◆ AI Coding Agents

Continue

v1.2.22-vscode open-source

models:
  - provider: openai
    model: gpt-4o
    useResponsesApi: false
cn review
cn checks
{
  "tools": {
    "run_terminal_command": {
      "prompt": "Only run read-only commands. Never modify files."
    }
  }
}
continue --agent ./agents/my-agent.yaml
continue oauth
continue --headless
cn ls
cn ls
cn ls
cn ls
{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["-y", "my-mcp-server"],
      "apiKey": "sk-my-bearer-token"
    }
  }
}
cn --mcp https://my-mcp-server.example.com/sse
cn --id <agent-id>
curl -X POST http://localhost:<port>/pause
mcpServers:
  - name: my-registry-server
    serverName: custom-server-name
{
  "MY_API_KEY": "abc123",
  "ANOTHER_VAR": "value"
}
cn status
cn serve --id my-session
cn ls
cn serve --id <agent-id>
{
  "MY_API_KEY": "sk-...",
  "SOME_ENDPOINT": "https://internal.example.com"
}
{
  "MY_API_KEY": "sk-...",
  "SOME_ENV": "production"
}
cn serve --id my-workspace-server
cn ls
cn remote --config ./my-project-config.yaml
/init
/info
env:
  OPENAI_API_KEY: sk-...
  MY_CUSTOM_VAR: some-value
continue --model gpt-4o --mcp my-mcp-server
continue --model gpt-4o --mcp ./mcp-server.json --prompt 'Review this codebase for hardcoded credentials'
continue --prompt 'Review the auth module for hardcoded credentials and summarize findings'
env:
  OPENAI_API_KEY: sk-...
  ANTHROPIC_API_KEY: sk-ant-...
autocompleteOptions:
  debounceDelay: 350
  maxPromptTokens: 1024
context:
  - provider: docs
    params:
      useLocalCrawling: true
      maxDepth: 3
mcpServers:
  - name: my-mcp-server
    command: npx
    args: ['-y', 'my-mcp-package']
    cwd: /workspace/my-project
models:
  - provider: vertexai
    model: gemini-2.0-flash
    keyFile: /secrets/gcp-sa-key.json
    project: my-gcp-project
    region: us-central1
# .continue/rules/no-use-effect.md
---
name: No useEffect
trigger:
  regex: "\\.tsx?$"
---
Do not use useEffect. Prefer derived state or event handlers.
mcpServers:
  - name: my-mcp
    command: npx
    args: ['-y', 'my-mcp-server']
    requestOptions:
      timeout: 30000
      headers:
        Authorization: 'Bearer <token>'
models:
  - name: my-model
    provider: ollama
    model: llama3
    minP: 0.05
    frequencyPenalty: 0.3
    presencePenalty: 0.3
mcpServers:
  my-server:
    command: npx
    args: ['-y', 'my-mcp-server']
    requestOptions:
      timeout: 30000
      headers:
        Authorization: 'Bearer <token>'
models:
  - name: my-model
    provider: ollama
    model: llama3
    minP: 0.05
    frequencyPenalty: 0.3
    presencePenalty: 0.2
models:
  - name: starcoder2-3b
    provider: ollama
    model: starcoder2:3b
    tabAutocompleteOptions:
      debounceDelay: 100
      maxPromptTokens: 512
  - name: deepseek-coder
    provider: ollama
    model: deepseek-coder:6.7b
    tabAutocompleteOptions:
      debounceDelay: 300
      maxPromptTokens: 1024
# Place secrets here — loaded before <workspace>/.env
OPENAI_API_KEY=sk-proj-...
ANTHROPIC_API_KEY=sk-ant-...
models:
  - name: my-model
    provider: openai
    model: gpt-4o
    maxStopWords: 4
    defaultCompletionOptions:
      stream: true
rules:
  - name: coding-standards
    description: Enforce team coding standards in every session
    alwaysApply: true
    content: Always use snake_case for variable names.
# Place your secrets in the workspace-scoped location so they take precedence
mkdir -p <workspace>/.continue
echo 'ANTHROPIC_API_KEY=sk-ant-...' > <workspace>/.continue/.env
---
name: Security Baseline
description: Always-on security coding guidelines
alwaysApply: true
---

Never log secrets. Sanitize all user input before use.
models:
  - name: my-model
    provider: openai
    model: gpt-4o
    defaultCompletionOptions:
      stream: true
      maxStopWords: 4
globs: ["**/*.ts"]
name: typescript-style
description: Enforce TypeScript conventions
content: Always use strict null checks and explicit return types.
models:
  - name: my-reasoning-model
    provider: anthropic
    model: claude-3-7-sonnet-latest
    reasoning: true
    reasoningBudgetTokens: 8000
models:
  - name: ollama-codellama
    provider: ollama
    model: codellama
    num_gpu: 35
"chatOptions": {
  "baseSystemMessage": "You are a security-aware coding assistant. Always flag use of deprecated crypto APIs and suggest modern alternatives."
}
{
  "name": "jira",
  "params": {
    "domain": "https://your-org.atlassian.net",
    "token": "<your-token>",
    "maxResults": 20
  }
}
{
  "name": "http",
  "params": {
    "url": "https://internal.corp/context",
    "headers": {
      "Authorization": "Bearer <token>",
      "X-Team": "security"
    }
  }
}
{
  "title": "My Custom LLM",
  "provider": "openai",
  "model": "my-fine-tuned-model",
  "contextLength": 16384
}
models:
  - name: my-llama
    provider: ollama
    model: llama3
    promptTemplates:
      chat: "<|system|>\n{system_message}\n<|user|>\n{user_message}\n<|assistant|>"

Summary

Continue is an open-source coding agent available as a VS Code extension, a JetBrains plugin, and a CLI. It is licensed under Apache 2.0 and is designed for application developers working within IDEs. The project's documentation positions it alongside other AI developer tooling, and it is currently noted that the primary repository is read-only.

What Continue answers

What different environments can I use the agent in?

VS Code extension, JetBrains plugin, and CLI

What specific licenses does the tool operate under?

Apache 2.0

How can I see the most recent updates?

GitHub Releases

What external locations can I find its code?

VS Code Marketplace, OpenVSX Registry, npm, and GitHub

What documentation is available for setup?

docs.continue.dev

Do I need to worry about telemetry being collected?

Anonymous telemetry is removed in the latest release

Command line

composed command

option surface across analysed releases

options at that release added, per release removed, per release

option	found in	since	description

Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.

Release history

v1.2.22-vscode Mar 27, 2026 · issue -145

Continue v1.2.22 adds workspace-scoped session history filtering and a new .continue/configs directory for multi-config support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.22-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.22-vscode
```
- ›Adds .continue/configs directory support, enabling multiple configuration files to coexist in a single workspace.
- ›Adds the ability to filter session history by workspace directory, making it easier to find past sessions scoped to a specific project.
v1.2.19-vscode Mar 26, 2026 · issue -146

Adds useResponsesApi opt-out option and OpenRouter app-identification headers in Continue v1.2.19.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.19-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.19-vscode
```
└──▷ USE IT
Opt out of the OpenAI Responses API when it causes compatibility issues with your deployment.
yaml
```
models:
  - provider: openai
    model: gpt-4o
    useResponsesApi: false
```
- ›Adds useResponsesApi option to config.yaml to opt out of the OpenAI Responses API.
- ›Sends HTTP-Referer and X-Title headers on OpenRouter requests to identify the Continue app to the provider.
v1.2.18-vscode Mar 25, 2026 · issue -147

Continue v1.2.18 adds Tensorix and MiniMax LLM providers, Bedrock API key auth, CLI skill importing, and session export/import.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.18-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.18-vscode
```
└──▷ TRY IT
Run a code review using custom checks defined in your project's .continue/checks/ directory.
```
$ cn review
```
- ›Adds feat(bedrock): support Bedrock API key authentication — enables API key-based auth for the AWS Bedrock provider.
- ›Adds feat(cli): discover .continue/checks/ directory in cn review for custom review checks.
- ›Adds feat(cli): invokable skills and import any skill — CLI can now invoke and import arbitrary skills.
- ›Adds feat(cli): export and import sessions — persist and restore CLI sessions.
- ›Adds Tensorix as a new LLM provider.
+4 moreshow less
- ›Adds MiniMax as a new LLM provider with M2.7 as the default model.
- ›Adds Qwen multi-file FIM template for repository-level autocompletion.
- ›Supports Gemini through the AI SDK provider path.
- ›Sends x-api-key instead of api-key as the header for Azure-hosted Anthropic service.
v1.2.17-vscode Mar 13, 2026 · issue -158

Continue v1.2.17 adds AI SDK provider integration, background bash execution, hooks system, turn-level prompt caching, and z.ai support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.17-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.17-vscode
```
- ›Adds environment variable to enable the AI SDK provider (feat: use env variable to enable ai sdk).
- ›Adds ai-sdk provider integration, with support for xai and deepseek backends.
- ›Adds a hooks system for CLI event interception, enabling programmatic interception of agent events.
- ›Enables bash tool execution in the background, with background job permission checks allowed by default.
- ›Adds turn-level prompt caching and conversation message caching to AnthropicApi, reducing token costs on repeated context.
+6 moreshow less
- ›Adds /rename as an alias for the /title CLI command.
- ›Moves agent configuration directory from .continue/agents to .continue/checks.
- ›Adds 5 new agent checks derived from codebase history.
- ›Adds support for z.ai as a model provider, alongside Claude Sonnet and Opus 4.6 model updates.
- ›Adds pre-install suggestions CLI in devbox blueprints.
- ›Adds quiz answers subcommand to the CLI.
└──▷ BREAKING ON UPGRADE
- !Agent configuration directory is moved from .continue/agents to .continue/checks; existing agent configs must be relocated.
v1.2.16-vscode Feb 17, 2026 · issue -181

Continue v1.2.16 adds .continue/agents support, a cn checks CLI command, MCP App integration, and LM Studio agent mode.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.16-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.16-vscode
```
└──▷ TRY IT
Run code quality checks against your project from the terminal using the new CLI subcommand.
```
$ cn checks
```
- ›Adds cn checks CLI subcommand for running checks from the command line.
- ›Introduces .continue/agents directory support for defining and managing agents as local config files.
- ›Adds limited MCP (Model Context Protocol) App support as a new integration surface.
- ›Enables agent mode support for LM Studio models.
- ›Makes create/read rule tools disabled by default, changing the out-of-the-box agent tool permissions.
+1 moreshow less
- ›Adds curl/irl installation scripts for the Continue CLI.
└──▷ BREAKING ON UPGRADE
- !The create/read rule tools are now disabled by default; existing setups relying on these agent tools being enabled will need to explicitly re-enable them.
v1.2.15-vscode Feb 4, 2026 · issue -194

Continue v1.2.15 adds cn review, subagents, agent skills, OpenRouter, Ask Sage, and tool prompt overrides via .continuerc.json.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.15-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.15-vscode
```
└──▷ USE IT
Override the prompt for a specific tool in a project without editing the global config.
json
```
{
  "tools": {
    "run_terminal_command": {
      "prompt": "Only run read-only commands. Never modify files."
    }
  }
}
```
- ›Adds cn review CLI subcommand (previously cn check) for AI agent code review with UX improvements.
- ›Adds tool prompt override support in .continuerc.json, letting users customize tool prompts at the project level.
- ›Allows MCP/Bash tools by default in headless mode, removing manual opt-in for agent automation workflows.
- ›Adds subagents support, enabling agents to spawn and coordinate child agents.
- ›Adds agent skills feature (in both VS Code extension and CLI) for composable, reusable agent capabilities.
+8 moreshow less
- ›Adds OpenRouter provider with dynamic model loading.
- ›Adds Ask Sage as a supported provider for the Continue CLI.
- ›Adds new OVHcloud models as a provider.
- ›Adds Nous Research Hermes models as a provider.
- ›Adds a remove rule button in the UI for managing active rules.
- ›Adds automatic resubmission on overloaded/rate-limit errors from providers.
- ›Adds message counter display on the history page.
- ›Adds WSL detection in the CLI to spawn the appropriate shell automatically.
@continuedev/[email protected] Feb 3, 2026 · issue -195

Continue 1.42.0 adds Nous Research Hermes models and OpenRouter provider support with dynamic model loading.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds OpenRouter as a provider with dynamic model loading.
- ›Adds Nous Research Hermes models as a supported provider.
@continuedev/[email protected] Feb 3, 2026 · issue -195

Continue adds tool prompt override support via .continuerc.json
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds tool prompt override support in .continuerc.json, allowing per-project customization of tool prompts.
@continuedev/[email protected] Jan 31, 2026 · issue -198

