct URL access by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35676](https://github.com/BerriAI/litellm/pull/35676) - fix(caching): close evicted LLM clients so their connections are reclaimed by [@yassin-berriai](https://github.com/yassin-berriai) in [#35492](https://github.com/BerriAI/litellm/pull/35492) - chore(deps): update brace-expansion, postcss, and gitpython to current patch releases by [@yuneng-berri](https://github.com/yuneng-berri) in [#35692](https://github.com/BerriAI/litellm/pull/35692) - refactor(ui): rename the create MCP server component to PascalCase by [@yuneng-berri](https://github.com/yuneng-berri) in [#35686](https://github.com/BerriAI/litellm/pull/35686) - fix(openai): drop undefined Union from owns\_wrapped\_http\_client annotation by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35706](https://github.com/BerriAI/litellm/pull/35706) - fix(openai): drop the undefined Union from owns\_wrapped\_http\_client by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35704](https://github.com/BerriAI/litellm/pull/35704) - chore(ui): note Google's Agent Platform rename in vector store setup by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#28076](https://github.com/BerriAI/litellm/pull/28076) - fix(proxy): apply key/team router\_settings.model\_group\_alias by [@yassin-berriai](https://github.com/yassin-berriai) in [#35486](https://github.com/BerriAI/litellm/pull/35486) - feat(complexity\_router): default session affinity off and expose it in the UI by [@tin-berri](https://github.com/tin-berri) in [#35714](https://github.com/BerriAI/litellm/pull/35714) - fix(datadog): read team callback dd\_\* params from kwargs instead of blocked dynamic params ([#35115](https://github.com/BerriAI/litellm/issues/35115) port) by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35687](https://github.com/BerriAI/litellm/pull/35687) - refactor(ui): extract the MCP create form's logic and field groups by [@yuneng-berri](https://github.com/yuneng-berri) in [#35694](https://github.com/BerriAI/litellm/pull/35694) - test(ui): tier the MCP create tests into unit and integration by [@yuneng-berri](https://github.com/yuneng-berri) in [#35697](https://github.com/BerriAI/litellm/pull/35697) - fix(proxy): redact credential headers from request logging copies by [@yucheng-berri](https://github.com/yucheng-berri) in [#35678](https://github.com/BerriAI/litellm/pull/35678) - feat(guardrails/rubrik): prompt moderation, response-text blocking, streaming buffer, failure logging by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35722](https://github.com/BerriAI/litellm/pull/35722) - fix(ui): render Responses API request and response in the logs drawer by [@yuneng-berri](https://github.com/yuneng-berri) in [#35718](https://github.com/BerriAI/litellm/pull/35718) - fix(ui): hide guardrail review buttons from non-admin users by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#27535](https://github.com/BerriAI/litellm/pull/27535) - feat(team): custom metadata validation hook for team create and update by [@yuneng-berri](https://github.com/yuneng-berri) in [#33353](https://github.com/BerriAI/litellm/pull/33353) - ci(circleci): install a pinned Rust toolchain on the Linux jobs by [@yuneng-berri](https://github.com/yuneng-berri) in [#35519](https://github.com/BerriAI/litellm/pull/35519) - fix(bedrock): stop forwarding no-op toolSpec.strict to Converse by [@tin-berri](https://github.com/tin-berri) in [#35688](https://github.com/BerriAI/litellm/pull/35688) - fix(ui): reject an auto-router keyword rule left empty instead of dropping it by [@tin-berri](https://github.com/tin-berri) in [#35705](https://github.com/BerriAI/litellm/pull/35705) - fix(guardrails/rubrik): attribute blocked requests to the caller that made them by [@yucheng-berri](https://github.com/yucheng-berri) in [#35734](https://github.com/BerriAI/litellm/pull/35734) - fix(responses): forward client headers to the provider on /v1/responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34531](https://github.com/BerriAI/litellm/pull/34531) - feat(spend): add net auto-router savings to the cost-optimization dashboard by [@tin-berri](https://github.com/tin-berri) in [#35521](https://github.com/BerriAI/litellm/pull/35521) - chore(typing): clear basedpyright Any errors in budget reset, access groups, and cache settings by [@mateo-berri](https://github.com/mateo-berri) in [#35719](https://github.com/BerriAI/litellm/pull/35719) - fix(spend): read what a request cost from the record instead of pricing it again by [@tin-berri](https://github.com/tin-berri) in [#35736](https://github.com/BerriAI/litellm/pull/35736) - perf: install hiredis so redis-py parses replies with its C parser by [@Classic298](https://github.com/Classic298) in [#35709](https://github.com/BerriAI/litellm/pull/35709) - feat(ui): show auto-router savings on the cost-optimization dashboard by [@tin-berri](https://github.com/tin-berri) in [#35522](https://github.com/BerriAI/litellm/pull/35522) - perf: build log messages lazily so filtered-out log records cost nothing by [@Classic298](https://github.com/Classic298) in [#35703](https://github.com/BerriAI/litellm/pull/35703) - fix(proxy): retry model cost map fetch with Retry-After-aware backoff and keep current map on reload failure by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#35739](https://github.com/BerriAI/litellm/pull/35739) - feat(otel): stamp service tier attributes on inference spans by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35679](https://github.com/BerriAI/litellm/pull/35679) - fix(proxy): log the model cost map reload failure lazily by [@tin-berri](https://github.com/tin-berri) in [#35750](https://github.com/BerriAI/litellm/pull/35750) - fix(groq): translate web\_search\_options to the browser\_search tool by [@hMED22](https://github.com/hMED22) in [#34971](https://github.com/BerriAI/litellm/pull/34971) - feat(ui): add admin-configurable user banner by [@yuneng-berri](https://github.com/yuneng-berri) in [#35729](https://github.com/BerriAI/litellm/pull/35729) - fix(e2e): make spend-counter redis connection env-driven for non-cluster deployments by [@yuneng-berri](https://github.com/yuneng-berri) in [#35732](https://github.com/BerriAI/litellm/pull/35732) - fix(proxy): make /cursor/chat/completions work with Cursor agent mode by [@tin-berri](https://github.com/tin-berri) in [#34029](https://github.com/BerriAI/litellm/pull/34029) - fix(proxy): propagate user\_email and bind api\_key on JWT auth attribution paths by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34331](https://github.com/BerriAI/litellm/pull/34331) - chore(build): move the Admin UI toolchain to Node 24 by [@yuneng-berri](https://g…

