66 posts tagged with "platform"

🚀 Highlights​

Version 1.1.0 brings faster task startup, more capacity for Quick run, and clearer target access management.

✨ New Features​

• Release notes in Workshop: Click the product name and version in the status bar to see what’s new.

🛠 Improvements​

• Faster task startup: Reduced delays between submitting a task and execution, with quicker status updates and less repeated preparation when rerunning unchanged Aleph code.
• Clearer target sharing: The access dialog now shows the target name, shared-user count, and when each user was added, with clearer progress indicators when adding or removing access.
• More consistent appearance: Refined Workshop’s dark theme, navigation buttons, and loading indicators.

🐛 Fixes​

• Fixed search results opening multiple times on double-click. Modified clicks now select results without opening them.
• Fixed help tooltips appearing behind dialogs or becoming unavailable to screen readers.
• Fixed Quick run tasks failing prematurely while waiting for cloud capacity.
• Improved cancellation of tasks awaiting dispatch, preventing delayed launches from running canceled work.

⚙️ Internal / Technical Changes​

• Improved background task coordination to reduce waiting between execution stages.
• Added warm execution capacity for Quick run to reduce cold-start delays.

🚀 Highlights​

Patch release increasing reliability of Aleph startup on self-hosted targets.

🐛 Fixes​

Fixed “Failed to validate execution token” errors caused by differences between API and target clocks.

🚀 Highlights​

Kothar Platform 1.0 brings a rebuilt Workshop, a unified task system, and a more capable Kai—bringing code, scientific data, compute, and results together in one workspace.

• One task system. Aleph scripts, tests, longer jobs, and OpenQASM executions now share a consistent way to track progress, read logs, and explore results.
• A fresh Workshop. Clearer typography, improved readability, a refined dark theme, and a brand-new light mode.
• An upgraded Kai. Bring your documents and data into the conversation, investigate results, write and check Aleph code, and carry out work with visible progress and reviewable changes.

✨ New Features​

• Kai attachments and scientific inspection. Attach PDFs, images, code, and data through uploads, drag and drop, or pasted images. Kai can inspect HDF5 datasets, task results, and execution logs, and search Aleph documentation and arXiv with citations.
• Explicit Ask and Work modes. Ask explores and explains without changing files or running scripts. Work can edit files, run Aleph scripts and tests, and inspect their results.
• Plans you can review. Use Make a plan to discuss an approach before execution. Revise it, select Start work when ready, and follow its progress. Changes cards provide access to before-and-after file diffs.
• Fix with Kai. Send a failed Aleph task to Kai with its failure context directly from the task or Output view.
• Compute for different workloads. Use Quick run for small experiments without setting up an agent, connect your own infrastructure, or choose a managed Large jobs target. Bring your own targets, and share them with other users.
• OpenQASM in Workshop. Edit .qasm files, select a compatible target, configure shots, and inspect quantum results alongside your other tasks. Quantum execution remains available to accounts with quantum access.
• Native HDF5 exploration. Browse groups, attributes, and datasets; inspect multidimensional slices and complex values; create line, scatter, and heatmap views; and save editable .figure snapshots. The read-only browser viewer supports files up to 128 MiB, with additional limits on individual reads and plots.
• API token management. Create scoped API tokens, choose their permissions and expiration, and revoke them from Account settings → API tokens.