Continue 1.40.0 adds CLI agent skills, WSL shell detection, OVHcloud models, and smarter output truncation.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds agent skills support to the cli (new agent skills capability for headless agent workflows).
- ›Adds automatic WSL detection in the cli to spawn the appropriate shell when running inside Windows Subsystem for Linux.
- ›Adds new OVHcloud models as selectable providers.
- ›Adds proportional output truncation for read and bash tool outputs instead of hard-cutting content.
- ›Raises an informative error for large files rather than silently truncating them.
+1 moreshow less
- ›Adds automatic retry logic for overloaded/rate-limit errors from model providers.
@continuedev/[email protected] Jan 26, 2026 · issue -203

Continue CLI gains automatic WSL detection to spawn the appropriate shell environment.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›CLI automatically detects WSL environments and spawns the appropriate shell.
@continuedev/[email protected] Jan 15, 2026 · issue -214

Continue 1.39.0 adds subagent support for orchestrating multi-agent workflows.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds subagents, enabling an agent to spawn and coordinate subordinate agents for multi-step tasks.
v1.2.14-vscode Jan 14, 2026 · issue -215

Continue v1.2.14-vscode adds OAuth for CLI MCPs, --agent path/URI support, Cohere Reasoning/Vision/Translate models, and a report-failure tool.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.14-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.14-vscode
```
└──▷ TRY IT
Run the CLI agent directly from a local agent definition file, skipping the interactive picker.
```
$ continue --agent ./agents/my-agent.yaml
```
Authenticate a CLI MCP server that requires OAuth before starting an agent session.
```
$ continue oauth
```
- ›Adds --agent flag support for paths and URIs, allowing the CLI agent to be invoked directly with a local or remote agent definition.
- ›Adds OAuth authentication flow for CLI MCP (Model Context Protocol) servers via continue oauth.
- ›Adds x-continue-unique-id header to all LLM requests, with normalized header casing, enabling per-request tracing through proxies and gateways.
- ›Allows overriding the authorization header in the OpenAI adapter, with extended support for x-api-key, enabling compatibility with non-standard API auth schemes.
- ›Adds a report failure tool for agents to explicitly signal task failure.
+11 moreshow less
- ›Adds Cohere support for Reasoning, Vision, and Translate model types.
- ›Adds per-tab model persistence and selection, so each editor tab can independently track its active model.
- ›Passes all environment variables to MCP servers instead of only PATH, ensuring MCP processes receive full environment context.
- ›CLI UI now always shows context window percentage usage.
- ›CLI UI now truncates long slash command descriptions to keep the interface readable.
- ›Throws an error and exits on MCP failure in headless mode, making failures visible rather than silent.
- ›Enhances autocomplete cache with async initialization and improved eviction logic.
- ›Stream error toggle is now open by default, making LLM error details immediately visible.
- ›Applied rules are removed from chat history to reduce context noise.
- ›Thinking block UI designs now occupy less screen space.
- ›Adds a file hotspot analysis script that mines git history to surface frequently changed files.
└──▷ BREAKING ON UPGRADE
- !continue.telemetryEnabled in VS Code preferences is deprecated.
v1.2.12-vscode Dec 11, 2025 · issue -249

Continue v1.2.12 adds headless CLI mode, grep/find/findstr search fallback, Gemini thought signatures, org profile selection, and auto-approval of parallel read-only tools.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.12-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.12-vscode
```
└──▷ TRY IT
Run the Continue CLI agent in a headless CI environment where no TTY is available.
```
$ continue --headless
```
- ›Removes TTY requirement for the CLI in headless mode, enabling non-interactive/CI environments to run the CLI without a terminal.
- ›Adds grep, find, and findstr as alternative search strategies in the CLI when ripgrep is unavailable.
- ›Adds support for Gemini thought signatures in streaming responses via the google/genai SDK, now used for all Gemini and Vertex streaming.
- ›Adds org profile selection on sign-in, letting users choose their organization during authentication.
- ›Auto-approves parallel read-only built-in tools, reducing interruptions during agent runs.
+11 moreshow less
- ›Adds Supabase-specific OAuth scopes to the mcp-remote fallback for MCP connections.
- ›Adds agent error reporting to the API in serve mode.
- ›Adds agent session metadata tracking and reporting to the control plane.
- ›Increases terminal command timeout from 30 seconds to 120 seconds, unblocking longer-running agent tasks.
- ›Adds auto-continuation after context compaction in chat streaming, so long sessions resume without manual intervention.
- ›Adds support for renaming a rule before creation in the rules UI.
- ›Adds support for claude-opus-4 and claude-sonnet-4.5 model updates.
- ›Adds a JCEF reload action for the JetBrains extension.
- ›Adds Klavis AI Strata to the MCP Cookbook.
- ›Adds support for grok-4.1-fast and gpt-5.1 models.
- ›Adds support for gemini-3-pro-preview.
@continuedev/[email protected] Dec 10, 2025 · issue -250

Continue 1.36.0 adds session-persistent chat history, usage metadata on assistant messages, and the Google GenAI SDK for Gemini/Vertex streaming.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds session ID support to the serve command to persist chat history across runs.
- ›Captures and attaches usage metadata (token counts) to assistant messages.
- ›Switches Gemini and Vertex AI streaming responses to the google/genai SDK.
@continuedev/[email protected] Dec 4, 2025 · issue -256

Continue CLI gains headless TTY-free operation and grep/find/findstr search fallback in v1.7.0
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds grep, find, and findstr as alternative search strategies in the CLI, giving the agent fallback file-search methods when the primary strategy is unavailable.
- ›Removes the TTY requirement for the CLI in headless mode, enabling unattended/CI pipeline use without a pseudo-terminal.
- ›Adds Supabase-specific OAuth scopes to the mcp-remote fallback path for MCP integrations.
- ›Switches Gemini and Vertex AI response streaming to the google/genai SDK.
- ›Auto-approves parallel read-only built-in tool calls, reducing friction in agentic workflows.
+2 moreshow less
- ›Adds support for the Gemini thought-signature field in model responses.
- ›Adds Klavis AI Strata to the MCP Cookbook as a new integration.
@continuedev/[email protected] Dec 4, 2025 · issue -256

Continue v1.35.0 auto-approves parallel read-only built-in tool calls without user prompts.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Auto-approves parallel read-only built-in tool invocations, removing manual confirmation prompts for non-mutating operations.
@continuedev/[email protected] Dec 2, 2025 · issue -258

Continue openai-adapters 1.34.0 adds Sonnet 4.5 model support and deprecates Sonnet 3.5.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds support for Claude Sonnet 4.5 and marks Sonnet 3.5 as deprecated.
@continuedev/[email protected] Dec 2, 2025 · issue -258

Continue adds grep/find/findstr search fallback, Supabase OAuth scopes for MCP, and org profile selection at sign-in.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds grep, find, and findstr as alternative search strategies in the CLI for code search operations.
- ›Adds Supabase-specific OAuth scopes to the mcp-remote fallback for MCP integrations.
- ›Supports selecting an org profile at sign-in.
- ›Adds support for Claude Opus 4/5 and Sonnet 4/5 model updates.
@continuedev/[email protected] Dec 2, 2025 · issue -258

Continue CLI gains grep/find/findstr search fallback, Supabase OAuth scopes for MCP, and org profile selection on sign-in.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds grep, find, and findstr as alternative search strategies in the Continue CLI for codebase search.
- ›Adds Supabase-specific OAuth scopes to the mcp-remote fallback in the MCP integration.
- ›Enables organization profile selection at sign-in time.
- ›Adds support for Claude Sonnet 4.5 model and marks Sonnet 3.5 as deprecated.
@continuedev/[email protected] Dec 1, 2025 · issue -259

Continue 1.33.0 adds grep/find/findstr search fallback in CLI, Supabase OAuth scopes for MCP-remote, and org profile selection at sign-in.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds grep, find, and findstr as alternative search strategies in the CLI when the primary search method is unavailable.
- ›Adds Supabase-specific OAuth scopes to the mcp-remote fallback flow, enabling authenticated Supabase MCP connections.
- ›Enables organization profile selection during sign-in, letting users choose their org context at authentication time.
@continuedev/[email protected] Nov 27, 2025 · issue -263

Continue 1.32.0 adds headless CLI mode, Gemini thought signatures, and Opus 4-5 model support.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Removes TTY requirement for the CLI, enabling headless/non-interactive operation in CI and automation pipelines.
- ›Adds support for Gemini thought signature in model responses.
- ›Adds Opus 4-5 model updates to the adapter layer.
- ›Adds Klavis AI Strata to the MCP Cookbook integrations.
- ›Allows renaming a rule before it is created in the UI.
@continuedev/[email protected] Nov 26, 2025 · issue -264

Continue v1.7.0 removes TTY requirement for headless CLI mode and adds Gemini thought signature support.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Removes TTY requirement for the CLI in headless mode, enabling use in non-interactive environments such as CI pipelines.
- ›Adds support for Gemini thought signature in LLM responses.
- ›Adds support for Claude Opus 4-5 model updates.
- ›Allows renaming a rule before creation in the rule editor.
@continuedev/[email protected] Nov 26, 2025 · issue -264

Continue CLI gains headless (no-TTY) mode, Gemini thought-signature support, and rule-renaming before creation.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Removes TTY requirement for the CLI in headless mode, enabling use in non-interactive pipelines and CI environments.
- ›Adds support for Gemini thought signatures, exposing chain-of-thought metadata from Gemini models.
- ›Allows renaming a rule before it is created in the UI.
- ›Adds Klavis AI's Strata to the MCP Cookbook as a new integration.
@continuedev/[email protected] Nov 25, 2025 · issue -265

Continue 1.6.0 adds a JCEF reload action and Klavis AI Strata to the MCP Cookbook.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a JCEF reload action for the JetBrains embedded browser panel.
- ›Adds Klavis AI's Strata integration to the MCP Cookbook.
@continuedev/[email protected] Nov 20, 2025 · issue -270

Continue 1.35.0 adds Cohere Reasoning/Vision/Translate model support and file URL loading for agent file operations.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds support for Cohere Reasoning, Vision, and Translate models via the Cohere integration.
- ›Supports local file paths and file URLs for agent file loading, expanding what agents can reference at runtime.
- ›Enhances autocomplete cache with async initialization and improved eviction logic, enabling more reliable completions under load.
@continuedev/[email protected] Nov 19, 2025 · issue -271

Cohere Reasoning/Vision/Translate model support and file URL/path loading for agents in openai-adapters 1.31.0
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Extends auth header override to support x-api-key in addition to standard authorization headers.
- ›Adds Cohere Reasoning, Vision, and Translate model support via the Cohere adapter.
- ›Supports file paths and file URLs for agent file loading.
- ›Enhances autocomplete cache with async initialization and improved eviction logic.
v1.2.11-vscode Nov 19, 2025 · issue -271