mubashir1osmani and others added 30 commits July 30, 2026 16:06

ci: add fork GHCR publish workflow for Concourse releases

ea47226

Merge pull request #11 from mubashir1osmani/litellm_concourse_ghcr_re…

e25a7a6

…lease ci: add fork GHCR publish workflow for Concourse releases

Merge branch 'BerriAI:litellm_internal_staging' into litellm_internal…

405b228

…_staging

chore: drop fork-only GHCR publish workflow from this branch

0de901a

That workflow is fork-local for Concourse and does not belong in the Azure pricing PR against BerriAI staging

feat(spend): add caller-scoped key/user/team/organization spend repor…

722d9ff

…t endpoints

fix(spend): scope org report team fallback to unstamped rows and boun…

26ffb5d

…d report date ranges

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

60259d7

…itellm_/spend-reports-implementation-25a080

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

5b61e80

…itellm_budget_reset_uow

perf(streaming): assemble streamed tool-call arguments in linear time

fb16749

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

560a4ac

…itellm_/elated-margulis-7f300f

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

9b972a4

…itellm_budget_reset_uow # Conflicts: # litellm/proxy/common_utils/reset_budget_job.py

fix(proxy): enforce per-model budgets against resolved cursor model v…

1cd481d

…ariants

Merge pull request #35835 from BerriAI/litellm_/elated-margulis-7f300f

e4fd790

refactor(ui): route MCP session tokens through the shared storage helper

refactor(proxy): make the cursor responses-path body single-assignment

334e104

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

a28f7be

…itellm_/cci-failing-tests-f73740

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

48b7620

…itellm_/terraform-provider-dep-bump-5feb4a

Merge pull request #35834 from BerriAI/litellm_fix_cursor_variant_bud…

1798d9d

…get_bypass fix(proxy): enforce per-model budgets against resolved cursor model variants

perf(streaming): group tool-call fragments once instead of rescanning…

1dad337

… per index

yuneng-berri and others added 3 commits August 4, 2026 18:40

test(e2e): skip view-backed global spend probes pending LIT-5211

e56a6ca

bump: litellm-proxy-extras 0.4.82 -> 0.4.83

6a0dcf1

yuneng-berri requested a review from ryan-crabbe-berri as a code owner August 5, 2026 01:45

tin-berri approved these changes Aug 5, 2026

View reviewed changes

greptile-apps Bot reviewed Aug 5, 2026

View reviewed changes

ryan-crabbe-berri approved these changes Aug 5, 2026

View reviewed changes

mateo-berri and others added 11 commits August 4, 2026 18:56

Merge pull request #35868 from BerriAI/litellm_gate_merge_head_base

727812b

fix(lint): pick the merge-aware base so in-progress merges are not blamed for base drift

