Qwen Code

Summary

Qwen Code is an open-source AI coding agent that operates within the terminal, and it uses an MIT license. It is run as a command-line tool for platform engineers, and its documentation describes it as an autonomous agent with auto-memory and multi-protocol support for various APIs. The project's resources indicate a stable deployment via self-contained installers for Linux, macOS, and Windows.

An open-source AI coding agent that lives in your terminal.

Command line

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

1. v0.22.3 Aug 28, 2026 · issue 009

   Qwen Code v0.22.3 adds named channel sessions, a qwen review ab-drive subcommand, standalone daemon session APIs, and a Mem0 extension skeleton.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.22.3 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.22.3

   └──▷ TRY IT
   Run execution-grade verification scripts against a PR tree and its base to confirm a fix actually passes before merging.
   copy

   $ qwen review ab-drive

   • ›Adds the qwen review ab-drive subcommand to run execution-grade verification scripts against PR and base trees with shared or fresh instances.
   • ›Adds a standalone daemon session API supporting create, list, resume, archive, and delete operations for top-level sessions.
   • ›Adds a private OpenTelemetry span attribute to report detailed LLM context usage metrics including input categories and remaining capacity.
   • ›Adds a configurable Mem0 extension skeleton providing a retrieval-only external-context-mem0 stdio Extension with bounded HTTP request support.
   • ›Enables daemon Extension installs to accept absolute local paths while rejecting relative paths and unsupported options like ref.
   +15 moreshow less

   • ›Adds owner-scoped named sessions in Channels, allowing users to manage up to eight persistent named tasks per chat.
   • ›Adds a triage gate that automatically identifies and closes duplicate PRs when their changes are already fully resolved by merged fixes.
   • ›Adds an opt-in composer add menu in Web Shell grouping attachments, files, extensions, MCP servers, and skills.
   • ›Adds an opt-in interactive browser terminal to Web Shell that manages independent PTY sessions per tab with persistent scrollback and state handling.
   • ›Adds an opt-in setting for embedded Web Shell hosts to hide the session source switch, pinning all sidebar catalogs to ordinary task conversations.
   • ›Adds fixConstraint field to review findings to specify existing facts or limits that suggested fixes must not violate.
   • ›Makes Aone a first-class platform for session PR bindings, enabling automatic branch-to-MR mapping and state refresh via the a1 CLI.
   • ›The /review command now remembers the last explicitly used --effort level per project for subsequent runs without arguments.
   • ›The /review command now warns when a subsystem's Critical issues repeatedly regrow across rounds by detecting successor chains.
   • ›Confirmed Critical issues now include direction and baseline axes to distinguish between false certifications, failures, regressions, and new surfaces.
   • ›Long-running review rounds now update their status comment every 10 minutes with elapsed time and last agent activity.
   • ›Backfills PR bindings for existing sessions and adds merge-state snapshots to track whether linked pull requests are open, merged, or closed.
   • ›Updates Web Shell sidebar to display GitHub-style colored state icons for sessions bound to pull requests based on their open, merged, or closed status.
   • ›Implements safe projection for reserved [FILE: ...] output markers by redacting malformed or oversized inline markers without uploading files.
   • ›Deferred review suggestions are now recoverable by external tooling via a stable invisible marker in the review body artifact.
2. v0.22.2 Aug 26, 2026 · issue 009

   Qwen Code v0.22.2 adds MCP 2026, DingTalk channel, --open-with-auth, --topology minimal, tools.workflowsEnabled, and a session token usage panel.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.22.2 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.22.2

   └──▷ TRY IT
   Start a local Web Shell with bearer-token authentication so only authorised clients can connect — useful when exposing the daemon on a shared host.
   copy

   $ qwen serve --open-with-auth

   Run a fast, single-pass review of a PR instead of the default multi-round pipeline — good for low-risk changes where speed matters more than exhaustive coverage.
   copy

   $ /review --topology minimal

   Opt in to dynamic workflow orchestration for a project by setting tools.workflowsEnabled in user settings.
   json copy

   {
     "tools": {
       "workflowsEnabled": true
     }
   }

   • ›Introduces qwen serve --open-with-auth to open a loopback Web Shell with bearer authentication using a provided or auto-generated token.
   • ›Enables dynamic workflows via the tools.workflowsEnabled user setting, replacing the previous undocumented environment variable method.
   • ›Adds tokensUsed field to GoalRecord to report total tokens consumed by a Goal alongside its turn count in the lastGoal summary.
   • ›Adds support for creating scheduled tasks that reuse an existing live session by providing an optional sessionId.
   • ›Adds a new find-simplifications sweep skill that identifies dead code and orphaned resources, generating evidence-backed proposals for maintainer review.
   +31 moreshow less

   • ›Introduces a built-in DingTalk Workspace channel supporting direct messages, mentions, document notifications, and todo tracking using authenticated DWS CLI profiles.
   • ›Adds a session token usage panel to the Web Shell.
   • ›Adds four built-in output styles (Concise, Proactive, Explanatory, Learning) to control how the agent reports work throughout a session.
   • ›Adds support for MCP 2026 core protocol and introduces an MCP Apps host for rendering inline applications in daemon-backed WebShell sessions.
   • ›Adds an opt-in liveness check for daemon child processes using ACP channels, with retries and timeouts to detect failures without false positives from host suspension.
   • ›Adds a goal-draft skill that writes verifier-judgeable Goals.
   • ›Introduces a per-project outside-repo artifact landing area.
   • ›Reports review findings to clients as a typed contract.
   • ›Adds temporal-reachability and incident-replay lenses to review briefs.
   • ›Adds a do-not-refute list and constructible rejection bar to the /review skill verifier to prevent invalid rejections of speculative findings.
   • ›Validates inline anchors for /review --comment on Aone targets before posting, relocating Critical findings to the summary body and discarding Suggestions if anchors are invalid.
   • ›Enables PR context fetching for Aone Code targets in the /review command, including native approval and issue fidelity.
   • ›The review skill now supports comment-status and presubmit flows for Aone Code targets, generating the same JSON report schema as GitHub for merge-gate and CI state checks.
   • ›Adds Kimi (Moonshot AI) as a built-in third-party provider with support for international and China endpoints and editable model catalogs.
   • ›Adds support for dual-role image generation models.
   • ›Compact mode now folds adjacent thinking, tool activity, and parallel agents into a single expandable summary row in the Web Shell, and is now the only mode.
   • ›Adds an optional async prepareSubmit callback for Web Shell hosts to resolve context dynamically before submission.
   • ›WebShell exposes an optional callback to report the active session's complete subagent task snapshot for embedding hosts.
   • ›Adds standalone sessions for projectless tasks via the CLI.
   • ›Enables managed auto-memory lifecycle via ACP.
   • ›Replaces built-in Computer Use tools with a bundled skill that automatically configures the external Node REPL MCP server and CUA SDK on first use.
   • ›The Computer Use SDK for Node.js is updated to v0.20.0, providing versioned accessibility observations and stable element tokens across macOS, Windows, and Linux.
   • ›Accepts cross-session messages behind an inbound gate.
   • ›create_sub_session is now declared only under qwen serve.
   • ›The Workflow tool now displays a detailed approval dialog showing the script name, phases, and arguments before execution.
   • ›Review executions now run the repository's own commands inside a container boundary defined by operator policy.
   • ›The VS Code companion adopts the shared WebShell transcript renderer as its default and only conversation timeline.
   • ›Web Shell now correctly refreshes composer skills after toggles.
   • ›Review compose surfaces a land-with-residual-risk advisory when critical findings persist across rounds.
   • ›Promoted language-pitfall and wrapper/proxy checks to dedicated high-effort Step 3A roles for more thorough code review.
   • ›The /review command adds an advisory note when the overall approach, rather than the current patch, is identified as the primary open question.
   └──▷ BREAKING ON UPGRADE

   • !The persistent Node REPL is now delivered as a standalone MCP server (refactored out of core); existing setups relying on the built-in Node REPL tool will need to migrate to the new MCP server configuration.
   • !The Electron desktop package has been removed; users of the built-in desktop app must migrate to the separately maintained OpenWork fork.
3. desktop-v0.2.2 Aug 26, 2026 · issue 008

   Qwen Code desktop-v0.2.2 adds DingTalk channel, containerized review runs, ACP liveness, scheduled tasks, and a --topology minimal review mode.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch desktop-v0.2.2 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout desktop-v0.2.2

   └──▷ TRY IT
   Run a fast single-pass code review in CI without the full multi-arm topology.
   copy

   $ qwen -p "/review --topology minimal"

   • ›Adds --topology minimal flag to the /review skill for a single-pass A/B review arm, reducing review overhead.
   • ›Adds DingTalk Workspace as a new IM channel, joinable via qwen channel.
   • ›Runs the reviewed repository's own commands inside a container during /review, isolating execution from the host.
   • ›Adds ACP channel transport liveness monitoring to the daemon, enabling reliable detection of dropped connections.
   • ›Adds support for current-session scheduled tasks in the daemon.
   +8 moreshow less

   • ›Adds a per-project outside-repo artifact landing directory, letting agents deposit outputs outside the repository root.
   • ›Requires an explicit user opt-in before the model launches a workflow, preventing accidental autonomous execution.
   • ›Changes get_goal's default view to a summary instead of the full catalog, reducing noise in Goal introspection.
   • ›Reports /review findings to clients as a typed contract, enabling structured downstream consumption.
   • ›Engages the severity floor earlier on a sustained convergence signal during /review, surfacing critical issues sooner.
   • ›Migrates the desktop build from Electron to Tauri, removing the Electron package while keeping the Tauri upgrade bridge.
   • ›Makes compact view the only mode in the web shell UI, removing the previous multi-mode toggle.
   • ›Manages agent view session lifecycle from the CLI.
4. v0.22.0 Aug 22, 2026 · issue 005

   Qwen Code v0.22.0 adds non-blocking slash commands, GitHub PR session binding, machine-readable review codes, and auto permission mode in Python/Java SDKs.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.22.0 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.22.0

   • ›Extends non-blocking slash commands to eleven built-ins including /theme and /tools, allowing immediate execution while a response is streaming.
   • ›Adds machine-readable convergence observation codes such as root-cause-triage and batch-fixes to enable automated review actions on review loop output.
   • ›Enables /review presubmit on Aone targets to detect self-MRs and head drift by routing through the a1 CLI and comparing author identity.
   • ›Updates /review --comment output on Aone targets to explicitly disclose that posted comments are unmarked and only join the generic discussion gate.
   • ›Extends the /review skill cleanup audit to Aone Code targets, flagging comments or edits made within the review window that were not submitted via the sanctioned path.
   +9 moreshow less

   • ›Integrates import widening logic into fetch-pr --since to streamline incremental scope calculation and reduce token usage.
   • ›Adds a secure fallback path for installing public GitHub extensions on older Git versions by resolving commits via GitHub's anonymous API and downloading archives directly.
   • ›Binds created GitHub PRs to their originating sessions with a searchable list and sidebar badge, supporting up to 10 PRs per session with latest-first ordering.
   • ›Updates Python and Java SDKs to support the auto permission mode, aligning them with the CLI and TypeScript SDK for LLM-based tool call approval.
   • ›Makes list_directory opt-in (disabled by default) in core.
   • ›Assigns review agents a dedicated subagent type with only six required tools to reduce token usage and improve performance.
   • ›Review loops now explain why they are not settling by citing specific files with recurring findings or comment volumes that are not shrinking.
   • ›Autofix now audits the PR approach for simplicity and minimal change instead of stopping automation immediately upon a growth-budget breach.
   • ›Web Shell keeps conversation turns expanded while their background shells are running, collapsing them only after completion.
5. v0.21.15 Aug 20, 2026 · issue 003

   Qwen Code v0.21.15 adds --resume for interrupted reviews, authenticated HTTPS Git installs, qwen3.8-max model, and Thinking toggle for hybrid models.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.21.15 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.21.15

   └──▷ TRY IT
   Resume an interrupted PR review in CI without re-running from scratch, as long as the PR head commit has not changed.
   copy

   $ qwen review run --resume

   Switch to the stable qwen3.8-max model mid-session to use the production-grade reasoning model instead of a preview build.
   copy

   $ /model qwen3.8-max

   • ›Adds --resume flag to /review, review run, and CI retries to continue interrupted reviews when the PR head has not moved.
   • ›Adds the stable qwen3.8-max model to the Token Plan model list, selectable via /model alongside the existing preview version.
   • ›The /review skill now supports posting comments and approvals to Aone Code via the a1 CLI when using the --comment flag.
   • ›Adds authenticated HTTPS Git extension installs with configurable credential persistence, enabling secure cloning of private repositories via the daemon.
   • ›Adds batch APIs to update Extension activation states for up to 100 extensions globally or for specific trusted workspaces.
   +13 moreshow less

   • ›Web Shell now supports inserting file attachments into active turns via the composer or @ selection, with preview and queue management.
   • ›Unifies file uploads in Web Shell to offer reference or upload options, storing attachments persistently with duplicate name handling.
   • ›Web Shell adopts Goal v3 controls, allowing goals to be managed independently of chat messages with a compact composer row.
   • ›Qwen hybrid models now expose a simple Thinking toggle for reasoning control, removing complex effort tiers for supported versions.
   • ›Adds PTY worker support to enable managed Agent View sessions with local terminal hosts and authenticated stream forwarding.
   • ›ACP child processes now track and report V8 old-generation heap metrics, including peak committed memory and major-GC counts, in daemon status.
   • ›Links daemon HTTP request spans to inbound W3C traceparent headers to maintain continuous distributed tracing context.
   • ›The bridge now exposes a strictly monotonic per-session watermark via BridgeSessionSummary.updatedAt in the live-state API.
   • ›Enables DingTalk to download and attach media from quoted messages, allowing agents to inspect referenced images and files.
   • ›Introduces primitives for standalone conversation isolation, enabling deterministic session identity and validated lineage checks.
   • ›Sessions now persist a privacy-preserving ledger of prompt outcomes to enable accurate cold-load reconciliation without storing user content.
   • ›Adds a one-time INFO message to the CLI that lists attached context files above the first user prompt, making invisible system prompt attachments visible in chat.
   • ›Autofix now requires mutation probes to verify that new guards or branches added in a round are covered by tests before committing changes.
6. v0.21.14 Aug 19, 2026 · issue 002

   Qwen Code v0.21.14 adds qwen sessions ps, /advisor slash command, new HTTP polling endpoints, and GitLab support via Aone Code.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.21.14 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.21.14

   └──▷ TRY IT
   Poll the current turn status of a daemon session without holding an SSE connection open — useful in scripts or CI jobs.
   copy

   $ curl -s http://localhost:<port>/session/<id>/turns/current

   Resume an interrupted PR review without re-running work already completed, reusing the existing worktree.
   copy

   $ qwen fetch-pr --resume <pr-number>

   • ›Adds qwen sessions ps subcommand to list running interactive sessions with optional JSON output, backed by a new live-session registry.
   • ›Adds trusted-only GET /workspaces/:workspace/sessions/live-state endpoint returning volatile session snapshots and a catalog version token to reduce polling.
   • ›Adds pollable HTTP endpoints GET /session/:id/turns/current and GET /session/:id/turns/:promptId to check daemon turn status without SSE.
   • ›Adds QWEN_SERVE_NEW_FILE_MODE environment variable to make the daemon's serve new-file mode configurable.
   • ›Adds fileUploadDirectory Web Shell config key to set a default upload directory, and enforces full drag-and-drop disablement when fileUploadEnabled is false.
   +14 moreshow less

   • ›Adds /advisor slash command for an independent, read-only second opinion on the current conversation without mutating history.
   • ›Enables workflow agents to pin a specific working directory via agent({workingDir}), allowing operation outside default bounds.
   • ›Adds Aone Code as a second review provider, enabling meta, issue-context, and fetch-pr commands for GitLab-based repositories.
   • ›Adds --resume flag to fetch-pr to resume interrupted reviews by validating on-disk state and reusing the existing worktree.
   • ›Adds skill-toggle mutation metadata attached to settings_changed events in the daemon.
   • ›Introduces privacy-safe diagnostics correlating oversized or mutated tool results using size measurements and HMAC hashes without exposing content.
   • ›Consolidates Local Control into a single daemon-owned implementation with a secondary listener, unified security model, and revocable pairing credentials.
   • ›Seeds the autofix takeover round counter with /takeover from N syntax.
   • ›Adds deterministic flakiness gate in the sandboxed verification lane that re-runs modified unit tests multiple times to detect non-deterministic failures.
   • ›Exported HTML viewer now includes a global 'Expand all / Collapse all' toolbar to toggle collapsible sections like thinking blocks and tool outputs.
   • ›Review comments posted via --comment now use plain reviewer prose instead of template scaffolding.
   • ›Improves Web Shell sidebar session management with consistent hover details, compact status indicators, and persistent workspace expansion behavior.
   • ›Adds end-to-end support for session-scoped media references so image previews persist across refreshes.
   • ›Enhances the review skill to analyze shell and CI scripts against the specific execution lanes and environments where they actually run.
7. v0.21.13 Aug 17, 2026 · issue -002

   Qwen Code v0.21.13 adds conversation forking, file drag-and-drop in Web Shell, --since flag for incremental PR review, and a new External Context Provider Extension Profile.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.21.13 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.21.13

   └──▷ TRY IT
   Scope a PR diff review to only changes since a local cache marker, for faster incremental validation in CI.
   copy

   $ qwen review fetch-pr --since <ledger-marker> <pr-number>

   Normalize findings inputs through final gates, accepting bracketed source tags without manual cleanup.
   copy

   $ qwen findings --to-anchors <findings-file>

   • ›Adds --since flag to qwen review fetch-pr for validating incremental review anchors and scoping diffs based on local cache or ledger markers.
   • ›Adds --to-anchors option to the findings pipeline to normalize inputs for final gates and accept bracketed source tags.
   • ›Introduces the External Context Provider Extension Profile v1 to enable provider-owned retrieval integrations via Qwen Extension and MCP boundaries.
   • ›The /review skill now uses dedicated platform subcommands meta and fetch-diff instead of executing raw gh commands.
   • ›Stopped takeover PRs now receive an autofix/needs-human label and appear in a new Takeover pool table on the dashboard.
   +13 moreshow less