Continue v1.2.11 adds OpenAI Responses API support, background agent mode, Watsonx image support, and new CLI capabilities including CONTINUE_CLI_DISABLE_COMMIT_SIGNATURE.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.11-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.11-vscode
```
└──▷ TRY IT
Browse and preview past sessions before resuming one, using the updated session selector.
```
$ cn ls
```
- ›Adds CONTINUE_CLI_DISABLE_COMMIT_SIGNATURE environment variable to disable commit signing in the Continue CLI.
- ›Replaces the --config flag with --agent flag in the Continue CLI command.
- ›Integrates the OpenAI Responses API, enabling GPT-5 features via the oai-adapters implementation.
- ›Adds a preview panel to the session selector for cn ls / /resume commands.
- ›Enables Background / Async / Remote mode: agents can be kicked off from /agents while inside the VS Code extension.
+9 moreshow less
- ›Adds cache_write_tokens and cache_read_tokens to Anthropic prompt token details for token usage reporting.
- ›Supports Granite 4 FIM (fill-in-the-middle) and tool calling.
- ›Adds Watsonx image support.
- ›Enables file reads outside the IDE workspace (with user permission).
- ›Makes account-level MCPs generally available.
- ›Adds instant edit for find/replace tools, applying changes immediately without a diff review step.
- ›Adds a gradient border visual indicator in edit mode.
- ›Removes the auto-accept edits setting.
- ›Adds a loading animation in the CLI when updating the version.
└──▷ BREAKING ON UPGRADE
- !The --config flag in the Continue CLI command is replaced by --agent; existing scripts using --config will break.
@continuedev/[email protected] Nov 19, 2025 · issue -271

Continue 1.5.0 adds Cohere reasoning/vision/translate models, Granite 4 FIM and tool calling, Continue OAuth for CLI MCPs, and a new failure-report tool.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds Continue OAuth support for CLI MCP servers, enabling authenticated MCP connections from the CLI.
- ›Adds a report failure tool for agents to signal task failure; filtered out automatically when no --id flag is provided.
- ›Adds support for Cohere Reasoning, Vision, and Translate models.
- ›Adds support for Granite 4 FIM (fill-in-the-middle) and tool calling.
- ›CLI now always shows the context window percentage in the UI.
+7 moreshow less
- ›CLI skips update checks when running in dev mode.
- ›Supports file paths and file URLs for agent file loading.
- ›Upgrades grok-code-fast model to version 1.
- ›Enhances autocomplete cache with async initialization and improved eviction logic.
- ›Thinking block UI designs now occupy less space for a more compact layout.
- ›MCP warning messages now display alongside configured MCPs.
- ›Stream error toggle defaults to open so errors are immediately visible.
@continuedev/[email protected] Nov 19, 2025 · issue -271

Continue 1.30.0 adds OAuth support for CLI-based MCP servers.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds OAuth authentication support for CLI MCP (Model Context Protocol) servers.
@continuedev/[email protected] Nov 19, 2025 · issue -271

Continue CLI gains OAuth for MCP servers, a failure-reporting tool, and long-line filtering in this release.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds Continue OAuth support for CLI MCP servers, enabling authenticated MCP connections from the CLI.
- ›Adds a report failure tool to the CLI (activated via --id), allowing agents to signal task failure explicitly.
- ›Stream error toggle now stays open by default, making LLM stream errors immediately visible without manual expansion.
- ›Lazy-apply prompt for Claude Sonnet models now preserves comments during code application.
@continuedev/[email protected] Nov 18, 2025 · issue -272

Continue 1.29.0 adds Granite 4 FIM and tool calling, a report failure tool, and CLI context percentage display.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a report failure tool, filterable via --id flag, giving agents a structured way to signal task failure.
- ›CLI now always displays the context window usage percentage.
- ›CLI skips checking for updates when running in dev mode.
- ›Adds support for Granite 4 fill-in-the-middle (FIM) and tool calling.
- ›MCP warning messages now surface which MCPs are configured.
+3 moreshow less
- ›Stream error toggle now stays open by default for easier debugging.
- ›Applied rules are no longer included in chat history or dev data.
- ›Thinking block UI redesigned to occupy less screen space.
@continuedev/[email protected] Nov 7, 2025 · issue -283

Continue 1.32.0 adds Granite 4 FIM and tool calling, Grok code-fast-1 support, and persistent context percentage display in the CLI.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Always displays the context window usage percentage in the CLI so practitioners can monitor token consumption at a glance.
- ›Skips update checks when running the CLI in dev mode, removing noise during development workflows.
- ›Adds support for IBM Granite 4 fill-in-the-middle (FIM) and tool calling.
- ›Upgrades Grok to the code-fast-1 model variant.
- ›Shows a warning message when MCP servers are configured but encounter issues, surfacing MCP connectivity problems earlier.
+1 moreshow less
- ›Removes applied rules from chat history and developer data, reducing leakage of internal rule metadata.
@continuedev/[email protected] Oct 29, 2025 · issue -292

Continue 1.28.0 adds OpenAI Responses API support, enabling GPT-5 features via the oai-adapters layer.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Implements the OpenAI Responses API in oai-adapters, enabling GPT-5 features through the adapter layer.
- ›Shows a gradient border in edit mode for visual distinction when editing.
- ›Removes the auto-accept edits setting.
└──▷ BREAKING ON UPGRADE
- !The auto-accept edits setting has been removed; any configuration relying on it will no longer be recognized after upgrade.
@continuedev/[email protected] Oct 29, 2025 · issue -292

Continue 1.31.0 integrates the OpenAI Responses API (enabling GPT-5 features) and removes the auto-accept edits setting.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Integrates the OpenAI Responses API to enable GPT-5 features, implemented in oai-adapters.
- ›Removes the auto-accept edits setting (previously a configurable toggle).
- ›Adds a gradient border visual indicator when in edit mode.
└──▷ BREAKING ON UPGRADE
- !The auto-accept edits setting has been removed; any configuration or workflow relying on it will no longer function after upgrading.
@continuedev/[email protected] Oct 29, 2025 · issue -292

Continue 1.4.0 adds OpenAI Responses API support (enabling GPT-5), a session preview panel, and surfaces fetch errors to the agent.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Browse and preview past sessions before resuming one, useful when you have many saved contexts.
```
$ cn ls
```
- ›Integrates the OpenAI Responses API, enabling GPT-5 features and parity support via oai-adapters.
- ›Adds a preview panel to the session selector, visible when running cn ls or /resume.
- ›Surfaces fetch errors back to the agent so it can react to network failures during tool calls.
- ›Adds a gradient border visual indicator when the UI enters edit mode.
└──▷ BREAKING ON UPGRADE
- !The auto-accept edits setting is removed; any configuration relying on it will no longer apply after upgrading.
@continuedev/[email protected] Oct 22, 2025 · issue -299

Continue 1.30.0 adds background agents, local takeover, and a session-selector preview panel.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Preview a past session's content before resuming it, useful for picking up the right context in a long-running investigation.
```
$ cn ls
```
- ›Adds a preview panel to the session selector, accessible via cn ls / /resume, to inspect session content before switching.
- ›Adds background agent creation and management, enabling agents to run without an active foreground session.
- ›Adds local takeover capability, allowing a local instance to take control of a background agent session.
- ›Reports cache write tokens from the Anthropic OpenAI adapter, surfacing prompt-caching cost data in token usage.
- ›Returns fetch errors back to the agent loop so agents can reason about and recover from network failures.
@continuedev/[email protected] Oct 21, 2025 · issue -300

Continue 1.5.0 adds background agents, secrets parsing for all CLI flags, and a session-selector preview panel.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds full secrets parsing for all CLI flags, so secrets are resolved across every flag passed to the CLI.
- ›Adds a preview panel to the session selector surfaced by cn ls and /resume, letting users inspect session history before resuming.
- ›Adds background agent creation and execution, enabling agents to run without an active foreground session.
- ›Reports cache write tokens from the Anthropic OpenAI adapter, surfacing prompt-cache cost data.
- ›Returns fetch errors to the agent runtime so agents can handle network failures programmatically.
v1.2.10-vscode Oct 21, 2025 · issue -300

Continue v1.2.10 adds token usage tracking, message editing in CLI, and renames workflows to agent files.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.10-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.10-vscode
```
- ›Adds token usage tracking to the OpenAI adapter, surfacing consumption data per request.
- ›Decouples anonymous telemetry from the CONTINUE_CLI_ENABLE_TELEMETRY environment variable, giving finer-grained control over telemetry opt-out.
- ›Allows the --agent flag to be used without a prompt in headless mode.
- ›Renames 'workflows' to 'agent files' throughout the product.
- ›Makes chat messages editable in the CLI and adds the ability to navigate back to an older message.
+1 moreshow less
- ›Rehauled onboarding flow updated for new billing.
└──▷ BREAKING ON UPGRADE
- !Bundled esbuild is removed from the VSCode extension; users must now have esbuild installed separately for config.ts to work.
@continuedev/[email protected] Oct 18, 2025 · issue -303

Continue 1.27.0 adds a session-selector preview panel and surfaces fetch errors to the agent.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Preview an existing session before resuming it, useful when you have multiple parallel agent runs and need to identify the right one.
```
$ cn ls
```
- ›Adds a preview panel to the session selector, accessible via cn ls and /resume, letting practitioners inspect a session before switching into it.
- ›Surfaces fetch errors back to the agent so failures during tool-use are visible and actionable rather than silently dropped.
- ›Introduces local takeover mode, enabling local override of remote agent sessions.
@continuedev/[email protected] Oct 17, 2025 · issue -304

Continue 1.3.0 adds background agents, full CLI secrets parsing, and Anthropic cache-write token reporting.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds full secrets parsing for all CLI flags, so secrets stored in the secrets manager are expanded across every command-line option.
- ›Adds background agent creation and execution, enabling agents to run without an active interactive session.
- ›Reports cache write tokens from the Anthropic OpenAI adapter, surfacing prompt-caching cost and usage data.
@continuedev/[email protected] Oct 17, 2025 · issue -304

Continue 1.26.0 adds background agents, full CLI secrets parsing, and Anthropic cache-write token reporting.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds full secrets parsing for all CLI flags, so secret values are resolved across every flag at invocation time.
- ›Adds background agent creation and execution, enabling agents to run asynchronously without blocking the foreground session.
- ›Reports cache write tokens from the Anthropic OpenAI-compatible adapter, surfacing prompt-cache cost data previously omitted.
@continuedev/[email protected] Oct 16, 2025 · issue -305

Continue v1.29.0 adds full secrets parsing across all CLI flags
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds full secrets parsing for all CLI flags, enabling secret values to be resolved from config.yaml for every command-line argument.
v1.2.9-vscode Oct 15, 2025 · issue -306

Continue v1.2.9 adds MCP OAuth, Bearer token auth, OpenRouter Anthropic caching, CLI workflows, and auto-accept agent edits.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.9-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.9-vscode
```
└──▷ USE IT
Authenticate an MCP server using a Bearer token directly in your config instead of relying on environment credentials.
json
```
{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["-y", "my-mcp-server"],
      "apiKey": "sk-my-bearer-token"
    }
  }
}
```
Connect the Continue CLI to a remote streamable-http MCP server by passing its URL directly to --mcp.
```
$ cn --mcp https://my-mcp-server.example.com/sse
```
- ›Adds apiKey field to mcpServers block schema for Bearer token authentication against MCP servers.
- ›Extends --mcp flag to accept URLs for streamable-http MCP servers in addition to local processes.
- ›Adds serverName option to registry MCP server configurations.
- ›Adds MCP OAuth support to the CLI via mcp-remote.
- ›Adds CLI workflows capability (cn command).
+8 moreshow less
- ›Adds invokable rule support to the CLI, including detection of rules located in the prompts directory.
- ›Adds OpenRouter API integration with Anthropic prompt caching support.
- ›Adds API key authentication support for the Bedrock provider.
- ›Adds auto-accept agent edits setting (auto accept edit tools) to automatically accept edits made by the agent.
- ›Adds Explore MCP Servers option to the /mcp slash command for in-IDE server discovery.
- ›Adds organization name display to the CLI intro screen.
- ›Adds actions to reference files, directories, and repo maps in the IntelliJ plugin.
- ›Adds beta status tool option with improved status tool descriptions.
@continuedev/[email protected] Oct 15, 2025 · issue -306

Continue 1.25.0 renames workflows to agent files and overhauled onboarding for updated billing.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Renames 'workflows' to 'agent files' across the product, reflecting a new operational surface name for reusable agent task definitions.
- ›Overhauled onboarding flow updated for revised billing tiers and free trial handling.
@continuedev/[email protected] Oct 12, 2025 · issue -309

Continue 1.24.0 adds CLI OAuth for MCP, workflow files with tool permissions, token usage tracking, and directory context mentions.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds MentionFileInChatAction and MentionRepoMapInChatAction context actions, letting users reference files and repo maps directly from the IDE context-actions group.
- ›Introduces workflow files for the CLI — supports parsing, serializing, and tool-permission declarations so agents can run with scoped tool access.
- ›Adds MCP OAuth support in the CLI via mcp-remote, enabling authenticated MCP server connections from the terminal.
- ›Adds token usage tracking to the OpenAI adapter, surfacing consumption data per request.
- ›Adds auto-accept agent edits setting so edit tools no longer require manual confirmation during agentic sessions.
+2 moreshow less
- ›Enables mentioning directories (and mixing directories with files) as context in chat.
- ›Adds session history navigation ('go back in history') in the CLI.
v1.2.8-vscode Oct 8, 2025 · issue -313

Continue v1.2.8 adds AWS credential onboarding, environment.json support, MCP JSON formats, and a /pause endpoint for cn serve.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.8-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.8-vscode
```
└──▷ TRY IT
Connect to an already-running remote agent by its ID instead of spawning a new one.
```
$ cn --id <agent-id>
```
Pause a running cn serve agent session via its REST endpoint, e.g. from a CI pipeline hook.
```
$ curl -X POST http://localhost:<port>/pause
```
- ›Adds .continue/environment.json file support, handled by cn serve, for managing environment configuration.
- ›Adds --id option to cn CLI to connect to existing remote agents via tunnel.
- ›Adds /pause endpoint to the cn serve command.
- ›Adds status tool for cn to report agent/session status.
- ›Enhances /init command to create custom slash commands.
+8 moreshow less
- ›Adds AWS credentials onboarding flow to the CLI.
- ›Supports standard MCP JSON formats, with MCP loading errors now surfaced in config loading errors.
- ›Adds UI for global rule creation.
- ›Adds tool call args preprocessing for improved agent tool use.
- ›Highlights the first incomplete item in CLI checklist display.
- ›Shows dangerous commands only once per session in the CLI.
- ›Makes ToolCallStatusMessage.tsx clickable in the UI.
- ›Adds Runloop blueprint CI integration for the cn CLI.
@continuedev/[email protected] Oct 8, 2025 · issue -313

