LiteLLM v1.99.0-dev.2

Verify Docker Image Signature

All LiteLLM Docker images are signed with cosign. Every release is signed with the same key introduced in commit 0112e53.

Verify using the pinned commit hash (recommended):

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

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.99.0-dev.2

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:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.99.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.99.0-dev.2

Expected output:

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

---

What's Changed

• fix(proxy): log spend for OpenAI passthrough embeddings with unmapped models by @mateo-berri in https://github.com/BerriAI/litellm/pull/37425
• fix(router): keep acreate_file fallbacks inside the requested model group by @mateo-berri in https://github.com/BerriAI/litellm/pull/37424
• fix(proxy): record estimated input tokens in spend logs for failed dispatched requests by @mateo-berri in https://github.com/BerriAI/litellm/pull/37365
• fix: accept bool thinking param instead of crashing with AttributeError by @mateo-berri in https://github.com/BerriAI/litellm/pull/37423
• refactor(ui): migrate the teams form graph off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37417
• fix(ui): restore the cache control Role and Index field hints by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37437
• feat(ui): add mounted-field projections for the MCP server form graph by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37440
• refactor(ui): extract the MCP server edit save payload into a pure builder by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37436
• test: derive vertex batch cost expectation from the cost map by @mateo-berri in https://github.com/BerriAI/litellm/pull/37444
• refactor(ui): port the create key form off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37442
• refactor(ui): port the add model form off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37446
• refactor(ui): host KeyLifecycleSettings tests in react-hook-form instead of antd Form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37449
• fix(ui): rebuild nested and list paths in the mounted-field projection by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37450
• fix(ui): gate the pass-through guardrail field inputs when the section is disabled by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37435
• fix(tests): keep a host PROXY_BASE_URL out of request-derived URL tests by @mateo-berri in https://github.com/BerriAI/litellm/pull/37451
• refactor(ui): port the MCP server forms off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37483
• test(e2e): pin the tag-routing denial to its actual cause by @mateo-berri in https://github.com/BerriAI/litellm/pull/37432
• fix(proxy): read through to the DB on registry misses so just-created models, guardrails, and agents resolve on sibling replicas by @mateo-berri in https://github.com/BerriAI/litellm/pull/36263
• fix(mcp): forward the per-server auth header on OpenAPI tool calls by @tin-berri in https://github.com/BerriAI/litellm/pull/37410
• chore(typing): drop 1.3k basedpyright errors across 42 Any hotspot files by @mateo-berri in https://github.com/BerriAI/litellm/pull/37439
• test(ui): drive fields with change events where the typing is not the behaviour by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37495
• fix(ui): restore tab strip styling and panel persistence lost in the shadcn migration by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37403
• feat(spend-logs): add lifecycle timestamps by @sytianhe in https://github.com/BerriAI/litellm/pull/37361
• refactor(ui): migrate the antd Button call sites onto the shadcn Button by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37505
• test(ui): split the vitest suite into unit, component, integration and type projects by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37488
• refactor(ptu): give the rollup a source-agnostic deployment record by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37501
• feat(auto-router)!: scope shadow eval jobs to multiple keys by @tin-berri in https://github.com/BerriAI/litellm/pull/37251
• refactor(ui): migrate the antd Alert call sites onto the shared Alert by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37513
• chore(ui): upgrade the dashboard to React 19 by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37411
• fix(streaming): accept provider cost objects when propagating usage cost by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36593
• fix(complexity-router): gate the reasoning override on a non-SIMPLE score by @tin-berri in https://github.com/BerriAI/litellm/pull/37500
• fix(mcp): stop reporting failed OpenAPI tool calls as successes by @tin-berri in https://github.com/BerriAI/litellm/pull/37496
• feat(e2e): add record/replay transport seam and fixture bundle format by @mateo-berri in https://github.com/BerriAI/litellm/pull/37360
• fix(proxy): accept inherited model sentinels in project key limits by @mateo-berri in https://github.com/BerriAI/litellm/pull/37515
• fix(model_prices): add provider-announced deprecation_date to 205 registry entries by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37283