🛠 Improvements​

• A more flexible workspace. Arrange split editors, move tool views between sidebars and the bottom panel, and detach Kai or Output into separate windows. A welcome tour and keyboard-shortcut guide help you find your way around.
• Better execution visibility. Follow live output without leaving your editor, inspect structured test results, and explore task hierarchies, resource metrics, inputs, and downloadable artifacts. Task search supports filters such as status, target, creator, and duration.
• Trace results back to their inputs. Tasks retain the exact saved input versions they used. File provenance links generated outputs back to their task and script.
• Richer file history. Preview earlier versions, compare text changes, inspect author information, and restore a version without deleting its history.
• Safer editing and recovery. Local text drafts survive reloads, conflicting server updates preserve your edits, and split views share the same working copy.
• Improved Aleph editing. Updated language integration and highlighting, runtime selection, and file drops that insert the appropriate Aleph reference for scripts, HDF5, CSV, JSON, NumPy, and lattice models.
• Refreshed scientific views. Figures offer graphical and JSON editing. The native lattice-model editor includes mathematical labels and SVG/PNG export with a separate export-theme choice.
• Rebuilt Sparks. Publish immutable snapshots from Workshop, manage them through My Sparks, and share public previews without requiring viewers to sign in. Visitors can download files or copy a selection into their own workspace.
• Loading on demand. Workspace folders load as needed, while editors and scientific viewers load when opened. Heavy HDF5 and geometry processing runs in background workers.

⚙️ Internal / Technical Changes​

• A simpler Go backend. The API and execution agent have been rewritten in Go, with feature-focused API modules and PostgreSQL providing durable coordination and event history.
• A self-contained agent binary. Linux AMD64 and ARM64 agents are statically linked, with no dynamically linked library dependencies—not even libc. Computational runtimes such as Aleph are downloaded and verified separately.
• Durable connections and events. Agents communicate through a Protobuf-over-WebSocket protocol. Persisted commands and events support reconnects across API instances without relying on sticky sessions or Redis coordination.
• A rebuilt frontend foundation. Workshop and Sparks use SolidJS, a shared design system, and reusable scientific viewers, with explicit boundaries between editing, rendering, and application state.

⚠️ Breaking Changes​

• API and SDK integrations need updating. The new platform uses the workspace, target, and task API. Existing integrations should migrate to the new client interfaces.
• Python SDK 1.0 replaces the legacy SDK. The package remains kotharcomputing, now follows the platform release version, and requires Python 3.11 or later.
• Existing credentials and agents need replacing. Legacy API tokens and agent registrations do not carry over.

🧪 Migration Notes​

• Continue using your existing account at https://workshop.kotharcomputing.com.
• Saved workspace files and their migrated history, historical jobs and quantum tasks, chat transcripts, and published Sparks are available in the new platform. Existing Spark links retain their public IDs.
• Historical jobs now appear in Tasks. Imported chats remain readable, and new messages use the redesigned Kai; previous tool operations are not resumed.
• Workshop starts with a fresh layout. Unsaved drafts that existed only in the old browser application were not part of the migration.
• Create replacement API tokens, update integrations, and reconnect personal agents using the new launch instructions.
• If something appears missing or behaves unexpectedly, please let us know on Discord. Thank you for your patience during the migration—and for helping us shape Kothar 1.0.

🚀 Highlights​

• Updated agent signature handling in preparation for upcoming Aleph runtime updates

🛠 Improvements​

• Improved agent signature validation to support upcoming Aleph runtime capabilities.

🐛 Fixes​

• Minor internal reliability improvements.

🚀 Highlights​

• Upgraded the underlying platform runtime

🛠 Improvements​

• Updated the underlying runtime to benefit from the latest performance, reliability, and security improvements.

🚀 Highlights​

• Internal release preparing for upcoming platform capabilities

🛠 Improvements​

• Added platform foundations and APIs supporting upcoming features that will be announced in a future release.

🐛 Fixes​

• Minor internal fixes and maintenance improvements.

🚀 Highlights​

• Internal release preparing for upcoming platform capabilities

🛠 Improvements​

• Added platform foundations and APIs supporting upcoming features that will be announced in a future release.

🐛 Fixes​

• Minor internal fixes and maintenance improvements.

🚀 Highlights​

• Standardized handling of Kothar file content types across the Platform and Sparks
• File versions now include attribution information
• SDK updates and dependency upgrades

✨ New Features​

• File attribution
  • File reads now include information about who last created, updated, or restored the file version.
  • Available through both the API and SDKs.