Merge pull request #35877 from BerriAI/litellm_bump_proxy_extras_0_4_83

420d9a7

chore: bump litellm-proxy-extras 0.4.82 -> 0.4.83

revert: "test(e2e): vendor API strategy coverage across endpoints (#3…

472dd27

…4649)" This reverts commit dcb4e50. The suites landed without the proof-of-fix and QA runbook the PR body itself flagged as outstanding, so the coverage they claim is unverified against a live proxy

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

a920870

…itellm_/revert-pr-34649-9f1755

fix(ui): derive auto-router preset tests from the bundled preset JSON

337d5a1

The template tests hardcoded the model names the presets happened to ship with, so editing autorouter_presets.json to name newer models turned every preset red in the fixtures and hung six waitFor calls

Merge remote-tracking branch 'origin/litellm_internal_staging' into l…

5bf9246

…itellm_gate_owns_basedpyright_heap

Merge pull request #35882 from BerriAI/litellm_fix_autorouter_preset_…

fa2d97f

…test_fixtures fix(ui): derive auto-router preset tests from the bundled preset JSON

Merge pull request #35881 from BerriAI/litellm_/revert-pr-34649-9f1755

1d39c5f

revert: "test(e2e): vendor API strategy coverage across endpoints" (#34649)

Merge pull request #35844 from BerriAI/litellm_/terraform-provider-de…

2e25519

…p-bump-5feb4a chore(deps): bump grpc and golang.org/x modules in the terraform provider

Merge pull request #35875 from BerriAI/litellm_/inspiring-franklin-05…

abcffa1

…8a96 test(e2e): skip view-backed global spend probes pending LIT-5211

veria-ai Bot reviewed Aug 5, 2026

View reviewed changes

yuneng-berri changed the title ~~chore(ci) promote internal staging to main~~ chore(ci): promote internal staging to main Aug 5, 2026

Merge pull request #35869 from BerriAI/litellm_gate_owns_basedpyright…

faf3c51

…_heap fix(lint): move the basedpyright heap flag into the type check gate

yuneng-berri merged commit ead6252 into main Aug 5, 2026
83 of 84 checks passed

veria-ai Bot reviewed Aug 5, 2026

View reviewed changes

Navigation Menu

Uh oh!

Uh oh!

chore(ci): promote internal staging to main - #35876

chore(ci): promote internal staging to main#35876
yuneng-berri merged 62 commits into
mainfrom
litellm_internal_staging

yuneng-berri commented Aug 5, 2026

Uh oh!

CLAassistant commented Aug 5, 2026 •

edited

Loading

Uh oh!

greptile-apps Bot commented Aug 5, 2026

Important Files Changed

Uh oh!

greptile-apps Bot Aug 5, 2026

Uh oh!

codecov Bot commented Aug 5, 2026 •

edited

Loading

Uh oh!

veria-ai Bot Aug 5, 2026

Uh oh!

veria-ai Bot commented Aug 5, 2026 •

edited

Loading

Uh oh!

Uh oh!

veria-ai Bot Aug 5, 2026

Uh oh!

codspeed-hq Bot commented Aug 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

Uh oh!

Uh oh!

Conversation

yuneng-berri commented Aug 5, 2026

TLDR

Relevant issues

Linear ticket

Pre-Submission checklist

Delays in PR merge?

Screenshots / Proof of Fix

Type

Changes

QA runbook

Final Attestation

Uh oh!

CLAassistant commented Aug 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

greptile-apps Bot commented Aug 5, 2026

Greptile Summary

Confidence Score: 4/5

Important Files Changed

Uh oh!

greptile-apps Bot Aug 5, 2026

Choose a reason for hiding this comment

Uh oh!

codecov Bot commented Aug 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

veria-ai Bot Aug 5, 2026

Choose a reason for hiding this comment

Uh oh!

veria-ai Bot commented Aug 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

PR overview

Open issues (2)

Uh oh!

Uh oh!

veria-ai Bot Aug 5, 2026

Choose a reason for hiding this comment

Uh oh!

codspeed-hq Bot commented Aug 5, 2026

Merging this PR will not alter performance

Footnotes

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

CLAassistant commented Aug 5, 2026 •

edited

Loading

codecov Bot commented Aug 5, 2026 •

edited

Loading

veria-ai Bot commented Aug 5, 2026 •

edited

Loading