BerriAI/litellm v1.109.0-dev.2 on GitHub

Verify Docker Image Signature

All LiteLLM Docker images are signed with cosign. This release is signed with the key introduced in commit e82a3c6.

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 published signing key:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
  ghcr.io/berriai/litellm:v1.109.0-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/v1.109.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.109.0-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(databricks): price the openjev decision model at its published 0.6 DBU per 1M input tokens by @kerry-berri in #48694
fix(tavily): return raw_content, score, favicon and the response envelope from Tavily search by @mrinal-berri in #48684
fix(ui): keep guardrail wizard navigation within the dialog by @tin-berri in #48688
fix(langfuse otel): emit request metadata under langfuse.observation.metadata and langfuse.trace.metadata on the OTEL v2 Langfuse mapper by @devin-ai-integration[bot] in #42697
fix(cohere): map string stop parameter to list of strings for stop_sequences by @Pyhroff in #47091
fix(anthropic): count search results and reject unsupported token-count blocks by @kerry-berri in #48699
fix(proxy)!: paginate customer lists and usage filters by @tin-berri in #48700
fix(responses): skip failed spend-log turns when rebuilding a session from previous_response_id by @ryan-crabbe-berri in #48647
fix(responses): reject or drop Responses params the chat completions bridge cannot translate by @ryan-crabbe-berri in #48655
fix(ui): prefill the key edit Organization picker from org_id by @mateo-berri in #39535
fix(responses): keep every MCP tool round in streaming follow-up input by @shivamrawat1 in #47698
docs(readme): link the LiteLLM OSS Champions program from Contributing by @zoveki in #48734
test(harness): audit #47530 by @norkelbyte in #48751
test(sagemaker): audit #47495 by @rj-cairn in #48767
test(gemini): audit #47542 by @zoveki in #48758
test(proxy): pin the max_parallel_requests slot release when a streamed /v1/messages MCP auto-execute ends by @mateo-berri in #47788
fix(cost-map): drop the gpt-5-nano priority input price OpenAI does not sell by @tessellark in #48763
test(spend): audit #47815 by @norkelbyte in #48774
feat: add ai& (aiand) provider by @islomjon-aiand in #38958
fix(router)!: count an explicit allowed_fails of 3 and keep fallback deployments out of cooldown by @HardMax71 in #46183
test(proxy): audit #47418 by @tavren27 in #48766
fix(router): let affinity pins yield to deployments that already failed this request by @aidanasingh in #32309
test(llms): audit #47535 by @tessellark in #48786
test(responses): audit #47504 by @norkelbyte in #48787
test(spend): audit #47353 by @rj-cairn in #48785
test(proxy): audit #46815 by @m6atlas in #48768
fix(bedrock): retry without strict when Bedrock rejects strict tool schemas under drop_params by @m6atlas in #48733
test(files): audit #40621 by @zoveki in #48788
test(anthropic, bedrock): audit #47489 by @zoveki in #48782
fix(anthropic): let drop_params drop speed on claude-opus-4-7 after Anthropic removed its fast mode by @norkelbyte in #48764
test(token_counter): audit #47586 by @simonp9 in #48800
test(anthropic): audit #47478 by @paveln83 in #48803
fix(router): continue Responses mid-stream fallbacks on models without assistant prefill by @tin-berri in #47672
test(router): audit #47498 by @mika-lt in #48799
test(decisions): audit #47508 by @tavren27 in #48777
test(router): audit #47376 by @norkelbyte in #48792
test(proxy): audit #47358 by @norkelbyte in #48784
test(router): audit #41368 by @tavren27 in #48794
refactor(fallback-generalizations)!: remove the legacy extends and mixed-rule shim by @norkelbyte in #48737
fix(streaming): exact-match the SSE [DONE] marker in BaseModelResponseIterator by @michelligabriele in #47832
test(nvidia_riva): audit #41021 by @quietjules in #48801
feat(proxy): per-provider and per-model rpm/tpm requirements for enforce_project_model_quota by @mateo-berri in #47693
feat(cli): keep the ChatGPT login with lite codex --subscription by @rj-cairn in #48741
test(proxy): audit #47352 by @norkelbyte in #48804
test(mcp): audit #47422 by @tavren27 in #48821