   • ›The runAllChunks command now outputs a diagnostic message on stderr when --all-chunks fans out a plan identified as Step 3A.
   • ›Web Shell composer now supports dragging, dropping, and pasting text files as named attachments alongside images.
   • ›Users can now fork conversations from any specific Assistant response using durable checkpoints.
   • ›Split-view panes now inherit the host's builtinAtProviders exclusions and custom @ mention categories from the host configuration.
   • ›Review sessions now record session IDs and diff hashes to credit agent work across interrupted runs.
   • ›The reverse-audit round cap now scales dynamically based on diff topology, allowing more rounds for small diffs and fewer for large ones.
   • ›Verified findings outside the PR footprint are now deferred to a follow-up queue and tracked in a dedicated issue.
   • ›Sessions now preserve active work when close is refused by draining queued tasks within an 8-second budget before teardown.
   • ›The hourly spam-minimization sweep now includes inline pull request review comments.
   • ›Duplicate suggestions in /review are now listed in a dedicated paragraph with links to existing comments instead of being counted as anchor failures.
   • ›PR review workflow now posts a fallback comment with retry guidance if the main review job dies abnormally.
   • ›Autofix includes a deny-by-default footprint gate and positional window censuses.
   • ›Release notes are now presented as a bilingual English and Chinese digest grouped by capability themes with attached screenshots.
8. v0.21.13 Aug 17, 2026 · issue 002

   Qwen Code v0.21.13 adds conversation forking, text-file drag-and-drop in Web Shell, --since flag for incremental review, and External Context Provider profiles.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.21.13 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.21.13

   
   └──▷ TRY IT
   Validate incremental review anchors for a PR, scoping the diff only to changes since the last cached marker — useful in CI to avoid re-reviewing already-covered hunks.
   copy

   $ qwen review fetch-pr --since <ledger-marker> <pr-number>

   • ›Adds --since flag to qwen review fetch-pr for validating incremental review anchors and scoping diffs based on local cache or ledger markers.
   • ›Adds --to-anchors option to the findings command to normalize inputs for final gates (also fixes silent input-file overwrite when the flag is misused).
   • ›The /review skill gains dedicated platform subcommands meta and fetch-diff, replacing raw gh command execution.
   • ›The runAllChunks command now outputs a diagnostic message on stderr when --all-chunks fans out a plan identified as Step 3A.
   • ›Introduces the External Context Provider Extension Profile v1 to enable provider-owned retrieval integrations via Qwen Extension and MCP boundaries.
   +12 moreshow less

   • ›Stopped takeover PRs now receive an autofix/needs-human label and appear in a new Takeover pool table on the dashboard.
   • ›Split-view panes now inherit the host's @ mention configuration, ensuring builtinAtProviders exclusions and custom categories apply consistently.
   • ›The reverse-audit round cap now scales dynamically based on diff topology — more rounds for small diffs, fewer for large ones, and capped at three for huge diffs when a clock is present.
   • ›Verified findings outside PR footprints are now deferred to a follow-up queue and tracked in a dedicated issue instead of being discarded.
   • ›Web Shell composer now supports dragging, dropping, and pasting text files as named attachments alongside images.
   • ›Users can now fork conversations from any specific Assistant response using durable checkpoints to ensure branch accuracy.
   • ›Sessions now preserve active work on close by draining queued tasks within an 8-second budget before teardown.
   • ›Review sessions now record session IDs and diff hashes to enable crediting agent work across interrupted runs.
   • ›Release notes are now presented as a bilingual (English and Chinese) digest grouped by capability themes with attached screenshots.
   • ›The hourly spam-minimization sweep now includes inline pull request review comments.
   • ›Duplicate suggestions in /review are now listed in a dedicated paragraph with links to existing comments instead of being counted as anchor failures.
   • ›The PR review workflow now posts a fallback comment with retry guidance if the main review job terminates abnormally.
9. v0.21.12 Aug 14, 2026 · issue -005

   Qwen Code v0.21.12 adds cross-worktree Git mutation guards, OpenTelemetry tracing, per-agent JSONL transcripts, and stricter Critical findings verification.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.21.12 https://github.com/QwenLM/qwen-code.git
   # already have the repo? check out this version:
   $ git checkout v0.21.12

   • ›Adds a guard to block cross-worktree Git mutations from model-issued commands that target directories outside the current session.
   • ›Adds optional OpenTelemetry trace and span IDs to daemon logs for correlation and debugging of sampled requests.
   • ›Adds OpenTelemetry-compliant traces for main agent invocations with stable identities and correct status semantics for success, cancellation, and errors.
   • ›Enables per-agent JSONL transcripts for all workflow agent dispatches, recording prompts, tool calls, and results consistently.
   • ›Implements a diff growth brake in autofix reviews to limit source and test line increases per window using configurable budgets.
   +11 moreshow less

   • ›Adds automatic escalation to maintainers when autofix diffs exceed growth budgets across multiple rounds.
   • ›Confirmed Critical findings now require an executed witness with observed output, automatically demoting unverified claims to low confidence and hiding them from PR posts.
   • ›Review ledger markers now include the anchor commit SHA to ensure accurate incremental diff scoping across environments.
   • ›Adds user settings to control review attribution footers, default effort levels, and default comments, preventing repository files from overriding these policies.
   • ›The /review command now identifies and reports entire classes of unbounded defects prospectively instead of listing individual instances.
   • ›Compact mode (Ctrl+O) now displays model reasoning as a foldable 'Thinking...' summary instead of hiding it entirely.
   • ›Supports uploading workspace files to the Web Shell composer via drag-and-drop or the @ file panel with progress tracking.
   • ›Web Shell Channel management now supports full policy configuration, workspace binding, and a redesigned management interface.
   • ›Background shells are now tracked in activeWork, enabling explicit negotiation of shell categories and preventing premature automatic cleanup.
   • ›Requests routed through Alibaba Cloud API Gateway domains now correctly include metadata fields for session tracing and log correlation.
   • ›Updates the review loop to validate feedback based on content accuracy rather than relying solely on the author's identity.
10. v0.21.12 Aug 14, 2026 · issue 002

    Qwen Code v0.21.12 adds cross-worktree Git mutation guards, OpenTelemetry tracing, per-agent JSONLJSONLA text format where each line is a self-contained, valid JSON object, making it easy to stream, append, and process large datasets record-by-record without loading an entire JSON array into memory. transcripts, and stricter Critical findings verification.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.12 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.12

    • ›Adds a guard to block cross-worktree Git mutations from model-issued commands targeting directories outside the current session.
    • ›Adds optional OpenTelemetry trace and span IDs to daemon logs to improve correlation and debugging for sampled requests.
    • ›Enables per-agent JSONL transcripts for all workflow agent dispatches, recording prompts, tool calls, and results consistently.
    • ›Adds user settings to control review attribution footers, default effort levels, and default comments, preventing repository files from overriding these policies.
    • ›Implements a diff growth brake in autofix reviews to limit source and test line increases per window using configurable budgets, with automatic escalation to maintainers when budgets are exceeded across multiple rounds.
    +8 moreshow less

    • ›Confirmed Critical findings now require an executed witness with observed output; unverified claims are automatically demoted to low confidence and hidden from PR posts.
    • ›The /review command now identifies and reports entire classes of unbounded defects prospectively instead of listing individual instances.
    • ›Web Shell Channel management now supports full policy configuration, workspace binding, and a redesigned management interface.
    • ›Supports uploading workspace files to the Web Shell composer via drag-and-drop or the @ file panel with progress tracking.
    • ›Compact mode (Ctrl+O) now displays model reasoning as a foldable 'Thinking...' summary instead of hiding it entirely.
    • ›Background shells are now tracked in activeWork, enabling explicit negotiation of shell categories and preventing premature automatic cleanup.
    • ›Requests routed through Alibaba Cloud API Gateway domains now correctly include metadata fields for session tracing and log correlation.
    • ›Review loop now validates feedback based on content accuracy rather than relying solely on the author's identity.
11. v0.21.11 Aug 13, 2026 · issue -006

    Qwen Code v0.21.11 adds Agent Plugins v1, the /coordinate multi-agent command, OpenTelemetry session lifecycle events, and a Channels sidebar view.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.11 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.11

    └──▷ TRY IT
    Spin up a multi-agent session where specialist read-only teammates contribute to a task and results are forwarded automatically to the leader agent.
    copy

    $ /coordinate

    Check memory health in the current session, including tool result sizes and warnings for any results over 30k characters that may degrade context.
    copy

    $ /doctor memory

    • ›Adds the /coordinate command to enable native multi-agent workflows with read-only teammates and automated result forwarding to the leader agent.
    • ›Adds /doctor memory command reporting that now includes tool result retention stats, character counts, and warnings for results exceeding 30k characters.
    • ›Adds support for Agent Plugins v1 to extend agent capabilities.
    • ›Adds session.start and session.end OpenTelemetry lifecycle events to improve observability of session creation and shutdown.
    • ›ACP sessions now use the unified Goal v3 runtime, supporting create, edit, pause, resume, and clear actions with improved turn scheduling.
    +8 moreshow less

    • ›Web Shell sidebar gains a Channels view to track integration sessions from DingTalk, Feishu, and WeCom alongside standard tasks.
    • ›Web Shell now supports Qwen 3.8 reasoning controls, letting users toggle Thinking mode and select effort levels directly from the model chip.
    • ›Terminal window titles now display status symbols (◐, ✳) to indicate task state in multiplexers where color cues are unavailable.
    • ›Adds an Aliyun OSS release mirror for desktop builds.
    • ›Project memory isolation now defaults to workspace scope for qwen serve runtimes, while standalone CLI behavior remains unchanged.
    • ›Improved text selection with word-wise drag on double-click and line-wise extension on triple-click in the UI.
    • ›Web Shell subagent rows now display persistent chevrons, improved hover states, and inline agent types and metrics.
    • ›Background task notifications in Web Shell are now localizable and display structured metadata in chat-style bubbles.
12. v0.21.11 Aug 13, 2026 · issue 002

    Qwen Code v0.21.11 adds Agent Plugins v1, native multi-agent /coordinate command, OpenTelemetry session events, and a Web Shell Channels view.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.11 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.11

    └──▷ TRY IT
    Spin up a multi-agent workflow where specialist sub-agents handle tasks and forward results to a coordinating leader agent.
    copy

    $ /coordinate

    Check how much memory tool results are consuming and surface any results that exceed the 30k-character warning threshold.
    copy

    $ /doctor memory

    • ›Adds /coordinate command for native multi-agent workflows with read-only teammates and automated result forwarding to the leader agent.
    • ›Adds /doctor memory command reporting that now includes tool result retention stats, character counts, and warnings for results exceeding 30k characters.
    • ›Adds OpenTelemetry session.start and session.end lifecycle events for observability of session creation and shutdown.
    • ›Adds Agent Plugins v1 support to extend agent capabilities via the extensions system.
    • ›Web Shell sidebar now includes a Channels view to track integration sessions from DingTalk, Feishu, and WeCom alongside standard tasks.
    +8 moreshow less

    • ›Web Shell now supports Qwen 3.8 reasoning controls, letting users toggle Thinking mode and select effort levels directly from the model chip.
    • ›ACP sessions now use the unified Goal v3 runtime, supporting create, edit, pause, resume, and clear actions with improved turn scheduling.
    • ›Terminal window titles now display status symbols (◐, ✳) to indicate task state in multiplexers where color cues are unavailable.
    • ›Adds an Aliyun OSS release mirror for desktop distribution.
    • ›Web Shell subagent rows now show persistent chevrons, improved hover states, and inline display of agent types and metrics.
    • ›Project memory isolation now defaults to workspace scope for qwen serve runtimes, while standalone CLI behavior remains unchanged.
    • ›Review skill's reverse audit now detects defects in modeled system layers such as sandboxes by comparing runtime state semantics against the model.
    • ›Background task notifications in the Web Shell are now localizable and display structured metadata within chat-style bubbles.
13. desktop-v0.2.1 Aug 12, 2026 · issue -007

    Qwen Code desktop v0.2.1 adds an Aliyun OSS release mirror, OpenTelemetry session lifecycle alignment, Goal v3 in ACP sessions, and improved subagent and tool activity UI.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch desktop-v0.2.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout desktop-v0.2.1

    • ›Adopts Goal v3 in ACP sessions via the CLI (feat(cli): adopt Goal v3 in ACP sessions).
    • ›Adds Aliyun OSS as a release mirror for desktop downloads.
    • ›Aligns session lifecycle telemetry with the OpenTelemetry standard.
    • ›Improves subagent activity rows in the web-shell UI.
    • ›Improves compact tool activity display in the web-shell UI.
    +1 moreshow less

    • ›Propagates session list cancellation in the serve layer.
14. desktop-v0.2.1 Aug 12, 2026 · issue 002

    Qwen Code desktop v0.2.1 adds an Aliyun OSS release mirror, Goal v3 in ACP sessions, session-list cancellation propagation, and improved subagent/tool activity UI.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch desktop-v0.2.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout desktop-v0.2.1

    • ›Adopts Goal v3 in ACP sessions via the CLI (feat(cli): adopt Goal v3 in ACP sessions), enabling richer goal-structured agent interactions over the ACP protocol.
    • ›Adds an Aliyun OSS release mirror for the desktop app, giving users in China a faster, regionally-hosted download path.
    • ›Propagates session-list cancellation in qwen serve daemon mode, so client-side cancellations are reliably reflected across the shared agent session.
    • ›Improves subagent activity rows in the web-shell UI for clearer visibility into parallel agent work.
    • ›Improves compact tool activity display in the web-shell UI.
15. v0.21.10 Aug 11, 2026 · issue -008

    Qwen Code v0.21.10 adds ACP reasoning effort configuration and Web Shell image preview with download support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.10 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.10

    • ›Adds ACP support for configuring reasoning effort levels (Default to Max) via session configuration.
    • ›Web Shell image preview now opens uploaded or pasted images in the artifact panel with download support.
    • ›OpenAI API log cleanup now applies to non-interactive sessions, headless invocations, and daemon modes to reduce disk usage.
    • ›Improves CLI performance by caching persisted session catalogs for organized and filtered daemon lists, with automatic invalidation on metadata changes.
    • ›Web Shell session lists now share cached data across components to reduce network requests.
16. v0.21.10 Aug 11, 2026 · issue 002

    Qwen Code v0.21.10 adds ACP reasoning-effort configuration, Web Shell image previews, and expanded OpenAI API log cleanup.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.10 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.10

    • ›Adds ACP support for configuring reasoning effort levels (Default to Max) via session configuration, giving clients fine-grained control over model inference depth.
    • ›Extends OpenAI API log cleanup to non-interactive sessions, headless invocations, and daemon modes to reduce disk usage.
    • ›Clicking uploaded or pasted images in the Web Shell now opens a full preview in the artifact panel with download support.
    • ›Improves CLI performance by caching persisted session catalogs for organized and filtered daemon lists, with automatic invalidation on metadata changes.
17. live-host-v0.1.1 Aug 11, 2026 · issue -008

    Qwen Code v0.1.1 adds SSE observability, Mem0 memory writes, voice ASR URLs, inline terminal images, and workflow pause/resume.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch live-host-v0.1.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout live-host-v0.1.1

    • ›Adds SSE stream and client observability to the daemon (feat(daemon): Add SSE stream and client observability).
    • ›Adds a batch skill toggle API to the daemon (feat(daemon): add batch skill toggle API).
    • ›Adds optional Mem0 memory writes via feat(external-context): Add optional Mem0 memory writes.
    • ›Exposes active work state from the serve layer (feat(serve): Expose active work state).
    • ›Supports trusted private ASR base URLs for voice (feat(voice): support trusted private ASR base URLs).
    +17 moreshow less

    • ›Renders inline terminal images in the CLI (feat(cli): render inline terminal images).
    • ›Surfaces the posted review link from /review submit in the CLI.
    • ›Adds a declarative repository-context manifest for the review workflow.
    • ›Adds cooperative pause and resume for workflows.
    • ›Adds Feishu ask-user question cards to the channels integration.
    • ›Supports group pairing in channels.
    • ›Adds Qoder plugin extension support to the core.
    • ›Enables installing Extensions from archives in the web-shell.
    • ›Checkpoints long-running Goal evidence in the core.
    • ›Shares compression caches with OpenAI, Gemini, and Vertex AI providers.
    • ›Improves parallel agent activity feedback in the web-shell.
    • ›Attributes daemon-spawned sessions via channel (daemon/desktop) in telemetry.
    • ›Enriches observed contact labels in the Feishu integration.
    • ›Includes non-bot mention target identifiers in inbound DingTalk context.
    • ›Observes daemon and child memory against real denominators in the serve layer.
    • ›Makes autofix fleet caps operator-tunable in CI.
    • ›Throttles Markdown AST parsing during streaming in the web-shell for performance.
18. live-host-v0.1.1 Aug 11, 2026 · issue 002

    Qwen Code v0.1.1 adds SSE observability, Mem0 memory writes, inline terminal images, voice ASR URLs, group pairing, workflow pause/resume, and more.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch live-host-v0.1.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout live-host-v0.1.1

    └──▷ TRY IT
    Surface the URL of a just-submitted code review directly in your terminal so you can share or open it immediately.
    copy

    $ qwen
    # Inside the session:
    /review submit

    • ›Adds SSE stream and client observability to the daemon (feat(daemon): Add SSE stream and client observability).
    • ›Adds a batch skill toggle API to the daemon (feat(daemon): add batch skill toggle API).
    • ›Adds active work state exposure to qwen serve (feat(serve): Expose active work state).
    • ›Adds optional Mem0 memory writes via feat(external-context): Add optional Mem0 memory writes.
    • ›Adds inline terminal image rendering to the CLI.
    +17 moreshow less

