Releasebot
Latest Create account

AI Agent Frameworks Release Notes

Release notes for AI agent platforms that allow you to set up and orchestrate AI agents

Get this feed:

Products (18)

Latest AI Agent Frameworks Updates

  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 13, 2026
    LangChain logo

    LangChain

    langchain==1.3.0

    LangChain adds version v3 support for stream_events and astream_events in agents.

    This release adds support for version="v3" in stream_events / astream_events for langchain agents. Refer to the event streaming guide for details.

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 13, 2026
    Windmill Labs logo

    Windmill by Windmill Labs

    v1.700.2

    Windmill fixes bulk instance config null handling and Bedrock tool schema integer conversion.

    1.700.2 (2026-05-12)

    Bug Fixes

    • preserve explicit nulls for typed fields in bulk instance config (#9123) (cab0000)
    • preserve negative integers in Bedrock tool schema conversion (#9116) (01e21c7)
    Original source

  • All of your release notes in one feed

    Join Releasebot and get updates from LangChain and hundreds of other software products.

    Create account
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Trigger.dev logo

    Trigger.dev

    trigger.dev v4.4.6

    Trigger.dev ships v4.4.6 with faster failure handling for uncaught exceptions and fixes a dev worker CPU spin issue after CLI disconnects, improving reliability for self-hosted and local development workflows.

    trigger.dev v4.4.6

    Upgrade

    npx trigger.dev@latest update # npm
pnpm dlx trigger.dev@latest update # pnpm
yarn dlx trigger.dev@latest update # yarn
bunx trigger.dev@latest update # bun
Self-hosted Docker image: ghcr.io/triggerdotdev/trigger.dev:v4.4.6

    Release notes

    Read the full release notes: https://trigger.dev/changelog/v4-4-6

    What's changed

    Improvements

    Fail attempts on uncaught exceptions instead of hanging to MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis) emitting "error" with no .on("error", ...) listener escalates to uncaughtException, which the worker previously reported but did not act on — runs drifted to maxDuration with empty attempts. They now fail fast with the original error and status FAILED, and respect the task's normal retry policy. You should still attach .on("error", ...) listeners to long-lived clients to handle errors gracefully. (#3529)

    Bug fixes

    Fix dev workers spinning at 100% CPU after the parent CLI disconnects. Orphaned trigger-dev-run-worker (and indexer) processes were caught in an uncaughtException feedback loop: a periodic IPC send via process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent closed the channel, which re-entered the same handler that itself called process.send, scheduled via setImmediate and amplified by source-map-support's prepareStackTrace. Fixed by (1) silently dropping packets in ZodIpcConnection when the channel is disconnected, (2) adding a process.on("disconnect", ...) handler in dev workers so they exit cleanly when the CLI closes the IPC channel, and (3) wrapping all uncaughtException-path process.send calls in a safeSend guard that checks process.connected and swallows synchronous throws. (#3491)

    All packages: v4.4.6

    @trigger.dev/build, @trigger.dev/core, @trigger.dev/python, @trigger.dev/react-hooks, @trigger.dev/redis-worker, @trigger.dev/rsc, @trigger.dev/schema-to-json, @trigger.dev/sdk, trigger.dev

    Contributors

    Eric Allam, @nicktrn, James Ritchie, @isshaddad, @d-cs, github-actions[bot], Matt Aitken, Saadi Myftija, Oskar Otwinowski

    Full changelog: v4.4.5...v4.4.6

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Trigger.dev logo

    Trigger.dev

    v.docker.4.4.6: chore: release v4.4.6 (#3501)

    Trigger.dev improves worker reliability with faster failure handling for uncaught exceptions and a fix for dev workers that could spin at 100% CPU after the CLI disconnects. The release helps tasks fail with the original error instead of hanging and exits orphaned processes cleanly.

    Summary

    1 improvement, 1 bug fix.

    Improvements

    Fail attempts on uncaught exceptions instead of hanging to MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis) emitting "error" with no .on("error", ...) listener escalates to uncaughtException, which the worker previously reported but did not act on — runs drifted to maxDuration with empty attempts. They now fail fast with the original error and status FAILED, and respect the task's normal retry policy. You should still attach .on("error", ...) listeners to long-lived clients to handle errors gracefully.
    (#3529)

    Bug fixes

    Fix dev workers spinning at 100% CPU after the parent CLI disconnects. Orphaned trigger-dev-run-worker (and indexer) processes were caught in an uncaughtException feedback loop: a periodic IPC send via process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent closed the channel, which re-entered the same handler that itself called process.send, scheduled via setImmediate and amplified by source-map-support's prepareStackTrace. Fixed by (1) silently dropping packets in ZodIpcConnection when the channel is disconnected, (2) adding a process.on("disconnect", ...) handler in dev workers so they exit cleanly when the CLI closes the IPC channel, and (3) wrapping all uncaughtException-path process.send calls in a safeSend guard that checks process.connected and swallows synchronous throws.
    (#3491)

    Releases

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    [email protected]