• fix(model_prices): correct gemini 3.1 flash image and deepseek v4 pricing, add openai deprecation dates by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37473
• fix(model_prices): set prompt_cache_min_tokens=4096 for Gemini 3.5/3.6/3.7 Flash and 3.1 Pro Preview by @mateo-berri in https://github.com/BerriAI/litellm/pull/37516
• fix(anthropic,bedrock): report provider thinking tokens instead of classifying them as text by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35998
• fix(batches): stop one bad output line from zeroing an entire batch's spend by @mateo-berri in https://github.com/BerriAI/litellm/pull/37457
• feat(e2e): canonical content-based match keys for record-and-replay by @mateo-berri in https://github.com/BerriAI/litellm/pull/37525
• feat(cli): add lite login --config-claude to wire Claude Code at login by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37507
• fix(auth): resolve bare model names against wildcard deployments in model access groups by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37492
• docs: run only the tests covering your change, leave suites to CI by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37528
• feat(complexity-router): make the reasoning override floor configurable by @tin-berri in https://github.com/BerriAI/litellm/pull/37537
• fix(ui): drop stale user search answers so Enter commits the current match by @mateo-berri in https://github.com/BerriAI/litellm/pull/37504
• refactor(ui): migrate the remaining dashboard pages off antd by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37524
• feat(proxy): auto-suppress the no-Redis banner for confirmed single-worker deployments by @mateo-berri in https://github.com/BerriAI/litellm/pull/36987
• fix(proxy): retry spend updates on Postgres deadlock instead of dropping them by @RayJueWang in https://github.com/BerriAI/litellm/pull/34887
• feat(search): add Amazon Bedrock AgentCore web search provider by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36331
• fix(helm): default litellm-helm to the ghcr.io/berriai/litellm image by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37491
• refactor(ui): migrate antd Modal onto the shared shadcn Dialog by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37540
• fix(ui): toggle unlimited budget when its text is clicked by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37547
• feat(proxy): fast-fail validation for batch input files at /v1/files by @mateo-berri in https://github.com/BerriAI/litellm/pull/37527
• chore: gitignore CLAUDE.local.md by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37545
• perf(otel): build the credential-scoped tracer Resource once per logger by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37542
• fix(ci): gate backend unit tests on the pull request's own file list by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37550
• chore(codeowners): require pricing owner approval for the model prices jsons by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37551
• fix(proxy): initialize the secret manager before resolving os.environ config references by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37544
• refactor(ui): swap @ant-design/icons for lucide-react by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37553
• refactor(ui): migrate shared primitives and common components off antd by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37521
• fix(spend-logs): backfill created_at/updated_at from row endTime instead of migration time by @mateo-berri in https://github.com/BerriAI/litellm/pull/37554
• refactor(ui): migrate the MCP servers pages off antd by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37522
• fix(vertex_ai): apply regional endpoint uplift to cost tracking by @mateo-berri in https://github.com/BerriAI/litellm/pull/37543
• fix(proxy): populate deployment attribution on failed-request spend logs by @mateo-berri in https://github.com/BerriAI/litellm/pull/37520
• refactor(ui): migrate the model and router settings pages off antd by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37523
• perf(ci): gate the lint, MCP and dashboard jobs on the pull request's file list by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37559
• feat(router): allow per-tier litellm_params in complexity autorouter config by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37064
• fix(anthropic): log partial stream spend when a /v1/messages client disconnects mid-stream by @mateo-berri in https://github.com/BerriAI/litellm/pull/37558
• fix(ui): clear pass-through header rows when the create modal is reopened by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37549
• fix(ui): render optional array and object MCP tool parameters as JSON inputs by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37548
• feat(proxy)!: default audit logs on for enterprise licenses by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37518
• feat(ui): standardize the Teams page header by @yuneng-berri in https://github.com/BerriAI/litellm/pull/36897
• feat(ptu): accrue flat cost for PTU deployments declared in config.yaml by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37556
• refactor(ui): migrate the last antd components off antd onto shadcn by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37569