    • ›Adds support for trusted private ASR base URLs for voice input.
    • ›Adds a declarative repository-context manifest for the review workflow.
    • ›Adds cooperative pause and resume to workflows.
    • ›Adds Feishu ask-user question cards to the channels integration.
    • ›Adds group pairing support to channels.
    • ›Supports installing Extensions from archives in the web-shell UI.
    • ›Adds Qoder plugin extension support to core.
    • ›Adds bridge for fork-PR reviews into the credentialed review lane in autofix.
    • ›Surfaces the posted review link directly from /review submit in the CLI.
    • ›Adds telemetry attribution of daemon-spawned sessions by channel (daemon/desktop).
    • ›Checkpoints long-running Goal evidence to improve resilience in extended sessions.
    • ›Shares compression caches with OpenAI, Gemini, and Vertex AI providers.
    • ›Enriches observed contact labels in the Feishu integration.
    • ›Includes non-bot mention target identifiers in inbound DingTalk context.
    • ›Improves parallel agent activity feedback in the web-shell UI.
    • ›Throttles Markdown AST parsing during streaming for smoother web-shell rendering.
    • ›Adds auto-assign of issues to area owners from labels in CI.
19. v0.21.9 Aug 10, 2026 · issue -009

    Qwen Code v0.21.9 adds Qoder plugin installs, Local Control QR pairing, batch Skills API, and model.openAILogRetentionDays log cleanup.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.9 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.9

    └──▷ USE IT
    Set OpenAI API log retention to 30 days so logs older than a month are automatically cleaned up in the background.
    json copy

    {
      "model.openAILogRetentionDays": 30
    }

    Get the review URL immediately after submitting a code review, suitable for piping into CI notifications.
    copy

    $ qwen review submit | jq '.url'

    • ›Adds model.openAILogRetentionDays setting (default: 7 days) to automatically purge expired OpenAI API logs in the background.
    • ›Adds a daemon API endpoint and SDK helpers to enable or disable up to 100 Skills in a single batch request with per-target error reporting.
    • ›Adds native support for installing Qoder plugins from directories, archives, Git repos, URLs, and npm packages, automatically loading system-prompt.md as extension context.
    • ›The qwen review submit command now outputs the direct URL to posted reviews in both stderr and JSON stdout.
    • ›Adds Local Control pairing to the CLI and Desktop app, enabling secure LAN access via QR code and a new Control menu option.
    +7 moreshow less

    • ›Web Shell now supports drag-and-drop of PNG, JPEG, GIF, WebP, and BMP images into the composer with attachment management and concurrency limits.
    • ›Web Shell displays context window usage as a mini progress pill in the status bar with tooltips and accessible labels.
    • ›Adds a fullscreen toggle to the Web Shell right panel for easier viewing of artifacts and subagent details.
    • ›Desktop automatically creates a default workspace at ~/Documents/Qwen and starts the runtime on first launch without blocking the main thread.
    • ›Adds a guard to pause tool execution after repeated failures within a single interactive ACP session.
    • ›Stable Qwen Live Host packages are now mirrored to Aliyun OSS with automatic fallback to GitHub and support for up to one-hour archive downloads.
    • ›Automatically assigns issues to area owners based on labels using a round-robin strategy that prefers owners with the fewest open assigned issues.
20. v0.21.9 Aug 10, 2026 · issue 002

    Qwen Code v0.21.9 adds Qoder plugin installs from directories/Git/npm, batch Skills API, Local Control QR pairing, and auto OpenAI log cleanup.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.9 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.9

    └──▷ USE IT
    Control how long OpenAI API logs are retained before automatic background cleanup removes them.
    settings.json copy

    {
      "model.openAILogRetentionDays": 14
    }

    Capture the review URL in CI after posting a code review, so the pipeline can link directly to the posted review.
    copy

    $ qwen review submit 2>review_url.txt

    • ›Adds model.openAILogRetentionDays setting (defaults to 7) to drive automatic background cleanup of expired OpenAI API logs.
    • ›Adds a daemon API endpoint and SDK helpers to enable or disable up to 100 Skills in a single batch request with per-target error reporting.
    • ›Adds native support for installing Qoder plugins from directories, archives, Git repos, URLs, and npm packages, automatically loading system-prompt.md as extension context.
    • ›The qwen review submit command now outputs the direct URL to posted reviews in both stderr and JSON stdout.
    • ›Adds Local Control pairing to the CLI and Desktop app, enabling secure LAN access via QR code and a new Control menu option.
    +7 moreshow less

    • ›Web Shell now supports dragging and dropping PNG, JPEG, GIF, WebP, and BMP images directly into the composer with attachment management and concurrency limits.
    • ›Web Shell displays context window usage as a mini progress pill in the status bar with tooltips and accessible labels.
    • ›Adds a fullscreen toggle to the Web Shell right panel for easier viewing of artifacts and subagent details.
    • ›Desktop automatically creates a default workspace at ~/Documents/Qwen and starts the runtime on first launch without blocking the main thread.
    • ›Adds a guard to pause tool execution after repeated failures within a single interactive ACP session.
    • ›Stable Qwen Live Host packages are now mirrored to Aliyun OSS with automatic fallback to GitHub and support for up to one-hour archive downloads.
    • ›Enhanced the Workflow tool description with orchestration policies and default pipelining guidance for improved model behavior.
21. v0.21.8 Aug 8, 2026 · issue -011

    Qwen Code v0.21.8 adds compression cache sharing for OpenAI/Gemini/Vertex, repository context manifests for /review, and new health endpoint fields.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.8

    └──▷ TRY IT
    Check live work state and memory pressure from the health endpoint — useful for monitoring long-running agent sessions.
    copy

    $ curl 'http://localhost:<port>/health?deep=1' | jq '{activeWork, activeWorkReporting, activeWorkStaleMs}'

    Pause a running Dynamic Workflow from the TUI without aborting it, so you can inspect state and resume later.
    copy

    $ /workflows p

    • ›Adds activeWork, activeWorkReporting, and activeWorkStaleMs fields to the GET /health?deep=1 endpoint to expose current work state.
    • ›Documents the --test-delta flag for severity adjustments when running /review, with a warning if the executing bundle is older than the current code.
    • ›Adds optional Mem0 memory write support to the Direct External Context integration, enabled explicitly in configuration.
    • ›Adds a repository context manifest to guide the /review command with bounded domains, related paths, and recommended tests for specific repository areas.
    • ›Enables compression cache sharing for all OpenAI-compatible providers, including stable session keys for the official OpenAI API, to reuse conversation prefixes and reduce redundant input processing.
    +11 moreshow less

    • ›Enables compression cache sharing for Gemini and Vertex AI to reuse conversation prefixes and reduce redundant input processing.
    • ›Supports installing Web Shell Extensions directly from local .zip or .tar.gz archive files via the Extension manager.
    • ›Dynamic Workflows now support cooperative pause and resume via the p shortcut in Background Tasks or the /workflows p command in the TUI.
    • ›Restores real-time autofix support for pull requests opened from forks by bridging review events to credentialed workflows.
    • ›Allows ACP agent tool calls to run concurrently at the configured limit, removing artificial serialization that slowed fan-out operations.
    • ›Group chats can now be approved once via a stable chat ID using the new group pairing policy, granting access to all members.
    • ›Enriches Feishu contact observations with sender display names and group names to replace opaque IDs with recognizable labels.
    • ›Feishu users can now answer structured single-select and multi-select questions directly via native Card V2 forms instead of text replies.
    • ›Enhances DingTalk integration to include stable identifiers of mentioned members in inbound context when the bot is mentioned alongside other users.
    • ›The daemon now observes and reports memory pressure levels and ratios using real denominators for both the root process and child heaps.
    • ›Improves telemetry attribution to distinguish daemon-spawned sessions from direct CLI launches in usage statistics.
22. v0.21.8 Aug 8, 2026 · issue 002

    Qwen Code v0.21.8 adds compression cache sharing across OpenAI/Gemini/Vertex, repository context manifests for /review, Mem0 memory writes, and concurrent ACP tool calls.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.8

    └──▷ TRY IT
    Check the current work state of a running daemon to detect stale or stuck agent sessions.
    copy

    $ curl 'http://localhost:<port>/health?deep=1'

    Run a /review with severity tuning when the executing bundle may be behind the current code.
    copy

    $ qwen -p "/review --test-delta"

    Pause an in-progress Dynamic Workflow from the TUI without killing the session.
    copy

    $ /workflows p

    • ›Adds activeWork, activeWorkReporting, and activeWorkStaleMs fields to the GET /health?deep=1 endpoint to expose current work state.
    • ›Adds optional Mem0 memory write support to the Direct External Context integration, enabled explicitly in configuration.
    • ›Adds a --test-delta flag to the /review command for severity adjustments when the executing bundle is older than the current code.
    • ›Adds Dynamic Workflow pause and resume via the 'p' shortcut in Background Tasks or the /workflows p command in the TUI.
    • ›Enables compression cache sharing for all OpenAI-compatible providers, including stable session keys for the official OpenAI API, to reuse conversation prefixes.
    +12 moreshow less

    • ›Enables compression cache sharing for Gemini and Vertex AI to reuse conversation prefixes and reduce redundant input processing.
    • ›Adds repository context manifests to guide the /review command with bounded domains, related paths, and recommended tests for specific repository areas.
    • ›Adds support for installing Web Shell Extensions directly from local .zip or .tar.gz archive files via the Extension manager.
    • ›Enables group chats to be approved once via a stable chat ID using the new group pairing policy, allowing access for all members.
    • ›Allows ACP agent tool calls to run concurrently at the configured limit, removing artificial serialization that slowed fan-out operations.
    • ›Restores real-time autofix support for pull requests opened from forks by bridging review events to the credentialed workflow lane.
    • ›Enriches Feishu contact context with sender display names and group names, replacing opaque IDs with recognizable labels.
    • ›Enhances DingTalk integration to include stable identifiers of mentioned members in the inbound context when the bot is mentioned.
    • ›Enables Feishu users to answer structured single-select and multi-select questions via native Card V2 forms instead of text replies.
    • ›Improves /review performance by moving remote matching to a deterministic CLI subcommand, achieving up to 93.3% prompt cache hit rates.
    • ›Adds daemon memory pressure monitoring: the daemon now observes and reports memory pressure levels and ratios for both the root process and child heaps.
    • ›Improves Web Shell feedback for parallel subagents by keeping status visible, auto-expanding details during work, and collapsing groups upon completion.
23. v0.21.7 Aug 6, 2026 · issue -013

    Qwen Code v0.21.7 adds inline terminal images, a review context manifest, and configurable ASR gateway routing.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.7 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.7

    └──▷ USE IT
    Route voice transcription through an internal HTTP ASR gateway in a managed deployment where public HTTPS endpoints are unavailable.
    json copy

    {
      "security": {
        "allowedInsecureVoiceBaseUrls": ["http://asr.internal.corp:8080"]
      }
    }

    Prevent silent CI hangs on long-running /review streams by capping stream lifetime to 10 minutes.
    copy

    $ QWEN_STREAM_MAX_LIFETIME_MS=600000 qwen review

    Bootstrap a repo-specific review context manifest so /review plans include project-aware context.
    copy

    $ qwen review repo-context

    • ›Adds security.allowedInsecureVoiceBaseUrls setting to route voice transcription through specific HTTP or private-network ASR gateways in managed deployments.
    • ›Introduces .qwen/review-context.json declarative manifest and the review repo-context command to customize review plans with repository-specific context.
    • ›Adds QWEN_STREAM_MAX_LIFETIME_MS setting to cap the total lifetime of streaming responses and prevent silent hangs in GitHub-triggered /review runs.
    • ›Enables rendering inline terminal images from model and tool outputs in the interactive CLI, supporting Kitty, Ghostty, and chafa.
    • ›Adds observability for REST SSE connections with stable UUIDs and telemetry for stream lifecycle events, including slow-client warnings and evictions.
24. v0.21.7 Aug 6, 2026 · issue 002

    Qwen Code v0.21.7 adds inline terminal images, a review-context manifest, ASR gateway routing, and removes the 50-turn Goal limit.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.7 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.7

    └──▷ USE IT
    Route voice transcription through a private HTTP ASR gateway in a managed deployment.
    .qwen/settings.json copy

    {
      "security": {
        "allowedInsecureVoiceBaseUrls": ["http://internal-asr.corp.example.com"]
      }
    }

    Seed a repository-specific review context so the /review skill tailors its plans to your codebase.
    copy

    $ qwen review repo-context

    • ›Adds security.allowedInsecureVoiceBaseUrls setting to allow managed deployments to route voice transcription through specific HTTP or private-network ASR gateways.
    • ›Introduces the .qwen/review-context.json declarative manifest and the review repo-context command to customize review plans with repository-specific context.
    • ›Adds QWEN_STREAM_MAX_LIFETIME_MS setting to cap the total lifetime of streaming responses, preventing silent hangs in GitHub-triggered /review runs.
    • ›Enables rendering inline terminal images from model and tool outputs in the interactive CLI, with support for Kitty, Ghostty, and chafa.
    • ›Adds observability for REST SSE connections with stable UUIDs and telemetry for stream lifecycle events, including slow-client warnings and evictions.
25. live-host-v0.1.0 Aug 6, 2026 · issue -013

    Qwen Code live-host-v0.1.0 adds local GitHub auth, mid-turn read-only shell commands, and reverse-dependency diff testing.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch live-host-v0.1.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout live-host-v0.1.0

    • ›Supports local GitHub (gh) authentication via channels, enabling offline or self-hosted auth flows.
    • ›Enables the web shell to run read-only informational commands immediately mid-turn, without waiting for the current turn to complete.
    • ›Adds reverse-dependency closure testing for diffs in the review workflow, surfacing dependency-impact caveats alongside review results.
26. live-host-v0.1.0 Aug 6, 2026 · issue 002

    Qwen Code live-host v0.1.0 adds local GitHub auth for channels and faster read-only web-shell commands mid-turn.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch live-host-v0.1.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout live-host-v0.1.0

    • ›Adds local GitHub authentication support to qwen channel, enabling channel integrations to authenticate via a local gh credential.
    • ›Web-shell now runs read-only informational commands immediately mid-turn without waiting for the current turn to complete, reducing latency in agentic sessions.
    • ›Extends the review workflow to test a diff's reverse-dependency closure and surface disclosed caveats alongside review results.
27. v0.21.6 Aug 5, 2026 · issue -014

    Qwen Code v0.21.6 adds Live Voice for WebShell, a new qwen review cost-ledger command, and an external tool guard provider for managed deployments.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.6 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.6

    └──▷ TRY IT
    Audit total model token spend across all past review runs stored locally — useful for cost accountability after a batch of PR reviews.
    copy

    $ qwen review cost-ledger

    • ›Adds the qwen review cost-ledger command to aggregate model usage statistics from existing review records stored on disk.
    • ›Adds an optional external tool guard provider for managed serve deployments to enforce pre-execution allow/deny policies.
    • ›Adds experimental native Live Voice support to WebShell on macOS, enabling real-time audio interactions via a dedicated global shortcut.
    • ›Read-only info commands /stats, /about, and /context now execute immediately mid-turn in Web Shell without waiting for streaming to finish.
    • ›GitHub Channels can now reuse the daemon host's existing gh auth login credentials when no personal access token is explicitly configured.
    +3 moreshow less

    • ›The record_artifact tool now explicitly guides users to register URLs for pull requests, issues, and comments as link artifacts for later access.
    • ›The Chrome extension alpha gains daemon and browser-automation onboarding states, runtime MCP diagnostics, and an automated acceptance flow for real-Chrome testing.
    • ›Review tests now cover the full reverse-dependency closure of code changes to catch behavioral regressions in dependent workspaces.
28. v0.21.6 Aug 5, 2026 · issue 002

    Qwen Code v0.21.6 adds Live Voice for WebShell, qwen review cost-ledger, an external tool guard provider, and instant mid-turn info commands.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.6 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.6

    └──▷ TRY IT
    Audit total model token spend across all past review runs without re-running any scans.
    copy

    $ qwen review cost-ledger

    • ›Adds the qwen review cost-ledger command to aggregate model usage statistics from existing review records on disk.
    • ›Read-only info commands /stats, /about, and /context now execute immediately mid-turn in Web Shell without waiting for streaming to finish.
    • ›Adds an optional external tool guard provider for managed qwen serve deployments to enforce pre-execution allow/deny policies.
    • ›Adds experimental native Live Voice support to WebShell on macOS for real-time audio interactions via a dedicated global shortcut.
    • ›The record_artifact tool now explicitly guides users to register URLs for pull requests, issues, and comments as link artifacts for later access.
    +3 moreshow less

    • ›GitHub Channels can now reuse the daemon host's existing gh auth login credentials when no personal access token is explicitly configured.
    • ›Chrome extension alpha now includes daemon and browser-automation onboarding states, runtime MCP diagnostics, and an automated acceptance flow for real-Chrome testing.
    • ›Review tests now cover the full reverse-dependency closure of code changes to catch behavioral regressions in dependent workspaces.
29. desktop-v0.1.0 Aug 5, 2026 · issue -014

    Qwen Code desktop v0.1.0 adds session-scoped MCP, git branch/PR UI, streaming charts, channel management, and voice hold mode.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch desktop-v0.1.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout desktop-v0.1.0

    • ›Adds session-scoped runtime MCP via acp so each session can carry its own Model Context Protocol server without affecting others.
    • ›Adds a Channel management page and Channel configuration flows in the web shell UI for creating and editing channel integrations.
    • ›Adds Channel pairing request management in the web shell, letting users accept or reject incoming channel pairings.
    • ›Adds git branch picker, commit dialog, and create PR flow directly in the web shell composer.
    • ›Adds a native workspace folder picker in the web shell for selecting working directories.
    +18 moreshow less