Continue 1.27.0 adds MCP OAuth via mcp-remote, auto-accept agent edits, and directory context referencing in chat.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds auto-accept agent edits setting that automatically accepts edit tools invoked by the agent, removing manual approval prompts during agentic workflows.
- ›Adds MCP OAuth support in the CLI via mcp-remote, enabling authenticated MCP server connections from the command line.
- ›Adds MentionFileInChatAction and directory mention support, letting users reference both individual files and entire directories as chat context simultaneously.
- ›Adds MentionRepoMapInChatAction to include the repository map as chat context directly from the IDE action menu.
- ›Adds a Continue icon to the context actions group in the IDE for quicker access to context-related actions.
@continuedev/[email protected] Oct 6, 2025 · issue -315

Continue 1.26.0 adds workflow files for CLI, API-key auth for Bedrock, and OpenRouter with Anthropic prompt caching.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds workflow file support for the CLI, including parsing, serializing, and tool permissions driven by workflow files.
- ›Adds API key authentication support for the Bedrock provider.
- ›Adds OpenRouter API integration with Anthropic prompt caching support.
@continuedev/[email protected] Oct 6, 2025 · issue -315

Continue's OpenAI adapters v1.23.0 adds API key authentication support for the Bedrock provider.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds API key authentication support for the Bedrock provider, enabling Bedrock access without IAM role or credential-file configuration.
@continuedev/[email protected] Oct 5, 2025 · issue -316

Continue 1.22.0 adds OpenRouter with Anthropic prompt caching and a serverName option for registry MCP servers.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds serverName option for registry MCP servers, allowing custom naming of MCP server instances.
- ›Adds OpenRouter API integration with Anthropic prompt caching support.
@continuedev/[email protected] Oct 2, 2025 · issue -318

Continue config-yaml 1.25.0 adds serverName option for registry MCP servers.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ USE IT
Override the default name of a registry MCP server to avoid conflicts or clarify its role in your config.
yaml
```
mcpServers:
  - name: my-registry-server
    serverName: custom-server-name
```
- ›Adds serverName option to registry MCP server entries in Continue's config YAML, allowing explicit server name overrides.
@continuedev/[email protected] Oct 1, 2025 · issue -319

Continue 1.21.0 adds AWS credential onboarding, remote agent tunneling, environment.json support, and a new cn status tool.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ USE IT
Define environment variables for a Continue workspace so cn serve picks them up automatically.
json
```
{
  "MY_API_KEY": "abc123",
  "ANOTHER_VAR": "value"
}
```
- ›Adds --id option to the CLI to connect to an existing remote agent via tunnel.
- ›Adds .continue/environment.json file support for environment variable configuration, also handled by cn serve.
- ›Adds status tool for cn to inspect agent state.
- ›Enhances the /init command to create a custom slash command.
- ›Adds AWS credentials onboarding flow to the CLI.
+5 moreshow less
- ›Supports Claude Code MCP JSON config format, with YAML-to-JSON and JSON-to-YAML conversion for MCP configs.
- ›MCP loading errors are now surfaced in config loading errors.
- ›Adds new Grok model options.
- ›Adds UI for global rule creation.
- ›Dangerous command warnings are now shown only once per session in the CLI.
@continuedev/[email protected] Oct 1, 2025 · issue -319

Continue 1.24.0 adds a cn status command, UI for global rule creation, and MCP loading errors surfaced in config diagnostics.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Quickly inspect whether the cn agent has tool access configured correctly before running a pipeline.
```
$ cn status
```
- ›Adds status subcommand to the cn CLI for inspecting tool state.
- ›Surfaces MCP loading errors inside config loading error reporting, making misconfigured MCP servers visible during diagnostics.
- ›Adds UI for creating global rules directly from the settings page.
- ›Adds tool call argument preprocessing to normalize inputs before dispatch.
- ›Hides empty resources and prompts sections from the UI when none are configured.
v1.2.7-vscode Oct 1, 2025 · issue -319

Continue v1.2.7 adds CLI auto-updates, Lemonade/CometAPI providers, AGENTS.md support, AWS Bedrock tool streaming, and fuzzy file search.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.7-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.7-vscode
```
└──▷ TRY IT
Serve a Continue session with a specific identifier so remote clients can discover it by name.
```
$ cn serve --id my-session
```
List all active remote Continue sessions to see which named sessions are available.
```
$ cn ls
```
- ›Adds --id flag to cn serve for naming/identifying a served session.
- ›Adds cn ls command to display remote sessions.
- ›Adds grep and glob ignore support for VS Code and JetBrains context search.
- ›Adds invokable option to markdown rule creation, enabling rules to be triggered as slash commands.
- ›Supports ~ when resolving uses blocks in config.
+21 moreshow less
- ›Adds headless mode that surfaces errors and exits with code 1 on failure.
- ›Adds Lemonade as a new model provider integration.
- ›Adds CometAPI as a new model provider.
- ›Adds Mercury Apply endpoint support to Inception LLM provider.
- ›Adds AWS Bedrock provider tool streaming support.
- ›Adds Anthropic prompt caching support to the OpenRouter LLM implementation.
- ›Adds CLI auto-update capability.
- ›Supports AGENTS.md for agent-level instructions.
- ›Revamps file search with fuzzy matching support.
- ›Exposes legacy /share command to the VS Code UI.
- ›Adds mark unread capability for chat sessions.
- ›Adds MCP server connection status display with richer status information.
- ›Adds keyboard shortcuts display for accept/reject diff buttons.
- ›Adds in-UI installation guides for MCP commands.
- ›Adds next-edit character-level diff capability.
- ›Adds search-and-replace error codes for clearer failure reporting.
- ›Adds grok model updates with new model entries.
- ›Adds fullscreen command back to the UI.
- ›Splits large blocks of chat history rendering to reduce UI flickering.
- ›Adds more robust context length validation before LLM API calls.
- ›Moves tool icon names into tool definitions for consistent rendering.
@continuedev/[email protected] Sep 29, 2025 · issue -321

Continue 1.23.0 adds --id option to connect to existing remote agents via tunnel and a boolean mode for cn serve.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Reconnect to an already-running remote agent by its ID rather than launching a new tunnel session.
```
$ cn serve --id <agent-id>
```
- ›Adds --id option to connect to an existing remote agent via tunnel instead of spinning up a new one.
- ›Adds boolean support to cn serve command.
@continuedev/[email protected] Sep 26, 2025 · issue -324

Continue 1.22.0 adds --id flag for cn serve, .continue/environment.json, AWS credentials onboarding, CometAPI provider, and AWS Bedrock tool streaming.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ USE IT
Declare project-scoped environment variables that Continue picks up automatically at runtime.
json
```
{
  "MY_API_KEY": "sk-...",
  "SOME_ENDPOINT": "https://internal.example.com"
}
```
- ›Adds --id flag to cn serve for named server instances.
- ›Adds .continue/environment.json as a new per-project environment configuration file.
- ›Adds AWS credentials onboarding flow to the CLI.
- ›Adds CometAPI as a model provider.
- ›Adds tool streaming support for the AWS Bedrock provider.
+4 moreshow less
- ›Adds Claude Code MCP JSON format support for MCP server definitions.
- ›Enhances the /init CLI command to create a custom slash command.
- ›Improves MCP connection status reporting with richer status indicators.
- ›Adds fullscreen command back to the CLI.
@continuedev/[email protected] Sep 26, 2025 · issue -324

Continue 1.1.0 adds .continue/environment.json support, AWS credentials onboarding, and Claude Code MCP JSON format.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ USE IT
Inject environment variables into a Continue server without hardcoding them in your main config — useful for API keys or org-specific overrides.
json
```
{
  "MY_API_KEY": "sk-...",
  "SOME_ENV": "production"
}
```
- ›Adds .continue/environment.json file support for defining environment variables, consumed by cn serve at startup.
- ›Adds AWS credentials onboarding flow to the CLI for configuring AWS-based model access.
- ›Supports Claude Code MCP server JSON config format, enabling MCP servers defined in Claude Code's JSON schema to be used directly.
- ›Adds YAML ↔ JSON conversion for MCP config, allowing MCP server definitions to be expressed in either format interchangeably.
- ›CLI now shows dangerous command warnings only once per session rather than on every invocation.
v1.2.6-vscode Sep 26, 2025 · issue -324

Continue v1.2.6 adds improved support for the mercury-coder apply model for ultra-fast code edits.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.6-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.6-vscode
```
- ›Improves support for mercury-coder apply, enabling faster AI-driven code edits via Inception Labs' speculative decoding model.
v1.2.5-vscode Sep 25, 2025 · issue -325

Continue v1.2.5 adds invokable rules, terminal stop controls, thinking-tag dimming, HuggingFace router detection, and MCP request timeouts.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.5-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.5-vscode
```
- ›Adds transform option to YAML autocomplete configuration (previously missing from autocomplete).
- ›Adds MCP request timeout when calling a tool, preventing hung tool invocations.
- ›Adds invokable rules — rules that can be explicitly called rather than always applied.
- ›Adds ability to stop foreground terminal commands from within the extension.
- ›Enables thinking/reasoning toggle for Ollama models.
+10 moreshow less
- ›Adds HuggingFace OpenAI-compatible router auto-detection.
- ›Adds autoformatting detection for edit tools.
- ›Adds message queueing in the CLI.
- ›Parses <think> / thinking tags and dims them in the UI to visually separate reasoning from output.
- ›Improves find-and-replace capability.
- ›Improves compaction UI, surfacing compaction status as a status message.
- ›Allows Cmd+L / Cmd+I on an empty selection to select the entire file.
- ›Excludes single-file edit mode for models capable of handling multi-file edits.
- ›Auto-selects scope for org API keys in the Continue network.
- ›Updates CLI fetch tool to use fetchUrlContent from core.
@continuedev/[email protected] Sep 24, 2025 · issue -326

Continue gains CometAPI as a new model provider in the OpenAI adapters package.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds CometAPI as a supported model provider, enabling routing of completions and chat through the CometAPI backend.
@continuedev/[email protected] Sep 24, 2025 · issue -326

Continue 1.19.0 adds AGENTS.md support, improved MCP connection status, headless error surfacing, and a /share command in VS Code.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds support for AGENTS.md to define agent-level rules and instructions.
- ›Headless mode now surfaces errors and exits with code 1 on failure, enabling reliable CI integration.
- ›Exposes legacy /share command to the VS Code UI for sharing conversations.
- ›Improves MCP connection status visibility so users can see server connectivity at a glance.
- ›Adds 'mark unread' capability for chat sessions.
+1 moreshow less
- ›Cleans up Anthropic messaging handling for improved model communication.
@continuedev/[email protected] Sep 22, 2025 · issue -328

Continue 1.18.0 adds --id flag for cn serve, AWS Bedrock tool streaming, and improved search-and-replace fallbacks.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Assign a stable identity to a cn serve instance, useful when running multiple servers and needing to distinguish them.
```
$ cn serve --id my-workspace-server
```
- ›Adds --id flag to the cn serve command for identifying server instances.
- ›Enables tool call streaming for the AWS Bedrock provider.
- ›Introduces search-and-replace fallback logic with unified handling across edit operations.
- ›Adds PostHog telemetry tracking for CLI tool errors.
@continuedev/[email protected] Sep 20, 2025 · issue -330

Continue 1.17.0 adds char-level next-edit diffs, fuzzy file search, and remote session listing via cn ls.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
List all active sessions, including remote ones, to audit what is currently running.
```
$ cn ls
```
- ›Adds remote session visibility to cn ls, letting practitioners inspect active remote sessions alongside local ones.
- ›Revamps file search with fuzzy matching support for faster, more flexible codebase navigation.
- ›Adds character-level diff rendering for next-edit suggestions, providing finer-grained change visibility.
- ›Splits large chat history blocks to reduce UI flickering during long sessions.
@continuedev/[email protected] Sep 19, 2025 · issue -331

Continue 1.16.0 adds Mercury Apply endpoint support, invokable markdown rules, tilde path resolution, and recommended models for tools.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds Mercury Apply endpoint support to the Inception LLM integration.
- ›Adds invokable option to markdown rule creation, enabling on-demand rule invocation.
- ›Supports tilde (~) expansion when resolving uses blocks in config.
- ›Adds more robust context length validation to prevent overflows.
- ›Adds installation guides for MCP commands.
+2 moreshow less
- ›Surfaces recommended models function for tool selection.
- ›Displays keyboard shortcuts for accept/reject diff buttons in the UI.
@continuedev/[email protected] Sep 19, 2025 · issue -331

Continue config-yaml 1.21.0 adds Mercury Apply endpoint support to the Inception LLM provider.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds Mercury Apply endpoint support to the Inception LLM provider.
@continuedev/[email protected] Sep 18, 2025 · issue -332

Continue config-yaml 1.19.0 adds an invokable option for markdown rules and more robust context length validation.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds invokable option to markdown rule creation, allowing rules to be explicitly triggered rather than applied automatically.
- ›Adds more robust context length validation to catch configuration issues before they cause runtime failures.
- ›Uses recommended-models function for tools, improving default model selection when configuring tool use.
- ›Adds block icons back to the lump UI panel.
v1.2.4-vscode Sep 18, 2025 · issue -332

Continue v1.2.4 adds CLI shell mode, terminal security warnings, dynamic tool policies, and a new experimental range tool for file operations.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.4-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.4-vscode
```
└──▷ TRY IT
Run the CLI against a specific config file when connecting to a remote agent, without modifying your default config.
```
$ cn remote --config ./my-project-config.yaml
```
Bootstrap a new project context from the CLI using the /init slash command.
```
$ /init
```
Check CLI diagnostics — environment, model, and config details — from inside a running session.
```
$ /info
```
- ›Adds --config flag to cn remote to pass a config file path at invocation time.
- ›Adds /init slash command to the CLI for project initialization.
- ›Adds /info screen diagnostics to the CLI, surfacing environment and configuration details.
- ›Adds CLI shell mode, enabling an interactive shell session via the Continue CLI.
- ›Adds ctrl+c once to clear chat input and twice to exit in the CLI TUI.
+11 moreshow less
- ›Adds terminal command security warnings to both the VS Code extension and CLI, flagging potentially dangerous commands before execution.
- ›Introduces dynamic tool policies, with the terminal tool as the first implementation, allowing per-tool execution policy control.
- ›Adds an experimental range tool for scoped file read/write operations.
- ›Adds filepath as a variable available in apply prompt templates.
- ›Adds org-level policies for indexing and MCP (Model Context Protocol) configuration.
- ›Runs dependent indexers automatically based on the active context provider.
- ›Returns token usage data for OpenAI providers.
- ›Shows the current git branch in the CLI interface when available.
- ›Adds a commit signature feature to the CLI.
- ›Skips telemetry in the CLI when no internet connection is detected.
- ›Updates supported models for the Scaleway provider.
@continuedev/[email protected] Sep 17, 2025 · issue -333