• chore(ui): drop the antd dependency and its leftovers by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37574
• refactor(ui): map hardcoded Tailwind palette classes onto semantic tokens by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37576
• fix(ptu): hand the prune a plain delete filter the query builder can serialise by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37571
• feat(proxy): enqueued-token rate limiting for batches with refund on completion and cancellation by @mateo-berri in https://github.com/BerriAI/litellm/pull/37539
• fix(ui): restore hover feedback and dark-mode variants lost in the token migration by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37579
• fix(ci): run the full dashboard suite when a change reaches outside src/ by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37563
• fix(ui): keep semantic button colours on hover after the no-op hover cleanup by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37580
• fix: add supports_mid_conversation_system to bare first-party Claude cost-map keys by @oneKn8 in https://github.com/BerriAI/litellm/pull/36969
• feat: add bedrock grok 4.6 to model cost map by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37517
• fix: preserve prompt cache for mid-conversation system on unflagged Claude models by @oneKn8 in https://github.com/BerriAI/litellm/pull/36968
• fix(router): routed deployment's own litellm_params beat forwarded auto_router marker params by @mateo-berri in https://github.com/BerriAI/litellm/pull/37615
• refactor(ci): fold the nine thin unit-shard callers into one matrix by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37590
• chore(ci): close the test-census blind spots and move scripts out of workflows/ by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37586
• test: retire tests/old_proxy_tests, which holds no tests by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37605
• feat(ci): ratchet the test suite's zero-assert, mock-echo and global-state debt by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37588
• feat(proxy): native CLI login with OAuth authorization code + PKCE by @mateo-berri in https://github.com/BerriAI/litellm/pull/37626
• feat(prompt-caching): map cache_control_injection_points to OpenAI prompt_cache_breakpoint on GPT-5.6+ targets by @mateo-berri in https://github.com/BerriAI/litellm/pull/37628
• fix(realtime): bound Vertex credential resolution and make realtime failures loud by @mateo-berri in https://github.com/BerriAI/litellm/pull/37604
• fix(anthropic): map metadata.user_id to prompt_cache_key on the /v1/messages bridge by @mateo-berri in https://github.com/BerriAI/litellm/pull/37623
• fix(passthrough): resolve vertex live credentials from db model deployments by @mateo-berri in https://github.com/BerriAI/litellm/pull/37602
• fix(prompt_management): don't route no-prompt_id requests to prompt managers that can't run them by @mateo-berri in https://github.com/BerriAI/litellm/pull/37575
• test: remove the five test functions a later definition shadows by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37591
• feat(ci): guard shard assignment across every sharded test tree by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37593
• feat(ui): multi-key shadow eval picker and per-key breakdown by @tin-berri in https://github.com/BerriAI/litellm/pull/37389
• fix(ui): make dark-mode form controls visible by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37648
• fix(ui): give status colours a readable foreground and drop the muted 70% step by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37649
• fix(ui): make inline styles and code blocks follow the theme by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37651
• fix(ui): move the policy flow builder onto theme tokens by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37654
• test: settle three allowlist entries that were open questions by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37598
• feat(ci): ratchet tests that skip themselves when a credential is absent by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37612
• feat(ci): catch files a -k expression deselects from every job by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37601
• test: run the 30 test files stranded in the second mirror by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37595
• fix(ui): make hardcoded palette surfaces theme-aware by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37650
• feat(cli): store the lite login credential in the OS keychain by @mateo-berri in https://github.com/BerriAI/litellm/pull/37566
• fix(ui): draw one Per Day savings bar per date on Cost Optimization by @tin-berri in https://github.com/BerriAI/litellm/pull/37643
• feat(mistral): add zai-glm-5-2 and glm-5-2 model pricing by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/37110
• feat(complexity_router): add business classification rubric preset by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37534
• feat(ui): serve a dark-mode variant of the LiteLLM logo by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37656
• fix(otel): route Phoenix traces to per-key/team projects under otel v2 by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/36706
• test: replace blind sleeps with deadline waits in callback and caching tests by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37660
