fix(deps): update all non-major dependencies - #57
Conversation
dcf78d4 to
033a411
Compare
9f368fc to
abc438e
Compare
1a7bad6 to
c91c888
Compare
|
Warning Review the following alerts detected in dependencies. According to your organization's Security Policy, it is recommended to resolve "Warn" alerts. Learn more about Socket for GitHub.
|
c23fdd9 to
166f465
Compare
c386f7b to
dc2c62e
Compare
This PR contains the following updates:
3.0.9→3.0.902.0.5→2.0.422.3.14→2.5.6^0.12.0→^0.20.04.20260113.0→4.20260702.12.3.0→2.7.15.2.8→5.3.05.2.7→5.3.01.57.0→1.62.11.1.11→1.2.61.3.3→1.3.111.1.12→1.1.202.2.16→2.3.71.1.15→1.1.232.1.16→2.1.242.1.8→2.1.151.1.15→1.1.231.1.8→1.1.161.2.10→1.2.182.2.6→2.3.71.1.8→1.1.151.2.4→1.3.31.2.6→1.3.71.1.13→1.1.211.2.8→1.2.164.1.18→4.3.3^0.5.0→^0.8.0^0.9.0→^0.10.01.27.7→1.33.25.90.16→5.101.41.156.0→1.170.181.156.0→1.167.01.156.0→1.168.2316.3.1→16.3.2^0.1.32→^0.2.025.0.7→25.9.519.2.8→19.2.1819.2.3→19.2.48.53.0→8.65.08.53.0→8.65.02.3.3→2.3.41.5.0→1.7.15.1.2→5.2.06.0.30→6.0.2383.0.2→3.2.0^0.2.9→^0.3.04.1.0→4.4.00.31.8→0.31.109.39.2→9.39.54.4.4→4.4.55.3.1→5.4.04.32.11→4.32.1228.0.0→28.1.0^0.563.0→^0.577.04.20260107.0→4.20260730.024.13.0→24.18.110.28.2→10.34.519.2.3→19.2.89.13.0→9.14.019.2.3→19.2.83.6.0→3.10.13.4.0→3.6.04.1.18→4.3.34.21.0→4.23.11.2.0→1.4.24.59.1→4.118.0Release Notes
vercel/ai (@ai-sdk/openai)
v3.0.90Compare Source
Patch Changes
9ecdefe]v3.0.89Compare Source
Patch Changes
23632b1: Add blocked domain filters to the OpenAI and Azure Responses API web search tools.v3.0.88Compare Source
Patch Changes
8100830: Apply reasoning, service tier, and image defaults to recognizable future OpenAI model family versions.v3.0.87Compare Source
Patch Changes
2f11af1: Preserve stored tool search output item IDs from provider metadata.v3.0.86Compare Source
Patch Changes
19093fd]v3.0.85Compare Source
Patch Changes
06fb54c]v3.0.84Compare Source
Patch Changes
356918c: feat(provider/openai): add GPT-5.6 reasoning and prompt cache controlsv3.0.83Compare Source
v3.0.82Compare Source
v3.0.81Compare Source
v3.0.80Compare Source
Patch Changes
ea1e95b]v3.0.79Compare Source
Patch Changes
fa850e6]v3.0.78Compare Source
Patch Changes
64a701d: Return a helpful error when the Responses stream parser receives Chat Completions chunks.v3.0.77Compare Source
Patch Changes
b30e43a]v3.0.76Compare Source
Patch Changes
2ee1700: feat(openai): add support for web_search_call.results include optionf19334d]v3.0.75Compare Source
Patch Changes
1b40ac7: Publish all packages under the@ai-v6dist tag.1b40ac7]v3.0.74Compare Source
Patch Changes
466544d: feat(openai): add orchestration token usage details to Responses API usagev3.0.73Compare Source
Patch Changes
1274c07: fix(provider/openai): send client-executed tool calls as full function_call items in the Responses API so they pair with their function_call_output by call_idv3.0.72Compare Source
Patch Changes
779f5cd]v3.0.71Patch Changes
bfa5864]f42aa79]v3.0.69Compare Source
Patch Changes
9a55f6d: feat(openai): add namespaces for tool definitionsv3.0.68Compare Source
Patch Changes
c65c952: fix(openai): round-tripnamespaceon function_call input itemsWhen
tool_searchdispatches a deferred tool, the resultingfunction_callcarries anamespacefield identifying which deferred-tool group the model picked.#14789preserved this on the read side (providerMetadata.openai.namespace), but the write side still serializedfunction_callinput items withoutnamespace. Multi-step / multi-turn conversations then failed withMissing namespace for function_call '<name>'. ... Round-trip the model's function_call item with its namespace field included.convert-to-openai-responses-input.tsnow readsnamespacefromproviderOptions.openai.namespace(orproviderMetadata.openai.namespace) ontool-callparts and includes it on the serializedfunction_callitem, mirroring howitemIdis round-tripped.v3.0.67Compare Source
Patch Changes
c679fec: feat(provider/azure):web search tool in the Azure OpenAI Responses API.v3.0.66Compare Source
Patch Changes
c82ab42: feat(openai): forwardweb_search_call.action.queriesfrom Responses APIv3.0.65Compare Source
Patch Changes
eb52378: fix(openai): skip passing reasoning items when using previous response idv3.0.64Compare Source
Patch Changes
b7ed8bd: feat(openai): add opt-in pass-through for unsupported file media typesv3.0.63Compare Source
Patch Changes
f591416]v3.0.62Compare Source
Patch Changes
65edcca: feat: add allowedTools provider option for OpenAI Responsesv3.0.61Compare Source
Patch Changes
