Sourced from @​vercel/connect's changelog.

@​vercel/connect

• See full diff in compare view

Sourced from ai's releases.

ai@7.0.162

Patch Changes

• 857ca45: Restore server-defined tool metadata, dynamic status, and title when validating tool approval continuations so approval policies receive the same tool definition fields as new model calls.
• 4d6d830: Support a single telemetry operation for durable WorkflowAgent runs, including the prompt, final output, steps, and tools. Events recorded in the workflow are reported on completion or suspension with their original timestamps. For OpenTelemetry, pass the same OpenTelemetryIdGenerator instance as the tracer provider's idGenerator and sampler and as new OpenTelemetry({ durable }). This explicit bridge carries parent trace context and sampling across steps, reports model spans live with provider requests nested beneath them, and reconstructs the enclosing invoke_agent tree when the run completes. Without the bridge, existing live per-model tracing is preserved. Add typed experimental durable context hooks for telemetry integrations; remove reliance on process-global ID-generator detection.
• Updated dependencies [fa15312]
  • @​ai-sdk/provider-utils@​5.0.74
  • @​ai-sdk/gateway@​4.0.135

Sourced from ai's changelog.

7.0.162

Patch Changes

• 857ca45: Restore server-defined tool metadata, dynamic status, and title when validating tool approval continuations so approval policies receive the same tool definition fields as new model calls.
• 4d6d830: Support a single telemetry operation for durable WorkflowAgent runs, including the prompt, final output, steps, and tools. Events recorded in the workflow are reported on completion or suspension with their original timestamps. For OpenTelemetry, pass the same OpenTelemetryIdGenerator instance as the tracer provider's idGenerator and sampler and as new OpenTelemetry({ durable }). This explicit bridge carries parent trace context and sampling across steps, reports model spans live with provider requests nested beneath them, and reconstructs the enclosing invoke_agent tree when the run completes. Without the bridge, existing live per-model tracing is preserved. Add typed experimental durable context hooks for telemetry integrations; remove reliance on process-global ID-generator detection.
• Updated dependencies [fa15312]
  • @​ai-sdk/provider-utils@​5.0.74
  • @​ai-sdk/gateway@​4.0.135

7.0.161

Patch Changes

• 51ca5b7: fix(ai): support cross-realm Uint8Array and ArrayBuffer in DefaultGeneratedFile
• 51ca5b7: fix(ai): handle cross-realm Uint8Array and ArrayBuffer in data-content and file-part-data
• 51ca5b7: fix(ai): support cross-realm binary buffers and circular structures in cloneModelMessages
• Updated dependencies [51ca5b7]
• Updated dependencies [dc6f1c3]
• Updated dependencies [4ae6986]
  • @​ai-sdk/provider-utils@​5.0.73
  • @​ai-sdk/gateway@​4.0.134

7.0.160

Patch Changes

• a71172d: fix(ai): clarify inverted smoothStream prefix error message

• cf27969: add steering.queue() to send a message once the current task is done

• 17b6923: fix(ai): validate streamed data parts against dataPartSchemas

  processUIMessageStream looked up dataPartSchemas by the full chunk type (data-weather) instead of the bare part name (weather), so useChat / Chat never validated streamed data parts. Invalid data parts now raise a TypeValidationError.

• Updated dependencies [2099d45]

• Updated dependencies [d05ff62]

  • @​ai-sdk/gateway@​4.0.133

7.0.159

Patch Changes

• Updated dependencies [cbc9ac0]
  • @​ai-sdk/gateway@​4.0.132

7.0.158

Patch Changes

• 8ba3a5c: fix(ai): repair partial JSON that ends with a minus sign at the start of an array
• 5c247e9: feat(sandbox): add stat, listDirectory, and deleteFile to Experimental_SandboxSession, and specify that relative paths in every method resolve against the directory run and spawn start in

... (truncated)