• fix(cli): keep the --pkce refresh token in the OS keychain, not in token.json by @mateo-berri in https://github.com/BerriAI/litellm/pull/37665
• fix(ui): keep keyword tier rules that target operator-defined tiers when hydrating the edit modal by @tin-berri in https://github.com/BerriAI/litellm/pull/37413
• feat(proxy): add POST /auto_router/validate_complexity_router_config to dry-run the complexity-router write gate by @tin-berri in https://github.com/BerriAI/litellm/pull/37409
• feat(ui): let admins supply a dark-mode variant of their custom logo by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37662
• fix(proxy): run pre-call guardrails on batch input file uploads by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37519
• feat(ui): add a light/dark/system theme toggle to the top bar by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37669
• feat(proxy): redact or drop individual batch records instead of rejecting the file by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37561
• refactor(ui): mark dark as beta in the theme menu instead of the toolbar by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37680
• ci: lint the test tree for undefined names (F821) and fix all 30 by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37671
• feat(e2e): move record/replay to the provider edge (LIT-5745) by @mateo-berri in https://github.com/BerriAI/litellm/pull/37565
• fix(mcp): let a salt-key-orphaned OAuth credential be replaced by re-authorization by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37672
• fix(mcp): normalize auth schemes so MCP egress emits exactly one prefix by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37668
• test: add six ruff rules that catch tests which cannot fail by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37709
• perf(ci): measure unit-shard coverage with the sys.monitoring core by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37589
• test: merge three stranded twins into the files that shadow them by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37600
• test(ci): reject coverage-allowlist entries that no longer match a file by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37608
• feat(ci): assert .github/workflows holds only workflows, correctly named by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37616
• feat(ci): freeze the conftest save/restore inventory so it can only shrink by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37621
• fix(a2a): accept the whole JSON-RPC id union the spec defines by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37704
• fix(ptu): refuse an incomplete config.yaml reservation the way the endpoints do by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37703
• chore: bump litellm-enterprise 0.1.57 -> 0.1.58, litellm-proxy-extras 0.4.87 -> 0.4.88 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37717
• feat(perplexity): add Agent API third-party models by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/37112
• fix(ui): surface the paginated fallback on Cost Optimization by @tin-berri in https://github.com/BerriAI/litellm/pull/37659
• feat(shadow_eval)!: gate the per-key budget on dollar spend instead of turns by @tin-berri in https://github.com/BerriAI/litellm/pull/37555
• feat(ui): per-model reasoning effort in the complexity tier editor by @tin-berri in https://github.com/BerriAI/litellm/pull/37673
• feat(proxy): authenticate to Azure Postgres with Microsoft Entra ID tokens by @mateo-berri in https://github.com/BerriAI/litellm/pull/37663
• fix(scim): keep the matched user_id on POST /Users email match by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37701
• fix(scim): fail group sync when a member add or user creation fails (LIT-5105) by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37688
• fix(auth): cache team member default budget as a typed model (LIT-5311) by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37695
• feat(proxy): add maximum_health_check_retention_period to bound the health-check table by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37681
• fix(reset_budget_job): reconnect and retry on transient DB transport errors by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37705
• fix(proxy): split agent inference and management routes so admin nodes can create agents by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37730
• feat(helm): compose DATABASE_URL_READ_REPLICA from a reader host secret key by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37109
• fix(datadog): normalize alias-derived tag values so metrics match what was sent by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37682
• fix(router): isolate deployment model info from cached backend metadata by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37687
• fix(logging): bound the shared logging executor backlog by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37694
• fix(proxy): capture requester IP in 401 and auth-time 429 failure logs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37707
• fix(logging): bound oversized error payloads written to stdout by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37684
• perf(budget_reservation): tokenize each request once, off the event loop for large prompts by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37683