    • ›Adds streaming chart rendering via markdown-chart in the web shell for live data visualization.
    • ›Adds submitted-prompt auto recall in external-context, surfacing previously submitted prompts automatically.
    • ›Adds submitted-prompt provenance tracking in hooks, recording where each prompt originated.
    • ›Gates session writer lease behind an opt-in flag, giving operators control over write-lock acquisition.
    • ›Adds voice hold mode support in the web shell, scoped to the composer workspace.
    • ›Adds BTW side-question suggestions in the web shell composer footer.
    • ›Adds a composer footer renderer in the web shell for extensible footer content.
    • ›Adds monitor task details view in the web shell for inspecting running task status.
    • ›Exposes loop tools in daemon sessions via the channels layer.
    • ›Dispatches GitHub notifications by reason in the channels integration, enabling reason-based routing.
    • ›Adds ARMS session user ID field to core session tracking.
    • ›Adds full-resolution image zoom tool in core with bounded image reads for reliability.
    • ›Persists and replays Goal v3 state in core, and connects Goal v3 to the turn engine.
    • ›Adds early Anthropic cache breakpoint on the stable system prefix for reduced latency on repeated calls.
    • ›Adds autofix deferred suggestions after five change rounds, reducing noise during iterative edits.
    • ›Adds autofix retry on deterministic rejection, improving success rate on first-pass linting failures.
    • ›Adds revert-pattern high-risk path detection in triage.
    • ›Makes triage verify reports readable in Chinese.
30. desktop-v0.1.0 Aug 5, 2026 · issue 002

    Qwen Code desktop-v0.1.0 adds session-scoped MCP, Goal v3 state persistence, web-shell git flows, channel management, streaming charts, and more.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch desktop-v0.1.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout desktop-v0.1.0

    • ›Adds session-scoped runtime MCP via feat(acp): add session-scoped runtime MCP, letting each ACP session carry its own MCP context.
    • ›Adds a Channel management page and Channel configuration flows to the web-shell UI for managing integrations in-browser.
    • ›Adds a Channel pairing request manager to the web-shell, enabling users to approve or reject new channel connections.
    • ›Adds a native workspace folder picker to the web-shell so users can browse and select project roots from the browser UI.
    • ›Adds a git branch picker, commit dialog, and create-PR flow to the web-shell, enabling full branch/PR workflows without leaving the browser.
    +20 moreshow less

    • ›Adds a composer footer renderer to the web-shell for richer input-area UI extensions.
    • ›Adds streaming chart rendering via markdown-chart in the web-shell, displaying live charts as the model streams output.
    • ›Adds a BTW (By The Way) suggestion flow to the web-shell for surfacing side questions during a conversation.
    • ›Persists and replays Goal v3 state (feat(core): persist and replay Goal v3 state) and connects Goal v3 to the turn engine, enabling durable multi-step goal tracking across sessions.
    • ›Adds a full-resolution image zoom tool with bounded image reads for reliable zoom behavior.
    • ›Adds submitted-prompt provenance tracking via hooks, recording where each submitted prompt originated.
    • ›Adds submitted-prompt auto-recall in external-context, automatically surfacing previously submitted prompts.
    • ›Gates session writer lease behind an opt-in flag (feat: Gate session writer lease behind opt-in).
    • ›Adds ARMS session user ID tracking to core sessions.
    • ›Exposes loop tools in daemon sessions (feat(channels): expose loop tools in daemon sessions).
    • ›Dispatches GitHub notifications by reason in the channels integration, routing notifications more precisely.
    • ›Adds revert-pattern high-risk path detection to the triage system.
    • ›Adds autofix deferred suggestions after five change rounds, reducing noise during iterative edits.
    • ›Adds autofix retry on deterministic rejection, improving resilience of automated fixes.
    • ›Scopes voice input to the composer workspace in the web-shell and adds voice hold mode support.
    • ›Adds monitor task details view to the web-shell for observing running agent tasks.
    • ›Makes the triage verify report readable in Chinese.
    • ›Adds early Anthropic cache breakpoint on the stable system prefix (perf(acp): add early Anthropic cache breakpoint) to reduce latency on repeated calls.
    • ›Preloads providers after session creation (perf(acp): Preload providers after session creation) to cut session startup time.
    • ›Makes ripgrep usage more robust (feat: robust ripgrep) for more reliable code search.
31. v0.21.5 Aug 4, 2026 · issue -015

    Qwen Code v0.21.5 adds a finding-centric Web Shell review view, Qwen 3.8 reasoning effort support, and safer MCP replay controls.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.5

    • ›Enables Qwen 3.8 reasoning effort levels by mapping existing effort flags to the provider-specific reasoning_effort parameter.
    • ›Introduces a structured, finding-centric view in Web Shell for review results, displaying severity, confidence, and suggested fixes alongside durable reports.
    • ›Adds an opt-in one-time update bridge for macOS users to migrate from the Electron desktop app to the new Tauri shell.
    • ›Introduces detailed execution-specific outcome tracking for tool calls to distinguish between invocation success, failure, and cancellation.
32. v0.21.5 Aug 4, 2026 · issue 002

    Qwen Code v0.21.5 adds a finding-centric Web Shell review view, Qwen 3.8 reasoning effort support, and safer MCP replay controls.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.5

    • ›Maps existing effort flags to the provider-specific reasoning_effort parameter, enabling Qwen 3.8 reasoning effort levels.
    • ›Introduces a structured, finding-centric view in Web Shell for review results, displaying severity, confidence, and suggested fixes alongside durable reports.
    • ›Adds an opt-in one-time update bridge for macOS users to migrate from the Electron desktop app to the new Tauri shell.
    • ›Introduces detailed execution-specific outcome tracking for tool calls to distinguish between invocation success, failure, and cancellation.
    • ›Blocks unsafe replay of MCP tool calls after connection loss unless the tool is explicitly marked idempotent and the workspace is trusted.
    +1 moreshow less

    • ›Transitions Goal mode to a usage_limited state requiring user intervention after evidence catalog exhaustion, stopping infinite retries.
33. v0.21.4 Aug 3, 2026 · issue -016

    Qwen Code v0.21.4 adds new review/drive commands, configurable memory agents, session workflow toggles, and a desktop Web Shell.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.4

    └──▷ USE IT
    Limit memory agents to a fixed number of turns to cap runaway agent loops in large repos.
    yaml copy

    # In your Qwen Code config
    memory:
      agentMaxTurns: 20

    Enable Plan & Review mode and the Workflow DAG for session-level orchestration of multi-step tasks.
    yaml copy

    # In your Qwen Code config
    experimental:
      sessionWorkflow: true

    Poll for review service readiness and verify facts without relying on fixed sleep delays in CI.
    copy

    $ qwen review drive

    • ›Adds experimental.sessionWorkflow setting to optionally enable Session Workflow features including Plan & Review mode and the Workflow DAG.
    • ›Adds memory.agentMaxTurns setting to configure turn limits for all managed memory agents; set to 0 to disable the limit entirely.
    • ›Adds qwen review drive command to poll for service readiness and verify completion facts instead of relying on fixed sleep delays.
    • ›Adds qwen review mock-provider command to record OpenAI-compatible requests as JSONL for testing against a faithful outside-world simulation.
    • ›Adds qwen review publish-assets command to host evidence images in a user-designated repository for embedding in PR review comments.
    +9 moreshow less

    • ›The /summary command now accepts an optional path argument to save project summaries to custom locations, automatically creating parent directories as needed.
    • ›Sub-session concurrency caps are now configurable via the serve surface.
    • ›Web Shell is now packaged as a release-ready desktop app with native lifecycle management, single-instance behavior, and automatic updates.
    • ›Enables full Web Shell management for GitHub and GitLab channels, allowing users to configure tokens and policies without editing settings files.
    • ›Adds a built-in Java/JVM performance checklist to the review tool that flags correctness traps and JVM-cost defects in Java files.
    • ›Adds a repo-hygiene skill and weekly workflow to automatically scan for and propose fixes for documentation and code quality issues.
    • ›PR review timeout now scales with change size, allowing up to 240 minutes for large pull requests exceeding 300 lines.
    • ›Non-interactive CLI /goal commands now use the Goal v3 runtime for consistent state persistence and improved streaming behavior.
    • ›The review verifier now treats unverified findings as low-confidence confirmations rather than rejections, instructing it to check cited sources first.
34. v0.21.4 Aug 3, 2026 · issue 002

    Qwen Code v0.21.4 adds qwen review drive, qwen review mock-provider, qwen review publish-assets, memory.agentMaxTurns, experimental.sessionWorkflow, and daemon memory-budget reporting.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.4

    └──▷ USE IT
    Limit memory agents to a fixed number of turns in long-running sessions to control cost and prevent runaway loops.
    yaml copy

    memory:
      agentMaxTurns: 20

    Enable experimental Plan & Review mode and the Workflow DAG for session-level orchestration.
    yaml copy

    experimental:
      sessionWorkflow: true

    Record all OpenAI-compatible requests during a review run as JSONL to replay or inspect in testing.
    copy

    $ qwen review mock-provider

    • ›Adds qwen review drive command to poll for service readiness and verify completion facts instead of relying on fixed sleep delays.
    • ›Adds qwen review mock-provider command to record OpenAI-compatible requests as JSONL for testing against a faithful outside-world simulation.
    • ›Adds qwen review publish-assets command to host evidence images in a user-designated repository for embedding in PR review comments.
    • ›Adds memory.agentMaxTurns setting to configure turn limits for all managed memory agents; set to 0 to disable the limit entirely.
    • ›Introduces experimental.sessionWorkflow setting to optionally enable Session Workflow features including Plan & Review mode and the Workflow DAG.
    +11 moreshow less

    • ›Adds sub-session concurrency caps as a configurable serve parameter via qwen serve.
    • ›The /summary command now accepts an optional path argument to save project summaries to custom locations, automatically creating parent directories if needed.
    • ›Adds a built-in Java/JVM performance checklist to the review tool that flags correctness traps and JVM-cost defects in Java files.
    • ›Adds a repo-hygiene skill and weekly workflow to automatically scan for and propose fixes for documentation and code quality issues.
    • ›Enables full Web Shell management for GitHub and GitLab channels, allowing users to configure tokens and policies without editing settings files.
    • ›Web Shell is now packaged as a release-ready desktop app with native lifecycle management, single-instance behavior, and automatic updates.
    • ›PR review timeout now scales with change size, allowing up to 240 minutes for pull requests exceeding 300 lines.
    • ›Updates non-interactive CLI /goal commands to use the Goal v3 runtime for consistent state persistence and improved streaming behavior.
    • ›Updates the review verifier to treat unverified findings as low-confidence confirmations rather than rejections, checking cited sources first.
    • ›Forked subagents are now isolated from sibling forks, ensuring each agent accesses only its own assigned instructions and directives.
    • ›Chat compression now reuses the main conversation prompt cache on supported providers, reducing latency without executing tools.
35. v0.21.3 Aug 1, 2026 · issue -018

    Qwen Code v0.21.3 adds fork profiles, display_image tool, /review test-plan validation, and background workflow runs.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.3

    └──▷ TRY IT
    Configure a dedicated model for compressing long chat histories without affecting the primary model.
    copy

    $ /model --compaction qwen2.5-72b-instruct

    Enable Anthropic's 1-hour extended prompt-cache tier to reduce latency on large repeated contexts.
    json copy

    {
      "generationConfig": {
        "cacheRetention": "1h"
      }
    }

    Hide bundled and project-level skills to keep the skill menu clean in a tightly controlled environment.
    yaml copy

    skills:
      disabledLevels:
        - bundled
        - project

    • ›Adds generationConfig.cacheRetention settings to support Anthropic's extended 1-hour prompt-cache tier alongside the default 5-minute retention.
    • ›Adds skills.disabledLevels setting to hide bundled, project, user, or extension skills without affecting host-provided skills.
    • ›Adds --compaction flag to the /model command to configure a dedicated model for chat compression.
    • ›Enables POST /session to accept and validate a caller-supplied sessionId instead of silently ignoring it.
    • ›Adds a SessionDelete hook event triggered after successfully deleting a historical session via /delete or ACP.
    +17 moreshow less

    • ›Adds optional source_type and source_id fields to lifecycle hooks to help platforms distinguish sessions created through different entry points.
    • ›Adds project-level named fork profiles via markdown files in the .qwen/fork-profiles directory to define tool allowlists and prompt hints.
    • ›Adds a display_image tool to the TUI that renders PNGs using native terminal features or chafa fallbacks with an 8 MiB limit.
    • ›Adds the verify-capture.mjs script to generate evidence images for PR verification with a single command.
    • ›Enables workflows to support an opt-in background run mode that returns a run ID and reports results via a dedicated channel.
    • ›Raises the daemon default maximum session limit per workspace from 20 to 32.
    • ›Allows safe slash commands /status, /settings, and /help to run immediately while model responses are streaming.
    • ›Enhances the /review command with Test Plan assertion validation, measured test-failure attribution, adjudication rendering, workflow step extraction, and seven new verification lenses.
    • ›Running /triage on a pull request now triggers the sandboxed verify lane in parallel to start building and running tests immediately.
    • ›Adds an optional host tool invocation guard that can deny execution before a tool runs.
    • ›Adds OpenTelemetry GenAI streaming attributes to LLM spans, recording time-to-first-chunk for streaming requests.
    • ›Auto-generated Skills are tracked for usage, marked stale after 30 days of inactivity, and archived after 90 days via a new project-scoped curator.
    • ›Adds a Session Workflow view that visualizes plan execution, agent calls, and transcripts as a dependency graph.
    • ›Enables workflow agents to surface approval requests for shell commands and edits directly to the parent interface.
    • ›Web Shell transcript and review views now include a Download action for artifacts, supporting HTML, Markdown, and workspace file exports.
    • ›Review output footers now include the Qwen Code CLI version to help trace findings to specific releases.
    • ›Adds the foundational runtime supervisor for Agent View, enabling local session management and terminal stream bridging.
36. v0.21.3 Aug 1, 2026 · issue 002

    Qwen Code v0.21.3 adds fork profiles, display_image tool, workflow background runs, /review test-plan validation, and per-workspace session isolation.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.3

    └──▷ TRY IT
    Configure a dedicated smaller model for chat compaction to reduce token costs while keeping a powerful model for coding tasks.
    copy

    $ /model --compaction qwen-turbo

    Enable Anthropic's extended 1-hour prompt-cache tier to reduce latency on large, repeated context across long sessions.
    json copy

    {
      "generationConfig": {
        "cacheRetention": "1h"
      }
    }

    Hide bundled and project-level skills from the skill menu without touching host-provided skills.
    yaml copy

    skills:
      disabledLevels:
        - bundled
        - project

    • ›Adds --compaction flag to the /model command to configure a dedicated model for chat compression.
    • ›Adds generationConfig.cacheRetention settings to support Anthropic's extended 1-hour prompt-cache tier alongside the default 5-minute retention.
    • ›Adds skills.disabledLevels setting to hide bundled, project, user, or extension skills without affecting host-provided skills.
    • ›Adds SessionDelete hook event triggered after successfully deleting a historical session via /delete or ACP.
    • ›Adds source_type and source_id optional fields to lifecycle hooks to help platforms distinguish sessions created through different entry points.
    +21 moreshow less

    • ›Enables POST /session to accept and validate a caller-supplied sessionId instead of silently ignoring it.
    • ›Adds project-level named fork profiles via markdown files in the .qwen/fork-profiles directory to define tool allowlists and prompt hints.
    • ›Adds display_image tool to the TUI that renders PNGs using native terminal features or chafa fallbacks, with an 8 MiB limit.
    • ›Adds OpenTelemetry GenAI streaming attributes to LLM spans, recording time-to-first-chunk for streaming requests.
    • ›Allows /status, /settings, and /help slash commands to run immediately while model responses are streaming.
    • ›Workflows now support an opt-in background run mode that returns a run ID and reports results via a dedicated channel.
    • ›Enables workflow agents to surface approval requests for shell commands and edits directly to the parent interface.
    • ›Enhances the /review command with Test Plan assertion validation, measured test-failure attribution, adjudication rendering, workflow step extraction, and seven new verification lenses.
    • ›Running /triage on a pull request now triggers the sandboxed verify lane in parallel to start building and running tests immediately.
    • ›The daemon default maximum session limit per workspace increases from 20 to 32.
    • ›Daemon channel adapter state is now isolated by workspace to safely support persistent browser authentication across multiple workspaces.
    • ›Auto-generated Skills are now tracked for usage, marked stale after 30 days of inactivity, and archived after 90 days via a new project-scoped curator.
    • ›Adds a Session Workflow view that visualizes plan execution, agent calls, and transcripts as a dependency graph.
    • ›The Web Shell transcript and review views now include a Download action for artifacts, supporting HTML, Markdown, and workspace files.
    • ›Review output footers now include the Qwen Code CLI version to help trace findings to specific releases.
    • ›Review round ledgers are now embedded in the posted review body to persist across environments and enable the default effort level to recover previous round data.
    • ›Adds the verify-capture.mjs script to generate evidence images for PR verification with a single command.
    • ›Adds an optional host tool invocation guard that can deny execution before a tool runs.
    • ›Adds a transient emoji to GitLab notes while the agent is working, removed upon completion.
    • ›Added the foundational runtime supervisor for Agent View, enabling local session management and terminal stream bridging.
    • ›Plain-text messages sent during an active turn now enter the running turn by default with visible queue management.
37. v0.21.2 Jul 31, 2026 · issue -019

    Qwen Code v0.21.2 adds Auto Recall, review run, fork_tools allowlist, GitLab polling, DingTalk cards, and a security.allowPrivateNetworkHooks setting.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.2

    └──▷ TRY IT
    Run a headless review and get a machine-readable verdict in CI pipelines without interactive output.
    copy