🛠 Improvements​

• Content type normalization

  • Kothar file formats now use consistent content types across uploads, downloads, imports, and Sparks.
  • Improves interoperability and file handling consistency.

• SDK enhancements

  • Added content-type helpers and constants to the SDKs.

• Platform maintenance

  • Updated backend dependencies across the API, agents, and infrastructure components.

🚀 Highlights​

• Patch release updating Kai model configuration

🛠 Improvements​

• Adjusted Kai model settings to improve overall response quality, reliability, and user experience.

🚀 Highlights​

• Patch release fixing a file upload regression

🐛 Fixes​

• Fixed a regression introduced in 0.101.3 that could prevent file uploads from completing successfully.

🚀 Highlights​

• Patch release improving file transfer performance

🐛 Fixes​

• Fixed issues that could introduce unnecessary latency during file upload and download operations.

🛠 Improvements​

• Improved responsiveness and reliability of file transfer workflows.

🚀 Highlights​

• Patch release improving cache behavior and responsiveness

🛠 Improvements​

• Improved cache response handling to enhance performance and reliability.

🐛 Fixes​

• Minor stability improvements related to caching.

🚀 Highlights​

• Patch release fixing a permission-related issue

🐛 Fixes​

• Fixed a minor permission issue affecting specific platform operations.

🚀 Highlights​

• Maintenance release with bug fixes and edge-case improvements

🐛 Fixes​

• Fixed several minor bugs across the platform.
• Improved handling of edge cases to enhance reliability and stability.

🚀 Highlights​

• Higher-resolution PNG exports for CeTZ and Quill diagrams
• Runtime upgrades for both the API and agents

🛠 Improvements​

• Diagram exports

  • Increased PNG export resolution for CeTZ diagrams and Quill quantum circuits, resulting in sharper exported images.

• Runtime updates

  • Updated the underlying runtime used by both the Platform API and agents.
  • Includes ongoing performance, reliability, and security improvements.

🐛 Fixes​

• Minor stability and maintenance improvements.

🚀 Highlights​

• Patch release with internal bug fixes

🐛 Fixes​

• Internal bug fixes and reliability improvements.

🚀 Highlights​

• Added platform APIs for upcoming capabilities
• Improved Kai error reporting

🛠 Improvements​

• Platform readiness

  • Added new APIs supporting upcoming features that will be announced later.

• Kai reliability

  • Improved error reporting and diagnostics to provide clearer feedback when issues occur.

🐛 Fixes​

• Minor fixes related to Kai error handling and reporting.

🚀 Highlights​

• Full support for historical file versions
• Jobs now execute against pinned file versions for improved reproducibility
• File creation and updates during job execution are now tracked

✨ New Features​

• Historical file versions

  • List available versions of a file.
  • Retrieve or download a specific historical version.
  • Restore a previous version when needed.

• Job file version pinning

  • When a job is scheduled, both the entry point and its dependencies are pinned to specific file versions.
  • Pinned version information is available in Job Details.

• Execution file tracking

  • Files created or modified during Aleph execution are now tracked.
  • Job Details report:
    • Created or updated action
    • File path
    • Resulting file version

🛠 Improvements​

• Improved job reproducibility and auditability through version-aware execution.

🚀 Highlights​

• Added support for manually launching single-use agents for job execution

✨ New Features​

• Single-use agents (limited access)
  • Users with access can now manually launch dedicated single-use agents to run jobs.
  • These agents are created specifically for a job workload and are intended for isolated execution scenarios.

🛠 Improvements​

• Expanded job execution options for advanced workflows.

🚀 Highlights​

• Aleph tests can now be executed directly from inline content
• Kai can now access past conversations within the same workspace

✨ New Features​

• Inline test execution

  • Aleph tests can now be run directly from editor content, without requiring a saved file.
  • Brings test execution in line with the existing direct execution workflow.