test(scim): audit #47544 by @zoveki in #48791
build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http by @yujonglee-berri in #48039
fix(http): honor transport settings for Rust WebSockets by @yujonglee-berri in #47968
fix(vertex_ai): send Vertex Claude labels as X-Vertex-AI-Labels header instead of the request body by @ryan-crabbe-berri in #48753
fix(cost-map): rolling provider pricing, capability and retirement audit by @devin-ai-integration[bot] in #48188
fix(proxy/auth): apply max_end_user_budget_id to end users without a row on cached keys by @moe-berri in #48704
refactor(http): build outbound requests as reqwest::Request by @yujonglee-berri in #48041
refactor(rust): adopt one error discipline across litellm-rust with source chains and Report by @yujonglee-berri in #48042
feat(rust): one typed decline from core up to each host by @yujonglee-berri in #47772
fix(huggingface): stop forcing truncate=false on TEI rerank and pass truncate params through by @moe-berri in #48706
fix(ollama): forward embedding credentials, headers and timeout by @moe-berri in #48707
fix(router)!: isolate child tier pins in user turn mode by @tin-berri in #48701
fix(refuseless): update GLM 5.3 and DeepSeek V4.1 Flash prices by @moe-berri in #48844
fix(ui): match simple auto router models to advanced setup by @moe-berri in #48851
fix(ui): show reasoning in the Playground for /v1/responses by @moe-berri in #48850
fix(responses): forward top-level moderation param to OpenAI by @moe-berri in #48708
fix(proxy): store boolean settings as JSON booleans on /config/field/update by @shrey-berri in #48595
fix(azure): map context_length_exceeded error code to ContextWindowExceededError by @shrey-berri in #48616
fix(images): honor max_retries and prevent Router retry amplification by @moe-berri in #48705
fix(vertex-ai): preserve image size aspect ratios by @shrey-berri in #48463
fix(otel)!: label configured pass-through routes litellm.passthrough instead of chat by @yucheng-berri in #48675
fix(chatgpt): derive the upstream session id from prompt_cache_key by @occ in #42014
fix(cost-map)!: price Mistral Large 4 at its list price now that the launch sale ended by @zoveki in #48825
fix(anthropic-messages): merge deployment and client anthropic-beta instead of overwriting by @shrey-berri in #48594
feat(proxy): log one line per token count call by @mateo-berri in #47657
fix(otel): suppress spans for excluded proxy requests by @tin-berri in #48720
fix(baseten): price the two decision models at their published input rates by @devin-ai-integration[bot] in #48849
fix(router)!: resolve trusted JEV connection environment references by @tin-berri in #48717
chore(cost-map): fill fireworks spot router capability fields from base models by @kerry-berri in #48858
fix(mistral): replay assistant reasoning as a Mistral thinking chunk by @rj-cairn in #48778
fix(images): normalize absent images in async edits by @tin-berri in #48872
fix(count_tokens)!: audit #47441 and keep the framed estimate for Bedrock count models from the cost map by @rj-cairn in #48805
fix(responses)!: answer 400 before counting a lone Responses built-in tool on Claude by @tessellark in #48798
fix(router): drop the deployment rpm filter from enable_pre_call_checks by @kerry-berri in #48873
fix(router): pass lifecycle events through on background OpenAI responses streams that cannot fall back by @simonp9 in #48817
fix(batches): stop unbillable batches from blocking file deletes and new-batch polling by @tessellark in #48752
fix(audio): reject unsupported transcription providers with 400 by @shrey-berri in #47971
fix(azure): share one Entra token request per worker and audit #47348 by @tessellark in #48769
fix(cost-map): add mistral/deepseek-v4-1-flash-1017 by @devin-ai-integration[bot] in #48879
feat(decisions): support Ollama decision models by @moe-berri in #48871
fix(gemini)!: accept Google's current Managed Agents fields on create and interactions by @zoveki in #48750
fix(openai)!: send the whole reasoning_effort dict when chat is bridged to Responses by @m6atlas in #48807
fix(proxy): account for media in combined TPM reservations by @tin-berri in #48865
feat(providers): add ZeroGPU as an OpenAI-compatible provider by @amaan-ai20 in #43874