Continue config-yaml now resolves tilde (~) in uses block paths.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Supports tilde (~) expansion when resolving paths in the uses block of config YAML files.
@continuedev/[email protected] Sep 17, 2025 · issue -333

Continue config-yaml 1.17.0 adds global request configuration support.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds global request configuration (global req) to the config-yaml schema, enabling request-level settings to be defined once across the configuration.
@continuedev/[email protected] Sep 16, 2025 · issue -334

Continue config-yaml 1.15.0 adds capability-based exclusion of single-file edit mode for capable models.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds exclusion of single-file edit mode for models flagged as capable, allowing more powerful models to bypass single-file edit constraints.
@continuedev/[email protected] Sep 16, 2025 · issue -334

Continue fetch 1.2.0 adds the ability to exclude single-file edit mode for capable models.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds the ability to exclude single-file edit mode for models that support more capable editing workflows.
@continuedev/[email protected] Sep 16, 2025 · issue -334

Continue 1.14.0 adds HuggingFace router detection, Qwen2.5VL image autodetect, and diff stats in the find-and-replace toolbar.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds HuggingFace OpenAI-compatible router auto-detection so models served through HuggingFace's routing layer are identified correctly without manual configuration.
- ›Autodetects image support for Qwen2.5VL models, enabling vision workflows without manually flagging the capability.
- ›Shows diff stats (lines added/removed) in the find-and-replace toolbar for at-a-glance change awareness.
- ›Includes model identity in tool call stats, making it possible to attribute latency and usage to specific models.
- ›Auto-selects scope for org API keys in Continue Network, reducing setup friction for organization-level deployments.
v1.2.3-vscode Sep 10, 2025 · issue -340

Continue v1.2.3 adds Tetrate Agent Router, MCP SSL verification, SSE/streamable-HTTP for MCP, on-prem proxy in CLI, and pause/resume support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.3-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.3-vscode
```
- ›Adds sse and streamable http transport support for MCP in the CLI (feat(cli): support sse and streamable http for mcp).
- ›Adds SSL verification for MCP connections.
- ›Adds Tetrate Agent Router Service as a new model provider.
- ›Supports on-premises proxy in the CLI.
- ›Adds pause and resume capability in the CLI (cn).
+3 moreshow less
- ›Adds image paste support in the CLI.
- ›Warns users when running the CLI from their home directory.
- ›Keeps the assistant menu open when clicking reload.
v1.2.2-vscode Sep 4, 2025 · issue -346

Continue v1.2.2-vscode adds env support in config YAML, Sentry error tracking, Inception model support, and unsafe file read protection.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.2-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.2.2-vscode
```
└──▷ USE IT
Declare API keys or other environment variables directly in your Continue config file instead of relying on shell environment injection.
yaml
```
env:
  OPENAI_API_KEY: sk-...
  MY_CUSTOM_VAR: some-value
```
- ›Adds env section to config.yaml for declaring environment variables directly in the Continue configuration file.
- ›Adds Sentry error tracking with privacy-first anonymization for improved diagnostics.
- ›Adds salvage functionality for security-sensitive values in glob patterns to prevent accidental secret exposure.
- ›Adds protection against unsafe file reads in the agent/tool file access path.
- ›Adds gpt-oss model to the AWS Bedrock provider.
+8 moreshow less
- ›Adds support for Inception models via the OpenAI adapter.
- ›Enables native tool support for the Novita provider.
- ›Enables native tool support for the Kimi K2 model.
- ›Updates default-included context providers set.
- ›Rebrands 'assistants' as 'agents' in the UI.
- ›Updates the MCP context provider label to 'MCP Resources' in the UI.
- ›Wraps recently viewed code snippets in token blocks for clearer context display.
- ›Respects the useReranking field from configuration to control reranking behavior.
@continuedev/[email protected] Sep 3, 2025 · issue -347

Continue 1.13.0 adds a continuous AI Guide, image-paste instructions, and CLI tips for practitioners.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a continuous AI Guide to surface contextual AI assistance inline.
- ›Shows users how to paste images into the chat interface.
- ›Adds tips UI for the CLI to help users discover available actions.
@continuedev/[email protected] Aug 27, 2025 · issue -354

Continue 1.11.0 adds --mcp and --model CLI flags, multi-edit and single search-and-replace tools, a Unified Terminal, and a FIM/next-edit toggle.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Run Continue against a specific model and MCP server from the command line, useful in CI or scripted workflows.
```
$ continue --model gpt-4o --mcp my-mcp-server
```
- ›Adds --mcp and --model flags to the CLI for specifying MCP server and model at invocation time.
- ›Introduces multi-edit and single search-and-replace tools for applying targeted code changes across files.
- ›Adds UI for diff tools, surfacing multi-edit and single-replace operations in the editor interface.
- ›Adds single-replace to the default tools set.
- ›Adds a user-friendly toggle between FIM (fill-in-the-middle) and next-edit autocomplete modes.
+1 moreshow less
- ›Introduces a Unified Terminal UI.
@continuedev/[email protected] Aug 27, 2025 · issue -354

Continue 1.11.0 adds a user-friendly toggle between FIM and next-edit autocomplete modes.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a user-friendly toggle to switch between FIM (fill-in-the-middle) and next-edit autocomplete modes.
@continuedev/[email protected] Aug 25, 2025 · issue -356

Continue gains --mcp, --model, and --prompt CLI flags, new multi-edit tools, Novita provider tool support, and a Unified Terminal.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Run Continue non-interactively against a specific model and MCP server, passing a prompt directly — useful in CI pipelines.
```
$ continue --model gpt-4o --mcp ./mcp-server.json --prompt 'Review this codebase for hardcoded credentials'
```
- ›Adds --mcp and --model CLI flags for specifying MCP servers and models directly from the command line.
- ›Adds --prompt CLI flag to supply a prompt directly at invocation.
- ›Adds multi-edit and single search-and-replace tools for applying targeted code edits across files.
- ›Adds info slash command.
- ›Adds tool support for Novita provider models.
+4 moreshow less
- ›Introduces a Unified Terminal UI.
- ›Adds resource monitoring capability.
- ›Adds UI for diff tools, surfacing multi-edit and single-replace actions inline.
- ›Adds plan mode system prompt for structured agent planning workflows.
@continuedev/[email protected] Aug 24, 2025 · issue -357

Continue 1.10.0 adds --prompt flag, env config section, Novita tool support, /info slash command, and resource monitoring.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
└──▷ TRY IT
Run Continue non-interactively from CI or a script by supplying the prompt directly on the command line.
```
$ continue --prompt 'Review the auth module for hardcoded credentials and summarize findings'
```
Declare API keys or other secrets in the Continue config file instead of pre-setting them in the shell environment.
yaml
```
env:
  OPENAI_API_KEY: sk-...
  ANTHROPIC_API_KEY: sk-ant-...
```
- ›Adds --prompt flag to the CLI for passing a prompt directly at invocation.
- ›Adds env section support in config.yaml, allowing environment variables to be declared in the config file.
- ›Adds tool support for Novita provider models, enabling agentic tool calls through Novita-hosted LLMs.
- ›Adds /info slash command to the interactive interface.
- ›Adds resource monitoring capability to track system resource usage.
+1 moreshow less
- ›Updates agent and plan mode system prompts to include apply-formatting instructions for more consistent edits.
@continuedev/[email protected] Aug 22, 2025 · issue -359

Continue's OpenAI adapters 1.9.0 adds GPT-OSS support on Bedrock and hardens file-read security.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds gpt-oss model support to the Amazon Bedrock provider.
- ›Introduces a secure image component to guard against unsafe image rendering.
v1.0.80-vscode Aug 22, 2025 · issue -359

Continue v1.0.80 adds GPT-OSS on Bedrock, Kimi K2 native tools, and unsafe file read prevention.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.80-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.80-vscode
```
- ›Adds gpt-oss model support to the AWS Bedrock provider.
- ›Enables native tool support for Kimi K2 models.
- ›Adds protection against unsafe file reads to harden the extension against malicious workspace content.
- ›Updates the default-included context providers.
- ›Wraps each recently viewed code snippet inside a token block for clearer context attribution.
v1.0.24-vscode Aug 20, 2025 · issue -361

Continue v1.0.24 adds GPT-5, LGAI EXAONE support, MCP OAuth, and org policy enforcement.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.24-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.24-vscode
```
└──▷ USE IT
Enable autocomplete tuning in a YAML config file now that autocompleteOptions is supported there.
yaml
```
autocompleteOptions:
  debounceDelay: 350
  maxPromptTokens: 1024
```
- ›Adds autocompleteOptions support in .yaml config files for controlling autocomplete behavior.
- ›Adds MCP OAuth authentication support.
- ›Adds GPT-5 model support.
- ›Adds support for LGAI EXAONE models.
- ›Enforces org policies, allowing organizations to control user-facing configuration options.
+4 moreshow less
- ›Adds more next edit endpoints to the protocol.
- ›Adds a tool call status icon for the search and replace UI.
- ›Adds more prompt templates.
- ›Opens conversation summary by default.
@continuedev/[email protected] Aug 19, 2025 · issue -362

Continue openai-adapters 1.7.0 adds model-capability checks before applying full file diffs and polishes the assistant selector.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a model capability check before using full file diffs, preventing incompatible models from receiving diff payloads they cannot handle.
- ›Polishes the 'select assistant' UI experience with visual and interaction improvements.
@continuedev/[email protected] Aug 19, 2025 · issue -362

Continue 1.6.0 adds mercury-coder model support, a new edit completions endpoint, non-streaming API method, and rebrands assistants as agents.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds overrides to handle /edit/completions requests for the next-edit provider, wiring it to the new edit endpoint.
- ›Adds a non-streaming method alongside the existing streaming path for OpenAI adapter calls.
- ›Adds mercury-coder-specific constants and prompt generation templates, replacing the previous nextedit model reference with mercury-coder.
- ›Rebrands assistants as agents throughout the product UI and internals.
v1.0.22-vscode Aug 14, 2025 · issue -363