• 2feaeec Version Packages (#24410)
• 857ca45 fix(ai): restore server tool metadata for approval continuations (#24422)
• 4d6d830 feat(workflow): trace durable agent runs as a single operation (#24408)
• 7498799 Version Packages (#24380)
• 51ca5b7 fix(ai): preserve cross-realm binary data and message cycles (#24370)
• 563b3ff Version Packages (#24294)
• cf27969 feat(ai): add steering.queue() to send a message once the current task is don...
• a71172d fix(ai): clarify inverted smoothStream prefix error message (#24301)
• 17b6923 fix(ai): validate streamed data parts against dataPartSchemas (#24298)
• f3e2cc2 Version Packages (#24264)
• Additional commits viewable in compare view

Sourced from eve's releases.

eve@0.91.0

Released 2026-10-30 · Compare with 0.90.0

Breaking Changes

• session.clear() now cancels a running turn and every working task before it clears history, instead of waiting for the turn to finish. Previously a clear sent while a turn waited on tasks didn't run until the tasks finished, and never ran if one hung. Tasks a clear stops end with task.ended outcome: "cancelled", and no task result the cleared conversation hadn't read reaches the next turn. (#5619)

Features

• Hooks can start a session's next turn with ctx.continue() from turn.settled and * handlers. Other handlers don't receive it. It continues a completed turn, or a turn the same hook cancelled, and hooks that continue one turn share its next turn. It takes MessageContent with session.send()'s context and an optional auth, returns { queued } synchronously, and yields to any other turn, cancel, clear, or reset that comes first. delivery.admitted records source: { channel, hook }. (#5555)

Bug Fixes

• The bash tool now keeps only the last 50 KiB of each output stream while a command runs, so a verbose command no longer holds its whole stdout and stderr in memory. Very large output no longer fails with Cannot create a string longer than 0x1fffffe8 characters. Output past the limit is noted as earlier output omitted, as it already was for commands left running. Thanks @​mrud for reporting this in #5651. (#5653)
• HTTP Basic auth now compares the username and password in constant time on every request, so response timing no longer reveals whether the username matched. (#5521)
• Anthropic agents no longer fail with a 400 when the model calls a server tool, such as web_search or programmatic code_execution, beside a local tool. Anthropic runs that server tool after the local results arrive and returns its result at the start of the next response, so the next request must end on those local results. Until that result arrives, eve now holds a message that steers the turn for one model step, holds changed catalog or skill announcements, sends an empty-response retry's note as a system instruction, and keeps compaction from separating the deferred result from its call or adding a resumption message after the local results. When the result can no longer arrive, because the turn was cancelled, failed, or retried, or a new turn starts, eve answers the server call as one whose outcome is unknown, so the model reads the new message right away. Thanks @​jam3gw for reporting this in #4890. (#4891)
• A Discord display: "select" request with an option id longer than 100 characters now fails with a clear error instead of posting a select whose truncated value came back as an id the request never offered, which dropped or mismatched the user's choice. (#5533)
• Sessions now fail controls their eve version does not support, so the control's delivery settles failed instead of never settling. (#5622)
• A provider tool result that arrives in the response after its call, such as an Anthropic tool search the model started beside a local tool, now settles the call the earlier step introduced. Previously eve published that call a second time, so with the session-event checker on (eve dev, eve eval, or EVE_CHECK_SESSION_EVENTS=1) the step failed with introduced-twice, and without it the session log recorded one call introduced twice. (#5648)
• A turn cancellation raised while the model is being resolved now cancels the turn instead of failing the session with MODEL_SELECTION_FAILED, even when it arrives before the turn's abort signal fires. Thanks @​burn2delete for reporting this and proposing the fix in #4273. (#4274)
• Session steps now return only the session projection rows they changed, instead of every row of each changed table, so a step's stored output no longer grows with the calls and parts the turn already settled. Thanks @​mrud for reporting this in #5635. (#5642)
• Slack approval and question cards now show their prompt, tool input, and answer as literal text. A model-written <!channel> or <url|label> in a prompt or tool input no longer notifies the channel or hides a link's real destination from the approver. Card(...) rendering is unchanged. (#5517)
• A connection in agent/connections/*.ts now keeps an approval written as { request, response, prompt }, so its tools ask for approval and run its response policy. Previously only the function form was kept and the object form was dropped, so the connection's tools ran without asking anyone. A malformed approval now fails resolution instead of being ignored. (#5632)
• Teams approval and question cards now show the prompt, tool input, and answer as literal text. A model-written [docs](https://evil.example) no longer renders as a link whose label hides its destination. The cards use RichTextBlock text runs, and the message text is sent as plain text. (#5529)
• Teams inbound verification now accepts only RS256-signed Bot Connector tokens, as Microsoft documents, instead of using the algorithm named in the token header. (#5530)
• ctx.turn.input keeps the turn's input after the turn pauses for an approval, a question, a sign-in, or a budget answer. Dynamic values no longer see empty input after the pause, including auto() if its per-turn memo was invalidated. (#5628)
• web_fetch now rejects a timeout of zero or less as invalid tool input, instead of throwing an opaque RangeError or aborting the request immediately. (#5532)
• eve setup now opens browser URLs on Windows through rundll32 instead of cmd /c start, so & or | in a URL is no longer interpreted by the shell. (#5522)