    $ qwen review run

    Allow HTTP hooks to call internal services on private networks in a platform-managed deployment.
    yaml copy

    security:
      allowPrivateNetworkHooks: true

    Restrict a fork-type subagent to only use specific tools, limiting its blast radius during automated fix cycles.
    yaml copy

    fork_tools:
      - read_file
      - grep
      - bash

    • ›Adds security.allowPrivateNetworkHooks setting to allow HTTP hooks to reach private network addresses in trusted platform-managed environments.
    • ›Adds reasonFilter setting for GitHub channels to skip unwanted notification reasons and prevent unintended agent actions.
    • ›Introduces fork_tools allowlist on fork-type subagents to restrict execution to specific canonical tool names or MCP server patterns.
    • ›Adds review run subcommand for headless, machine-readable review verdicts.
    • ›Adds qwen review test-efficacy command that detects unprotected safety statements using statement-level mutation probes.
    +18 moreshow less

    • ›Adds byte-cursor paging to large text file reads across HTTP, ACP, and SDK surfaces for efficient retrieval without rescanning.
    • ›Adds an opt-in Auto Recall profile that automatically searches external context on prompt submission, with built-in security limits.
    • ›Adds a GitLab polling channel adapter that converts GitLab todos into inbound messages for automated processing.
    • ›Adds DingTalk interactive cards support for channels.
    • ›Adds APIs and SDK helpers to list approved pairing senders and revoke access within a specific workspace.
    • ›Adds UI controls in the Channel editor to view, approve, and revoke pairing approvals with explicit confirmation dialogs.
    • ›Enhances the /verify command with seven new maintainer verification techniques, evidence screenshots in reports, and an increased agent budget from 25 to 120 minutes.
    • ›Adds a threshold setting to automatically preload deferred tools into the context window when their total size fits within limits.
    • ›Autofix defers lower-severity suggestions after five change rounds, restricting further modifications to critical findings and failed checks only.
    • ›Adds automatic milestone summaries every tenth takeover round to provide visibility into long-running fix attempts.
    • ›Web Shell gains contextual task panels, theme-aware composer highlights, interactive dot animations, and a typewriter effect for placeholders.
    • ›GitHub channels now display an eyes reaction on issues and comments while an agent turn is actively running.
    • ›GitHub channels now emit exactly one final comment per event.
    • ›Goal v3 connected to the turn engine with deterministic permit handling so runtime continuations do not consume session or recursive turn budgets.
    • ›Static image reads now return a canonical, auto-oriented JPEG overview with source dimensions to support reliable zooming.
    • ›Triage comments now lead with a clear pass/fail verdict and display English by default with Chinese translations folded.
    • ›Review approvals with zero findings on non-trivial diffs now explicitly disclose low-signal status in the verdict line.
    • ›Triage system mechanically triggers the 2b-bis sandboxed-lane recommendation when a Stage 2 draft contains a not-verified sentence.
38. v0.21.2 Jul 31, 2026 · issue 002

    Qwen Code v0.21.2 adds Auto Recall, review run, fork_tools allowlist, GitLab polling, DingTalk cards, and a security.allowPrivateNetworkHooks setting.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.2

    └──▷ TRY IT
    Run a headless, machine-readable review in CI to get a structured verdict without launching the interactive UI.
    copy

    $ qwen review run

    Allow HTTP hooks to call internal/private network endpoints in a trusted platform-managed deployment.
    yaml copy

    security:
      allowPrivateNetworkHooks: true

    • ›Adds security.allowPrivateNetworkHooks setting to allow HTTP hooks to reach private network addresses in trusted platform-managed environments.
    • ›Adds reasonFilter setting for GitHub channels to skip unwanted notification reasons and prevent unintended agent actions.
    • ›Introduces fork_tools allowlist on fork-type subagents to restrict execution to specific canonical tool names or MCP server patterns.
    • ›Adds review run subcommand for headless, machine-readable review verdicts.
    • ›Adds the qwen review test-efficacy command, which uses statement-level mutation probes (single-line deletions) to detect unprotected safety statements.
    +18 moreshow less

    • ›Adds an opt-in Auto Recall profile that automatically searches external context on prompt submission, with built-in security limits.
    • ›Adds byte-cursor paging to large text file reads across HTTP, ACP, and SDK surfaces for efficient retrieval of subsequent content without rescanning.
    • ›Adds a GitLab polling channel adapter that converts GitLab todos into inbound messages for automated processing.
    • ›Adds DingTalk interactive card support to channels.
    • ›Enhances the /verify command with seven new maintainer verification techniques, evidence screenshot capture in reports, and an increased agent time budget from 25 to 120 minutes.
    • ›Adds APIs and SDK helpers to list approved pairing senders and revoke channel pairing access within a specific workspace.
    • ›Adds UI controls in the Channel editor to view, approve, and revoke pairing approvals with explicit confirmation dialogs.
    • ›Adds automatic milestone summaries every tenth takeover round for visibility into long-running fix attempts.
    • ›Adds a temporary eyes reaction to GitHub issues and comments while an agent turn is running to indicate active processing.
    • ›Adds contextual task panels to Web Shell.
    • ›Adds a threshold setting to automatically preload deferred tools into the context window when their total size fits within limits.
    • ›Autofix now defers lower-severity suggestions after five change rounds, allowing only critical findings and failed checks to drive further code modifications, and posts visible notices when refusing to proceed due to round limits.
    • ›Triage comments now lead with a clear pass or fail verdict and display English by default with Chinese translations folded.
    • ›Review approvals with zero findings on non-trivial diffs now explicitly disclose low-signal status in the verdict line.
    • ›Web Shell gains theme-aware composer highlights, interactive dot animations for empty sessions, and a typewriter effect for placeholders.
    • ›WebShell now uses a shared renderer for streaming charts, enabling canonical markdown-chart blocks without extra host configuration.
    • ›GitHub channels now emit exactly one final comment per event.
    • ›Static image reads now return a canonical, auto-oriented JPEG overview with source dimensions to support reliable zooming.
39. v0.21.1 Jul 28, 2026 · issue -022

    Qwen Code v0.21.1 adds qwen review comment-status, GitHub channel adapter, context_search tool, retry delay settings, and sandboxed /verify lane.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.1

    └──▷ TRY IT
    Triage existing inline PR review comments to reduce redundant API calls during a review run.
    copy

    $ qwen review comment-status

    Tune retry delays when a provider enforces strict rate-limit quota windows on SSE streams.
    json copy

    {
      "retryInitialDelayMs": 2000,
      "retryMaxDelayMs": 30000
    }

    Cap live journal size to avoid disk pressure on long-running agent sessions.
    copy

    $ qwen --max-journal-events 5000 --max-journal-bytes 4194304

    • ›Introduces qwen review comment-status subcommand to quickly triage existing inline review comments and reduce API calls during review runs.
    • ›Adds retryInitialDelayMs and retryMaxDelayMs settings to configure SSE stream rate-limit retry delays for provider quota windows.
    • ›Adds a retrieval-only context_search tool for external corpora, configured by administrators without automatic recall or write capabilities.
    • ›Adds a sandboxed /verify deep-verification lane on the triage CI path.
    • ›Exposes workspace Channel management API on the serve layer, with a Channel management page and configuration flows in the Web Shell.
    +24 moreshow less

    • ›Adds a GitHub channel adapter that polls notifications and responds to mentions by posting comments using a signal-based wakeup architecture; dispatches notifications by reason.
    • ›Adds --max-journal-events and --max-journal-bytes flags to configure live journal caps (defaults raised to 10,000 events and 8 MiB).
    • ›Updates the /stats command and Session tab to display generation timing metrics including TTFT, duration, output tokens, and TPS.
    • ›Enables hot-reloading of workspace trust changes in the running daemon, applying new policies immediately without a process restart.
    • ›Adds model grade selection for subagent spawn.
    • ›Adds Goal v3 runtime orchestration with worker tools, state persistence, and replay.
    • ›Adds session-scoped runtime MCP support (acp).
    • ›Introduces an overridable default-disabled state for skills, allowing soft defaults that yield to explicit enablement while hard disables remain absolute.
    • ›Enforces a strict write contract for review submissions and adds a tripwire to detect and flag bypass attempts via terminal commands.
    • ›Adds a read-only GitHub pull requests panel to the Web Shell.
    • ›Adds git branch picker, commit dialog, and create PR flow to the Web Shell.
    • ›Adds native workspace folder picker to the Web Shell.
    • ›Adds full-resolution image zoom tool.
    • ›Adds triage revert-pattern high-risk path detection.
    • ›Supports outbound image delivery in the DingTalk integration.
    • ›Exposes loop tools in daemon channel sessions.
    • ›Gates session writer lease behind opt-in.
    • ›Adds submitted prompt provenance tracking via hooks.
    • ›Adds monitor task details view to the Web Shell.
    • ›Allows widening the Web Shell sidebar up to half the window width.
    • ›Scopes voice input to the composer workspace and adds voice hold mode support.
    • ›Adds mutation testing of tests in the review test-coverage pass (Agent 5).
    • ›Adds script-lint as a deterministic gate in compose-review, reading the report without an agent.
    • ›Adds BTW suggestion for side questions in the Web Shell composer.
40. v0.21.1 Jul 28, 2026 · issue 002

    Qwen Code v0.21.1 adds qwen review comment-status, GitHub channel adapter, context_search tool, retry delay settings, and Goal v3 orchestration.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.1

    └──▷ TRY IT
    Triage inline review comments on a PR to reduce redundant API calls during a review run.
    copy

    $ qwen review comment-status

    Configure rate-limit retry delays for a provider with aggressive quota windows (e.g. short burst limits).
    json copy

    {
      "retryInitialDelayMs": 2000,
      "retryMaxDelayMs": 30000
    }

    • ›Introduces qwen review comment-status subcommand to quickly triage existing inline review comments and reduce API calls during review runs.
    • ›Adds retryInitialDelayMs and retryMaxDelayMs settings to configure SSE stream rate-limit retry delays for better provider quota compatibility.
    • ›Adds a retrieval-only context_search tool for external corpora, configured by administrators without automatic recall or write capabilities.
    • ›Adds a GitHub channel adapter that polls notifications and responds to mentions by posting comments using a signal-based wakeup architecture.
    • ›Adds Goal v3 runtime orchestration with worker tools, state persistence, and replay support.
    +22 moreshow less

    • ›Exposes a workspace Channel management API from qwen serve and adds a Channel management page and configuration flows in the Web Shell.
    • ›Adds a read-only GitHub pull requests panel to the Web Shell UI.
    • ›Updates the /stats command and Session tab to display generation timing metrics including TTFT, duration, output tokens, and TPS.
    • ›Enables hot-reloading of workspace trust changes in the running daemon, applying new policies immediately without a process restart.
    • ›Adds model grade selection for subagent spawn, allowing fine-grained control over which model tier child agents use.
    • ›Adds a sandboxed /verify deep-verification lane in triage and surfaces sandboxed lanes on the CI path.
    • ›Introduces an overridable default-disabled state for skills, allowing soft defaults that yield to explicit enablement while hard disables remain absolute.
    • ›Adds revert-pattern high-risk path detection in triage.
    • ›Enforces a strict write contract for review submissions and adds a tripwire to detect and flag bypass attempts via terminal commands.
    • ›Adds a session-scoped runtime MCP via acp.
    • ›Adds a full-resolution image zoom tool in the core.
    • ›Adds a native workspace folder picker in the Web Shell.
    • ›Adds a git branch picker, commit dialog, and create PR flow to the Web Shell.
    • ›Supports outbound image delivery for the DingTalk channel.
    • ›Dispatches GitHub notifications by reason for more targeted channel routing.
    • ›Adds submitted prompt provenance tracking in hooks.
    • ›Gates session writer lease behind opt-in.
    • ›Exposes loop tools in daemon sessions.
    • ›Adds monitor task details view to the Web Shell.
    • ›Adds voice hold mode support and scopes voice to the composer workspace in the Web Shell.
    • ›Introduces mutation testing of tests in the review test-coverage pass (Agent 5).
    • ›Adds script-lint as a deterministic gate in compose-review, reading the lint report without an agent.
41. v0.21.0 Jul 24, 2026 · issue -026

    Qwen Code v0.21.0 adds QWEN_SYSTEM_IDENTITY_MD override, MCP force-reconnect, native video in /learn, @ session references, and configurable image-gen models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.0

    └──▷ TRY IT
    Override the agent's core identity for a custom deployment persona without modifying source files.
    copy

    $ export QWEN_SYSTEM_IDENTITY_MD=/path/to/my-identity.md
    qwen

    Pass a video file to /learn so the agent can ingest and reason about recorded demos or walkthroughs.
    copy

    $ /learn /recordings/demo.mp4

    • ›Adds QWEN_SYSTEM_IDENTITY_MD environment variable to fully override the core system identity/prompt.
    • ›Adds a usage statistics environment override via feat(cli): add usage statistics environment override (new env var for telemetry control).
    • ›Supports forced MCP reconnects in serve, allowing clients to re-establish dropped MCP connections without restarting the daemon.
    • ›Adds renderChatHeader slot to the web-shell component for injecting a custom session header.
    • ›Supports native video input in the /learn CLI command.
    +22 moreshow less

    • ›Adds @ syntax for referencing prior sessions in the CLI, with completion tabs for discoverability.
    • ›Adds configurable image generation models in core settings.
    • ›Supports custom skill directories via CLI settings.
    • ›Adds workspace selector button with add/switch dropdown in the composer toolbar.
    • ›Shows subagent sessions in the web-shell detail panel.
    • ›Adds rendered file previews in the web-shell.
    • ›Adds workspace agent management UI in the web-shell.
    • ›Adds a git mode selector when creating new sessions in the web-shell.
    • ›Adds selective Shadow DOM isolation for web-shell component embedding.
    • ›Adds workspace-level content generation in the serve layer.
    • ›Persists workspace channel configuration across restarts.
    • ›Adds daemon transport to the Java SDK (sdk-java).
    • ›Emits the OAuth login URL as a single OSC 8 hyperlink in the terminal.
    • ›Adds Goal v3 state protocol in core.
    • ›Adds explicit channel delivery in the daemon.
    • ›Scopes channel lifecycle to workspace runtimes.
    • ›Auto-reruns a CI check that died on infrastructure failure, once (autofix).
    • ›Auto-updates a PR when the merge gate rejects it due to a stale base (autofix).
    • ›Posts PR review bodies bilingually when the PR description is in Chinese.
    • ›Runs channel loops in daemon workers.
    • ›Adds bounded Goal evidence verification in core.
    • ›Propagates trusted daemon invocation context to child agents.
42. v0.21.0 Jul 24, 2026 · issue 002

    Qwen Code v0.21.0 adds QWEN_SYSTEM_IDENTITY_MD override, native video in /learn, @ session references, MCP forced reconnects, and Java daemon transport.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.21.0

    └──▷ TRY IT
    Replace the default agent identity with a custom persona for a security-focused deployment.
    copy

    $ export QWEN_SYSTEM_IDENTITY_MD="$(cat /etc/qwen/security-identity.md)"
    qwen

    Feed a screen-recording video directly to /learn so the agent can infer steps from a visual walkthrough.
    copy

    $ qwen
    # Inside the session:
    /learn /path/to/demo.mp4

    Reference a prior session by @ handle with tab completion to continue context across sessions.
    copy

    $ qwen
    # Inside the session, type:
    @<TAB>   # shows completable prior session IDs
    @session-abc123 summarise what we decided yesterday

    • ›Adds QWEN_SYSTEM_IDENTITY_MD environment variable to override the core system identity/prompt at runtime.
    • ›Supports native video input in the /learn slash command.
    • ›Adds @ syntax for referencing prior sessions in the CLI with completion tabs.
    • ›Supports forced MCP reconnects in qwen serve mode.
    • ›Adds daemon transport to the Java SDK (sdk-java).
    +16 moreshow less

    • ›Adds configurable image generation models in core settings.
    • ›Supports custom skill directories via CLI settings.
    • ›Web shell gains a workspace selector button with add/switch dropdown in the composer toolbar.
    • ›Web shell shows subagent sessions in the detail panel.
    • ›Web shell adds rendered file previews.
    • ›Web shell adds a renderChatHeader slot for custom session headers.
    • ›Web shell adds git mode selector for new session creation.
    • ›Web shell adds workspace agent management.
    • ›Autofix auto-reruns a CI check that died on infrastructure failure (once).
    • ›Autofix auto-recovers a PR parked on a stale base.
    • ›OAuth login URL is now emitted as a single OSC 8 hyperlink in the terminal.
    • ›PR reviews are posted bilingually when the PR description is in Chinese.
    • ›Adds workspace-level generation and persisted workspace channel configuration in qwen serve.
    • ›Adds explicit channel delivery and scopes channel lifecycle to workspace runtimes in the daemon.
    • ›Adds Goal v3 state protocol and bounded Goal evidence verification in core.
    • ›Adds selective Shadow DOM isolation in the web shell.
43. v0.20.1 Jul 21, 2026 · issue -029

    Qwen Code v0.20.1 adds built-in web search, sidebar customization API, git history browser, custom slash commands, and Singapore token region.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.20.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.20.1

    • ›Adds opt-in built-in web_search tool backed by the DashScope Responses API for grounding agent responses in live web content.
    • ›Adds fork_turns parameter to fork subagents, giving callers explicit turn-budget control over spawned sub-agents.
    • ›Adds sidebar customization API for branding, navigation, session actions, and footer in the web-shell.
    • ›Adds ACP initialize handshake timeout as a configurable value in the serve layer.
    • ›Adds Singapore Token Plan region to the auth provider list.
    +17 moreshow less

    • ›Adds worktree-isolated sessions in the web-shell for parallel task execution.
    • ›Adds custom slash command actions support in the web-shell.
    • ›Adds a git commit history browser in the web-shell.
    • ›Adds content-safe memory recall telemetry in the channels layer.
    • ›Surfaces the running model name in every autofix report.
    • ›Autofix can now be re-armed on a stranded PR via @qwen-code /retry instead of deleting a marker.
    • ›Autofix raises the strict round cap from 5 to 10.
    • ›Autofix renders the managed PR fleet into the scan run summary.
    • ›Autofix picks up managed fork PRs in real time instead of waiting for the throttled schedule.
    • ›Autofix supports label-driven takeover and release of PRs.
    • ›Autofix directly takes over maintainer-fork PRs without requiring a label.
    • ›Autofix auto-manages the bot's own fork PRs without requiring a label.
    • ›Daemon advertises ACP preheat readiness.
    • ›Plan-mode shell commands are now routed by safety classification.
    • ›Core adds the ability to inspect persisted conversation branches.
    • ›Supports workspace display names.
    • ›Web-shell surfaces worktree isolation status in the new-session empty state.
44. v0.20.0 Jul 19, 2026 · issue -031

