Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedBot user detected. To trigger a single review, invoke the You can disable this status message by setting the
Comment |
5dd5a3b to
28bf1c9
Compare
28bf1c9 to
a2f1b67
Compare
a2f1b67 to
5abec1a
Compare
Update dependency @ai-sdk/anthropic to v3
🚨 Report Summary
For more details view the full report in OpenZeppelin Code Inspector |
5abec1a to
9f29c59
Compare
9f29c59 to
6f7fa53
Compare
6f7fa53 to
f9d7416
Compare
f9d7416 to
5f43570
Compare
5f43570 to
e131a6a
Compare
e131a6a to
c339f1a
Compare
c339f1a to
a8effb9
Compare
a8effb9 to
32d1354
Compare
| }, | ||
| }, | ||
| "packages": { | ||
| "@ai-sdk/anthropic": ["@ai-sdk/anthropic@2.0.0", "", { "dependencies": { "@ai-sdk/provider": "2.0.0", "@ai-sdk/provider-utils": "3.0.0" }, "peerDependencies": { "zod": "^3.25.76 || ^4" } }, "sha512-uyyaO4KhxoIKZztREqLPh+6/K3ZJx/rp72JKoUEL9/kC+vfQTThUfPnY/bUryUpcnawx8IY/tSoYNOi/8PCv7w=="], | ||
| "@ai-sdk/anthropic": ["@ai-sdk/anthropic@3.0.33", "", { "dependencies": { "@ai-sdk/provider": "3.0.6", "@ai-sdk/provider-utils": "4.0.11" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MvQzipOAK99Ct3nX6d8oz2AJ9c8kbiU2uSpGYK3F5oBBa8Gy04+LbYBoB9oH8bbZJxFafkgwBq1+k8xpU7vVxQ=="], | ||
|
|
||
| "@ai-sdk/azure": ["@ai-sdk/azure@1.3.22", "", { "dependencies": { "@ai-sdk/openai": "1.3.21", "@ai-sdk/provider": "1.1.3", "@ai-sdk/provider-utils": "2.2.7" }, "peerDependencies": { "zod": "^3.0.0" } }, "sha512-X3Vlxwh0MSmmZ8Q7LgzCXHvPq0XsNL1dTODIZ3ziC7n8cME8yHvjpwPwMAHLK0a7YbWO7eOW0OsDnZXdong10g=="], | ||
|
|
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
068de01 to
a55dba0
Compare
a55dba0 to
ba44e45
Compare
ba44e45 to
01e3269
Compare
| "eventsource-parser": ["eventsource-parser@3.0.3", "", {}, "sha512-nVpZkTMM9rF6AQ9gPJpFsNAMt48wIzB5TQgiTLdHiuO8XEDhUgZEhqKlZWXbIzo9VmJ/HvysHqEaVeD5v9TPvA=="], | ||
| "eventsource-parser": ["eventsource-parser@3.0.6", "", {}, "sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg=="], | ||
|
|
||
| "exa-js": ["exa-js@1.6.13", "", { "dependencies": { "cross-fetch": "~4.1.0", "dotenv": "~16.4.7" } }, "sha512-SkUJCZQwuqXA7OO70fTQnGV9vHFeDiu1jL2sot0Hl6vhxSuGWfvS5sXReKx/1j5R9qL5JAYAcohOFUiusjqNbg=="], |
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
01e3269 to
9e181ec
Compare
9e181ec to
aab580a
Compare
aab580a to
06afd67
Compare
06afd67 to
4123323
Compare
4123323 to
c203367
Compare
c203367 to
e88646c
Compare
e88646c to
14714bc
Compare
14714bc to
fee7da1
Compare
fee7da1 to
8992ef7
Compare
| }, | ||
| "dependencies": { | ||
| "@ai-sdk/anthropic": "^2.0.0", | ||
| "@ai-sdk/anthropic": "^3.0.0", |
There was a problem hiding this comment.
Bug: The code sets both temperature and topP, which is incompatible with the upgraded Anthropic v3 API, causing requests to fail for Anthropic models.
Severity: HIGH
Suggested Fix
In lib/agents/manual-researcher.ts, modify the logic to ensure temperature and topP are not set simultaneously for requests to Anthropic models. For example, conditionally remove the topP parameter when the provider is Anthropic.
Prompt for AI Agent
Review the code at the location below. A potential bug has been identified by an AI
agent.
Verify if this is a real issue. If it is, propose a fix; if not, explain why it's not
valid.
Location: package.json#L16
Potential issue: The pull request upgrades `@ai-sdk/anthropic` to v3, which enforces
stricter API validation. The `manualResearcher()` function in
`lib/agents/manual-researcher.ts` unconditionally sets both `temperature` and `topP`
parameters. Anthropic's API does not allow both parameters to be specified in the same
request. As a result, when a user selects an Anthropic model (e.g., Claude 3.5 Sonnet),
any call to the manual researcher agent will be rejected by the API, causing a runtime
error and breaking the feature for that provider.
| }, | ||
| "dependencies": { | ||
| "@ai-sdk/anthropic": "^2.0.0", | ||
| "@ai-sdk/anthropic": "^3.0.0", |
There was a problem hiding this comment.
Bug: The manualResearcher function sets both temperature and topP. The Anthropic API requires that only one of these be set, which will cause a runtime error.
Severity: HIGH
Suggested Fix
In lib/agents/manual-researcher.ts, modify the call to streamText() to provide either the temperature parameter or the topP parameter, but not both, to comply with the Anthropic API requirements.
Prompt for AI Agent
Review the code at the location below. A potential bug has been identified by an AI
agent.
Verify if this is a real issue. If it is, propose a fix; if not, explain why it's not
valid.
Location: package.json#L16
Potential issue: The `manualResearcher` function in `lib/agents/manual-researcher.ts`
configures calls to the Vercel AI SDK with both `temperature: 0.6` and `topP: 1`. The
pull request upgrades the `@ai-sdk/anthropic` package, and the underlying Anthropic API
enforces mutual exclusivity for these two parameters. When a request is made to an
Anthropic model using this configuration, the API will reject it, resulting in a runtime
error and causing the `manualResearcher` function to fail.
| }, | ||
| "dependencies": { | ||
| "@ai-sdk/anthropic": "^2.0.0", | ||
| "@ai-sdk/anthropic": "^3.0.0", |
There was a problem hiding this comment.
Bug: The @ai-sdk/anthropic package depends on a different major version of @ai-sdk/provider (v3) than the core ai package (v1), which may cause runtime incompatibility.
Severity: MEDIUM
Suggested Fix
Align the versions of @ai-sdk/provider across all related packages. This likely involves either downgrading @ai-sdk/anthropic to a version compatible with @ai-sdk/provider@1.x or upgrading the ai package and all other providers to versions compatible with @ai-sdk/provider@3.x.
Prompt for AI Agent
Review the code at the location below. A potential bug has been identified by an AI
agent.
Verify if this is a real issue. If it is, propose a fix; if not, explain why it's not
valid.
Location: package.json#L16
Potential issue: The update to `@ai-sdk/anthropic@3.0.55` introduces a dependency on
`@ai-sdk/provider@3.0.8`. However, the core `ai` package and other providers in the
project depend on an older major version, `@ai-sdk/provider@1.1.3`. This version
mismatch means that when the Anthropic provider is registered with the `ai` package's
registry, it may present an incompatible API interface. This could potentially cause
runtime errors when attempting to use the Anthropic language model, as the provider's
interface from v3 may not match what the core `ai` package expects from a v1 provider.
This PR contains the following updates:
^2.0.0→^3.0.0Release Notes
vercel/ai (@ai-sdk/anthropic)
v3.0.58Compare Source
Patch Changes
v3.0.57Compare Source
Patch Changes
43a74df]v3.0.56Compare Source
Patch Changes
2f8ac87]v3.0.55Compare Source
Patch Changes
7ee3f10]v3.0.54Compare Source
Patch Changes
462ad00]v3.0.53Compare Source
Patch Changes
e2dac8b]v3.0.52Compare Source
Patch Changes
035b927]v3.0.51Compare Source
Patch Changes
51aa5de: backport: test server51aa5de]v3.0.50Compare Source
Patch Changes
58bc42d]v3.0.49Compare Source
Patch Changes
d98d9ba: Migrated deprecatedoutput_formatparameter tooutput_config.formatfor structured outputs + Enabled native structured output support for Bedrock Anthropic models viaoutput_config.format.v3.0.48Compare Source
Patch Changes
2164cdf: feat(anthropic): add the new code_execution toolv3.0.47Compare Source
Patch Changes
17978c6: PasscacheControlprovider option as top-levelcache_controlin Anthropic API request body to support automatic caching.v3.0.46Compare Source
Patch Changes
v3.0.45Compare Source
Patch Changes
2dc9bfa]v3.0.44Patch Changes
23ac4a3: fix(provider/anthropic): minor follow up to support no-op speed standardv3.0.43Patch Changes
4024a3a]v3.0.42Compare Source
Patch Changes
ab57783]v3.0.41Compare Source
Patch Changes
ad4cfc2]v3.0.40Compare Source
Patch Changes
824b295]v3.0.39Compare Source
Patch Changes
0a0d29c: feat(anthropic): add support for Opus 4.6 fast modev3.0.38Patch Changes
46f46e4]v3.0.37Patch Changes
e288302: feat(anthropic): add support for Opus 4.6v3.0.36Compare Source
Patch Changes
1652320: feat(anthropic): support custom tool-reference content for deferred tool loadingv3.0.35Compare Source
Patch Changes
53f6731]v3.0.34Compare Source
Patch Changes
4867635: feat (provider/gateway): add video generation supportv3.0.33Compare Source
Patch Changes
445cbe3: fix streaming context_management field location - was incorrectly expected inside delta object but API returns it at message_delta root levelv3.0.32Patch Changes
c33343b: fix(anthropic): add missing param in tool schemav3.0.31Patch Changes
d5f7312: fix(openai): change web search tool action to be optionalv3.0.30Patch Changes
ff12133: feat(provider/openai): support native skills and hosted shellv3.0.29Patch Changes
e2ee705: feat: differentiate text vs image input tokensv3.0.28Patch Changes
4024a3a]v3.0.27Patch Changes
99fbed8: feat: normalize provider specific model options type names and ensure they are exportedv3.0.26Patch Changes
7168375]v3.0.25Patch Changes
0bb9bcd: feat(provider/anthropic): add computer_20251124 tool for claude opus 4.5v3.0.24Patch Changes
462ad00]v3.0.23Patch Changes
2810850]v3.0.22Patch Changes
1524271: chore: add skill information to README filesv3.0.21Patch Changes
2c70b90: chore: update provider docsv3.0.20Patch Changes
53f6731: feat (ai, provider): experimental generate video support53f6731]v3.0.19Patch Changes
96936e5]v3.0.18Patch Changes
d6ec0e2]v3.0.17Patch Changes
af0955e]v3.0.16Compare Source
Patch Changes
81adf59]v3.0.15Compare Source
Patch Changes
3a73fb3]v3.0.14Compare Source
Patch Changes
46f46e4]v3.0.13Compare Source
Patch Changes
1b11dcb]v3.0.12Compare Source
Patch Changes
34d1c8a]v3.0.11Compare Source
Patch Changes
891a60a: feat (provider/gateway): add provider-defined perplexity searchv3.0.10Compare Source
Patch Changes
2696fd2: chore(provider/gateway): Update gateway model settings filesv3.0.9Compare Source
Patch Changes
d937c8f]v3.0.8Compare Source
Patch Changes
8ec1984: fix(gateway): bump@vercel/oidcto 3.1.0v3.0.7Compare Source
Patch Changes
9a9ae73: feat(ai/rsc): readStreamableValuev3.0.6Compare Source
Patch Changes
v3.0.5Compare Source
Patch Changes
863d34f: fix: trigger release to update@latest863d34f]v3.0.4Compare Source
Patch Changes
v3.0.3Compare Source
Patch Changes
c44166d: Add support for Amazon Nova Models, cross region inference profiles and OpenAI gpt-oss in@ai-sdk/amazon-bedrockproviderfbc9f06: feat(amazon-bedrock): add topK supportv3.0.2Compare Source
Patch Changes
863d34f: fix: trigger release to update@latest863d34f]v3.0.1Compare Source
Patch Changes
29264a3]v3.0.0Compare Source
Major Changes
dee8b05: ai SDK 6 betaMinor Changes
78928cb: release: start 5.1 betaPatch Changes
0c3b58b: fix(provider): add specificationVersion to ProviderV34920119: fix the "incomplete_details" key from nullable to nullish for openai compatibility0adc679: feat(provider): shared spec v392c6241: feat(openai): additional settings for file search tool88fc415: feat(openai): add the new provider 'apply_patch' tool817e601: fix(openai); fix url_citation schema in chat apidae2185: fix(openai): extract meta data from first chunk that contains any046aa3b: feat(provider): speech model v3 specf1277fe: feat(provider/openai): send assistant text and tool call parts as reference ids when store: true8d9e8ad: chore(provider): remove generics from EmbeddingModelV3Before
After
60f4775: fix: remove code for unsuported o1-mini and o1-preview models9a51b92: support OPENAI_BASE_URL envd64ece9: enables image_generation capabilities in the Azure provider through the Responses API.2625a04: feat(openai); update spec for mcp approval2e86082: feat(provider/openai):OpenAIChatLanguageModelOptionstype0877683: feat(provider/openai): support conversations apid0f1baf: feat(openai): Add support for 'promptCacheRetention: 24h' for gpt5.1 series831b6cc: feat(openai): adding provider mcp tool for openai95f65c2: chore: use import * from zod/v4edc5548: feat(provider/openai): automatically add reasoning.encrypted_content include when store = false954c356: feat(openai): allow custom names for provider-defined tools544d4e8: chore(specification): rename v3 provider defined tool to provider tool77f2b20: enables code_interpreter and file_search capabilities in the Azure provider through the Responses API0c4822d: feat:EmbeddingModelV373d9883: chore(openai): enable strict json by defaultd2039d7: feat(provider/openai): add GPT 5.1 Codex Max to OpenAI Responses model IDs list88edc28: feat (provider/openai): include more image generation response metadatae8109d3: feat: tool execution approvaled329cb: feat:Provider-V33bd2689: feat: extended token usage1cad0ab: feat: add provider version to user-agent headere85fa2f: feat(openai): add sources in web-search actions423ba08: Set the annotations from the Responses API to doStream401f561: fix(provider/openai): fix web search tool input types4122d2a: feat(provider/openai): add gpt-5-codex model id0153bfa: fix(openai): fix parameter exclusion logic8dac895: feat:LanguageModelV3304222e: Add streaming support for apply_patch partial diffs.23f132b: fix: error schema for Responses API1d0de66: refactoring(provider/openai): simplify code000e87b: fix(provider/openai): add providerExecuted flag to tool start chunks2c0a758: chore(openai): add JSDoc to responses options1b982e6: feat(openai): preserve file_id when converting file citationsb82987c: feat(openai): support openai code-interpreter annotations457318b: chore(provider,ai): switch to SharedV3Warning and unified warningsb681d7d: feat: expose usage tokens for 'generateImage' function79b4e46: feat(openai): add 'gpt-5.1' modelID3997a42: feat(provider/openai): local shell tool348fd10: fix(openai): treat unknown models as reasoning9061dc0: feat: image editingfe49278: feat(provider/openai): only send item references for reasoning when store: truecb4d238: The built in Code Interpreter tool input code is streamed intool-input-<start/delta/end>chunks.357cfd7: feat(provider/openai): add new model IDsgpt-image-1-mini,gpt-5-pro,gpt-5-pro-2025-10-0638a4035: added support for external_web_access parameter on web_search tool40d5419: feat(openai): addo3-deep-researchando4-mini-deep-researchmodels366f50b: chore(provider): add deprecated textEmbeddingModel and textEmbedding aliases2b0caef: feat(provider/openai): preview image generation resultsb60d2e2: fix(openai): allow open_page action type url to be nullishfd47df5: fix(openai): revised_prompt sometimes returns null, causing errors4616b86: chore: update zod peer depenedency version7756857: fix(provider/openai): add truncation parameter support for Responses APIcad6445: feat(openai); adding OpenAI's new shell tool64aa48f: Azure OpenAI enabled web-search-preview0b9fdd5: fix(provider/openai): end reasoning parts earlier61c52dc: feat (provider/openai): add gpt-image-1.5 model supportef739fa: fix(openai): refactor apply-patch tool3220329: fix openai responses input: process all provider tool outputs (shell/apply_patch) so parallel tool results aren’t dropped and apply_patch outputs are forwarded.d270a5d: chore(openai): update tests for apply-patch tool to use snapshotsf18ef7f: feat(openai): add gpt-5.2 models21e20c0: feat(provider): transcription model v3 spec522f6b8: feat:ImageModelV3484aa93: Add 'default' as service tier88574c1: ChangeisReasoningModeldetection from blocklist to allowlist and add override option68c6187: feat(provider/openai): support file and image tool results3794514: feat: flexible tool output content supportcbf52cd: feat: expose raw finish reason10c1322: fix: moved dependency@ai-sdk/test-serverto devDependencies5648ec0: Add GPT-5.2 support for non-reasoning parameters (temperature, topP, logProbs) when reasoningEffort is none.78f813e: fix(openai): allow temperature etc setting when reasoning effort is none for gpt-5.140dc7fa: fix(openai): change find action type to find_in_page action type0273b74: fix(openai): add support for sources type 'api'5bf101a: feat(provider/openai): add support for OpenAI xhigh reasoning effort1bd7d32: feat: tool-specific strict moded86b52f: distinguish between OpenAI and Azure in Responses API providerMetadata95f65c2: chore: load zod schemas lazily59561f8: fix(openai); fix url_citation schema in chat apiUpdated dependencies [
0c3b58b]Updated dependencies [
0adc679]Updated dependencies [
50b70d6]Updated dependencies [
d1bdadb]Updated dependencies [
dee8b05]Updated dependencies [
046aa3b]Updated dependencies [
8d9e8ad]Updated dependencies [
78928cb]Updated dependencies [
dce03c4]Updated dependencies [
2625a04]Updated dependencies [
37c58a0]Updated dependencies [
3b1d015]Updated dependencies [
2b0caef]Updated dependencies [
95f65c2]Updated dependencies [
016b111]Updated dependencies [
58920e0]Updated dependencies [
954c356]Updated dependencies [
544d4e8]Updated dependencies [
0c4822d]Updated dependencies [
521c537]Updated dependencies [
4c44a5b]Updated dependencies [
e8109d3]Updated dependencies [
03849b0]Updated dependencies [
ed329cb]Updated dependencies [
e06565c]Updated dependencies [
32d8dbb]Updated dependencies [
53f3368]Updated dependencies [
d116b4b]Updated dependencies [
3bd2689]Updated dependencies [
293a6b7]Updated dependencies [
703459a]Updated dependencies [
bb36798]Updated dependencies [
83e5744]Updated dependencies [
7e32fea]Updated dependencies [
3ed5519]Updated dependencies [
8dac895]Updated dependencies [
a755db5]Updated dependencies [
cbb1d35]Updated dependencies [
475189e]Updated dependencies [
457318b]Updated dependencies [
b681d7d]Updated dependencies [
db913bd]Updated dependencies [
9061dc0]Updated dependencies [
32223c8]Updated dependencies [
c1efac4]Updated dependencies [
366f50b]Updated dependencies [
4616b86]Updated dependencies [
81d4308]Updated dependencies [
9549c9e]Updated dependencies [
af3780b]Updated dependencies [
4f16c37]Updated dependencies [
81e29ab]Updated dependencies [
522f6b8]Updated dependencies [
6306603]Updated dependencies [
fca786b]Updated dependencies [
763d04a]Updated dependencies [
10d819b]Updated dependencies [
3794514]Updated dependencies [
cbf52cd]Updated dependencies [
e9e157f]Updated dependencies [
960ec8f]Updated dependencies [
1bd7d32]Updated dependencies [
f0b2157]Updated dependencies [
95f65c2]Configuration
📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.
This change is