b93f9b4: feat(provider/openai): forward imageDetail providerOptions on tool-result image contentv3.0.60Compare Source
Patch Changes
6dcd8e6: feat(openai): add GPT-5.5 chat model IDsv3.0.59Compare Source
Patch Changes
38966ab: fix(openai, openai-compatible): only send null content for assistant messages with tool callsv3.0.58Compare Source
Patch Changes
2370948: feat(openai): preservenamespaceon function_call output itemsv3.0.57Compare Source
Patch Changes
d33e7cc: chore(provider/openai): add type for image model options for type-safe processingv3.0.55Compare Source
Patch Changes
a727da4: chore: ensure consistent import handling and avoid import duplicates or cyclesa727da4]v3.0.54Compare Source
Patch Changes
a7f3c72: trigger release for all packages after provenance setup408a2ad: patch - send content: null instead of empty string for tool-only assistant messagesc71ad14: feat(provider/openai): add gpt-image-2 model supporta7f3c72]v3.0.53Compare Source
Patch Changes
953385d: fix(openai): default undefined tool-call input to empty object before serializing tool argumentsv3.0.52Compare Source
Patch Changes
d42076d: Add AI Gateway hint to provider READMEsv3.0.51Compare Source
Patch Changes
6247886]v3.0.50Compare Source
Patch Changes
0469aed]v3.0.49Compare Source
Patch Changes
bc01093: fix(openai): support file-url parts in tool output contentv3.0.48Compare Source
Patch Changes
9c548de: Addgpt-5.4-mini,gpt-5.4-mini-2026-03-17,gpt-5.4-nano, andgpt-5.4-nano-2026-03-17models.bcb04df: fix(openai): preserve raw finish reason for failed responses stream eventsHandle
response.failedchunks in Responses API streaming sofinishReason.rawis preserved fromincomplete_details.reason(e.g.max_output_tokens), and map failed-without-reason cases to unifiederrorinstead ofother.v3.0.47Compare Source
Patch Changes
055cd68: fix: publish v6 to latest npm dist tag055cd68]v3.0.46Compare Source
Patch Changes
75fc0e7: feat(openai): add new tool search toolv3.0.45Compare Source
Patch Changes
023088c: feat(provider/openai): addgpt-5.3-chat-latestv3.0.44Compare Source
Patch Changes
f4a734a: fix(provider/openai): drop reasoning parts without encrypted content when store: falsev3.0.43Compare Source
Patch Changes
64ac0fd]v3.0.42Compare Source
Patch Changes
2589004: feat(provider/openai): add GPT-5.4 model supportv3.0.41Compare Source
Patch Changes
ad4cfc2]v3.0.40Compare Source
Patch Changes
824b295]v3.0.39Compare Source
Patch Changes
08336f1]v3.0.38Compare Source
Patch Changes
64a8fae: chore: remove obsolete model IDs for Anthropic, Google, OpenAI, xAIv3.0.37Compare Source
Patch Changes
58bc42d: feat(provider/openai): support custom tools with alias mapping58bc42d]v3.0.36Compare Source
Patch Changes
53bdfa5: fix(openai): allow null/undefined type in streaming tool call deltasAzure AI Foundry and Mistral deployed on Azure omit the
typefield instreaming tool_calls deltas. The chat stream parser now accepts a missing
typefield (treating it as"function") instead of throwingInvalidResponseDataError: Expected 'function' type.Fixes #12770
v3.0.35Compare Source
Patch Changes
5e18272: fix(openai): include reasoning parts without itemId when encrypted_content is presentWhen
providerOptions.openai.itemIdis absent on a reasoning content part,the converter now uses
encrypted_contentas a fallback instead of silentlyskipping the part with a warning. The OpenAI Responses API accepts reasoning
items without an
idwhenencrypted_contentis supplied, enablingmulti-turn reasoning even when item IDs are stripped from provider options.
Also makes the
idfield optional on theOpenAIResponsesReasoningtype toreflect that the API does not require it.
Fixes #12853
v3.0.34Compare Source
Patch Changes
66a374c: Supportphaseparameter on Responses API message items. Thephasefield ('commentary'or'final_answer') is returned by models likegpt-5.3-codexon assistant message output items and must be preserved when sending follow-up requests. The phase value is available inproviderMetadata.openai.phaseon text parts and is automatically included on assistant messages sent back to the API.v3.0.33Compare Source
Patch Changes
624e651: Added missing model IDs to OpenAIChatModelId, OpenAIResponsesModelId, OpenAIImageModelId, OpenAISpeechModelId, OpenAITranscriptionModelId, and OpenAICompletionModelId types for better autocomplete support.v3.0.32Compare Source
Patch Changes
0c9395b: feat(provider/openai): addgpt-5.3-codex[`v3.0.
Configuration
📅 Schedule: (UTC)
🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.
This PR was generated by Mend Renovate. View the repository job log.