eve@0.90.0

Released 2026-10-29 · Compare with 0.89.0

Breaking Changes

• GET /eve/v1/info now serves only operator principals and returns 403 to end users. The route answers service and runtime principals and callers a configured localDev() admits, and returns 403 with code info_forbidden to everyone else. To give another credential access, return principalType: "service" from its AuthFn, or allowAgentInfo: true from an EveAuthFn; allowAgentInfo: false denies a caller that would otherwise qualify. The payload stays at version 5 with every field, and client.info() now ignores unknown fields and reads unknown enum strings as "unrecognized", so handle that value when switching on fields such as mode or sourceKind. kind discriminants stay closed, so a new variant needs a version bump. (#5542)
• Tool-stub grants on Vercel OIDC subjects move from vercelOidc to the new eveVercelOidc helper in eve/channels/eve.

... (truncated)

Sourced from eve's changelog.

0.91.0

Released 2026-10-30 · Compare with 0.90.0

Breaking Changes

• session.clear() now cancels a running turn and every working task before it clears history, instead of waiting for the turn to finish. Previously a clear sent while a turn waited on tasks didn't run until the tasks finished, and never ran if one hung. Tasks a clear stops end with task.ended outcome: "cancelled", and no task result the cleared conversation hadn't read reaches the next turn. (#5619)

Features

• Hooks can start a session's next turn with ctx.continue() from turn.settled and * handlers. Other handlers don't receive it. It continues a completed turn, or a turn the same hook cancelled, and hooks that continue one turn share its next turn. It takes MessageContent with session.send()'s context and an optional auth, returns { queued } synchronously, and yields to any other turn, cancel, clear, or reset that comes first. delivery.admitted records source: { channel, hook }. (#5555)