    Patch Changes

    • Fix dev workers spinning at 100% CPU after the parent CLI disconnects. Orphaned trigger-dev-run-worker (and indexer) processes were caught in an uncaughtException feedback loop: a periodic IPC send via process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent closed the channel, which re-entered the same handler that itself called process.send, scheduled via setImmediate and amplified by source-map-support's prepareStackTrace. Fixed by (1) silently dropping packets in ZodIpcConnection when the channel is disconnected, (2) adding a process.on("disconnect", ...) handler in dev workers so they exit cleanly when the CLI closes the IPC channel, and (3) wrapping all uncaughtException-path process.send calls in a safeSend guard that checks process.connected and swallows synchronous throws.
      (#3491)
    • Fail attempts on uncaught exceptions instead of hanging to MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis) emitting "error" with no .on("error", ...) listener escalates to uncaughtException, which the worker previously reported but did not act on — runs drifted to maxDuration with empty attempts. They now fail fast with the original error and status FAILED, and respect the task's normal retry policy. You should still attach .on("error", ...) listeners to long-lived clients to handle errors gracefully.
      (#3529)

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    • Fix dev workers spinning at 100% CPU after the parent CLI disconnects. Orphaned trigger-dev-run-worker (and indexer) processes were caught in an uncaughtException feedback loop: a periodic IPC send via process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent closed the channel, which re-entered the same handler that itself called process.send, scheduled via setImmediate and amplified by source-map-support's prepareStackTrace. Fixed by (1) silently dropping packets in ZodIpcConnection when the channel is disconnected, (2) adding a process.on("disconnect", ...) handler in dev workers so they exit cleanly when the CLI closes the IPC channel, and (3) wrapping all uncaughtException-path process.send calls in a safeSend guard that checks process.connected and swallows synchronous throws.
      (#3491)
    • Fail attempts on uncaught exceptions instead of hanging to MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis) emitting "error" with no .on("error", ...) listener escalates to uncaughtException, which the worker previously reported but did not act on — runs drifted to maxDuration with empty attempts. They now fail fast with the original error and status FAILED, and respect the task's normal retry policy. You should still attach .on("error", ...) listeners to long-lived clients to handle errors gracefully.
      (#3529)

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Trigger.dev logo

    Trigger.dev

    helm-v4.4.6: chore: release v4.4.6 (#3501)

    Trigger.dev fixes dev workers stuck at 100% CPU after CLI disconnects and improves task handling so uncaught exceptions fail fast with the original error instead of hanging until max duration.

    Summary

    1 improvement, 1 bug fix.

    Improvements

    Fail attempts on uncaught exceptions instead of hanging to
    MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis)
    emitting "error" with no .on("error", ...) listener escalates to
    uncaughtException, which the worker previously reported but did not
    act on — runs drifted to maxDuration with empty attempts. They now fail
    fast with the original error and status FAILED, and respect the task's
    normal retry policy. You should still attach .on("error", ...)
    listeners to long-lived clients to handle errors gracefully.
    (#3529)

    Bug fixes

    Fix dev workers spinning at 100% CPU after the parent CLI disconnects.
    Orphaned trigger-dev-run-worker (and indexer) processes were caught in
    an uncaughtException feedback loop: a periodic IPC send via
    process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent
    closed the channel, which re-entered the same handler that itself called
    process.send, scheduled via setImmediate and amplified by
    source-map-support's prepareStackTrace. Fixed by (1) silently dropping
    packets in ZodIpcConnection when the channel is disconnected, (2)
    adding a process.on("disconnect", ...) handler in dev workers so they
    exit cleanly when the CLI closes the IPC channel, and (3) wrapping all
    uncaughtException-path process.send calls in a safeSend guard that
    checks process.connected and swallows synchronous throws.
    (#3491)

    Raw changeset output

    Releases

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    [email protected]

    Patch Changes

    Fix dev workers spinning at 100% CPU after the parent CLI disconnects.
    Orphaned trigger-dev-run-worker (and indexer) processes were caught in
    an uncaughtException feedback loop: a periodic IPC send via
    process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent
    closed the channel, which re-entered the same handler that itself called
    process.send, scheduled via setImmediate and amplified by
    source-map-support's prepareStackTrace. Fixed by (1) silently dropping
    packets in ZodIpcConnection when the channel is disconnected, (2)
    adding a process.on("disconnect", ...) handler in dev workers so they
    exit cleanly when the CLI closes the IPC channel, and (3) wrapping all
    uncaughtException-path process.send calls in a safeSend guard that
    checks process.connected and swallows synchronous throws.
    (#3491)

    Fail attempts on uncaught exceptions instead of hanging to
    MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis)
    emitting "error" with no .on("error", ...) listener escalates to
    uncaughtException, which the worker previously reported but did not
    act on — runs drifted to maxDuration with empty attempts. They now fail
    fast with the original error and status FAILED, and respect the task's
    normal retry policy. You should still attach .on("error", ...)
    listeners to long-lived clients to handle errors gracefully.
    (#3529)