• Kai conversation history

  • Kai can now access previous conversations from the same workspace and user.
  • Helps provide better continuity and context across discussions.

🚀 Highlights​

• Maintenance release with a minor bug fix

🐛 Fixes​

• Fixed a minor issue to improve overall platform reliability.

🚀 Highlights​

• Runtime upgrade for improved platform foundations
• Added support for upcoming Workshop capabilities

🛠 Improvements​

• Runtime update

  • Updated the underlying runtime version for continued stability, performance, and security improvements.

• Platform readiness

  • Added new platform capabilities required for upcoming Workshop features.

🐛 Fixes​

• Minor internal fixes and reliability improvements.

🚀 Highlights​

• Maintenance release focused on stability, reliability, and internal improvements

🛠 Improvements​

• Upgraded core dependencies and internal infrastructure components.
• Internal refactoring to improve maintainability and robustness.
• Improved handling of various edge cases across the platform.

🐛 Fixes​

• Miscellaneous bug fixes and reliability improvements.

🚀 Highlights​

• Kai now supports diagram and quantum circuit generation using Typst Quill and CeTZ
• Improved Kai code generation and diff quality

✨ New Features​

• Diagram & quantum circuit generation
  • Kai can now understand and generate:
    • Diagrams using the Typst CeTZ dialect
    • Quantum circuits using Typst Quill

🛠 Improvements​

• Kai generation quality
  • Updated Kai system prompt to improve:
    • Generated code quality
    • Diff consistency and reliability

🐛 Fixes​

• Minor reliability improvements across Kai workflows.

🚀 Highlights​

• Kai now understands the new Aleph test framework and can generate tests alongside code
• Runtime upgrade improving network handling and reliability

🛠 Improvements​

• Kai test framework support

  • Updated Kai system prompt with knowledge of the new Aleph test framework.
  • Kai can now generate tests alongside Aleph code.

• Runtime upgrade

  • Updated the underlying runtime version to improve network handling, stability, and reliability.

🐛 Fixes​

• Minor networking and runtime-related fixes.

🚀 Highlights​

• Added platform support for the new Aleph test mode

✨ New Features​

• Aleph test mode support
  • Added SDK, API, and agent support for the new Aleph test mode.
  • Workshop integration is coming soon, with Kai support planned afterward.

🛠 Improvements​

• Expanded platform capabilities to support upcoming Aleph testing workflows.

🚀 Highlights​

• Maintenance-focused release with reliability and quality improvements
• Better Kai stability and arXiv availability
• Reduced monitoring noise and improved documentation sourcing

🛠 Improvements​

• Kai reliability

  • Reduced erroneous tool error reporting in edge cases.
  • Improved arXiv rate-limit handling for better availability and responsiveness.

• Documentation integration

  • Kai now sources the Aleph specification directly from the public documentation website.

• Operational improvements

  • Internal monitoring refinements to reduce alert noise and improve signal quality.
  • General code maintenance and cleanup across the platform.

🚀 Highlights​

• Patch release improving API stability and networking reliability

🐛 Fixes​

• Fixed descriptor leaks in the File REST API.
• Fixed an issue related to TLS handling.

🚀 Highlights​

• Patch release improving Kai reliability and schema handling

🛠 Improvements​

• Improved figure and lattice model schema handling in Kai for more reliable validation and editing workflows.
• Kai now gracefully handles:
  • Maximum tool round limits
  • Oversized context errors

🚀 Highlights​

• Kai now supports figures and lattice model files
• Faster Kai processing through system prompt optimizations

✨ New Features​

• Figure & lattice model support
  • Kai can now:
    • Read figure and lattice model files
    • Create new files
    • Edit and Validate existing content

🛠 Improvements​

• Faster Kai responses
  • Optimized Kai system prompt for improved processing speed and efficiency.