    Qwen Code v0.20.0 adds daemon log rotation, round-labeled review findings, WebShell history replay, and the qwen3.8-max-preview model.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.20.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.20.0

    • ›Adds qwen3.8-max-preview to the Token Plan model list, making it selectable for inference.
    • ›Adds bounded daemon log rotation to the CLI, preventing unbounded log growth.
    • ›Bakes the round label into a review finding's identity line and key, making multi-round findings uniquely addressable.
    • ›Enables replay of ChatRecord history in read-only WebShell sessions.
    • ›Lets users read the full plan from the exit_plan_mode confirmation dialog before accepting.
45. v0.19.12 Jul 18, 2026 · issue -032

    Qwen Code v0.19.12 adds archived session export, a workspace session-info endpoint, per-model sub-agent concurrency limits, and a web_fetch overhaul.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.12 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.12

    └──▷ HOW TO FIND IT
    Toggle the web-shell session sidebar without reaching for the mouse during an active coding session.
    📍Press Cmd+B (macOS) or Ctrl+B (Windows/Linux) in the web-shell to open or close the session sidebar.
    • ›Adds a workspace session-info aggregate endpoint (feat(serve)) for querying session state across workspaces.
    • ›Supports per-model sub-agent concurrency limits, letting operators cap how many sub-agents run in parallel for a given model.
    • ›Adds archived session export from the web-shell UI.
    • ›Adds mouse text selection and copy in VP mode for the CLI.
    • ›Adds same-turn message steering support in the CLI.
    +22 moreshow less

    • ›Supports full-turn multimodal routing for image prompts.
    • ›Overhauled web_fetch with improved content fidelity, binary handling, security, and resilience.
    • ›Adds skill management pages to the web-shell UI.
    • ›Adds a workspace Goals page to the web-shell and preserves /goal state on daemon resume.
    • ›Adds git status chip, visual working-tree diff, and sidebar git status to the web-shell.
    • ›Adds directory autocomplete to the Add Workspace dialog in the web-shell.
    • ›Toggles the session sidebar with Cmd+B / Ctrl+B in the web-shell.
    • ›Persists split view state across refresh, per browser tab, in the web-shell.
    • ›Suggests sending new-topic drafts in a new session from the web-shell.
    • ›Routes VSCode extension logs to the 'Qwen Code Companion' output channel.
    • ›Adds formatDisplayPath() and wires improved descriptions for grep, glob, and ripGrep tools.
    • ›Exposes workspace-scoped observed contacts from channels.
    • ›Observes group names from inbound channel messages.
    • ›Enables per-message relevant memory recall in channels.
    • ›Confirms natural memory mutations and saves explicit multi-fact memory safely in channels.
    • ›Stamps daemon sourceId with channel instance name on created sessions.
    • ›Shows active path in compact tool summaries in the CLI.
    • ›Adds a daemon Todo stop guard to the CLI.
    • ›Propagates prompt IDs to turn events in the daemon.
    • ›Enables artifact defaults and write reminders in core.
    • ›Improves sub-agent delegation defaults and guardrails.
    • ›Traces cold first-session startup in the daemon for performance visibility.
46. v0.19.11 Jul 16, 2026 · issue -034

    Qwen Code v0.19.11 adds /learn, archived session export, DingTalk DMs, general.notificationMode, and MCP workspace management.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.11 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.11

    └──▷ TRY IT
    Teach the agent a reusable skill from the CLI so it can recall and apply it in future sessions.
    copy

    $ /learn

    • ›Adds general.notificationMode config key to silence per-approval notifications selectively.
    • ›Adds /learn command for user-initiated skill creation directly from the CLI.
    • ›Changes the default approval mode from default to auto.
    • ›Adds archived session export via the CLI (feat(cli): Add archived session export).
    • ›Adds stateless generation SSE endpoint to the daemon for streaming without session state.
    +18 moreshow less

    • ›Adds workspace MCP management via the serve layer, enabling per-workspace MCP server control.
    • ›Adds structured channel memory management with support for natural memory references.
    • ›Supports DingTalk webhook delivery to direct messages (in addition to group channels).
    • ›Emits liveness heartbeats for silent foreground shell commands, preventing false timeout detection.
    • ›Adds a PDF vision bridge fallback so PDF content can be processed when primary vision path is unavailable.
    • ›Adds aggregate deep health reporting across workspaces in the daemon.
    • ›Exposes tool-call preparation lifecycle events via the ACP layer.
    • ›Adds workspace path lock in the web-shell to prevent accidental workspace switches.
    • ›Adds an extension management page in the web-shell UI.
    • ›Adds zoom, pan, and drag controls to Mermaid diagram rendering in the web-shell.
    • ›Adds the ability to maximize a single split pane in the web-shell split view.
    • ›Color-codes each split pane by workspace for at-a-glance orientation in multi-workspace sessions.
    • ›Auto-posts visual previews (screenshots and flow GIFs) on PRs from the web-shell.
    • ›Shows sessions awaiting user action in a dedicated web-shell view.
    • ›Adds immutable session source metadata to daemon sessions.
    • ›Tags daemon sessions with their originating channel source.
    • ›Adds VP mode UX improvements to the CLI interface.
    • ›Builds Step 4 (verify) and Step 5 (reverse-audit) prompts into the review pipeline and proves they ran.
47. sdk-typescript-v0.1.8 Jul 14, 2026 · issue -036

    Qwen Code SDK v0.1.8 adds session resumption, multi-modal input, concurrent batch execution, MCP progress updates, and a Coding Plan auth mode.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch sdk-typescript-v0.1.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout sdk-typescript-v0.1.8

    └──▷ TRY IT
    Resume a previous session by ID to continue work exactly where it left off.
    copy

    $ qwen --session-id <your-session-id> 'continue the refactor we started'

    Inject provider-specific parameters (e.g. enable_thinking) into requests to an OpenAI-compatible endpoint.
    json copy

    {
      "extra_body": { "enable_thinking": true }
    }

    Set environment variables for the CLI through the settings file instead of the shell environment.
    yaml copy

    env:
      MY_API_KEY: "sk-..."
      HTTP_PROXY: "http://proxy.corp:8080"

    • ›Adds --session-id CLI flag and resume/continue SDK options to resume or continue existing sessions by ID.
    • ›Adds settings.env field for environment variable configuration directly in settings.
    • ›Adds contextWindowSize configuration key to control the model context window.
    • ›Adds extra_body support for OpenAI-compatible providers to pass provider-specific request fields.
    • ›Adds export command for session history in markdown and HTML formats.
    +22 moreshow less

    • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
    • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
    • ›Adds Coding Plan authentication mode with unified AuthDialog and Coding Plan configuration management.
    • ›Adds MCP tool progress update support in TUI and SDK mode.
    • ›Adds experimental LSP support for code intelligence.
    • ›Adds symlink support for the skill manager.
    • ›Adds concurrent runner for batch CLI execution.
    • ›Promotes Agent Skills from experimental to stable.
    • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
    • ›Adds a Zed extension for the Qwen Code agent server.
    • ›Adds TPM throttling error handling with a 1-minute retry delay for rate-limited requests.
    • ›Adds support for JSON Schema draft-2020-12 for MCP tools.
    • ›Improves retry logic for 429 and 5xx error handling.
    • ›Adds cache_control for system and last user text messages in the Anthropic content generator.
    • ›Adds debug mode output refactor routing console calls to a logfile-first debugLogger.
    • ›Adds large paste placeholder and improved enter-submit behaviour on macOS.
    • ›Preserves UTF-8 BOM when editing files.
    • ›Adds model selection through ACP in the VS Code IDE companion.
    • ›Removes the Smart Edit tool and ClearcutLogger.
    • ›Removes the read_many_files tool; replaces it with a readManyFiles utility for user @-commands.
    • ›Adds source information tracking in telemetry logs.
    • ›Clarifies output formats for non-interactive mode.
    └──▷ BREAKING ON UPGRADE

    • !The disable* settings are renamed to enable* (negative naming changed to positive naming); any config using disable* keys will no longer be recognised.
    • !The read_many_files tool is removed; usages must migrate to the readManyFiles utility via user @-commands.
    • !The Smart Edit tool is removed; workflows depending on it will no longer function.
48. v0.19.10 Jul 14, 2026 · issue -036

    Qwen Code v0.19.10 adds multi-workspace ACP, SDK effort/model controls, configurable shell timeouts, and xAI Grok as a built-in provider.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.10 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.10

    • ›Adds SDK methods to control reasoning effort, list available models, and query account and context usage statistics at runtime.
    • ›Both the TypeScript and Python SDKs now expose transport selection and query options for finer control over daemon communication.
    • ›Foreground shell commands now respect a configurable default timeout, preventing long-running commands from blocking indefinitely.
    • ›Daemon now supports workspace-qualified ACP endpoints, allowing SDK and web shell clients to open sessions scoped to specific workspaces in multi-workspace deployments.
    • ›The qwen serve daemon can now host channel workers for multiple trusted workspaces, binding each worker to its respective workspace directory.
    +34 moreshow less

    • ›The daemon now exposes read-only session catalogs for untrusted workspaces, letting clients browse sessions without write access.
    • ›New API endpoint lets you toggle workspace skills programmatically.
    • ›Workspace registrations added at runtime are now persisted so they survive daemon restarts without manual reconfiguration.
    • ›Workspaces can now be removed at runtime without restarting the server.
    • ›A new MessageDisplay hook fires incrementally during assistant streaming, allowing observers to track reply text before the turn completes.
    • ›Web shell gains a right-side review panel for inspecting edited files, artifacts, and scheduled tasks with diffs, file navigation, and session-scoped tabs.
    • ›Multi-workspace split view now supports cross-workspace sessions, workspace labels, and a responsive layout for side-by-side editing.
    • ›Rewind and shell actions now work across multiple workspaces.
    • ›Session export is now workspace-qualified so exports stay organized across workspaces.
    • ›Voice input is now qualified per workspace for better multi-workspace support.
    • ›Scheduled tasks from all workspaces are now aggregated into a single view in the web shell for easier monitoring.
    • ›SDK-hosted agents now forward user answers from ask_user_question tool approvals back to the model, enabling interactive question flows in TypeScript and Python SDK integrations.
    • ›DingTalk channels can now optionally mention group message senders in bot replies using visible @ tokens, with Markdown rendering preserved for replies without mentions.
    • ›Channel workers now reconnect automatically when the daemon restarts, restoring DingTalk and Feishu sessions without manual intervention.
    • ›Expanding thinking blocks with Alt+T during streaming now displays full reasoning content in real-time instead of a truncated preview.
    • ›Scheduled task prompts now support inline extension, skill, and MCP reference tags via floating pickers that serialize cleanly into the saved prompt text.
    • ›Subagent views now show untruncated live commands, deeper progress history, execution transcript paths, and recent tool context on inline approvals.
    • ›Sub-agent activity is now shown as a chronological transcript with a parallel-agent timeline for easier multi-task inspection.
    • ›Workspace transcript reader now provides persisted conversation history per workspace for server-side session browsing.
    • ›Code review now includes procedural correctness checks, adjustable effort levels, and guardrails that verify findings before posting.
    • ›PR triage comments now include a confidence score, sequence diagram, files overview, and review footer.
    • ›Daemon status now reports model API error counts and retry metrics.
    • ›Added xAI Grok as a built-in model provider preset.
    • ›Extension management upgraded to v2 with improved install, update, and removal flows.
    • ›Session groups in the web shell now support custom Hex color codes for easier visual organization.
    • ›The composer now accepts custom placeholder text, allowing embedders to show context-specific prompts to users.
    • ›Adds a composer header render slot and an opt-in mobile welcome footer placement so embedders can show custom content above the composer on small screens.
    • ›The web shell session sidebar is now configurable, letting embedders choose which session metadata and actions to display.
    • ›User-scope settings can now be edited directly in the panel, with in-panel model management.
    • ›Skill installation paths are now exposed so users can see where skills are stored.
    • ›The composer toolbar now displays the current Git branch as a chip.
    • ›Markdown tables in web shell now show row, column, and cell selection statistics.
    • ›Double-clicking a cell in a rendered Markdown table opens a dialog with the full cell value for easy reading and copying.
    • ›Web shell fires a callback when a new session is created, enabling custom integrations.
49. v0.19.9 Jul 10, 2026 · issue -040

    Qwen Code v0.19.9 adds qwen update, webhook-triggered channel tasks, PDF-to-image fallback, cursor-paged transcript replay, and multi-workspace sidebar.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.9 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.9

    └──▷ TRY IT
    Keep the Qwen Code CLI up to date without leaving the terminal.
    copy

    $ qwen update

    • ›Adds qwen update and /update commands with auto-update support, letting users self-update the CLI in place.
    • ›Adds create_sub_session tool for scheduled tasks, enabling isolated run mode with precondition gating.
    • ›Adds serve --channel channel worker settings reload, so channel configuration changes take effect without restarting the server.
    • ›Adds workspace-qualified core REST routes, exposing per-workspace API surfaces.
    • ›Adds cursor-paged transcript replay endpoint (serve) for streaming session history replay.
    +22 moreshow less

    • ›Adds forceGlobalCacheScope config for Anthropic proxy providers, enabling cross-request prompt-cache sharing.
    • ›Adds parentSessionId recording and querying for sub-sessions, making sub-session lineage queryable from the daemon.
    • ›Adds voiceBridge support for ACP audio prompts.
    • ›Adds webhook-triggered channel tasks, allowing external webhooks to fire channel-side agent tasks.
    • ›Adds session owner index for workspace runtimes, improving multi-workspace session tracking.
    • ›Adds listing of persisted sessions for trusted workspaces and archived/organized sessions for non-primary workspaces.
    • ›Adds background memory agent timeout configuration (feat(memory)).
    • ›Adds Ctrl+O frozen transcript view and unified tool output rendering in the TUI.
    • ›Renders PDF pages as images when text extraction overflows or fails, enabling vision-model processing of dense PDFs.
    • ›Adds web-shell workspace management sidebar with dynamic registration (daemon multi-workspace phase 4).
    • ›Adds context mention customization to the web-shell.
    • ›Adds collapse/expand toggle to the web-shell AskUserQuestion panel.
    • ›Adds bottom status items and assistant turn footer slot to the web-shell.
    • ›Adds inline VP-mode thought expand on click with auto-hiding scrollbar.
    • ›Posts code-review Suggestion findings as inline PR comments.
    • ›Assigns an accountable reviewer to every line of a large diff in the review workflow.
    • ›Adds QQ bot group message handling and cron-msg-experimental support.
    • ›Adds session runtime status exposure from the daemon.
    • ›Allows long /goal conditions in the CLI.
    • ›Adds pure-ASCII fast path to text token estimation, improving throughput for ASCII-heavy workloads.
    • ›Gates browser automation MCP on an external adapter, making the integration opt-in.
    • ›Persists session artifacts across daemon restarts.
    └──▷ BREAKING ON UPGRADE

    • !The feat(daemon) change drops isolated scheduled-task mode: sub-sessions now use parentSessionId tracking instead of the previous isolated run mode.
50. v0.19.8 Jul 8, 2026 · issue -042

    Qwen Code v0.19.8 adds multi-workspace routing, serve env isolation, hook payload enrichment, hot-reload plugins, and split-view composer.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.8

    └──▷ USE IT
    Pin a subagent to an existing git worktree so it operates in a fixed directory, regardless of the parent session's workspace.
    json copy

    {
      "tool": "Agent",
      "working_dir": "/home/user/project/feature-branch",
      "prompt": "Refactor the auth module and run tests."
    }

    Disable DM/private messages in a channel integration so the bot only responds in public channels.
    yaml copy

    dmPolicy: disable

    • ›Adds dmPolicy config key to channels to disable private/DM messages.
    • ›Adds working_dir field to the Agent tool for pinning subagents to an existing worktree.
    • ›Adds serve environment isolation and total admission control to the serve subcommand.
    • ›Enables multi-workspace session routing so a single serve instance can dispatch across workspaces.
    • ›Bounds replay snapshot history in the serve subsystem to cap memory growth.
    +5 moreshow less

    • ›Auto-retries the next available port when the requested serve port is already in use.
    • ›Adds extension file hot-reload: watches for plugin changes and reloads the runtime without restarting.
    • ›Shows a permission-mode badge in the footer for DEFAULT mode.
    • ›Exposes external split controls in the web shell for programmatic pane management.
    • ›Adds inline preview, editor handoff, and an in-dialog off switch when reviewing auto-generated skills.
51. v0.19.7 Jul 7, 2026 · issue -043

    Qwen Code v0.19.7 adds session export, model fallback chains, per-tool-call timeouts, daemon status dashboards, and LSP hot reload.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.7 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.7

    └──▷ TRY IT
    Export a full session from the daemon API to archive or audit an agent conversation.
    copy

    $ curl -s http://localhost:<port>/daemon/session/<session-id>/export | jq .

