Continue context
ComponentUpdates related to the context component of Continue.
All CONTEXT Features
- Introduced support for subagents.(@continuedev/config-yaml@1.39.0)
- Enabled faster Grok code processing (grok code fast 1).(v1.2.14-vscode)
- Introduced the ability to skip checking for updates when running in development mode in the CLI.(v1.2.14-vscode)
- Enabled always showing the context percentage in the CLI.(v1.2.14-vscode)
- Added a warning message to show configured Mission Control Providers (MCPs).(v1.2.14-vscode)
- Removed applied rules from the chat history display.(v1.2.14-vscode)
- Added reporting for tool failures.(v1.2.14-vscode)
- Enabled filtering CLI output lines that exceed 1000 characters.(v1.2.14-vscode)
- Kept the stream error toggle open by default.(v1.2.14-vscode)
- Designed thinking blocks to occupy less screen space.(v1.2.14-vscode)
- Added Sonnet lazy apply prompt functionality.(v1.2.14-vscode)
- Enabled Continue CLI Git AI integration for tracking AI-authored code.(v1.3.29-vscode)
- Added a staging blueprint (cn-staging) for isolated testing environments.(v1.3.29-vscode)
- Added a reusable Continue Agents workflow.(v1.3.29-vscode)
- Enabled users to select images using Cmd+A shortcut.(v1.3.29-vscode)
- Added support for the Xiaomi MiMo provider, specifically the MiMo-V2-Flash model.(v1.3.29-vscode)
- Added new supported models for Ask Sage.(v1.3.29-vscode)
- Updated Ask Sage models to support tool calling.(v1.3.29-vscode)
- Introduced Continue CLI Git AI integration for tracking AI-authored code.(v1.0.58-jetbrains)
- Added a staging blueprint (cn-staging) for isolated testing environments.(v1.0.58-jetbrains)
- Added a reusable workflow for Continue Agents.(v1.0.58-jetbrains)
- Enabled selecting images using Cmd+A shortcut.(v1.0.58-jetbrains)
- Added support for Xiaomi MiMo provider, specifically the MiMo-V2-Flash model.(v1.0.58-jetbrains)
- Added new supported models for Ask Sage, including updates to support tool calling.(v1.0.58-jetbrains)
- Added reusable Continue Agents workflow for enhanced automation.(@continuedev/openai-adapters@1.37.0)
- Introduced a staging blueprint (cn-staging) for isolated testing environments.(@continuedev/openai-adapters@1.37.0)
- Enabled selecting images using Cmd+A shortcut.(@continuedev/openai-adapters@1.37.0)
- Added the Xiaomi MiMo logo to assets.(@continuedev/openai-adapters@1.37.0)
- Introduced the new MiMo-V2-Flash model.(@continuedev/openai-adapters@1.37.0)
- Refined CLI bash tool truncation and added related documentation.(@continuedev/openai-adapters@1.37.0)
- Enabled case insensitive matching strategy for find and replace operations.(@continuedev/config-yaml@1.38.0)
All CONTEXT Bug Fixes
- Fixed an issue where the GH_TOKEN was not added to the continue-agents workflow.(@continuedev/config-yaml@1.39.0)
- Resolved a circular dependency by extracting tool names.(@continuedev/config-yaml@1.39.0)
- Fixed CLI compaction for missing tool results.(@continuedev/config-yaml@1.39.0)
- Added detection for context length errors.(@continuedev/config-yaml@1.39.0)
- Corrected the list of built-in tool names.(@continuedev/config-yaml@1.39.0)
- Fixed incorrect import order in ToolPermissionService.(@continuedev/config-yaml@1.39.0)
- Fixed decoding of URI-encoded pathname for WSL workspace paths.(@continuedev/config-yaml@1.39.0)
- Merged yaml.schemas settings to resolve conflicts.(@continuedev/config-yaml@1.39.0)
- Ensured proper resolution of WSL2 workspace paths when running terminal commands.(@continuedev/config-yaml@1.39.0)
- Resolved circular dependency issues in the subagent executor and subagent tool.(@continuedev/config-yaml@1.39.0)
- Wrapped fileURLToPath in a try-catch block for improved WSL2 compatibility.(@continuedev/config-yaml@1.39.0)
- Fixed context pollution between sessions in the CLI.(v1.2.14-vscode)
- Fixed an issue where 'instant reject all' did not work correctly in VS Code.(v1.2.14-vscode)
- Fixed typechecking for write file arguments.(v1.2.14-vscode)
- Fixed the apply prompt to correctly preserve comments in code changes.(v1.2.14-vscode)
- Fixed CLI validation for required parameters in tool calls.(v1.2.14-vscode)
- Fixed an issue where the prepended fim_prefix tag was incorrectly used in the mercury coder.(v1.2.14-vscode)
- Fixed a loading bug that occurred in headless mode.(v1.2.14-vscode)
- Prevented sensitive files from being included in next edit diffs.(v1.2.14-vscode)
- Fixed the command title from 'View History' to 'View Logs'.(v1.2.14-vscode)
- Fixed Mission Control Processor (MCP) error output and related bugs.(v1.2.14-vscode)
- Fixed an auto compaction loop in the CLI and ensured messages are pruned until valid.(v1.2.14-vscode)
- Fixed the use of system prompts for default endpoint type instances in the next edit operation.(v1.2.14-vscode)