🚀 Highlights​

• Major upgrades to Kai intelligence, memory, and scientific research capabilities
• Kai now supports long-term workspace memory
• Kai can search and read ArXiv scientific papers
• Aleph code generated by Kai is now automatically formatted using the Aleph Language Server

✨ New Features​

• Kai workspace memory

  • Kai now supports durable long-term memory on a per-user, per-workspace basis.
  • Enables better continuity and contextual understanding across conversations.

• ArXiv paper search and reading

  • Kai can now search and read scientific papers from ArXiv.
  • Improves research workflows, literature exploration, and scientific recommendations.

🛠 Improvements​

• Kai system prompt optimization

  • Improved response quality, efficiency, and consistency.

• Automatic Aleph code formatting

  • Kai now formats generated Aleph code using the Aleph Language Server for cleaner and more consistent outputs.

• Python SDK enhancements

  • AlephLanguageServerClient now supports:
    • Code formatting
    • AST filtering capabilities

🐛 Fixes​

• Minor reliability and integration improvements across Kai workflows.

🚀 Highlights​

• Kai now dynamically optimizes model usage for better reliability and responsiveness

🛠 Improvements​

• Smarter model selection

  • Kai can now switch models dynamically based on available quotas and workload type.
  • Lightweight, low-reasoning models are used for simpler tasks to improve responsiveness and capacity availability.

• Improved reliability

  • Better handling of provider limits and quota pressure during peak usage.

🚀 Highlights​

• Major Kai infrastructure upgrade to improve reliability and reduce capacity issues
• Kai can now read saved workspace files for better context awareness
• SDKs updated to use the new Aleph Language Server endpoint

✨ New Features​

• Kai workspace file reading
  • Kai can now read files directly from the workspace to better understand project context.
  • Currently limited to files and versions saved to the backend.

🛠 Improvements​

• Kai provider migration

  • Migrated Kai to a new provider backend.
  • Added automatic conversation summarization.
  • Optimized token usage and system prompts for faster and more reliable responses.
  • These changes should significantly reduce the capacity issues encountered in recent weeks.

• SDK updates

  • SDKs now target the new Aleph Language Server URL.

⚠️ Breaking Changes​

• Existing Kai conversations are now read-only

  • Due to the provider migration and conversation format updates, users must start new conversations to continue using Kai.

• Aleph Language Server URL migration

  • The previous LSP endpoint will be retired soon.
  • Integrations should migrate to the updated endpoint.

🧪 Migration Notes​

• Start new Kai conversations after updating.
• Update integrations and SDK configurations to use the new Aleph Language Server URL.

🚀 Highlights​

• Patch release improving Kai reliability

🐛 Fixes​

• Fixed issues with Kai related to the AI provider.

🚀 Highlights​

• Improved reliability of Aleph output capture
• Enhanced platform security

🐛 Fixes​

• Fixed an issue where output or print statements at the end of execution could be missed or truncated.

🛠 Improvements​

• Security hardening
  • Strengthened platform security certificates for improved protection.

🚀 Highlights​

• Improved reliability when cancelling jobs and executions
• Kai gains workspace file awareness for better context
• Python SDK enhanced with AST export support

✨ New Features​

• Kai workspace awareness

  • Kai can now list and search files in the workspace.
  • Improves context understanding and relevance of responses.

• AST export (Python SDK)

  • Aleph Language Server support now includes AST export via the analyze endpoint.

🛠 Improvements​

• Cancellation reliability
  • The API now automatically re-sends cancellation signals if executions or jobs are still running.
  • Reduces cases where cancellations fail silently.

🚀 Highlights​

• Improved reliability for Kai requests with automatic retries
• Python SDK expanded with Aleph Language Server support

✨ New Features​

• Aleph Language Server client (Python)
  • Added AlephLanguageServerClient to the Python SDK.
  • Full request and response types are now exported for easier integration.

🛠 Improvements​

• Kai request reliability
  • Automatic retries added to improve success rate for transient failures.

Release description not available.