    Check live daemon activity metrics — including runtime.activity fields — from the status endpoint.
    copy

    $ curl -s http://localhost:<port>/daemon/status | jq '.runtime.activity'

    • ›Adds GET /daemon/status endpoint with runtime.activity fields, now backing a dedicated daemon status page in the web shell.
    • ›Adds session export endpoint to the daemon API for retrieving full session data.
    • ›Adds per-tool-call execution timeout as an opt-in scheduler feature.
    • ›Adds model fallback chain — automatically switches to backup models on overload.
    • ›Adds onSessionChange and onSubmitBefore callbacks to the web-shell API.
    +28 moreshow less

    • ›Adds Phase 1 workspace runtime registry via the CLI.
    • ›Adds large pipe frame measurement to the CLI.
    • ›Surfaces PreToolUse hook 'ask' responses as a TUI confirmation dialog.
    • ›Adds token-usage analytics dashboard to the Daemon Status page in the web shell.
    • ›Adds a Scheduled Tasks management page to the web shell.
    • ›Adds session organization (grouping, naming, color tags) in the daemon and web-shell sidebar.
    • ›Adds archive, unarchive, and delete session management to the web-shell sidebar.
    • ›Adds named session groups and color tags to the web-shell sidebar.
    • ›Adds MCP mentions and iconized @ references in the web shell.
    • ›Adds custom @ mention panel in the web shell.
    • ›Adds icon chips for mention tags in the web shell.
    • ›Adds compact echarts full-data block rendering support in the web shell.
    • ›Adds time-series metrics charts to the Daemon Status page in the web shell.
    • ›Adds Settings and Daemon Status as in-place panels in the web shell.
    • ›Adds batch session load replay to the ACP protocol.
    • ›Adds EventBus subscriber byte cap to the ACP bridge.
    • ›Adds vision-bridge image capability advertisement in ACP initialize response.
    • ›Adds proactive channel loop tools.
    • ›Supports multi-folder workspaces in CLI file system boundary checks.
    • ›LSP Server now supports hot reload.
    • ›Surfaces daemon prompt queue status in the CLI.
    • ›Stabilizes tool schema declaration order for consistent model behavior.
    • ›Routes suggestion-level review findings to an updatable PR comment.
    • ›Adds issue-fidelity and root-cause ownership gate to /review.
    • ›Notifies the model when extension capabilities change at runtime.
    • ›Pruning of ignored directories now occurs during glob traversal rather than post-filter, improving performance.
    • ›Memoizes skill scans, debounces sleep-inhibitor logging, and guards IDE readdir calls for improved performance.
    • ›Caches LoadedSettings per workspace with stat-based invalidation for faster CLI startup.
52. v0.19.6 Jul 3, 2026 · issue -047

    Qwen Code v0.19.6 adds nested sub-agents, session artifact APIs, mobile-mcp, dataviz skill, and configurable cron job expiration.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.6 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.6

    • ›Adds visionModelId field to workspace provider status; exposed in the daemon API and web-shell model dialog.
    • ›Introduces session artifact APIs in the daemon (feat(daemon): add session artifact APIs).
    • ›Vendors mobile-mcp with opt-in 0–1000 relative coordinate mode for mobile automation.
    • ›Makes recurring cron/loop job expiration configurable in the scheduler.
    • ›Allows sub-agents to spawn nested sub-agents up to a configurable depth.
    +7 moreshow less

    • ›Adds a bundled dataviz skill to core.
    • ›Adds daemon UI support for vision model selection in the web-shell.
    • ›Displays nested sub-agents as a tree in the web-shell tasks panel.
    • ›Adds sessionless workspace memory forget and dream operations.
    • ›Improves slash command discovery with a taller menu, group counts, and fuzzy search.
    • ›Syncs vendored cua-driver from 0.6.8 to 0.7.0.
    • ›Shows the qwen-code version in the sidebar footer.
53. v0.19.5 Jul 2, 2026 · issue -048

    Qwen Code v0.19.5 adds HTTPS/TLS serving, a /effort command, DingTalk proactive send, and credential redaction for worker output.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.5

    └──▷ TRY IT
    Run the Qwen Code server over HTTPS using your own TLS certificate and key.
    copy

    $ qwen serve --tls-cert /etc/certs/server.crt --tls-key /etc/certs/server.key

    Lower the model's reasoning effort mid-session to trade off quality for speed on routine tasks.
    copy

    $ /effort low

    • ›Adds --tls-cert and --tls-key flags to the serve subcommand to enable HTTPS/TLS on the server.
    • ›Adds the /effort slash command for unified control of reasoning effort level from the CLI.
    • ›Adds listSessions to ChannelAgentBridge for programmatic session enumeration in channel integrations.
    • ›Adds credential redaction for worker stderr forwarding, preventing secrets from leaking into logs.
    • ›Adds DingTalk proactive send support for channel loops, enabling outbound messaging from agent sessions.
    +7 moreshow less

    • ›Adds identity and task lifecycle metadata to channel adapters.
    • ›Adds lifecycle status display in channel adapters.
    • ›Adds retry with exponential backoff for MCP capability discovery.
    • ›Adds description and level fields to /skills ACP output.
    • ›Adds leader approval workflow for plan-required teammates in multi-agent core.
    • ›Adds a compact session timeline rail to the web shell UI.
    • ›Overhauled list-dialog interaction in the web shell with keyboard navigation and accessibility improvements.
54. v0.19.4 Jul 1, 2026 · issue -049

    Qwen Code v0.19.4 adds --insecure, --safe-mode, /config, glob MCP filters, voice dictation, resumable ACP streams, and a revived Chrome extension.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.4

    └──▷ TRY IT
    Connect to a self-hosted LLM endpoint using a self-signed certificate without TLS errors.
    copy

    $ qwen --insecure --model my-local-model 'explain this codebase'

    Isolate a broken session to rule out extensions or hooks as the cause.
    copy

    $ qwen --safe-mode 'why is my build failing?'

    Restrict MCP tool access to a subset of servers using glob patterns in config.
    yaml copy

    mcp:
      allowed:
        - 'filesystem/*'
        - 'search/*'
      excluded:
        - 'filesystem/delete*'

    • ›Adds --insecure flag to skip TLS verification when connecting to self-signed endpoints.
    • ›Adds --safe-mode flag to disable all customizations (extensions, hooks, settings) for troubleshooting.
    • ›Adds /config key=value slash command to set any configuration setting interactively from the prompt.
    • ›Adds ui.history.collapsePreviewCount setting to control how many turns are shown when resuming a collapsed session.
    • ›Adds classifyAllShell setting to route all shell commands through the auto-mode classifier.
    +20 moreshow less

    • ›Supports glob patterns in mcp.allowed and mcp.excluded config fields for MCP tool filtering.
    • ›Adds configurable idle timeout for MCP tool calls (new config option in core).
    • ›Adds configurable auto-compact threshold and Stop hook context usage via new core config.
    • ›Resumable /acp session stream via Last-Event-ID header, plus opt-in SDK transports export.
    • ›Supports @extension mentions in daemon mode.
    • ›Adds serve --channel flag with a daemon-managed channel worker.
    • ›Adds channel loop support, group history backfill, and explicit channel memory for messaging channels.
    • ›Adds session archive support to the daemon.
    • ›Injects a .qwen/loop.md task file at fire time via sentinels for the /loop command.
    • ›Adds autonomous mode for a bare /loop invocation (no task file required).
    • ›Supports inline one-shot model override in the /model slash command.
    • ›Adds sessionless workspace remember for the serve subcommand.
    • ›Revives the Chrome extension via a daemon-direct architecture.
    • ›Adds voice dictation in the desktop app.
    • ›Adds mouse click and hover support in alternate-screen (TUI) mode.
    • ›Adds a tabbed Settings dialog with Status and Stats tabs in the CLI.
    • ›Adds a mobile sidebar drawer with session list in the web shell.
    • ›Adds browser tab favicon to the web shell.
    • ›Adds queued-prompt UX and friendlier Esc interruption in the web shell.
    • ›Resumes an interrupted turn without injecting a synthetic 'continue' message.
55. v0.19.3 Jun 28, 2026 · issue -052

    Qwen Code v0.19.3 adds voice/control APIs, team memory, vision model fallback, MCP live reload, and a fleet of new CLI and web-shell capabilities.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.3

    └──▷ TRY IT
    Cap how long a streaming response can sit idle before timing out — useful when running behind a strict gateway.
    copy

    $ QWEN_STREAM_IDLE_TIMEOUT_MS=30000 qwen

    Map a custom provider ID to the OpenAI SDK protocol in config so Qwen Code speaks the right wire format.
    json copy

    {
      "providerProtocol": "openai"
    }

    • ›Adds QWEN_STREAM_IDLE_TIMEOUT_MS environment variable to configure the stream idle timeout in the OpenAI pipeline.
    • ›Adds providerProtocol config key to map a provider ID to an SDK protocol.
    • ›Adds /model --vision subcommand flag to designate a fallback vision model.
    • ›Adds /cd command support in ACP sessions.
    • ›Adds a user-configurable keyterms file for voice dictation.
    +25 moreshow less

    • ›Adds 'voice' to ComposerToolbarAction for external visibility control of the voice toolbar button.
    • ›Adds daemon workspace voice and control APIs to the serve layer.
    • ›Adds a new API endpoint to query a single session's status by ID.
    • ›Adds a git-shared team memory tier, enabling memory shared across a team via a git repository.
    • ›Adds a bundled extension creator skill and supports @extension mention in CLI input autocomplete.
    • ›MCP servers now reconcile live on settings change — no restart required.
    • ›Web-shell /mcp dialog now allows browsing MCP server resources.
    • ›Makes the telemetry sensitive span attribute limit configurable.
    • ›Adds recordApiRequestBreakdown wiring into endLLMRequestSpan for richer LLM request telemetry (Phase 4c).
    • ›Adds skill usage stats display in the CLI.
    • ›Auto-generated skills now require user confirmation before being persisted.
    • ›Vendors qwen-cua-driver with opt-in 0–1000 relative coordinate mode.
    • ›TUI now partitions tool display by type — collapsing read/search tools and showing mutation tools individually.
    • ›CLI now warns before foreground shell timeout expires.
    • ›CLI footer now shows the count of scheduled tasks.
    • ›Built-in status line preset is now enabled by default for new users.
    • ›Registers Telegram bot command menu via the channels integration.
    • ›Web-shell markdown tables gain Excel-style interactions and a manual toggle to enable/disable the enhanced table view.
    • ›Web-shell code blocks now stream-highlight syntax as they arrive.
    • ›Web-shell adds a workspace session sidebar.
    • ›Web-shell adds a mobile responsive view for the TodoPanel.
    • ›Web-shell adds error boundaries to prevent a render crash from white-screening the embed.
    • ›Web-shell allows the host to override streaming loading phrases.
    • ›Web-shell shows duration on finished thinking summaries.
    • ›Startup text in auto mode is simplified and emoji removed.
    └──▷ BREAKING ON UPGRADE

    • !The /remember command is decoupled from auto-extract and no longer writes to QWEN.md; existing workflows that relied on /remember updating QWEN.md will stop receiving those writes after upgrading.
56. cua-driver-rs-v0.6.8 Jun 26, 2026 · issue -054

    cua-driver-rs v0.6.8 ships relative-coordinate support, zero-config computer-use via MCP, Feishu channel, --worktree flag, and post-tool-batch hooks.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch cua-driver-rs-v0.6.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout cua-driver-rs-v0.6.8

    └──▷ TRY IT
    Enable relative-coordinate mode in the CUA driver to use normalised coordinates (0–1000 scale) instead of absolute pixels.
    copy

    $ CUA_DRIVER_RS_COORDINATE_SPACE=1 CUA_DRIVER_RS_COORDINATE_SCALE=1000 qwen-code

    • ›Enables relative-coordinate mode in the CUA driver via CUA_DRIVER_RS_COORDINATE_SPACE=1 (default 0); optional scale tuning with CUA_DRIVER_RS_COORDINATE_SCALE=1000.
    • ›Adds --worktree startup flag (Phase D) with symlinkDirectories support and PR refs for isolated worktree sessions.
    • ›Adds respectUserColors and hideContextIndicator options for the statusline.
    • ›Adds auto-dream and auto-skill defaulting to on, plus a /memory toggle command.
    • ›Adds /compress instructions, PreCompact hook plumbing, and plan/subagent attachments to the auto-compact follow-up workflow.
    +26 moreshow less

    • ›Adds post-tool-batch hooks (post tool batch hooks) for running actions after a full tool batch completes.
    • ›Adds user prompt expansion hooks.
    • ›Adds PermissionDenied hook emission for AUTO classifier blocks.
    • ›Injects context environment variables — session, agent, and prompt ID — into shell subprocesses.
    • ›Adds CPU profiling support for Chrome DevTools analysis.
    • ›Adds AUTO mode denial observability and caps.
    • ›Auto-dumps memory diagnostics to disk on pressure detection.
    • ›Adds memory pressure monitor to core.
    • ›Adds atomic write rollout covering credentials, memory, config, and JSONL files.
    • ›Adds zero-config built-in computer-use via the open-computer-use MCP server.
    • ›Ships a codesigned and notarized @qwen-code/open-computer-use fork as a universal binary with QwenCuaDriver.app on macOS; unsigned x86_64 + arm64 binaries for Linux (glibc 2.31 floor) and Windows.
    • ›Adds Feishu (Lark) channel adapter.
    • ›Adds MiniMax-M3 model to the searchable model setup.
    • ›Adds standalone auto-update support.
    • ›Adds release-asset verification to the installer, switching public docs to a standalone entrypoint.
    • ›Adds a virtual viewport for long conversations on Ink 7.
    • ›Adds background housekeeping for stale file-history directories.
    • ›Adds a simplify bundled skill to core.
    • ›Adds agent reproduction workflows to skills.
    • ›Adds a triage skill for issue/PR gatekeeping.
    • ›Adds a fork subagent feature gate with 'Don't peek / Don't race' prompt discipline.
    • ›Adds a settings JSON corrupted warning dialog in the CLI.
    • ›Adds retry visibility for qwen-code.llm_request telemetry (Phase 4b).
    • ›Adds background-shell completion notifications.
    • ›Improves hooks matcher display.
    • ›Enhances system prompts with global reasoning discipline, iterative planning, dedicated tool priority, and step-by-step communication guidance.
    └──▷ BREAKING ON UPGRADE

    • !The refactor(core): tail-preservation compaction is replaced with summary + restoration attachments, which changes how context is compacted on resume.
57. v0.19.2 Jun 24, 2026 · issue -056

    Qwen Code v0.19.2 adds voice dictation, image-to-text transcription, workspace permissions API, and MCP resource read tool.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.2

    • ›Adds workspace permissions rules API (feat(cli): Add workspace permissions rules API) for programmatic control of workspace-level permission rules.
    • ›Adds a remote LSP status route to the serve daemon, exposing Language Server Protocol state over HTTP.
    • ›Adds vision-bridge image-to-text transcription so text-only models can process image inputs by automatically converting them to text.
    • ›Adds voice dictation over the daemon for the Web Shell, enabling speech input in browser-based sessions.
    • ›Refines ASR transcripts with a fast model before inserting dictated text, improving voice input accuracy.
    +5 moreshow less

    • ›Adds deterministic guards for destructive commands in auto mode, preventing unsafe operations from running without confirmation.
    • ›Exposes an MCP resource read tool, allowing agents to directly read MCP resources.
    • ›Matches MCP resources globally on a bare @ reference and shows full resource references in the CLI.
    • ›Adds extension operation polling in the CLI for tracking asynchronous extension tasks.
    • ›Optimizes serve daemon startup performance.
58. v0.19.1 Jun 23, 2026 · issue -057

    Qwen Code v0.19.1 adds MCP resource completion by name and automatic MCP server discovery.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.1

    • ›Adds MCP resource completions matched by name and automatic MCP server discovery in the CLI.
59. v0.19.0 Jun 23, 2026 · issue -057

    Qwen Code v0.19.0 adds voice dictation, revivable sub-agents, an Artifact HTML publisher, Dynamic Workflows, and MCP resource browsing.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.19.0

    • ›Adds fastOnly and voiceOnly flags to model definitions to hide models from the main model picker — keeping fast and voice-specific models out of the primary list.
    • ›Enables preserve_thinking by default for the DashScope provider so chain-of-thought tokens are retained automatically.
    • ›Adds an [HH:MM:SS] timestamp display before each assistant turn in the CLI (optional).
    • ›Adds a thinking block viewer in the TUI, toggled with Alt+T to expand or collapse model reasoning blocks.
    • ›New Artifact tool lets the agent publish interactive HTML pages directly from a session.
    +10 moreshow less

    • ›Supports an artifact auto-open setting so published HTML artifacts open automatically.
    • ›Adds voice dictation with native audio capture, streaming transcription, and biasing support.
    • ›Introduces revivable background sub-agents with a configurable subagent transcript TTL.
    • ›Completes the Dynamic Workflows port — supporting resume, saved workflows, keyword triggers, and notifications.
    • ›Adds daemon session branching in the web-shell interface.
    • ›Adds browsing of MCP server resources inside the /mcp dialog.
    • ›Supports installing extensions from archive sources.
    • ›Respects configurable agent ignore files so the agent skips paths defined in project-level ignore configs.
    • ›Desktop file preview now opens in a resizable side panel instead of fullscreen.
    • ›TUI removes tool group borders and auto-collapses completed tool results for a cleaner conversation view.
60. v0.18.5 Jun 21, 2026 · issue -059

    Qwen Code v0.18.5 adds a Requesty provider, MCP resource/prompt support, and faster git branch reads.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.18.5

    • ›Adds Requesty as a new model provider.
    • ›Supports MCP resources and reliably surfaces MCP prompts.
    • ›Reads the current git branch directly from .git instead of spawning a git subprocess, reducing overhead in large repos.
61. v0.18.4 Jun 20, 2026 · issue -060

    Qwen Code v0.18.4 adds QQ Bot channel, token-usage stats, configurable ACP timeouts, daemon idle detection, and a second-resolution session wakeup engine.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.18.4

    └──▷ TRY IT
    Check whether the Qwen Code daemon is idle before scheduling a new task in CI or an orchestration script.
    copy

    $ curl -s 'http://localhost:<port>/health?deep=true'