• perf(prometheus): render /metrics off the event loop and coalesce concurrent scrapes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37702
• fix(token_counter): stop large token counts from blocking the proxy event loop by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37697
• fix(router): give auto prompt caching deployment affinity (LIT-5535) by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37689
• test(e2e): pin prompt-cache, service-tier, and cost-header billing as permanent regressions by @mateo-berri in https://github.com/BerriAI/litellm/pull/37607
• feat(rust): route /chat/completions through the Rust core for anthropic and bedrock by @yassin-berriai in https://github.com/BerriAI/litellm/pull/37241
• test(e2e): pin query params and multipart form fields as replay match-key identity by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/37679
• fix(a2a): return SSE (text/event-stream) for message/stream instead of NDJSON by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35037
• fix(proxy): fail the standalone prisma migration entrypoint on migration errors by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37692
• feat(sso): source generic OIDC user claims from ID/access token when UserInfo is incomplete by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37696
• fix(proxy): claim batch cost rows atomically so multi-pod polling can't double-bill by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37685
• fix(jwt): retry JWKS fetches, serve stale keys, and return 503 when the IdP is unreachable by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37690
• fix(ui): stop the Add Model mapping table from looping the page by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37741
• fix(containers): surface provider errors from container file content endpoint by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37737
• test(ci): serve /moderations from the canned OpenAI mock by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37739
• test: point the live web search, groq and vertex image suites at models that still exist by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37733
• fix(model-costs): correct gpt-5.6 max input tokens to 922k by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37722
• fix(db): apply the configured connection params to the read replica URL by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37691
• feat(fal_ai): add gpt-image-2 image generation support by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37729
• fix(scim): propagate team roster write failures on group and user writes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37700
• fix(redis): apply Azure AD and GCP IAM auth to every async client path by @mateo-berri in https://github.com/BerriAI/litellm/pull/37740
• test: assert the prefixed model the responses bridge now hands back by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37744
• perf(reset_budget_job): elect one sweeper per tick and bound the window scan by @yassin-berriai in https://github.com/BerriAI/litellm/pull/36497
• feat(proxy): add admin toggle to block requests for models without pricing by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35181
• fix(model_prices): consolidate eleven open registry audits into one changeset by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37658
• feat(ui): edit project input and output TPM limits from the Projects modal by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37676
• fix(vertex_ai): only fall back to a placeholder thought signature on the first parallel function call by @ljogeiger in https://github.com/BerriAI/litellm/pull/37541
• test(lint): ban blind pytest.raises(Exception) with ruff B017 by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/37731
• fix(responses_bridge): map incomplete responses to finish_reason length instead of 500 by @mateo-berri in https://github.com/BerriAI/litellm/pull/37710
• feat(cognition): give Cognition its own provider identity by @mateo-berri in https://github.com/BerriAI/litellm/pull/37743
• fix: add moonshot/kimi-k3 to the cost map on main by @mateo-berri in https://github.com/BerriAI/litellm/pull/37753
• fix(caching): bound the semantic cache embedding lookup so a dead embedding endpoint can't block requests by @mateo-berri in https://github.com/BerriAI/litellm/pull/37742
• test: assert the prefixed model the azure responses bridge now hands back by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37749
• test: point the live together_ai suites at a model together still serves by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37746
• test(e2e): pin openai_passthrough routing, cost logging, and file list isolation by @mateo-berri in https://github.com/BerriAI/litellm/pull/37618
• chore(ci): promote internal staging to main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37721

New Contributors

• @sytianhe made their first contribution in https://github.com/BerriAI/litellm/pull/37361
• @RayJueWang made their first contribution in https://github.com/BerriAI/litellm/pull/34887
• @oneKn8 made their first contribution in https://github.com/BerriAI/litellm/pull/36969

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.99.0-dev.1...v1.99.0-dev.2