refactor(ui): use the shadcn Kbd primitive for keyboard hints by @yuneng-berri in #48885
fix(pricing): sync databricks model prices by @devin-ai-integration[bot] in #48884
fix(cli): let the proxy decide when a classic lite login token has expired by @mateo-berri in #47712
fix(aiohttp_openai): forward service_tier in transform_response by @TemoSulava in #47263
refactor(rust-bridge): require the native extension by @yujonglee-berri in #48852
fix(streaming): surface upstream abort as server errors (LIT-10159) by @sorgfresser in #48328
fix(ui): bundle the Aria avatar so it loads in every deployment by @yuneng-berri in #48890
fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy by @mateo-berri in #47537
fix(files)!: scope provider and model file lists to the caller's managed files under require_managed_files by @mateo-berri in #47682
fix(anthropic): map model_context_window_exceeded stop reason to length by @moe-berri in #48874
feat(accounting): add accounting contracts, PricingSnapshot and ledger schema (LIT-10193) by @devin-ai-integration[bot] in #48862
fix(ci): spend logs guard requires the approval to cover the head's spend-log lines by @kerry-berri in #48904
fix(guardrails)!: make hide-secrets honor skip_tool_message_in_guardrail by @yucheng-berri in #48689
fix(pricing): add databricks priority pay per token prices by @kerry-berri in #48891
fix(ci): keep the spend logs guard approval through a later COMMENTED review (LIT-10242) by @kerry-berri in #48901
fix(logging): bill each SDK call its own native Bedrock guardrail trace when calls share one metadata dict by @kerry-berri in #48923
fix(aiohttp_transport): keep the owned session open while a response stream is still being read (LIT-10237) by @kerry-berri in #48920
ci(spend-logs-guard): run only on pull_request_target, re-run by hand after approving by @kerry-berri in #48941
fix(router): cool down failing deployments when fallbacks use string targets (LIT-10238) by @kerry-berri in #48913
fix(migration_data_checks): size btree entries by the bytes Postgres stores (LIT-10244) by @kerry-berri in #48911
feat(daily-activity): per-guardrail spend breakdown in user, team and organization daily activity by @mrinal-berri in #48702
feat(ui): search and multi-select tools in the MCP toolset editor by @mrinal-berri in #48601
fix(gemini): preserve every grounding web source by @SilverMarcs in #48745
feat(proxy)!: model family and access group entries in model_max_budget by @mateo-berri in #47722
test(routing): audit #46601 by @tessellark in #48910
feat(skills): add a litellm-setup agent skill by @mateo-berri in #47731
fix(ci): flag any schema.prisma change inside model LiteLLM_SpendLogs in the spend logs guard by @kerry-berri in #48905
feat(router): add deployment rpd and tpd daily limits to enforce_model_rate_limits by @kerry-berri in #48875
feat(tencent): add Seedream image generation and editing through TokenHub by @tessellark in #48735
test(spend): audit #47506 by @quietjules in #48919
feat(proxy): accept request priority from the x-litellm-priority header by @mubashir1osmani in #47618
fix(websearch): strip Claude Code instructional prefix in short-circuit search by @agustin18 in #43458
feat(accounting): add durable event ledger writer by @joshua-berri in #48883
refactor(types): replace Any with proven types in 28 files by @rj-cairn in #48903
test(gemini): cover every web source for a grounded passage by @moe-berri in #48861
fix(router): reject string fallback targets at Router init (LIT-10238) by @kerry-berri in #48943
fix(vertex-ai): add batch above 200k and image output batch prices for gemini models by @devin-ai-integration[bot] in #48945
fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF by @rj-cairn in #48755
refactor(router): fence the router surface and document the router-core boundary by @narmstrong-berri in #48839
test(extraction): audit #47473 by @paveln83 in #48898
ci: run zizmor with --no-ignores and move the spend logs and cost map guards to pull_request by @yuneng-berri in #48947
refactor(images): remove dall-e-2 and dall-e-3 code paths by @kerry-berri in #48703
test(proxy): audit #46997 by @zoveki in #48918