Continue v1.0.22-vscode adds chain-of-next-edits, MCP Prompt display, Gemma/Moonshot tool calling, model response caching, and pluggable system-message tool frameworks.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.22-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.22-vscode
```
- ›Adds edit file lint hook for Claude to run linting after file edits in agent workflows.
- ›Adds tool call support for Moonshot models via the moonshot provider integration.
- ›Adds tool calling support for Gemma models.
- ›Introduces 'chain of next edits' — the model now proposes a sequence of chained edit locations rather than a single next-edit suggestion.
- ›Adds plug-and-play system message tool frameworks, enabling swappable tool-use instruction sets in agent system messages.
+14 moreshow less
- ›Caches model responses for near-instant autocomplete suggestions on repeated or similar inputs.
- ›MCP Prompts now display inline when inserted into the chat input.
- ›Updates available Cerebras models and their capability-handling functions.
- ›Adds support for more next-edit models, broadening which LLMs can drive the next-edit feature.
- ›Shows a yellow border in the UI when staging mode is active.
- ›Makes tool policy alerts sticky so they remain visible during agent runs.
- ›Makes disabled tool policies more clearly communicated via tooltips.
- ›Adds unsupported-platform notification so users on unsupported OSes get an explicit message.
- ›Adds middle-mouse-button click handling to close tabs in the tab bar.
- ›Adds parallelization instructions to the agent system message to encourage concurrent tool use.
- ›Shows config error details in the UI with improved error messaging.
- ›Adds improved error messages for Anthropic API responses.
- ›Shows a notification when no tools are available in agent/tool mode.
- ›Removes the PostgreSQL context provider.
└──▷ BREAKING ON UPGRADE
- !The PostgreSQL context provider has been removed and is no longer available.
v1.0.20-vscode Aug 6, 2025 · issue -363

Continue v1.0.20 adds parallel tool calling, LLM stream retries, conversation compaction, watsonx support, and Qwen3 autocomplete.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.20-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.20-vscode
```
└──▷ USE IT
Enable local crawling with depth control when indexing docs in your Continue config.
yaml
```
context:
  - provider: docs
    params:
      useLocalCrawling: true
      maxDepth: 3
```
- ›Adds useLocalCrawling and maxDepth settings for indexed documents, restoring control over local doc crawl behavior.
- ›Adds slug field to rule objects in dev data.
- ›Supports parallel tool calling, enabling multiple tool calls to execute simultaneously in a single assistant turn.
- ›Adds automatic LLM streamChat retries to recover from transient stream failures.
- ›Adds conversation compaction with a UI button to compress long chat histories and stay within context limits.
+11 moreshow less
- ›Adds a Continue Docs MCP server for serving documentation via the Model Context Protocol.
- ›Adds watsonx as a supported model provider with tool support.
- ›Adds Qwen3 support for the autocomplete function.
- ›Supports the @Terminal context provider and 'Run in Terminal' button for the JetBrains plugin.
- ›Improves the search-and-replace tool to support multiple diffs per tool call.
- ›Adds codebase/colocated rules caching to speed up rule lookups.
- ›Adds a warning message when the last user input is pruned due to context length limits.
- ›Adds a Continue proxy OpenAI adapter for routing requests through the Continue proxy.
- ›Adds caching with multiple swappable strategies to the Anthropic OpenAI adapter.
- ›Introduces session file persistence for chat sessions.
- ›Improves Next Edit developer experience with enhanced UX for JetBrains (MVP for internal testing).
@continuedev/[email protected] Jul 28, 2025 · issue -364

Continue 1.5.0 adds a Vertex AI OpenAI-compatible adapter and editOutcome logging for Agent Mode.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds a Vertex AI OpenAI adapter, enabling Vertex AI models to be used via the OpenAI-compatible interface.
- ›Adds editOutcome logging for Agent Mode to capture edit result telemetry.
- ›Adds commit ID to main build version strings for easier build tracing.
@continuedev/[email protected] Jul 24, 2025 · issue -364

Adds a Vertex AI OpenAI adapter and IntelliJ terminal integration including runCommand() and getTerminalContents().
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds slug field to rule objects in dev data.
- ›New Vertex AI OpenAI adapter enables routing Continue through Google Cloud Vertex AI endpoints.
- ›Implements runCommand() method in IntelliJIde.kt with TerminalOptions support, aligning IntelliJ terminal behavior with the VS Code extension.
- ›Adds getTerminalContents() in IntelliJIde.kt to read content from the selected terminal panel.
- ›Terminal panels now reuse existing terminals by matching terminalName before spawning a new one.
+1 moreshow less
- ›Terminal UI gains collapse/expand toggle for large output content.
@continuedev/[email protected] Jul 22, 2025 · issue -364

Continue config-yaml 1.3.0 adds slug field to rule objects in dev data.
└──▷ GET THIS VERSION
```
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]
```
- ›Adds slug field to rule objects in dev data for identifying rules by a stable, human-readable identifier.
v1.0.19-vscode Jul 16, 2025 · issue -364

Continue v1.0.19 adds Plan Mode, Amazon Nova/claude-opus-4/LlamaStack support, VertexAI key auth, MCP cwd, and mermaid diagram rendering.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.19-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.19-vscode
```
└──▷ USE IT
Pin a working directory for an MCP server so its tools resolve paths relative to your project root.
yaml
```
mcpServers:
  - name: my-mcp-server
    command: npx
    args: ['-y', 'my-mcp-package']
    cwd: /workspace/my-project
```
Authenticate to VertexAI using a service-account key file instead of ADC, useful in CI or multi-project environments.
yaml
```
models:
  - provider: vertexai
    model: gemini-2.0-flash
    keyFile: /secrets/gcp-sa-key.json
    project: my-gcp-project
    region: us-central1
```
- ›Adds cwd option to MCP server configuration in the Continue YAML config, allowing working-directory control for MCP tools.
- ›Adds keyFile, keyJson, and express/apiKey fields to VertexAI provider configuration for flexible credential management.
- ›Adds uri field for context items in the HTTP context provider.
- ›Adds tool call support for deepseek-chat and deepseek-reasoner models.
- ›Adds claude-opus-4 tool support for Amazon Bedrock models.
+19 moreshow less
- ›Enables Amazon Nova models.
- ›Adds a Bedrock OpenAI adapter, allowing Bedrock to be used via OpenAI-compatible interfaces.
- ›Adds LlamaStack provider support.
- ›Introduces Plan Mode for agent interactions, keeping the model in a planning-only state before executing tool calls.
- ›Adds o-series model autodetection for OpenAI-compatible providers.
- ›Adds @codebase context provider tool-calling mode under an experimental flag.
- ›Adds icon UI control to truncate conversation history at the last tool call.
- ›Allows interrupting in-progress tool calls from the UI.
- ›Dynamically switches between ghost-text and SVG decoration rendering for autocomplete based on model output.
- ›Adds a 'Generate Rule' dialog for creating rules directly from the UI.
- ›Adds a custom llmstxt plugin.
- ›Adds mermaid diagram rendering in chat responses.
- ›Adds a sessions loading indicator in the UI.
- ›Adds multi-stage matching algorithm to improve history search quality.
- ›Surfaces indexing errors to the Indexing menu instead of halting the entire indexing process.
- ›Enforces a limit on read-file tool calls: files exceeding half the context length are not added.
- ›Adds a continue init prompt command.
- ›Adds isWorkspaceRemote message type support in the IntelliJ extension.
- ›Enhances context provider search with improved filtering.
└──▷ BREAKING ON UPGRADE
- !The default mode is now agent mode; setups that relied on chat mode as the default will launch in agent mode after upgrading.
v1.0.18-vscode Jul 13, 2025 · issue -364

Continue v1.0.18 adds regex rule triggers, hot-reloading rules, vLLM reranking, Ollama tool-call streaming, and a search-and-replace tool experiment.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.18-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.18-vscode
```
└──▷ USE IT
Activate a rule automatically whenever a file matches a regex pattern — no manual toggling needed.
yaml
```
# .continue/rules/no-use-effect.md
---
name: No useEffect
trigger:
  regex: "\\.tsx?$"
---
Do not use useEffect. Prefer derived state or event handlers.
```
Configure MCP server request options (e.g. custom headers or timeouts) directly in the YAML config.
yaml
```
mcpServers:
  - name: my-mcp
    command: npx
    args: ['-y', 'my-mcp-server']
    requestOptions:
      timeout: 30000
      headers:
        Authorization: 'Bearer <token>'
```
Tune sampling behavior for a model by setting presence and frequency penalties in the YAML config.
yaml
```
models:
  - name: my-model
    provider: ollama
    model: llama3
    minP: 0.05
    frequencyPenalty: 0.3
    presencePenalty: 0.3
```
- ›Adds requestOptions to YAML config for MCP server definitions.
- ›Adds minP, frequencyPenalty, and presencePenalty parameters to YAML config model blocks.
- ›Adds proxy support for ripgrep download, enabling use in air-gapped or proxy-restricted environments.
- ›Supports regex-based rule triggers in .continue/rules files, letting rules activate automatically when file content or context matches a pattern.
- ›Adds manual on/off toggling of individual rules during a session.
+11 moreshow less
- ›Introduces hot-reloading for .continue/rules files — changes take effect without restarting the extension.
- ›Adds vLLM response_format support in reranking logic.
- ›Adds Ollama streaming support for tool calls in agent mode.
- ›Adds @codebase as an experimental tool available in agent mode.
- ›Adds an experimental search-and-replace tool for agent/edit workflows.
- ›Adds a 'Manually trigger reasoning' button to enable reasoning mode in the UI.
- ›Adds MCP provider refresh for @mention dropdown submenu items, keeping available tools current without a restart.
- ›Reads NODE_EXTRA_CA_CERTS and improves NO_PROXY logic in the fetch layer for enterprise network compatibility.
- ›Adds a custom fetch environment flag (Custom Fetch Env Flag) for controlling fetch behavior.
- ›Supports tools for prompt definitions, allowing prompts to declare which tools they can invoke.
- ›Refreshes Cohere provider support with updated integration.
└──▷ BREAKING ON UPGRADE
- !@codebase is removed from the default context providers list.
v1.0.16-vscode Jul 10, 2025 · issue -364

Continue v1.0.16 adds vLLM reranking, regex rule triggers, hot-reload for rules, Ollama tool-call streaming, and a search-and-replace tool experiment.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.16-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.16-vscode
```
└──▷ USE IT
Add per-MCP-server HTTP options (e.g. custom headers or timeouts) directly in your YAML config.
yaml
```
mcpServers:
  my-server:
    command: npx
    args: ['-y', 'my-mcp-server']
    requestOptions:
      timeout: 30000
      headers:
        Authorization: 'Bearer <token>'
```
Set fine-grained sampling parameters for a model via YAML config.
yaml
```
models:
  - name: my-model
    provider: ollama
    model: llama3
    minP: 0.05
    frequencyPenalty: 0.3
    presencePenalty: 0.2
```
- ›Adds requestOptions to YAML config for MCP servers, enabling per-server HTTP options in .continue/config.yaml.
- ›YAML config now loads minP, frequencyPenalty, and presencePenalty model parameters.
- ›Adds proxy support for ripgrep download via environment-level fetch configuration.
- ›Adds CONTINUE_CUSTOM_FETCH_ENV flag (Custom Fetch Env Flag) to control fetch behaviour via environment variable.
- ›Reads NODE_EXTRA_CA_CERTS and improves NO_PROXY logic in the core fetch layer.
+18 moreshow less
- ›Supports vLLM response_format in reranking logic, enabling vLLM as a reranker backend.
- ›Refreshes Cohere integration with updated support.
- ›Supports Ollama streaming for tool calls in agent mode.
- ›Adds regex-based rule triggers so .continue/rules files can activate conditionally on file content or path patterns.
- ›Enables manually toggling individual rules on and off from the UI.
- ›Adds hot reloading for .continue/rules files — changes take effect without restarting the extension.
- ›Adds an experimental search-and-replace tool for agent/edit workflows.
- ›Adds @codebase as an experimental tool available in agent mode.
- ›Adds support for tools inside prompts (Support tools for prompts).
- ›Adds an 'Enable Reasoning' button to the UI for compatible models.
- ›Adds MCP provider refresh for @mention dropdown submenu items, keeping context providers current.
- ›Adds a webview listener for index progress to dynamically load submenu items.
- ›Adds Sentry error reporting (including thread dumps attached to Sentry events and caught exceptions) for the IntelliJ extension.
- ›Introduces Next Edit MVP — a new edit prediction/navigation capability.
- ›Increases the default context length and adds detection tests for context-length limits.
- ›Limits glob tool output size.
- ›Improves the AssistantAndOrgListbox UI component for assistant/org selection.
- ›Logs tool call success and failure outcomes for observability.
└──▷ BREAKING ON UPGRADE
- !@codebase is removed from the default context providers list; it is now available only as an experimental agent-mode tool.
v1.0.14-vscode Jun 21, 2025 · issue -365

Continue v1.0.14 adds requestRule tool, streamable-http MCP support, per-model autocomplete config, next-edit prediction, and a Fetch URL Content tool.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.14-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.14-vscode
```
└──▷ USE IT
Tune autocomplete aggressiveness differently per model — e.g. a faster model gets a shorter debounce.
yaml
```
models:
  - name: starcoder2-3b
    provider: ollama
    model: starcoder2:3b
    tabAutocompleteOptions:
      debounceDelay: 100
      maxPromptTokens: 512
  - name: deepseek-coder
    provider: ollama
    model: deepseek-coder:6.7b
    tabAutocompleteOptions:
      debounceDelay: 300
      maxPromptTokens: 1024
```
Store workspace-specific API keys so they take precedence over repo-root credentials without touching the shared .env.
```
$ # Place secrets here — loaded before <workspace>/.env
OPENAI_API_KEY=sk-proj-...
ANTHROPIC_API_KEY=sk-ant-...
```
- ›Adds streamable-http transport support for MCP servers, configurable in config.yaml.
- ›Adds tabAutocompleteOptions configuration on a per-model basis in config.yaml, enabling different autocomplete tuning per LLM.
- ›Adds caBundlePath support for data URIs, enabling inline CA bundle configuration.
- ›Secrets are now fetched from <workspace>/.continue/.env before falling back to <workspace>/.env, giving workspace-level credential precedence.
- ›Adds requestRule tool, allowing the assistant to request applicable rules during a session.
+22 moreshow less
- ›Adds a RulesContextProvider for surfacing rules as context in chat.
- ›Adds rule co-location support, enabling rules to live alongside the code they govern.
- ›Adds a 'Fetch URL Content' tool for retrieving web content directly from within the assistant.
- ›Adds support for autocomplete context from other open editor tabs.
- ›Adds simple context deduplication for autocomplete to reduce redundant suggestions.
- ›Adds a shortcut to force autocomplete in VS Code.
- ›Adds 'next edit' prediction capability alongside autocomplete.
- ›Adds an 'Edit Highlighted Code' submenu item in the editor context menu.
- ›Adds verbose logging option for the custom fetch layer.
- ›Adds terminal color and escape sequence rendering in the Continue terminal.
- ›Enables Continue terminal support for additional VS Code Remote Host Types.
- ›Adds Inception as a supported LLM provider.
- ›Adds IBM Watsonx as a supported LLM provider.
- ›Adds claude-4-sonnet and Opus models to LLM info.
- ›Adds Gemini model info entries.
- ›Includes MCP server names in tool names to disambiguate tools across servers.
- ›Adds support for completions through a proxy.
- ›Adds a 'Quick pick' UI for entering API keys directly in VS Code.
- ›Config and block errors are now surfaced in the extension GUI.
- ›Adds a 'resubmit' button on the error dialog for recoverable failures.
- ›Adds a markdown rules creation shortcut in the notch UI.
- ›Always shows the active file in the input toolbar instead of the codebase context.
v1.0.12-vscode Jun 10, 2025 · issue -365