🚀 Highlights​

• Kai updated to leverage the latest Aleph APIs for faster and more efficient responses

🛠 Improvements​

• Kai system prompt optimization
  • Updated to take advantage of the latest Aleph APIs.
  • Improved efficiency and response speed.

🚀 Highlights​

• Patch release improving cloud job reliability

🐛 Fixes​

• Fixed a race condition that could prevent some cloud jobs from starting correctly.

🚀 Highlights​

• Fix for a Kai error affecting certain prompts
• Runtime upgrade for improved performance and security

🐛 Fixes​

• Fixed an issue in Kai that could trigger a "finishReason" error for certain prompts.

🛠 Improvements​

• Runtime upgrade
  • Improved overall performance.
  • Enhanced security and stability.

🚀 Highlights​

• Patch release addressing Kai credit usage issues

🐛 Fixes​

• Updated Kai configuration to enforce a specific AI provider, resolving credit-related issues experienced by some users.

🚀 Highlights​

• Improved handling and visibility of transient errors
• Internal groundwork for upcoming bindings

🛠 Improvements​

• Transient error handling

  • More robust detection and reporting of temporary failures to improve reliability and troubleshooting.

• Platform readiness

  • Background updates preparing the platform for upcoming bindings and integrations.

🚀 Highlights​

• Improved API documentation and SDKs
• runtimeId is now optional when creating executions and jobs

🛠 Improvements​

• API & SDK enhancements

  • Clearer API documentation.
  • Updated SDKs for better developer experience and consistency.

• Simplified execution & job creation

  • runtimeId is now optional when creating executions or jobs.
  • Defaults automatically to the current Aleph version if not specified.

🧪 Migration Notes​

• Existing integrations can omit runtimeId unless a specific runtime version is required.

🚀 Highlights​

• Internal pre-release focused on improving interoperability and integration scenarios
• No user-facing changes in this release.

🛠 Improvements​

• Backend enhancements to support broader integration use cases.
• Internal changes preparing the platform for upcoming interoperability features.

🚀 Highlights​

• Kai model updated to improve AI code generation quality

🛠 Improvements​

• Kai model upgrade
  • Improved code generation accuracy and consistency.
  • Better adherence to project structure and conventions.
  • More reliable diffs and suggested changes.

🚀 Highlights​

• Improved execution diagnostics with signal capture
• Safeguard added to prevent excessive file uploads during executions

✨ New Features​

• Execution signal capture
  • In addition to exit codes, the platform now captures the process termination signal.
  • Provides clearer insight into whether a process exited normally or was interrupted (e.g., killed, timeout, etc.).

🛠 Improvements​

• Upload safety guard
  • If more than 100 files are created or modified during an execution:
    • All affected files are bundled into a single ZIP archive.
    • The archive is uploaded as-is to the platform.
  • Prevents rogue or misconfigured scripts from uploading excessive numbers of files.

🧪 Migration Notes​

• No action required for users.
• Workflows generating large numbers of files may now produce a ZIP artifact instead of individual files.

🚀 Highlights​

• Patch release fixing file listing pagination

🐛 Fixes​

• Fixed an issue affecting pagination when listing files.

🚀 Highlights​

• Kai updated to better support figures and admonitions in generated content

🛠 Improvements​

• Kai system prompt update
  • Improved support for generating figures.
  • Improved handling of Markdown admonitions (note, tip, warning, etc.).

🐛 Fixes​

• Minor internal improvements to AI content formatting.

🚀 Highlights​

• Internal platform updates and maintenance release

🚀 Highlights​

• Patch release fixing default timeout handling for Cloud Agents

🐛 Fixes​

• Fixed handling of default timeouts for Cloud Agents to ensure executions behave as expected.

🚀 Highlights​

• Cloud agents now report accurate system information
• Improved error reporting for cloud job scheduling failures

🛠 Improvements​

• Accurate cloud agent system info

  • Cloud agents now correctly report CPU core count and total memory.