test(responses): audit #47445 by @tavren27 in #48902
fix(vertex_ai)!: send the caller's anthropic-version in the Vertex Claude /v1/messages body, not the header by @zoveki in #48814
refactor(model-catalog): parse, lower and validate the catalog into typed prices by @yujonglee-berri in #48853
test(router): set string fallback targets after Router init in the sdk cooldown cases (LIT-10238) by @kerry-berri in #48954
fix(health): ask OpenAI and Azure audio chat models for audio output in the health check probe by @mateo-berri in #47730
fix(proxy): stop log lines from leaving terminal colors on by @ryan-crabbe-berri in #48966
fix(bedrock): omit system prompt from audio transcription and report its token usage by @david-koh in #41565
fix(logging): stop dumping the request body at every layer under --detailed_debug by @ryan-crabbe-berri in #48973
fix(stream): the last usage frame carries litellm's bill in usage.cost by @kerry-berri in #48955
fix(responses): drop params compact rejects and send Azure compaction to the v1 route by @simonp9 in #48876
fix(guardrails): scan Responses tool results in texts-mode guardrails by @mika-lt in #48827
fix(guardrails): skip embeddings input in google_text_moderation by @simonp9 in #48934
feat!: add StreamLake provider metadata by @ZHOUKAILIAN in #41006
fix(proxy): let typesafe/* allowlists cover /typesafe Jev calls and list Jev in the model picker by @mateo-berri in #47697
feat(router): daily_reset_time picks when deployment rpd and tpd daily limits start over by @kerry-berri in #48957
test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit by @devin-ai-integration[bot] in #45040
feat(ocr)!: support outputContentFormat=markdown for Azure Document Intelligence by @zoveki in #48926
feat(azure_ai): reach Foundry agents through the project Responses API by @mateo-berri in #47717
docs(adrs): add ADRs for the Python SDK and proxy, starting with provider usage extras by @devin-ai-integration[bot] in #36668
fix(responses): drop the null created_by OpenAI rejects when output items are replayed by @tessellark in #48783
fix(cli): give lite codex aliases of a Codex-known model that model's catalog entry by @tessellark in #48894
fix(proxy)!: enforce an end user's per-model budget from their linked budget by @mika-lt in #48815
fix(context_management)!: count the system prompt toward the clear_tool_uses input_tokens trigger by @AlonSoko in #47857
fix(google_genai): read one-object and null spellings of repeated fields in countTokens and generateContent by @zoveki in #48771
fix(proxy)!: stop labelling management and health rejections as auth failures by @tavren27 in #48739
test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio by @devin-ai-integration[bot] in #43370
fix(credentials): keep the stored secret when PATCH echoes its masked read-back by @tessellark in #48950
fix(responses): call the renamed drops_params helper on the compact path by @ryan-crabbe-berri in #49030
docs(qa): allow focused proof for mechanical PRs by @mateo-berri in #49031
fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded by @paveln83 in #48915
build(deps): bump langgraph and tornado and add dated scan ignores to clear osv-scan and image-scan by @devin-ai-integration[bot] in #48302
fix(responses): stream every citation batch before completion by @SilverMarcs in #48747
fix(token_counter): count OpenAI models newer than tiktoken's table with o200k_base by @rj-cairn in #48728
fix(cost_map): mark fireworks_ai/minimax-m3 as vision and pin capabilities verified against live calls by @devin-ai-integration[bot] in #43390
feat(responses): support Codex client tool_search on Anthropic and other bridged providers by @mateo-berri in #48972
fix(proxy)!: list every priced Vertex family under a vertex_ai/* grant by @devin-ai-integration[bot] in #41959
fix(responses): keep each Codex tool once when its tool list repeats across turns by @ryan-crabbe-berri in #49006
feat(providers): add BigModel support and model pricing by @AaronHowell in #48563
fix(health)!: openai realtime health check reports healthy with a missing or invalid api key by @devin-ai-integration[bot] in #41233
fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn by @simonp9 in #48912