Continue v1.0.12 adds MCP Streamable HTTP, new YAML config keys, OS-aware terminal, and automatic current-file chat context.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.12-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.12-vscode
```
└──▷ USE IT
Cap stop words and enable streaming explicitly for a model in your YAML config to control generation behavior.
yaml
```
models:
  - name: my-model
    provider: openai
    model: gpt-4o
    maxStopWords: 4
    defaultCompletionOptions:
      stream: true
```
Force a rule to always apply to every chat and agent session by setting alwaysApply in your rules config.
yaml
```
rules:
  - name: coding-standards
    description: Enforce team coding standards in every session
    alwaysApply: true
    content: Always use snake_case for variable names.
```
- ›Adds maxStopWords to model config in YAML, letting users cap the number of stop words sent to a model.
- ›Adds stream to defaultCompletionOptions in YAML config, enabling explicit control over streaming behavior per completion.
- ›Adds description field support in markdown YAML front-matter for rules/prompts.
- ›Adds alwaysApply property to rules config for unconditional rule application regardless of context.
- ›Adds MCP Streamable HTTP transport support, expanding how Model Context Protocol servers can be connected.
+5 moreshow less
- ›Surfaces stderr output in error messages for failed MCP servers, making misconfiguration easier to diagnose.
- ›Automatically adds the current file as context in chat without requiring manual @file attachment.
- ›Makes the terminal command tool aware of the OS, platform, and shell it is running in for more accurate command generation.
- ›Removes 'Edit' as a distinct mode, consolidating the interaction surface.
- ›Adds MCP resource templates support.
└──▷ BREAKING ON UPGRADE
- !The 'Edit' mode has been removed; workflows that relied on Edit as a separate mode will need to migrate to the remaining modes.
v1.0.22-jetbrains Jun 3, 2025 · issue -365

Continue v1.0.22 adds Next Edit prediction, proxy-aware completions, verbose fetch logging, and Claude 4 Sonnet/Opus model support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.22-jetbrains https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.22-jetbrains
```
└──▷ TRY IT
Prioritize workspace-specific API keys or secrets over repo-root defaults in a shared project.
```
$ # Place your secrets in the workspace-scoped location so they take precedence
mkdir -p <workspace>/.continue
echo 'ANTHROPIC_API_KEY=sk-ant-...' > <workspace>/.continue/.env
```
- ›Secrets are now fetched from <workspace>/.continue/.env before falling back to <workspace>/.env, giving workspace-scoped credentials priority.
- ›Supports caBundlePath as a data URI, enabling inline CA bundle configuration without a file on disk.
- ›Adds verbose logging option for the custom fetch layer to aid in diagnosing network and proxy issues.
- ›Supports completions through a proxy, extending LLM reachability in firewalled or enterprise environments.
- ›Adds claude-4-sonnet and claude-opus (Opus) to the built-in LLM info registry.
+3 moreshow less
- ›Introduces Next Edit prediction, a new autocomplete-adjacent capability that anticipates the developer's next code edit.
- ›Adds a 'call alongside autocomplete' feature that allows additional calls to fire in parallel with autocomplete requests.
- ›Adds the JCEF out-of-process VM setting for the JetBrains plugin, improving rendering stability.
└──▷ BREAKING ON UPGRADE
- !The free trial provider has been removed; setups relying on it will no longer function after upgrade.
v1.0.11-vscode May 31, 2025 · issue -366

Continue v1.0.11 adds SSE MCP support, markdown rules, embedding prefixes, prompt caching, OpenRouter tool support, and a full theme colors framework.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.11-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.11-vscode
```
- ›Adds promptCaching to Default Completion Options in config.yaml, enabling prompt caching including Bedrock Tools Caching.
- ›Adds embedding prefixes support to config-yaml for embedding model configuration.
- ›Adds markdown rules capability, allowing rules to be authored in Markdown format.
- ›Enables OpenRouter tool support by default.
- ›Adds seed coder FIM (fill-in-the-middle) template.
+13 moreshow less
- ›Automatically respects HTTP_PROXY, HTTPS_PROXY, and NO_PROXY environment variables in the continuedev/fetch package.
- ›Reads custom environment configuration from macOS plist files and Linux /etc/ files.
- ›Adds a setting for auto-accepting agent mode edits.
- ›Adds display of rules used in the active session, giving visibility into which rules are applied.
- ›Adds support for Claude Sonnet 4.
- ›Adds Devstral as a model that supports tools.
- ›Adds full Theme Colors Framework for UI theming.
- ›Adds showFile implementation in JetBrains IDE.
- ›Opens prompt file or slug directly on edit click.
- ›Cancels autocomplete requests after a timeout is reached.
- ›Opens config when clicking 'edit the prompt'.
- ›Adds error message when an MCP argument contains an unsubstituted variable.
- ›Matches all context to rules.
v1.0.21-jetbrains May 29, 2025 · issue -366

Continue v1.0.21 for JetBrains adds SSE/Streamable-HTTP MCP, markdown rules, requestRule tool, alwaysApply rule property, and Claude Sonnet 4 support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.21-jetbrains https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.21-jetbrains
```
└──▷ USE IT
Force a rule to always apply in every session, regardless of context, by setting alwaysApply in a markdown rule file.
yaml
```
---
name: Security Baseline
description: Always-on security coding guidelines
alwaysApply: true
---

Never log secrets. Sanitize all user input before use.
```
Enable streaming and cap stop words in your model config so completions respect your latency budget.
yaml
```
models:
  - name: my-model
    provider: openai
    model: gpt-4o
    defaultCompletionOptions:
      stream: true
      maxStopWords: 4
```
- ›Adds alwaysApply property to rules for unconditional rule application regardless of context matching.
- ›Adds description field in markdown YAML front-matter for rule files.
- ›Adds stream key to defaultCompletionOptions in YAML config to control streaming behavior.
- ›Adds maxStopWords model config option in YAML for controlling stop-word limits.
- ›Adds requestRule tool enabling the agent to fetch and apply rules on demand.
+19 moreshow less
- ›Adds support for markdown-based rules (rules authored in .md files).
- ›Automatically respects HTTP_PROXY, HTTPS_PROXY, and NO_PROXY environment variables in the continuedev/fetch package for all outbound requests.
- ›Reads proxy/environment settings from macOS plist files and Linux /etc/ files for custom environment configuration.
- ›Reads proxy/environment settings from the Windows registry.
- ›Adds Devstral as a model with tool-calling support.
- ›Adds support for Claude Sonnet 4.
- ›Adds a SeedCoder FIM (fill-in-the-middle) template.
- ›Adds a new full theme colors framework for UI customization.
- ›Displays which rules were used in a chat session.
- ›Adds current file context automatically to chat.
- ›Terminal command execution is now OS-, platform-, and shell-aware.
- ›Cancels autocomplete requests after a configurable timeout is reached.
- ›Makes apply-streaming operations cancelable.
- ›Removes Edit as a standalone mode, consolidating into agent/chat modes.
- ›Adds a setting for auto-accepting agent mode edits.
- ›Shows stderr output in error messages for failed MCP servers.
- ›Implements showFile in JetBrains to open files directly from the UI.
- ›Adds a link to the Continue Hub from the Help Center.
- ›Opens prompt file or slug on edit click.
└──▷ BREAKING ON UPGRADE
- !Edit mode has been removed as a standalone mode; existing workflows relying on Edit mode will need to migrate to agent or chat mode.
v1.0.10-vscode May 17, 2025 · issue -366

Continue v1.0.10 adds custom MCP timeouts, SSE custom headers, Watsonx Messages API, and Llama 4/Codestral model support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.10-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.10-vscode
```
- ›Adds custom MCP timeout configuration, letting users override the default connection timeout for MCP servers.
- ›Adds support for custom headers in SSE transport, enabling authenticated or enterprise SSE MCP connections.
- ›Adds Watsonx Messages API integration as a supported provider.
- ›Adds Llama 4 Scout Cerebras to the model definition schema.
- ›Adds a Codestral prompt template.
+8 moreshow less
- ›Re-exports a configured openai object from the Continue SDK, simplifying client construction.
- ›Makes assistant optional on the Continue SDK.
- ›Adds a keyboard shortcut to the autocomplete quickpick.
- ›Includes rules in edit requests, applying configured rule sets during inline edits.
- ›Adds ghost text display for removed lines during apply, making streaming diffs more visible.
- ›Adds more visible assistant refresh controls and submenus in the UI.
- ›Marks all gpt- and o-series models as chat-only (routed to chat endpoints, not /v1/completions).
- ›Updates Qwen3 tool-use support.
└──▷ BREAKING ON UPGRADE
- !All gpt- and o-series models are now marked as chat-only and will no longer use the /v1/completions endpoint.
v1.0.9-vscode May 10, 2025 · issue -366

Continue v1.0.9 adds globs to rules, Mistral/DeepSeek agent support, new providers, and a Lazy Edit tool.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.9-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.9-vscode
```
└──▷ USE IT
Scope a rule to only TypeScript files so the agent applies it exclusively when working in .ts contexts.
yaml
```
globs: ["**/*.ts"]
name: typescript-style
description: Enforce TypeScript conventions
content: Always use strict null checks and explicit return types.
```
Enable extended reasoning for a model by capping its reasoning token budget in config.
yaml
```
models:
  - name: my-reasoning-model
    provider: anthropic
    model: claude-3-7-sonnet-latest
    reasoning: true
    reasoningBudgetTokens: 8000
```
Offload Ollama inference to a specific number of GPU layers for faster local completions.
yaml
```
models:
  - name: ollama-codellama
    provider: ollama
    model: codellama
    num_gpu: 35
```
- ›Adds globs field to rules in config to scope which files a rule applies to, and to the create-rule tool so agents can write glob-scoped rules.
- ›Adds standalone template parameter to YAML model config for controlling prompt formatting.
- ›Adds reasoning and reasoningBudgetTokens parameters to config schemas for models that support extended reasoning.
- ›Adds num_gpu support for Ollama models in config.
- ›Adds Mistral models as supported providers in Agent mode.
+13 moreshow less
- ›Adds DeepSeek models as supported providers in Agent mode.
- ›Adds OVHcloud AI Endpoints as a new model provider.
- ›Adds Venice as a new model provider.
- ›Adds OpenVINO Model Server as a supported provider.
- ›Adds gemini-2.5-pro to the built-in model list.
- ›Introduces a separate agent system message, distinct from the chat system message.
- ›Introduces a Lazy Edit tool for deferred, single-file edit operations.
- ›Provides the current workspace path to HttpContextProvider so context plugins can use it.
- ›Updates SambaNova model list with current available models.
- ›Adds full-text search support for multi-word queries in the codebase index.
- ›Shows embedding model errors in the UI and prompts to download missing local embedding models.
- ›Models in the Chat view are now sorted alphabetically.
- ›Carries over requestOptions from config to completion models.
└──▷ BREAKING ON UPGRADE
- !chatTemplate config key is renamed to chat.
v1.0.8-vscode May 2, 2025 · issue -366