- Fixed overzealous security regular expressions that were incorrectly flagging 'token' and 'credential' strings.(v1.3.29-vscode)
- Fixed issue where the system would fallback to a relative path when it shouldn't have for non-markdown files.(v1.3.29-vscode)
- Fixed crash/error handling by ensuring unhandled errors cause the process to exit with a non-zero code.(v1.3.29-vscode)
- Fixed corruption of the npm cache within the base blueprint.(v1.3.29-vscode)
- Fixed typo in context providers recommendation text.(v1.3.29-vscode)
- Fixed scope switching to correctly reflect changes without requiring a reload.(v1.3.29-vscode)
- Fixed an issue where hub errors were not being re-thrown for non-markdown hub slugs.(v1.3.29-vscode)
- Fixed CLI behavior to restart the CLI after a manual update.(v1.3.29-vscode)
- Fixed clarity issues related to parallel editing operations.(v1.3.29-vscode)
- Fixed the introductory message in the UI by changing 'Agent:' to 'Config:'.(v1.3.29-vscode)
- Fixed safe string handling in the continue-agents workflow by using environment variables.(v1.3.29-vscode)
- Fixed safe string handling in the Write job summary step by using environment variables.(v1.3.29-vscode)
- Fixed CLI context length handling and terminal output truncation.(v1.3.29-vscode)
- Fixed the lsTool command from incorrectly listing the filesystem root instead of the current folder.(v1.3.29-vscode)
- Fixed an issue where new rules were not immediately visible until a refresh.(v1.3.29-vscode)
- Fixed an issue where block secrets were not being rendered correctly by using a proxy for unrendered injected secrets.(v1.3.29-vscode)
- Fixed an issue where the GH_TOKEN was missing in the continue-agents workflow.(v1.3.29-vscode)
- Fixed context length error detection logic.(v1.3.29-vscode)
- Fixed CLI compaction when tool results were missing.(v1.3.29-vscode)
- Fixed handling of non-file URI schemes within the runTerminalCommand function, specifically for WSL2 environments.(v1.3.29-vscode)
- Fixed merging logic for yaml.schemas settings.(v1.3.29-vscode)
- Filtered out .md files when loading agent configurations.(v1.3.29-vscode)
- Fixed overzealous security regular expressions targeting 'token' and 'credential' strings.(v1.0.58-jetbrains)
- Fixed issue where the system would fallback to a relative path when the file was not markdown.(v1.0.58-jetbrains)
- Fixed crash/error handling by ensuring unhandled errors exit with a non-zero code.(v1.0.58-jetbrains)
- Fixed npm cache corruption issue within the base blueprint.(v1.0.58-jetbrains)
- Fixed typo in context providers recommendation text.(v1.0.58-jetbrains)
- Fixed scope switching to correctly reflect changes without requiring a reload.(v1.0.58-jetbrains)
- Fixed an issue where hub errors were not re-thrown for non-markdown hub slugs.(v1.0.58-jetbrains)
- Fixed CLI behavior to restart the CLI after a manual update.(v1.0.58-jetbrains)
- Fixed parallel edit clarity issues.(v1.0.58-jetbrains)
- Fixed the introductory message in the UI to correctly display 'Config:' instead of 'Agent:'.(v1.0.58-jetbrains)
- Fixed issues in the continue-agents workflow by using environment variables for safe string handling in job summary steps.(v1.0.58-jetbrains)
- Fixed CLI context length issues and terminal output truncation.(v1.0.58-jetbrains)
- Fixed the lsTool command to list the current folder contents instead of the filesystem root.(v1.0.58-jetbrains)
- Fixed an issue where new rules were not immediately visible until a refresh.(v1.0.58-jetbrains)
- Fixed an issue where proxying was required for unrendered injected block secrets.(v1.0.58-jetbrains)
- Fixed context length error detection logic.(v1.0.58-jetbrains)
- Fixed CLI compaction for missing tool results.(v1.0.58-jetbrains)
- Fixed handling of non-file URI schemes in runTerminalCommand for WSL2 environments.(v1.0.58-jetbrains)
- Fixed merging logic for yaml.schemas settings.(v1.0.58-jetbrains)
- Fixed missing hub mock rejection in tests.(@continuedev/openai-adapters@1.37.0)
- Ensured environment variables are used in the Write job summary step.(@continuedev/openai-adapters@1.37.0)
- Changed the introductory message label from 'Agent:' to 'Config:' for clarity.(@continuedev/openai-adapters@1.37.0)
- Clarified that editing cannot occur in parallel with itself.(@continuedev/openai-adapters@1.37.0)
- Addressed CLI compaction for missing tool results.(@continuedev/openai-adapters@1.37.0)
- Implemented CLI restart mechanism for manual updates.(@continuedev/openai-adapters@1.37.0)
- Improved detection and handling of context length errors.(@continuedev/openai-adapters@1.37.0)
- Implemented context length fixes and truncation logic.(@continuedev/openai-adapters@1.37.0)