• Better cloud job error reporting

  • Jobs that fail due to cloud provisioning issues now surface clear failure states instead of hanging in scheduled or staled status.

🐛 Fixes​

• Minor fixes to improve cloud execution reliability.

🚀 Highlights​

• CPU usage metrics updated to follow Linux conventions
• New Cloud Agents for Jobs offering dedicated, high-performance machines (limited preview)
• Minor bug fixes and performance improvements

✨ New Features​

• Cloud agents for jobs
  • Jobs can now run on dedicated cloud agents with powerful machine configurations.
  • Designed for heavy, long-running, or performance-sensitive workloads.
  • Limited preview for now, we will open it up gradually

🛠 Improvements​

• CPU percent metrics aligned with Linux standards
  • CPU usage now reports 100% = one CPU core, instead of a percentage of total machine CPUs.
  • Metrics are now consistent with standard Linux tools and expectations.

🐛 Fixes​

• Minor bug fixes and general performance improvements.

⚠️ Breaking Changes​

• CPU metrics interpretation has changed
  • CPU percentages now follow Linux semantics.
  • Jobs executed before this release will not be retroactively updated and may show inconsistent CPU values.

🚀 Highlights​

• Point release focused on security and stability improvements

🛠 Improvements​

• Security hardening

  • Tighter API security headers and CORS handling to better protect requests.

• Stability improvements

  • Improved backend reliability for smoother execution and job handling.

🐛 Fixes​

• Minor fixes to improve overall robustness.

⚙️ Internal / Technical Changes​

• Minor update to the Agent Cloud Model to simplify alignement

🚀 Highlights​

• Renamed Communal Agent to Interactive (Shared) for clarity
• Improved load balancing for shared executions
• Added in-product guidance for understanding cloud agents

✨ New Features​

• Interactive (Shared) agent

  • The former Communal Agent is now called Interactive (Shared).
  • Provides a shared, cloud-hosted execution environment for interactive workloads.

• Cloud agent tooltip

  • Added a tooltip to explain the cloud agent model and when to use shared vs personal agents.

🛠 Improvements​

• Better load balancing
  • Improved execution distribution on shared agents for more consistent performance.

⚙️ Internal / Technical Changes​

• Refactored communal agents into a more general Cloud agent concept.

🚀 Highlights​

• Communal agents are now available for direct executions (internal user only ATM).

✨ New Features​

• Communal agents
  • A shared, load-balanced agent is now available for direct executions.
  • Communal agents are discoverable via the agents list for users who have access to it.
  • Designed for lightweight, shared execution without requiring an agent.

🚀 Highlights​

• AI Assistant now produces shorter, clearer chat summaries
• Improved diff generation with stricter rules for cleaner, more unified patches
• AI Assistant can now create Markdown files in addition to Aleph code

✨ New Features​

• Markdown file creation via AI Assistant
  The AI Assistant can now generate Markdown files directly, alongside Aleph source files.

🛠 Improvements​

• Shorter AI chat summaries
  Chat summaries are now more concise and focused, making conversations easier to scan and review.

• Stricter unified diff generation

  • Tighter rules ensure diffs are more consistent and easier to apply.
  • Reduces malformed or overly fragmented patches.
  • Improves reliability when applying AI-generated changes.

🚀 Highlights​

• System-level metrics are now collected during executions for better observability
• AI Chat assistant has been renamed
• AI Chat system prompt updated to significantly reduce hallucinations and improve API correctness

✨ New Features​

• Execution system metrics collection
  • The agent now periodically collects:
    • CPU usage
    • Memory usage (Resident Set Size)
  • For direct executions, a summarized metrics report is sent at the end of the execution.
  • For job executions, all collected samples are streamed to the API periodically during runtime.

🛠 Improvements​

• Improved AI Chat reliability
  • Updated system prompt to enforce stronger adherence to Aleph APIs.
  • Reduced hallucinations and off-spec responses when generating code or explanations.

