> ## Documentation Index
> Fetch the complete documentation index at: https://agents.candu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Track customer-facing updates to Candu Actions, including new features, improvements, and fixes for AI-driven product actions and wizards.

# Changelog

Customer-facing updates to Candu Actions, grouped by release.

<Update label="June 2, 2026" description="More reliable fullscreen wizard progress" tags={["Fix", "Wizards"]}>
  Improved fullscreen progress handling for initial-submission wizard flows, so users can move from progress to the next wizard step without confusing stuck states.
</Update>

<Update label="June 1, 2026" description="Google Gemini support for Candu Actions" tags={["Feature"]}>
  ### What changed

  Candu Actions now supports Google-backed AI capabilities, including Gemini model options in the product UI and provider support in the backend.

  This release also includes Candu SDK `1.3.29`, published alongside the Google provider work.

  ### Why it matters

  Teams can choose Gemini models for AI action workflows alongside existing provider options.
</Update>

<Update label="May 29, 2026" description="Fullscreen action progress refined for multi-tool turns" tags={["Improvement", "Wizards"]}>
  ### What changed

  Refined fullscreen tool progress for multi-action turns, including clearer phase coordination, smoother checklist motion, better pending states in simple chat, and Storybook coverage aligned to production behavior.

  ### Why it matters

  Longer-running action workflows are easier to follow while Candu Actions is working.
</Update>

<Update label="May 22, 2026" description="Attachment support for action workflows" tags={["Feature", "Wizards"]}>
  Added attachment tool-call and dropzone support across the SDK, backend, and product UI, so wizards and action flows can collect files when a workflow needs documents, images, or other uploaded context.
</Update>

<Update label="May 20, 2026" description="Agent version history and authoring polish" tags={["Improvement"]}>
  Added agent version history and shipped authoring improvements including quicker launch access, better tooltip positioning, copy support for tool slugs, and agent deletion support.
</Update>

<Update label="May 19, 2026" description="Wizard interaction polish" tags={["Improvement", "Wizards"]}>
  Polished wizard interactions across the SDK, backend, and product UI after the primitives redesign, making guided action flows feel more consistent as users move between prompts, tool UI, and results.
</Update>

<Update label="May 14, 2026" description="Redesigned wizard UI primitives" tags={["Feature", "Wizards"]}>
  ### What changed

  Redesigned the wizard UI primitives across SDK, backend, and product surfaces, with updated interaction patterns and implementation support for richer guided flows.

  ### Why it matters

  Builders can create guided action flows from reusable primitives instead of one-off UI patterns.
</Update>

<Update label="May 12, 2026" description="More wizard form field types" tags={["Feature", "Wizards"]}>
  Added number and email field support so wizard forms can collect structured input with fields that match the expected data.
</Update>

<Update label="May 8, 2026" description="Better context handling for long action histories" tags={["Improvement", "Security"]}>
  ### What changed

  Added safeguards for wizard history context, including response-mask application, bounded truncation for oversized tool results, pruning for over-budget history, and logging when context preparation changes the payload.

  ### Why it matters

  Longer action sessions can keep useful context without carrying oversized tool output into later turns.
</Update>

<Update label="May 7, 2026" description="Improved Candu Actions chat and progress UX" tags={["Improvement", "Wizards"]}>
  ### What changed

  Improved simple chat, fullscreen progress, streaming behavior, tool timing, thinking states, and wizard tool UI for Candu Actions workflows.

  ### Why it matters

  Users get clearer feedback while tools run and smoother transitions back to the assistant response.
</Update>

<Update label="April 29, 2026" description="Thumbnail-grid choices for wizards" tags={["Feature", "Wizards"]}>
  Added thumbnail-card support for wizard choice UI and aligned the backend configuration around the `thumbnailGrid` pattern, letting wizards present visual choices when text-only options are not enough.
</Update>

<Update label="April 28, 2026" description="Support for multi-tool action turns" tags={["Improvement"]}>
  Added support for multiple tool responses in the SDK and updated backend guidance so Candu Actions can complete several related steps in a single turn.
</Update>

<Update label="April 27, 2026" description="Initial file upload support for action workflows" tags={["Feature"]}>
  Added initial file upload support across the product UI, SDK, and backend, including S3-backed upload handling for workflows that need uploaded files as user input.
</Update>

<Update label="April 27, 2026" description="Clearer handling for invalid tool calls" tags={["Fix"]}>
  Added handling for cases where the model asks for a tool that is not available, marking those situations as errors so failed tool calls are easier to detect, recover from, and debug.
</Update>

<Update label="April 22, 2026" description="Modal and inline wizard launch modes" tags={["Feature", "Wizards"]}>
  ### What changed

  Added modal wizard mode, product-side wizard open mode, initial-submission triggering for agent actions, and an inline selector trigger.

  ### Why it matters

  Teams can start guided action flows from more places in the product, with launch behavior that better matches the surrounding UI.
</Update>

<Update label="April 21, 2026" description="Improved action logs and session visibility" tags={["Improvement"]}>
  ### What changed

  Improved action logs, session detail screens, and backend log handling.

  ### Why it matters

  Teams have better visibility into what happened during an action session when they need to review or troubleshoot it.
</Update>

<Update label="April 16, 2026" description="Simple mode and visible tool progress" tags={["Feature", "Wizards"]}>
  ### What changed

  Added simple mode for Candu Actions experiences and surfaced tool progress while agents are working.

  ### Why it matters

  Product teams can embed lighter-weight AI action experiences while still showing users when work is in progress.
</Update>

<Update label="April 13, 2026" description="Agent placement configuration" tags={["Feature"]}>
  ### What changed

  Added placement data models, backend storage, controller support, and product UI for configuring where Candu Actions agents appear.

  ### Why it matters

  Teams can manage where action experiences show up instead of treating placement as a one-off implementation detail.
</Update>

<Update label="April 13, 2026" description="Code Chat editing polish" tags={["Improvement"]}>
  ### What changed

  Added multi-line input and copy button support for Code Chat, plus better defaults for snapshot capture.

  ### Why it matters

  Code Chat helps teams talk directly to their product and discover possible actions; these editing improvements make longer prompts and repeated iteration easier.
</Update>

<Update label="April 9, 2026" description="Unified SDK foundation for Candu Actions" tags={["Improvement"]}>
  ### What changed

  Integrated the Candu Actions experience into the SDK and moved the product toward a unified SDK path.

  ### Why it matters

  A shared SDK foundation makes it easier to ship Candu Actions consistently across embedded and product-managed surfaces.
</Update>

<Update label="April 8, 2026" description="Session summaries for agent activity" tags={["Improvement"]}>
  ### What changed

  Added support for generating session summaries from agent activity and applying those summaries at the right points in the workflow.

  ### Why it matters

  Longer sessions become easier to review without reading every intermediate turn.
</Update>