- Prevented fallback to relative paths when the file is not markdown.(@continuedev/openai-adapters@1.37.0)
- Fixed lint errors and updated tests related to markdown-only fallback.(@continuedev/openai-adapters@1.37.0)
- Injected blocks tests for CLI secret resolution.(@continuedev/openai-adapters@1.37.0)
- Reduced vulnerabilities in package.json and package-lock.json for continue-sdk.(@continuedev/openai-adapters@1.37.0)
- Prevented string interpolation issues in remaining workflow steps.(@continuedev/openai-adapters@1.37.0)
- Fixed an issue related to hub error handling for non-markdown hub slugs.(@continuedev/openai-adapters@1.37.0)
- Regenerated package-lock.json to include the missing @types/node@25.0.3.(@continuedev/openai-adapters@1.37.0)
- Removed symlink logic from both production and staging blueprint templates.(@continuedev/openai-adapters@1.37.0)
- Ensured a newly created rule is immediately shown.(@continuedev/openai-adapters@1.37.0)
- Used environment variables for safe string handling in the continue-agents workflow.(@continuedev/openai-adapters@1.37.0)
- Implemented proxy usage for unrendered injected block secrets.(@continuedev/openai-adapters@1.37.0)
- Fixed issues related to context length, truncation, and usage token handling in OpenAI adapters, including defensive type checks and fallbacks for stream usage.(@continuedev/config-yaml@1.38.0)
- Resolved issues with tool_choice format and usage token emission in OpenAI streams, specifically addressing double-emission in Vercel SDK streams.(@continuedev/config-yaml@1.38.0)
- Fixed an issue where JSON contents of create_new_file operations were not handled correctly.(@continuedev/config-yaml@1.38.0)
- Fixed a ConcurrentModificationException when accessing keymaps in the IntelliJ extension.(@continuedev/config-yaml@1.38.0)
- Expanded model capability detection in the CLI to correctly include Llama, Nemotron, and Mistral models.(@continuedev/config-yaml@1.38.0)
- Fixed path conversion issues (path to URI and vice versa) within the CLI.(@continuedev/config-yaml@1.38.0)
- Ensured cross-target LanceDB binaries are correctly copied during builds.(@continuedev/config-yaml@1.38.0)
- Fixed logic so that tree-sitter lookup in .js and .ts files now correctly picks up only the last preceding comment before a code block.(@continuedev/config-yaml@1.38.0)
- Fixed an issue where the system would fallback to a relative path even when the file was not markdown.(@continuedev/config-yaml@1.38.0)
Releases with CONTEXT Changes
@continuedev/config-yaml@1.39.01 feature11 fixesThis release introduces a major new capability with the introduction of subagents, allowing for more complex task execution workflows. Several critical bug fixes address issues related to WSL path resolution, dependency management, and CLI tool result handling. Additionally, several underlying dependencies, including monaco-editor, have been upgraded.
v1.2.14-vscode10 features12 fixesThis release focuses heavily on improving the Command Line Interface (CLI) experience, including better context visibility and stability fixes. New features include faster Grok processing and UI refinements like smaller thinking blocks. Numerous bug fixes address issues related to context handling, prompt application, and headless mode stability.
v1.3.29-vscode7 features22 fixesThis release introduces significant new capabilities, including Git AI integration via the CLI and a new staging blueprint for isolated testing. Key fixes address security regexps, CLI stability, and improved handling of context lengths and tool results. The update also adds support for the Xiaomi MiMo-V2-Flash model and enhances documentation across several areas.
v1.0.58-jetbrains6 features19 fixesThis release introduces significant new capabilities, including Git AI integration via the CLI and a dedicated staging blueprint for isolated testing. Numerous bug fixes address issues related to CLI stability, context handling, and UI clarity. The update also includes dependency upgrades and documentation improvements for integrations and cloud agents.
@continuedev/openai-adapters@1.37.06 features19 fixesThis release introduces a reusable Continue Agents workflow and a new staging blueprint (cn-staging) for isolated testing. Key fixes focus on improving context length handling, resolving CLI update issues, and enhancing secret resolution security. Dependencies like mocha and monaco-editor have also been upgraded.
@continuedev/config-yaml@1.38.01 feature9 fixesThis release focuses heavily on stabilizing the OpenAI adapters, improving token usage tracking across various streaming scenarios, and fixing several CLI detection and path resolution issues. Key fixes include better handling of context length and ensuring compatibility with newer models like Llama and Mistral.