Continue v1.0.8 adds a create_rule_block tool, autocomplete prompt templates, HuggingFace/Voyage re-additions, and Azure o3/o4 tool support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.8-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.8-vscode
```
- ›Adds create_rule_block tool, enabling AI agents to programmatically create rule blocks during a session.
- ›Adds autocomplete prompt template configuration, giving users control over how autocomplete suggestions are generated.
- ›Re-adds HuggingFace and Voyage as supported provider integrations.
- ›Adds tool-calling support for Azure-hosted o3 and o4 models.
- ›Introduces the Continue SDK (feat: continue sdk), exposing a programmatic interface for extending Continue.
+6 moreshow less
- ›Enhances the terminal tool with an improved UI for agent-driven terminal interactions.
- ›Adds a 'Clear session history' button to the chat UI.
- ›Supports multiple edit ranges being highlighted simultaneously for improved text selection in edit mode.
- ›Adds 'instant apply' check for diff rejection, giving immediate feedback when a code diff is declined.
- ›Allows optional naming of context blocks in configuration.
- ›Clarifies that uses blocks in config are pulled from hub.continue.dev.
v1.0.7-vscode Apr 26, 2025 · issue -367

Continue v1.0.7 adds chatOptions.baseSystemMessage, lazy apply for full files, and a create-file button in the code block toolbar.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.7-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.7-vscode
```
└──▷ USE IT
Inject a standing security-focused instruction into every chat session without repeating it in each prompt.
json
```
"chatOptions": {
  "baseSystemMessage": "You are a security-aware coding assistant. Always flag use of deprecated crypto APIs and suggest modern alternatives."
}
```
- ›Adds chatOptions.baseSystemMessage config key to set a base system message for chat sessions.
- ›Reintroduces lazy apply for full files, enabling faster application of large AI-suggested edits.
- ›Adds a 'create file' button directly in the code block toolbar for one-click file creation from a suggestion.
- ›Adds a toolbar header to all code blocks, surfacing actions consistently across the UI.
- ›Adds a refresh button on the right of the assistant selector to reload available assistants.
+4 moreshow less
- ›Allows skipping the Ollama onboarding flow for users who have already configured Ollama.
- ›Adds no-diff stream progress indicator for fast-apply models, giving visual feedback without a diff view.
- ›Generates a JSON schema for the Continue configuration format.
- ›Profiles now refresh automatically on deeplink navigation and when selecting an org or profile.
v1.0.6-vscode Apr 17, 2025 · issue -367

Continue v1.0.6 adds Docker model runner, Inception/InceptionLabs providers, LS/Grep/Glob agent tools, prompt blocks, and Bedrock prompt caching.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.6-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.6-vscode
```
- ›Adds support for the Docker model runner as a model provider.
- ›Adds the inception provider for Inception Labs models.
- ›Adds the inceptionlabs provider as a dedicated InceptionLabs integration.
- ›Adds LS (list directory), Grep, and Glob built-in agent tools for file-system navigation during agentic sessions.
- ›Adds prompt blocks feature (feat: prompt blocks), enabling reusable prompt components in assistant configurations.
+13 moreshow less
- ›Adds Bedrock prompt caching support (feat/bedrock-prompt-caching and feat/bedrock-secure-prompt-caching) for AWS Bedrock-backed models.
- ›Enables embedding and reranking capabilities across all model providers.
- ›Lifts SiliconFlow to a reranker model provider and adds Google gemini-2.5-pro-exp-03-25 and additional models.
- ›Adds rich LLM logging for detailed request/response observability.
- ›Adds conditional rules support (if rules) for context-aware assistant behavior.
- ›Adds a CLI for linting config-yaml configurations.
- ›Implements hub client integration for Connect to Continue Hub workflows.
- ›Adds an option to always route through the Continue proxy.
- ›Enforces a file-size limit on file mentioning, blocking large files from being added as context.
- ›Enables tools support for Cogito models running on Ollama.
- ›Adds fallback to the chat model when the apply model is unavailable.
- ›Adds metadata fields to config-yaml schema.
- ›Improves MCP resource handling and refreshes context provider titles in the UI.
v1.0.5-vscode Mar 27, 2025 · issue -368

Continue v1.0.5 adds tools support for custom LLMs and fireworks.ai, Anthropic extended thinking, MCP text resources, AWS credential auto-retrieval, and more.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.5-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.5-vscode
```
└──▷ USE IT
Cap Jira issues returned as context to avoid overwhelming the model with large backlogs.
json
```
{
  "name": "jira",
  "params": {
    "domain": "https://your-org.atlassian.net",
    "token": "<your-token>",
    "maxResults": 20
  }
}
```
Add authenticated headers to an HTTP context provider so it can reach a protected internal API.
json
```
{
  "name": "http",
  "params": {
    "url": "https://internal.corp/context",
    "headers": {
      "Authorization": "Bearer <token>",
      "X-Team": "security"
    }
  }
}
```
Set a context-length cap on a custom LLM so Continue does not exceed the model's window.
json
```
{
  "title": "My Custom LLM",
  "provider": "openai",
  "model": "my-fine-tuned-model",
  "contextLength": 16384
}
```
- ›Adds contextLength attribute to LLMOptions for custom LLM configurations.
- ›Adds maxResults attribute to the Jira context provider to cap the number of returned issues.
- ›Adds headers support to the HTTP context provider for authenticated requests.
- ›Adds tools (function calling) support for custom LLMs.
- ›Adds tools support for fireworks.ai models.
+19 moreshow less
- ›Adds function calling support to the VertexAI provider.
- ›Adds watsonx reranker integration for codebase retrieval.
- ›Enables retrieval of AWS credentials from environment variables and ECS/EC2 instance metadata.
- ›Supports MCP text resources, allowing MCP servers to expose readable text content.
- ›Surfaces tool call arguments in the chat UI so users can inspect what the model is invoking.
- ›Displays citations in the output for Perplexity Sonar research models.
- ›Processes and streams Anthropic extended thinking blocks, showing them in the output tab — supported on both direct Anthropic and AWS Bedrock providers.
- ›Adds instant apply for unified diff format.
- ›Adds up/down arrow key history navigation in the editor's edit-mode input.
- ›Supports pulling missing Ollama models on demand.
- ›Adds new Gemini models to config_schema.json.
- ›Adds new DeepSeek models to the config schema.
- ›Chunks user queries before embedding to improve codebase retrieval quality.
- ›Implements walkdir caching to speed up file-tree traversal.
- ›Batches URIs for snippets queries, reducing retrieval overhead.
- ›Adds a schema: v1 declaration for YAML configuration.
- ›Adds YAML-based model capability configuration.
- ›Adds an 'Explore Hub' onboarding card in both VS Code and JetBrains IDEs.
- ›Removes unused MCP connections on config reload to reduce resource usage.
v1.0.4-vscode Mar 15, 2025 · issue -368

Continue v1.0.4 adds AWS Bedrock tool use with Claude 3.7, Gemini 2.0 Flash support, proxy tool support, and inline keyboard shortcuts.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.4-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.4-vscode
```
- ›Adds AWS Bedrock tool use support, including tools support for Claude 3.7 on Bedrock.
- ›Adds Gemini 2.0 Flash to the model selection GUI and to @continuedev/llm-info.
- ›Adds proxy tool support.
- ›Adds a shortcuts component for inline keyboard shortcuts in the UI.
- ›Adds VSCode URI query param handling.
+2 moreshow less
- ›Filters global Prompt Files to only show files ending with .prompt.
- ›Adds JetBrains cross-environment support for Continue Enterprise (CE).
v1.0.3-vscode Mar 7, 2025 · issue -368

Continue v1.0.3 adds session tabs, Claude 3.7 Sonnet support, and a profiles refresh button.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.3-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.3-vscode
```
- ›Adds Claude 3.7 Sonnet to config_schema.json and enables tool support for Claude 3.7 in toolSupport.ts.
- ›Introduces a Tabs feature for managing multiple chat sessions within the extension.
- ›Adds a shared config toggle for session tabs, letting users control whether tabs share or isolate configuration.
- ›Adds a Refresh Profiles button to reload available profiles without restarting the extension.
v1.0.1-vscode Feb 26, 2025 · issue -369

Continue v1.0.1-vscode adds Grok-2, Gemini 2.0 Flash, o3-mini tool support, promptTemplates in config.yaml, and dev data destinations.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.1-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v1.0.1-vscode
```
└──▷ USE IT
Define a custom prompt template for a specific model directly in config.yaml so Continue uses your system prompt format on every request.
yaml
```
models:
  - name: my-llama
    provider: ollama
    model: llama3
    promptTemplates:
      chat: "<|system|>\n{system_message}\n<|user|>\n{user_message}\n<|assistant|>"
```
- ›Adds promptTemplates key to config.yaml model entries, letting users define per-model prompt templates directly in config.
- ›Adds Grok-2 as a selectable chat model in the model setup UI.
- ›Adds gemini-2.0-flash to the config schema as a supported model.
- ›Adds tools support for o3-mini.
- ›Adds Dev Data Destinations feature, enabling routing of developer interaction data to configurable destinations.
+15 moreshow less
- ›Adds model toggles, allowing individual models to be enabled or disabled from the UI.
- ›Adds autocomplete language support for Lua and Luau.
- ›Adds Novita AI as a supported provider with updated base model info and logo.
- ›Improves autocomplete context for Codestral and Qwen Coder models.
- ›Broadens Granite 3 model detection for autocomplete.
- ›Switches the repo map tool to display function/method signatures instead of full bodies.
- ›Adds support for using multiple resources on a single MCP server (previously limited to one).
- ›Adds Angular and Django to the pre-indexed documentation set.
- ›Adds Windows ARM64 native vector database support via @lancedb/vectordb-win32-arm64-msvc.
- ›Updates Azure URI handling for Azure AI Foundry users.
- ›Intercepts Ollama errors before the webview to surface Download/Start options directly in the UI.
- ›Full-screen panel now opens in front of VS Code rather than behind it.
- ›Consolidates Account Settings into a unified view and improves the org/assistant switcher.
- ›Implements diff-snippet caching keyed on file save timestamp, reducing redundant context computation.
- ›Tools capability restricted to JSON-only mode for broader model compatibility.
└──▷ BREAKING ON UPGRADE
- !Default chat and autocomplete models are removed; existing setups that relied on built-in defaults will have no model selected after upgrade.
v0.8.56-vscode Nov 8, 2024 · issue -372

Adds a timestamp attribute to the file autocomplete.jsonl autocomplete log format.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.8.56-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v0.8.56-vscode
```
- ›Adds a timestamp attribute to entries in the file autocomplete.jsonl autocomplete log file.
v0.8.48-vscode Sep 1, 2024 · issue -374

Continue v0.8.48 adds a Repo Map context provider and improves codebase indexing progress UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.8.48-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v0.8.48-vscode
```
- ›Adds a Repo Map context provider for surfacing repository structure as context.
- ›Improves @codebase context quality by incorporating repomap.
- ›Improves the indexing progress UI to better surface codebase indexing status.
v0.8.47-vscode Aug 27, 2024 · issue -375

Continue v0.8.47 adds headless browser crawling and text-to-speech in the chat window.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.8.47-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v0.8.47-vscode
```
- ›Adds text-to-speech (TTS) support in the chat window.
- ›Switches documentation crawling to a headless browser for more complete page rendering and better results.
- ›Improves support for WatsonX models.
v0.0.53-jetbrains Jul 10, 2024 · issue -376

Continue v0.0.53 for JetBrains adds .prompt file support and a new onboarding experience.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.53-jetbrains https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout v0.0.53-jetbrains
```
- ›Supports .prompt files for defining reusable prompt templates.
- ›Introduces a new onboarding experience for first-time setup.

Continue

Summary

What Continue answers

Examples

Command line

Release history