fix(responses): resume background response streams with stream and starting_after by @paveln83 in #48819
test(integration): scope the signoz, otel conversation id, and series cap proxy fixtures to their module by @rj-cairn in #48965
fix(anthropic): drop the non-spec custom object from /v1/messages tool definitions by @zoveki in #48893
fix(responses): drop a malformed prompt_cache_breakpoint under drop_params on the direct /v1/responses path by @devin-ai-integration[bot] in #45330
test: fix flaky spend-log cleanup budget, login lockout, and wedged Redis tests by @devin-ai-integration[bot] in #47108
fix(vertex_ai): build the cachedContents collection URL under a custom api_base by @devin-ai-integration[bot] in #44783
fix(github_copilot): treat a malformed api-key.json like a missing one by @devin-ai-integration[bot] in #44723
feat(proxy)!: add suppress_startup_output to turn off startup prints by @mateo-berri in #47708
feat(proxy): let a Claude Code gateway user choose the session team by @simonp9 in #49001
feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key by @zoveki in #48980
fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails by @quietjules in #48916
fix(llms): move later developer messages for models declared system-first by @mika-lt in #48897
fix(openai): warn when the GPT-5 reasoning effort gate drops a level under drop_params by @mateo-berri in #47761
fix(websearch)!: keep the provider prefix on the agentic follow-up model by @msdianprince-7 in #38885
fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs by @tavren27 in #48888
fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough by @tavren27 in #48978
feat(providers): add Kyma API as an OpenAI-compatible provider by @m6atlas in #48756
fix(cost): bill a deployment's per-second rates on native Anthropic /v1/messages by @devin-ai-integration[bot] in #42417
fix(proxy): stream a guardrail block on /v1/messages as Anthropic events by @tessellark in #49010
fix(caching): read the cache key's model group from the router's metadata for the call by @mika-lt in #48917
fix(passthrough): forward OpenAI-Beta and default agents=v1 on the OpenAI passthrough by @mika-lt in #49009
test(router_strategy): keep foreign asyncio task noise out of the budget limiter caplog asserts by @devin-ai-integration[bot] in #43375
fix(bedrock)!: route region-prefixed embedding models to that region and bill its price by @tessellark in #49072
fix(anthropic)!: drop beta-gated body fields under drop_params by @tavren27 in #48793
ci: run the dashboard API types and Terraform endpoint checks on every change that can alter the spec by @tavren27 in #49022
refactor(types): replace Any with proven types in 14 files by @mika-lt in #48928
fix(fallback): read stored router_settings from the database on fallback writes by @mika-lt in #48999
build(model-catalog): ship the cost map inside the native extension by @yujonglee-berri in #48907
ci(model-catalog): check the cost map by loading it through model-catalog by @yujonglee-berri in #48908
feat(soniox): add realtime speech-to-text on /v1/realtime by @dan2k3k4 in #44822
fix(exceptions)!: honor status code when mapping OpenAI invalid_request_error exceptions by @otiscuilei in #32537
fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts by @mateo-berri in #47166
feat(vector_stores): add OpenSearch k-NN search as a vector store provider by @mateo-berri in #47759
feat(router): opt in to non-chat deployment filtering by @mateo-berri in #46257
feat(secret_managers): resolve oidc/google api_key references per request by @mateo-berri in #47703
fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails by @paveln83 in #49035
feat(dashscope)!: derive protocol bases from one domain by @Bytechoreographer in #47812
fix(proxy): persist tag spend and drain success callbacks within the shutdown budget by @devin-ai-integration[bot] in #48988
feat(proxy): replace the pre-migration row check with a rolled-back dry run of the pending migrations by @kerry-berri in #48961
fix!: retain unattributed daily activity across reports and exports by @mrinal-berri in #48925
refactor(router): add router entry points and keep the old members as a deprecated mixin by @narmstrong-berri in #48840
fix(caching): keep reasoning, citations, and audio on streamed cache hits by @jesco-absolut in #32096
fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping by @devin-ai-integration[bot] in #45039
refactor(router): move router callers onto the entry points and invert the proxy imports by @narmstrong-berri in #48847
feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store by @devin-ai-integration[bot] in #40631
fix(anthropic): keep Mistral thinking text on streaming /v1/messages by @zoveki in #49059
feat(guardrails): opt-in response_masked_data on PANW Prisma AIRS block by @mrinal-berri in #46219
fix(proxy)!: honor litellm_settings.drop_params for Claude Code and Codex requests by @simonp9 in #49058
docs: link README to Python SDK and autorouter guides by @moe-berri in #48986
feat(router): infer custom classifier tiers from model mappings by @moe-berri in #48987
fix(cost): finalize synchronous response cost once for header, spend log and rollups by @devin-ai-integration[bot] in #48993
fix(guardrails)!: make lakera_v2 on_flagged block reject PII-only detections, add mask by @yucheng-berri in #48944
fix(otel)!: give key/team Langfuse destinations user, tags and session on OTel v2 without global Langfuse keys by @yucheng-berri in #48718
feat(guardrails): scan sampled stream windows in the background by @yucheng-berri in #48952
fix(otel)!: print OTel v2 spans to stdout only when the operator asks by @yucheng-berri in #48723
ci: run the integration groups on GitHub Actions by @yuneng-berri in #48985
fix(responses): only merge repeated Codex tools when drop_params is on by @ryan-crabbe-berri in #49112
fix(caching): key cached async clients by a per-loop token instead of id(loop) by @paveln83 in #48877
test(otel): fix main's Langfuse destination tests after the stdout opt-in change by @yucheng-berri in #49129
ci: run the extensions integration group with 48 workers by @yuneng-berri in #49134
fix(guardrails): allow MCP call modes on the generic guardrail API by @jhoblitt in #48060
fix(mcp)!: restore upstream-token admission for legacy delegate servers by @shrey-berri in #48939
fix(ci): build base native extension for OpenAPI lint by @yujonglee-berri in #49136
fix(proxy)!: bill streamed /v1/completions without stream_options like chat by @devin-ai-integration[bot] in #45366
fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params by @zoveki in #49102
feat(ui): add i18next plumbing and move the Workflows page onto it by @yuneng-berri in #49144
fix(responses)!: keep the proxy's error body on litellm.responses errors from litellm_proxy models by @mika-lt in #49073
fix(context_management)!: run clear_tool_uses in the gateway on the Responses API path by @AlonSoko in #47861
chore: bump litellm-enterprise 0.1.80 -> 0.1.81, litellm-proxy-extras 0.4.111 -> 0.4.112 by @yuneng-berri in #49149
feat(dashscope): add image edits and text-to-speech by @zoveki in #48998
feat(pass-through): add eu/jev decision API pass-through with spend tracking by @edujuan in #46875
chore(caching)!: remove the disk cache backend by @yuneng-berri in #48114
test: update integration tests left stale by recent product changes by @yuneng-berri in #49143
feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex by @quietjules in #48949

New Contributors

@Pyhroff made their first contribution in #47091
@zoveki made their first contribution in #48734
@rj-cairn made their first contribution in #48767
@tessellark made their first contribution in #48763
@islomjon-aiand made their first contribution in #38958
@aidanasingh made their first contribution in #32309
@m6atlas made their first contribution in #48768
@mika-lt made their first contribution in #48799
@quietjules made their first contribution in #48801
@occ made their first contribution in #42014
@amaan-ai20 made their first contribution in #43874
@TemoSulava made their first contribution in #47263
@SilverMarcs made their first contribution in #48745
@david-koh made their first contribution in #41565
@ZHOUKAILIAN made their first contribution in #41006
@otiscuilei made their first contribution in #32537
@jhoblitt made their first contribution in #48060
@edujuan made their first contribution in #46875

Full Changelog: v1.109.0-dev.1...v1.109.0-dev.2