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Fix dev workers spinning at 100% CPU after the parent CLI disconnects.
    Orphaned trigger-dev-run-worker (and indexer) processes were caught in
    an uncaughtException feedback loop: a periodic IPC send via
    process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent
    closed the channel, which re-entered the same handler that itself called
    process.send, scheduled via setImmediate and amplified by
    source-map-support's prepareStackTrace. Fixed by (1) silently dropping
    packets in ZodIpcConnection when the channel is disconnected, (2)
    adding a process.on("disconnect", ...) handler in dev workers so they
    exit cleanly when the CLI closes the IPC channel, and (3) wrapping all
    uncaughtException-path process.send calls in a safeSend guard that
    checks process.connected and swallows synchronous throws.
    (#3491)

    Fail attempts on uncaught exceptions instead of hanging to
    MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis)
    emitting "error" with no .on("error", ...) listener escalates to
    uncaughtException, which the worker previously reported but did not
    act on — runs drifted to maxDuration with empty attempts. They now fail
    fast with the original error and status FAILED, and respect the task's
    normal retry policy. You should still attach .on("error", ...)
    listeners to long-lived clients to handle errors gracefully.
    (#3529)

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    @trigger.dev/[email protected]

    Patch Changes

    Updated dependencies:

    @trigger.dev/[email protected]

    Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    CrewAI logo

    CrewAI

    1.14.5a5

    CrewAI ships v1.14.5a4 with agent executor changes, improved Daytona sandbox tools, security patches, bug fixes, and new migration guides for OSS upgrades and crew-to-flow workflows.

    What's Changed

    Features

    • Deprecate CrewAgentExecutor, default Crew agents to AgentExecutor
    • Improve Daytona sandbox tools

    Bug Fixes

    • Fix missing code block in pt-BR first-flow guide
    • Log HITL pre-review and distillation failures, add learn_strict
    • Patch urllib3 for security vulnerabilities
    • Patch gitpython and langchain-core; ignore unpatched paramiko CVE
    • Refresh all published workspace packages on uv lock/sync

    Documentation

    • Add migration guide for inputs.id to restoreFromStateId
    • Add OSS upgrade and crew-to-flow migration guide
    • Update changelog and version for v1.14.5a4

    Contributors

    @akaKuruma, @greysonlalonde, @iris-clawd, @lorenzejay, @mislavivanda

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Trigger.dev logo

    Trigger.dev

    Trigger.dev v4.4.6

    Trigger.dev improves task failure handling and fixes a dev worker CPU spin issue. It now fails fast on uncaught exceptions instead of hanging until max duration, and dev workers exit cleanly after CLI disconnects with safer IPC handling.

    1 improvement and 1 bug fix.

    Improvements

    • Fail attempts on uncaught exceptions instead of hanging to MAX_DURATION_EXCEEDED. A Node EventEmitter (e.g. node-redis) emitting "error" with no .on("error", ...) listener escalates to uncaughtException, which the worker previously reported but did not act on: runs drifted to maxDuration with empty attempts. They now fail fast with the original error and status FAILED, and respect the task's normal retry policy. You should still attach .on("error", ...) listeners to long-lived clients to handle errors gracefully. (#3529)

    Bug fixes

    • Fix dev workers spinning at 100% CPU after the parent CLI disconnects. Orphaned trigger-dev-run-worker (and indexer) processes were caught in an uncaughtException feedback loop: a periodic IPC send via process.send would throw ERR_IPC_CHANNEL_CLOSED once the parent closed the channel, which re-entered the same handler via setImmediate, amplified by source-map-support's prepareStackTrace. Fixed by silently dropping packets in ZodIpcConnection when the channel is disconnected, adding a process.on("disconnect", ...) handler in dev workers so they exit cleanly, and wrapping all uncaughtException-path process.send calls in a safeSend guard. (#3491)

    How to upgrade

    Update the trigger.dev/* packages to v4.4.6 using your package manager:

    npx trigger.dev@latest update  # npm
pnpm dlx trigger.dev@latest update  # pnpm
yarn dlx trigger.dev@latest update  # yarn
bunx trigger.dev@latest update  # bun

    Self-hosted users: update your Docker image to ghcr.io/triggerdotdev/trigger.dev:v4.4.6.

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Vercel logo

    Vercel AI SDK by Vercel

    @ai-sdk/[email protected]

    Vercel AI SDK fixes telemetry step numbering in WorkflowAgent.stream for better per-step integrations.

    Patch Changes

    81e68da: Fix stepNumber on telemetry events emitted by WorkflowAgent.stream so per-step telemetry integrations (e.g. @ai-sdk/devtools) correctly key state per step.

    Updated dependencies [eaf849f]

    Updated dependencies [8565dcb]

    [email protected]

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Vercel logo

    Vercel AI SDK by Vercel

    @ai-sdk/[email protected]

    Vercel AI SDK ships a patch update with refreshed dependencies and ai canary support.

    Patch Changes

    Original source
  • May 12, 2026
    • Date parsed from source:
      May 12, 2026
    • First seen by Releasebot:
      May 12, 2026
    Vercel logo

    Vercel AI SDK by Vercel

    @ai-sdk/[email protected]

    Vercel AI SDK ships a patch update with refreshed dependencies.

    Patch Changes

    Original source