Bug Fixes

• The bash tool now keeps only the last 50 KiB of each output stream while a command runs, so a verbose command no longer holds its whole stdout and stderr in memory. Very large output no longer fails with Cannot create a string longer than 0x1fffffe8 characters. Output past the limit is noted as earlier output omitted, as it already was for commands left running. Thanks @​mrud for reporting this in #5651. (#5653)
• HTTP Basic auth now compares the username and password in constant time on every request, so response timing no longer reveals whether the username matched. (#5521)
• Anthropic agents no longer fail with a 400 when the model calls a server tool, such as web_search or programmatic code_execution, beside a local tool. Anthropic runs that server tool after the local results arrive and returns its result at the start of the next response, so the next request must end on those local results. Until that result arrives, eve now holds a message that steers the turn for one model step, holds changed catalog or skill announcements, sends an empty-response retry's note as a system instruction, and keeps compaction from separating the deferred result from its call or adding a resumption message after the local results. When the result can no longer arrive, because the turn was cancelled, failed, or retried, or a new turn starts, eve answers the server call as one whose outcome is unknown, so the model reads the new message right away. Thanks @​jam3gw for reporting this in #4890. (#4891)
• A Discord display: "select" request with an option id longer than 100 characters now fails with a clear error instead of posting a select whose truncated value came back as an id the request never offered, which dropped or mismatched the user's choice. (#5533)
• Sessions now fail controls their eve version does not support, so the control's delivery settles failed instead of never settling. (#5622)
• A provider tool result that arrives in the response after its call, such as an Anthropic tool search the model started beside a local tool, now settles the call the earlier step introduced. Previously eve published that call a second time, so with the session-event checker on (eve dev, eve eval, or EVE_CHECK_SESSION_EVENTS=1) the step failed with introduced-twice, and without it the session log recorded one call introduced twice. (#5648)
• A turn cancellation raised while the model is being resolved now cancels the turn instead of failing the session with MODEL_SELECTION_FAILED, even when it arrives before the turn's abort signal fires. Thanks @​burn2delete for reporting this and proposing the fix in #4273. (#4274)
• Session steps now return only the session projection rows they changed, instead of every row of each changed table, so a step's stored output no longer grows with the calls and parts the turn already settled. Thanks @​mrud for reporting this in #5635. (#5642)
• Slack approval and question cards now show their prompt, tool input, and answer as literal text. A model-written <!channel> or <url|label> in a prompt or tool input no longer notifies the channel or hides a link's real destination from the approver. Card(...) rendering is unchanged. (#5517)
• A connection in agent/connections/*.ts now keeps an approval written as { request, response, prompt }, so its tools ask for approval and run its response policy. Previously only the function form was kept and the object form was dropped, so the connection's tools ran without asking anyone. A malformed approval now fails resolution instead of being ignored. (#5632)
• Teams approval and question cards now show the prompt, tool input, and answer as literal text. A model-written [docs](https://evil.example) no longer renders as a link whose label hides its destination. The cards use RichTextBlock text runs, and the message text is sent as plain text. (#5529)
• Teams inbound verification now accepts only RS256-signed Bot Connector tokens, as Microsoft documents, instead of using the algorithm named in the token header. (#5530)
• ctx.turn.input keeps the turn's input after the turn pauses for an approval, a question, a sign-in, or a budget answer. Dynamic values no longer see empty input after the pause, including auto() if its per-turn memo was invalidated. (#5628)
• web_fetch now rejects a timeout of zero or less as invalid tool input, instead of throwing an opaque RangeError or aborting the request immediately. (#5532)
• eve setup now opens browser URLs on Windows through rundll32 instead of cmd /c start, so & or | in a URL is no longer interpreted by the shell. (#5522)

0.90.0

Released 2026-10-29 · Compare with 0.89.0

Breaking Changes

• GET /eve/v1/info now serves only operator principals and returns 403 to end users.

... (truncated)

• 523b5d7 Version Packages (#5625)
• 02113a3 fix(eve): keep requests ending on local results while an Anthropic server too...
• 32cef20 fix(eve): propagate turn cancellation raised during model resolution (#4274)
• c986b69 fix(eve): diff session projection tables row by row (#5635) (#5642)
• 86b68fb fix(eve): keep only the tail of bash output while a command runs (#5653)
• 423b91c test(eve): pin session state deltas carrying whole projection tables (#5635) ...
• 56e6a7d test(eve): pin bash buffering whole command output before truncation (#5651) ...
• 6c620df fix(eve): settle a provider result that arrives a step late (#5645) (#5648)
• d8368c0 test(eve): pin a late provider result introduced twice (#5645) (#5647)
• e44b89c fix(discord): refuse select option ids Discord would truncate (#5533)
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
• @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
• @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
• @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
• @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions