## Bundled CLI Version
This SDK release bundles CLI version: 0.25.3
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.25.2
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.25.1
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.25.0
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.24.7
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.24.6
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.24.5
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.24.3
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.24.1
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.23.3
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.23.2
Source: CLI built from source (same branch/ref as SDK)
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.23.1
Source: CLI built from source (same branch/ref as SDK)
---
## Highlights
The bundled CLI 0.23.0 includes two fixes requested in #11022:
- Managed memory availability now respects the `memory.enableManagedAutoMemory` setting (#6941). Hosts that disable managed auto memory no longer see remember/dream requests admitted or managed-memory instructions in the system prompt; local patches can be removed.
- Size-triggered microcompaction now clears old tool results toward a low watermark (#8464), so it no longer rewrites another part of the conversation prefix on every subsequent turn. Provider prompt-cache reuse is preserved across long tool-heavy sessions, reducing cached-input cost.
## Bundled CLI Version
This SDK release bundles CLI version: 0.23.0
Source: latest stable CLI from npm
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.19.10
Source: latest stable CLI from npm
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.15.3
Source: latest stable CLI from npm
---
## Bundled CLI Version
This SDK release bundles CLI version: 0.13.1
Source: latest stable CLI from npm
---
> Backfilled release for npm-published version 0.1.5 (original workflow failed before GitHub release creation).
## What's Changed
* chore: bump version to 0.8.2 by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1632
* chore(release): sdk-typescript v0.1.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/1633
* Fix: Use resolved authType to initialize ACP agent by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1622
* Add parentToolCallId and subagentType for ACP subagent tracking by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1620
* feat(core): improve error message when skill is invoked as tool by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1623
* fix(acp): stream subagent text + reasoning chunks by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1626
* fix: ensure output-language.md is created before config initialization by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1637
* fix(security): prevent command injection via newline bypass in shell command validation by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1638
* Fix Claude plugin resource collection to respect marketplace config by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1639
* feat(core): improve retry logic for better 429/5xx error handling by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1628
* feat: add extra_body support for OpenAI-compatible providers by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1654
* Support model selection through ACP in vscode ide companion by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1582
* feat: add multi-modal input support (image, PDF, audio) across all content generators by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1564
* Add Zed extension for Qwen Code agent server by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1630
* feat: clarify output formats for non-interactive mode by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1579
* feat: add concurrent runner for batch CLI execution by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1640
* Add experimental LSP support for code intelligence by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1401
* Fix: React/React-DOM version inconsistency in package.json and lockfile by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1659
* feat(webui): implement unified UI architecture with shared component library by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1543
* chore: bump version to 0.9.0 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1661
* Add contextWindowSize Configuration Support by @xuewenjie123 in https://github.com/QwenLM/qwen-code/pull/1539
* fix(core): avoid passing undici agent to Anthropic SDK by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1663
* fix(vscode-ide-companion): fix race conditions and improve @ file completion search by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1676
* fix(core): properly cleanup MCP server subprocesses on exit by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/1285
* test(cli): stabilize AuthDialog ESC assertion by @liqiongyu in https://github.com/QwenLM/qwen-code/pull/1535
* fix(cli): expand MCP @server: resource references by @liqiongyu in https://github.com/QwenLM/qwen-code/pull/1531
* fix(core): auto-enable WebFetch and WebSearch tools in Plan mode by @afarber in https://github.com/QwenLM/qwen-code/pull/1686
* feat(core): add symlink support for skill manager by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/1690
* fix: normalize skill file content in extensions to handle BOM and CRLF by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1667
* fix(ci): honor manual preview version input by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1665
* build: Improve build efficiency and add dev mode by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1681
* fix(core): handle heredoc in command substitution guard by @liqiongyu in https://github.com/QwenLM/qwen-code/pull/1701
* feat: Preserve UTF-8 BOM when editing files by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1680
* fix(core): Preserve trailing whitespace in newString during edits by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1688
* fix: enable Shift+Tab shortcut in Windows PowerShell by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1607
* fix(core): enforce tool restrictions in subagents by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1691
* [AnthropicContentGenerator] optimize: ADD cache_control for system and last user text message by @Weaxs in https://github.com/QwenLM/qwen-code/pull/1613
* refactor(i18n): translate Agent as 智能体 by @itchina110 in https://github.com/QwenLM/qwen-code/pull/1718
* fix(docker): fix build error and enable manual version builds by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1722
* chore(release): Bump version to 0.10.0 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1720
* fix(settings): rename negative settings to positive naming (disable* -> enable*) by @afarber in https://github.com/QwenLM/qwen-code/pull/1330
* ci(sdk-release): use stable CLI tags for SDK releases by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1710
* feat(query): add support for resuming sessions with session ID by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/1714