🚀 Highlights​

• Major refactor of the AI Chats API to improve reliability, extensibility, and alignment with the OpenAI API
• Streaming AI responses now supported for real-time content generation
• Backend now supports feature flags for safer rollouts
• New APIs added to update job names and notes

✨ New Features​

• Streaming AI responses
  AI-generated content can now be streamed as it is produced, enabling more responsive user experiences.

• Client + server tool support
  The AI API now supports client-side tools in addition to server-side tools, unlocking more flexible AI workflows.

• Job metadata API
  New endpoints allow updating job names and notes

• Backend feature flags
  Feature flag support added in the platform (in addition to the Workshop) to progressively enable or disable features without redeploying.

🛠 Improvements​

• AI API aligned with OpenAI’s canonical format
  The AI Chats API now uses a messages/roles structure consistent with the OpenAI API, simplifying integrations and future compatibility.

• Improved editor context handling
  Editor context is now explicitly passed and correctly processed by the model.

• Usage tracking per conversation

🐛 Fixes​

• Streaming endpoints now return errors correctly instead of silently failing.
• Improved request lifecycle handling to prevent orphaned or hanging AI requests.

⚙️ Internal / Technical Changes​

• Refactored AI tools container injection into a dedicated module.
• Added graceful cancellation of in-flight AI requests when the API shuts down (via AsyncDisposable callbacks).
• Client package updated to match the new AI API behavior and contracts.

⚠️ Breaking Changes​

• AI Chats API has been significantly refactored
  • Request and response formats have changed
  • System prompt behavior is different
  • Streaming behavior is now first-class

⚠️ This will break the existing AI Chat feature in production until the Workshop is updated.

🚀 Highlights​

A clearer and more capable AI experience behind the scenes, with improved model flexibility and stronger Aleph code support.

⚙️ Internal / Technical Changes​

• Internal users can now select which AI model to use.
• AI Chats now include Aleph code parsing and validation during code generation.

🚀 Highlights​

• Introduction of API tokens to support secure automation and machine-to-machine integrations.
• Improved internal AI Chat tooling and a more secure SSE/EventSource implementation in the TypeScript client.

✨ New Features​

• API Tokens — Enable automated workflows and machine-to-machine integrations. Each token is tied to a workspace and carries its own identity and permission scope.

⚙️ Internal / Technical Changes​

• Internal users can now choose between multiple presets for AI Chat features.
• The TypeScript client package now uses a refactored SSE/EventSource implementation with improved security.

🚀 Highlights​

• Improved onboarding flow for new users.
• Early groundwork completed for upcoming AI-assistant features.

✨ New Features​

• Personal workspace initialization — New users now receive a pre-populated workspace on their first login, making it easier to get started immediately.

🐛 Fixes​

• Resolved an intermittent issue where rate limits on job and user listings could cause partial results. A caching layer now reduces request pressure and prevents these failures.

⚙️ Internal / Technical Changes​

• Pre-release of the AI Chats feature is now available internally for testing and validation.

🚀 Highlights​

• Fix a bug that prevented some users to search in files
• Update agent reconnection logic

🛠 Improvements​

• Agents now wait more predictably between connection instances, and give up after 3 days of unsuccessful attempts
• Agents logging is less verbose

🐛 Fixes​

• Resolve a bug in search that prevented users to search in files if one of the file is empty

🧪 Migration Notes​

• Agents will self-update automatically

⚙️ Internal / Technical Changes

• Add internal endpoints for management

🧩 Fix

Commented include statements in Aleph scripts are no longer parsed as dependencies by the Agent. Example:

// include "dependency.aleph"

Previously, this line could incorrectly trigger dependency resolution and fail the execution. It is now correctly ignored.

🔧 Impact

This fix prevents incorrect dependency lookups and ensures consistent execution graphs when using commented or disabled includes.