* add hint for installing external source extensions by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1694
* Feat/javasdk alpha 202501 by @gwinthis in https://github.com/QwenLM/qwen-code/pull/1717
* Fix: clarify is_background parameter is required in docs and examples by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1716
* feat: Remove Smart Edit tool and ClearcutLogger by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1684
* Add export command for session history with markdown and HTML formats by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1515
* Add FORK_MODE support to ProcessTransport for Electron IPC integration by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1719
* feat(sdk): add resume, continue options and extend authType support by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1726
* Fix ACP model selection to handle all configured authentication types by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1555
* refactor: remove read_many_files tool, add readManyFiles utility for user @-commands by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1673
* fix(vscode-ide-companion): Fix UI display issues with server-side timestamp and file path extraction by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1682
* chore: Reduce Qwen OAuth free quota from 2000 to 1000 requests per day by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/1730
* fix(ui): resolve auth not updating in top-right corner by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1670
* feat: debug mode output refactor — route console calls to logfile-first debugLogger by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1610
* fix: use openai model instead of index=0 in acp integration test by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1733
* fix(cli): route sandbox diagnostic messages to stderr by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1735
* Add CLI source selection for SDK releases and fix subagent output handler by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1732
* feat(paste): add large paste placeholder and fix enter-submit on macOS by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1713
* fix(cli): prevent Tab key from cycling approval mode when autocomplete is active on Windows by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1736
* feat: promote Agent Skills from experimental to stable by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1738
* feat: add source information tracking in telemetry logs by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1653
* docs: Update Linux/Mac installation commands in README by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1739
* feat(settings): add settings.env field for environment variable configuration by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1751
* fix(mcp): improve MCP server management and authentication by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1752
* fix(core): properly handle MCP multi-part tool results in OpenAI converter by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1755
* Fix CLI argument parsing for /dist/cli/cli.js entry point by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1758
* fix(integration-tests): correct MCP tool name in simple-mcp-server test by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1763
* Fix SDK MCP integration tests by updating hardcoded tool names to use constants by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1769
* Fix: Warning in installation shell script by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1771
* fix(ui): resolve model not updating in top-right corner by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1662
* fix(cli): use PowerShell Get-Command for Windows sandbox detection by @afarber in https://github.com/QwenLM/qwen-code/pull/1604
* fix: prioritize local path detection in extension installation by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1770
* fix(auth-model-login-ui): prevent Enter key from triggering empty message submission by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/1773
* feat: add MCP tool progress update support in TUI and SDK mode by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/1756
* feat: add Coding Plan authentication mode with unified AuthDialog by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1788
* feat(coding-plan): implement Coding Plan configuration management and update prompts by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1805
* docs: update authentication documentation with Coding Plan setup guide by @joeytoday in https://github.com/QwenLM/qwen-code/pull/1800
* chore: bump version to 0.10.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/1808
* Fix: Fix node installation permission issue in shell script by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/1819
* fix: prevent AbortSignal listener memory leak by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1811
* feat: add TPM throttling error handling with 1-minute retry delay by @wenshao in https://github.com/QwenLM/qwen-code/pull/1791
* fix: correct showLineNumbers default value to true by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1813
* fix: support JSON Schema draft-2020-12 for MCP tools (fixes #1818) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/1821
* Add dev launch config and preserve existing NODE_OPTIONS by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/1784
* Fix abort listener accumulation in subagent while loop by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1825
* refactor(cli): unify Escape key handling in AppContainer by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1824
* Fix auth UI to use semantic theme colors and correct selection sync by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1823
* Add --session-id support for CLI and SDK by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1822
* chore: bump version to 0.10.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/1844
* docs: improve settings.json configuration guide with quick setup examples by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/1850
* feat: update readme by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/1853
* docs: add news banner about Qwen3.5-Plus launch by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/1854
* Fix sandbox user permission in integration tests by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1843
* Add Coding Plan Global/Intl region support by @Mingholy in https://github.com/QwenLM/qwen-code/pull/1860
* chore: bump version to 0.10.3 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/1863
* chore: bump version to 0.10.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/1864
## New Contributors
* @itchina110 made their first contribution in https://github.com/QwenLM/qwen-code/pull/1718
* @joeytoday made their first contribution in https://github.com/QwenLM/qwen-code/pull/1800
* @wenshao made their first contribution in https://github.com/QwenLM/qwen-code/pull/1791
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/sdk-typescript-v0.1.4...sdk-typescript-v0.1.5