    • ›Adds GET /health?deep=true endpoint with daemon idle detection for health-check integrations that need to know when the daemon is truly inactive.
    • ›Makes ACP permission timeout configurable in the serve layer, allowing operators to tune how long the agent waits for permission grants before timing out.
    • ›Passes the original API call ID (toolCallId) to the hook system, giving hook authors a stable handle to correlate tool invocations across the pipeline.
    • ›Exposes token usage statistics for cost visibility, surfacing per-run input/output token counts in the UI.
    • ›Adds a second-resolution session wakeup engine for the loop, enabling tighter scheduling of self-paced prompt-only /loop wakeups.
    +6 moreshow less

    • ›Adds a QQ Bot (QQ机器人) channel adapter, extending Qwen Code's messaging-platform integrations.
    • ›Adds workflow tool token budget tracking with per-run UI surfacing, making token consumption visible at the workflow level.
    • ›Auto-reveals the exit_plan_mode tool when the agent enters plan mode, reducing manual steps to leave plan mode.
    • ›Adds a desktop-pet skill for generating pixel-art companion applications.
    • ›Adds i18n support for extension displayName and description, enabling localized extension metadata.
    • ›Localizes tool display names in TUI and web-shell badges via i18n.
62. v0.18.2 Jun 17, 2026 · issue -063

    Qwen Code v0.18.2 adds daemon status API, sessions list command, workflow phase-tree, and collapsible thinking blocks with timers.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.18.2

    └──▷ TRY IT
    Check whether the Qwen Code daemon is running and inspect its reported capabilities from the CLI.
    copy

    $ qwen daemon status

    List recent sessions as machine-readable JSON, capped to the 10 most recent, for use in scripts or auditing active contexts.
    copy

    $ qwen sessions list --json --limit 10

    • ›Adds daemon status API via the CLI for querying daemon health and capabilities.
    • ›Adds sessions list subcommand with --json and --limit flags to enumerate active sessions from the CLI.
    • ›Adds /workflows command with workflow metadata and phase-tree display (Workflow P4).
    • ›Adds imperative composer API to the web-shell for external control of text input, tag insertion, and form submission.
    • ›Adds transcript event exposure in the web-shell so embedders can observe turn-by-turn transcript changes.
    +4 moreshow less

    • ›Adds support for custom footer renderer in the web-shell.
    • ›Adds per-turn time and token counts on the collapse seam in the web-shell, displayed below the prompt.
    • ›Adds collapsible thinking blocks with a duration timer in the TUI.
    • ›Enables delivery of web-shell mid-turn messages into the running daemon turn.
63. v0.18.1 Jun 15, 2026 · issue -065

    Qwen Code v0.18.1 adds durable cron jobs, project-scoped .mcp.json, Claude MCP server import, cross-platform Computer Use, and a wave of web-shell improvements.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.18.1

    └──▷ USE IT
    Configure a project-level MCP server so all contributors share the same server definition without touching global settings.
    json copy

    # Place at the root of your repository
    # .mcp.json
    {
      "mcpServers": {
        "my-server": {
          "command": "npx",
          "args": ["-y", "my-mcp-server"]
        }
      }
    }

    Run a workflow agent in an isolated git worktree so it cannot corrupt the main working tree while autonomously editing files.
    javascript copy

    agent({ schema: mySchema, agentType: 'coding', model: 'qwen-coder', isolation: 'worktree' })

    • ›Adds isolation:'worktree' parameter to agent({schema, agentType, model, isolation:'worktree'}) in Workflow P3, enabling agents that run in isolated git worktrees.
    • ›Adds project-scoped .mcp.json file for MCP server configuration, with workspace approval gating and aligned scope precedence.
    • ›Adds feat(cli): import Claude MCP servers — practitioners can now import MCP server definitions from Claude directly into Qwen Code.
    • ›Adds configurable screenshot max dimension for Computer Use via both a settings key and an environment variable.
    • ›Adds durable /loop cron jobs that persist and survive daemon restarts.
    +18 moreshow less

    • ›Gates direct session shell behind an explicit opt-in, requiring deliberate configuration before the shell surface is exposed.
    • ›Persists oversized tool results to disk instead of holding them in memory, enabling larger tool outputs without OOM.
    • ›Bubbles background sub-agent permission prompts to the parent session so they can be approved interactively.
    • ›Adds dedicated agent permission dialog via _meta.toolName for clearer per-agent permission handling in ACP.
    • ›Introduces DaemonTransport abstraction with ACP standard compliance, exposing a stable SDK/serve interface.
    • ›Delivers A2UI surfaces over MCP with a bridge extraction and action endpoint.
    • ›Supports user-invocable frontmatter in skills files.
    • ›Lets grep results satisfy prior-read checks, reducing redundant file-read steps in agent workflows.
    • ›Migrates Computer Use to cua-driver for cross-platform support.
    • ›Adds goal-status persistence in daemon transcript events, surfaced in both CLI and web-shell.
    • ›Web-shell: adds token usage display, settings panel, retry controls, streaming metrics, and hidden commands.
    • ›Web-shell: revamps floating todo panel interactions.
    • ›Web-shell: shows message timestamps on hover and per-task token and time detail on completed todos.
    • ›Web-shell: reveals full tool detail with auto-collapse of finished tools.
    • ›Web-shell: makes input shortcuts discoverable and clickable.
    • ›Web-shell: adds collapsible TodoWrite history with status diff.
    • ›Web-shell: collapses completed turns to prompt and final answer for a cleaner conversation view.
    • ›Desktop app: shows git branch in the working directory badge.
    └──▷ BREAKING ON UPGRADE

    • !Direct session shell is now gated behind an explicit opt-in; existing setups that relied on it being available by default will lose shell access until the opt-in is configured.
64. desktop-v0.0.4 Jun 15, 2026 · issue -065

    Qwen Code desktop-v0.0.4 adds zero-config computer-use, worktree support, Feishu channel, post-tool-batch hooks, and a /skills picker dialog.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch desktop-v0.0.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout desktop-v0.0.4

    └──▷ TRY IT
    Start a session in an isolated git worktree to safely run agent tasks in parallel without polluting the main branch.
    copy

    $ qwen-code --worktree

    Toggle memory (auto-dream/auto-skill) off mid-session when working with sensitive code you don't want persisted.
    copy

    $ /memory

    Customise the statusline to respect your terminal colour scheme and hide the context indicator for a cleaner UI.
    json copy

    {
      "statusline": {
        "respectUserColors": true,
        "hideContextIndicator": true
      }
    }

    • ›Adds --worktree startup flag (Phase D) alongside symlinkDirectories and PR-ref support for isolated git-worktree sessions.
    • ›Adds /memory toggle command to enable or disable auto-dream/auto-skill at runtime; both default to on.
    • ›Adds /compress instructions, PreCompact hook plumbing, and plan/subagent attachments to the auto-compact follow-up workflow.
    • ›Adds respectUserColors and hideContextIndicator options to the statusline configuration.
    • ›Adds post-tool-batch hooks, giving extension authors a new hook point that fires after an entire tool batch completes.
    +25 moreshow less

    • ›Adds user-prompt expansion hooks so extensions can rewrite prompts before they are sent to the model.
    • ›Adds PermissionDenied hook emission for AUTO classifier blocks, plus AUTO-mode denial observability and caps.
    • ›Adds zero-config built-in computer-use via the open-computer-use MCP server (signed + notarized @qwen-code/open-computer-use fork).
    • ›Adds Feishu (Lark) channel adapter, making Feishu a supported messaging channel.
    • ›Adds a /skills picker dialog for browsing, searching, toggling, and selecting skills interactively.
    • ›Adds a triage skill for automated issue/PR gatekeeping.
    • ›Adds agent-reproduction workflows as a new bundled skill set.
    • ›Adds a simplify bundled skill.
    • ›Adds CPU profiling support for Chrome DevTools analysis.
    • ›Adds MiniMax-M3 model to the searchable model-setup list.
    • ›Adds standalone auto-update support for the desktop installer.
    • ›Adds installer asset-signature verification and switches public docs to a standalone entrypoint.
    • ›Injects context environment variables (session ID, agent ID, prompt ID) into shell subprocesses.
    • ›Adds a memory pressure monitor and auto-dumps memory diagnostics to disk on pressure detection.
    • ›Adds atomic writes for credentials, memory, config, and JSONL files to prevent corruption.
    • ›Replaces tail-preservation compaction with summary + restoration attachments for context management.
    • ›Adds a fork subagent feature gate with 'Don't peek / Don't race' prompt discipline.
    • ›Adds virtual viewport rendering for long conversations (Ink 7).
    • ›Adds background housekeeping for stale file-history directories.
    • ›Adds a settings-JSON corrupted warning dialog.
    • ›Adds notification when background shells finish.
    • ›Adds retry visibility telemetry for qwen-code.llm_request spans (Phase 4b).
    • ›Adds qwen-code.subagent span with concurrent isolation to telemetry (Phase 3).
    • ›Adds skill-based real-time optimization telemetry foundation (P0+P1).
    • ›Improves hooks matcher display for better observability of hook matching.
    └──▷ BREAKING ON UPGRADE

    • !The 'Default' approval mode is renamed to 'Ask permissions', which may affect scripts or documentation that reference it by name.
    • !Context compaction now uses summary + restoration attachments instead of tail-preservation; existing compaction behaviour changes on upgrade.
65. v0.18.0 Jun 12, 2026 · issue -068

    Qwen Code v0.18.0 adds Agent Team parallelism, a Workflow tool sandbox, user-level auto-memory, /fork and /stats commands, and a desktop ACP app.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.18.0

    └──▷ TRY IT
    Copy the second-to-last AI response to the clipboard — useful when you want an earlier answer without scrolling.
    copy

    $ /copy 2

    Spawn a background sub-agent to work on a parallel task without blocking the current session.
    copy

    $ /fork

    Review cross-session token and request statistics directly in the terminal.
    copy

    $ /stats

    • ›Adds /fork background-agent command to spawn isolated sub-agents from the CLI.
    • ›Adds /stats interactive dashboard command with cross-session usage tracking.
    • ›Adds /skills picker dialog — browse, search, toggle, and pick skills interactively.
    • ›Adds /copy N command to copy the Nth-last AI message to the clipboard.
    • ›Adds user-level auto-memory stored at ~/.qwen/memories/ so memories persist across projects.
    +23 moreshow less

    • ›Adds description field to ExtensionConfig for richer extension metadata.
    • ›Adds declarative agent frontmatter v1 — wires permissionMode, maxTurns, and a color allowlist into agent skill files.
    • ›Enforces auto-skill- directory prefix for all auto-generated skills.
    • ›Adds Workflow tool (Phase 1) — minimal node:vm sandbox with sequential agent() calls for scripted multi-step workflows.
    • ›Adds experimental Agent Team feature for parallel sub-agent coordination.
    • ›Enables loop and cron tools by default so scheduled and looping agents need no manual opt-in.
    • ›Adds InstructionsLoaded hook that fires when instruction files are loaded, enabling prompt-expansion extensions.
    • ›Adds user prompt expansion hooks in core for pre-processing user input before it reaches the model.
    • ›Injects TRACEPARENT environment variable into shell child processes for distributed-tracing continuity.
    • ›Adds terminal sequence notifications support in hooks.
    • ›Adds layered tool-output truncation with per-message budget and per-tool limits to prevent context bloat.
    • ›Adds standalone auto-update support so the CLI self-updates without an external package manager.
    • ›Adds desktop app package with Qwen ACP SDK integration.
    • ›Adds ACP background notification surfacing in the VS Code extension.
    • ›Adds support for desktop Qwen integration via ACP.
    • ›Adds daemon-mode feature batch: background daemon process management.
    • ›Adds retry-visibility telemetry (qwen-code.llm_request span, Phase 4b) for observing LLM request retries.
    • ›Adds sub-agent span telemetry (qwen-code.subagent) with concurrent isolation (Phase 3).
    • ›Adds release-asset verification to the installer and switches public docs to a standalone entrypoint.
    • ›Adds auto-generated CHANGELOG.md synced from GitHub releases.
    • ›Adds @qwen /triage workflow for automated issue and PR triage in CI.
    • ›Adds PR review workflow using the bundled /review skill in CI.
    • ›Honors skill.allowedTools by auto-approving tools declared in a skill's manifest.
66. v0.17.1 Jun 3, 2026 · issue -077

    Qwen Code v0.17.1 adds post-tool-batch hooks, context env vars in shells, CPU profiling, MiniMax-M3 support, and auto-compact /compress plumbing.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.17.1

    └──▷ TRY IT
    Capture a CPU profile during a heavy session for analysis in Chrome DevTools to identify performance bottlenecks.
    copy

    $ qwen --cpu-profile

    • ›Adds respectUserColors and hideContextIndicator options for the statusline, letting users control terminal color and context indicator display.
    • ›Adds post tool batch hooks so hook scripts can now fire after each complete batch of tool calls, not just individual tool calls.
    • ›Injects context environment variables (session, agent, and prompt IDs) into shell subprocesses spawned during a session.
    • ›Adds CPU profiling support for Chrome DevTools analysis, enabling performance tracing of the CLI.
    • ›Adds a warning dialog when settings.json is detected as corrupted on startup.
    +17 moreshow less

    • ›Adds /compress instructions, PreCompact hook plumbing, and plan/subagent attachments as part of auto-compact follow-up.
    • ›Adds a memory pressure monitor and auto-dumps memory diagnostics to disk on pressure detection.
    • ›Adds MiniMax-M3 model to the searchable model setup flow.
    • ›Adds a triage skill for issue/PR gatekeeping workflows.
    • ›Adds agent reproduction workflows to the skills library.
    • ›Adds a simplify bundled skill to core.
    • ›Adds a fork subagent feature gate with 'Don't peek / Don't race' prompt discipline.
    • ›Adds notifications when background shell commands finish.
    • ›Adds background housekeeping for stale file-history directories.
    • ›Adds virtual viewport rendering for long conversations (ink 7), reducing UI overhead on extended sessions.
    • ›Adds atomic write rollout for credentials, memory, config, and JSONL files to prevent data corruption.
    • ›Adds AUTO mode denial observability and caps.
    • ›Switches the computer-use integration to use the @qwen-code/open-computer-use fork (signed and notarized).
    • ›Improves hooks matcher display in the UI.
    • ›Deduplicates tool guidance between system prompt and tool descriptions to reduce prompt bloat.
    • ›Enhances system prompts with global reasoning discipline and iterative planning.
    • ›Improves IME input handling by moving the physical cursor to the visual cursor position.
    └──▷ BREAKING ON UPGRADE

    • !The 'Default' approval mode is renamed to 'Ask permissions' in the CLI UI.
67. v0.17.0 May 29, 2026 · issue -082

    Qwen Code v0.17.0 adds a Feishu/Lark channel adapter, zero-config computer-use via MCP, and PermissionDenied hooks for AUTO classifier blocks.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.17.0

    • ›Emits PermissionDenied hooks when the AUTO classifier blocks a tool, enabling downstream integrations to react to permission decisions.
    • ›Adds a Feishu (Lark) channel adapter for routing Qwen Code interactions through Feishu/Lark.
    • ›Enables zero-config computer-use capability built in via the open-computer-use MCP — no manual setup required.
    • ›Lays telemetry foundation for skill-based real-time optimization (P0+P1 priority tiers).
    └──▷ BREAKING ON UPGRADE

    • !Context compaction strategy replaced: tail-preservation compaction is removed and replaced with summary + restoration attachments, which may change how long conversation contexts are truncated on upgrade.
68. v0.16.2 May 27, 2026 · issue -084

    Qwen Code v0.16.2 adds a --worktree flag, /memory toggle, W3C trace propagation, runaway-protection guardrails, and a redesigned three-tier auto-compaction ladder.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.16.2

    └──▷ TRY IT
    Work on a feature branch in an isolated Git worktree so the agent doesn't touch your main checkout.
    copy

    $ qwen --worktree feature/my-branch

    Toggle auto-skill and auto-dream memory features on or off mid-session without restarting.
    copy

    $ /memory

    Supply project-specific context to the agent by dropping a local memory file into your repo root.
    copy

    $ echo '# Project conventions
    Always use snake_case for variables.' >> .qwen/QWEN.local.md

    • ›Adds --worktree startup flag (Phase D) with symlinkDirectories support and PR refs for Git worktree-based parallel workflows.
    • ›Adds /memory slash command to toggle auto-dream and auto-skill on/off at runtime; both now default to enabled.
    • ›Loads .qwen/QWEN.local.md as project-local context, letting teams ship per-repo instructions without touching the global memory file.
    • ›Adds a memory-leak-debug skill for heap snapshot diagnosis.
    • ›Redesigns auto-compaction thresholds as a three-tier ladder, replacing the previous single threshold.
    +4 moreshow less

    • ›Adds headless/non-interactive runaway-protection guardrails for unattended CLI runs.
    • ›Adds a dense inline panel with keyboard navigation for parallel agent fan-out.
    • ›Adds client-side HTTP span telemetry and opt-in W3C traceparent header propagation.
    • ›Enables Token Plan cache control in the core.
    └──▷ BREAKING ON UPGRADE

    • !Auto-compaction thresholds are redesigned with a three-tier ladder — existing single-threshold configurations will behave differently after upgrade.
69. v0.16.0 May 21, 2026 · issue -090

    Qwen Code v0.16.0 adds Auto approval mode, /goal, /stuck, /diff, worktree isolation, ModelScope provider, and a new prompt hook type.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.16.0

    └──▷ TRY IT
    Set a session goal so Qwen Code judges each turn against it and continues autonomously until done — or fails fast if it detects the goal is impossible.
    copy

    $ /goal Refactor all usages of deprecated `fs.exists` to `fs.stat` across the repo

    Configure a custom directory for Plan Mode plans instead of the default location.
    json copy

    {
      "plansDirectory": "./docs/plans"
    }

    Run memory diagnostics to spot heap pressure or context bloat before a long agentic session.
    copy

    $ /doctor

    • ›Adds --auto completion flag to /rename with argument hint support.
    • ›Adds plansDirectory config key to make the directory used by Plan Mode configurable.
    • ›Adds TodoCreated and TodoCompleted hooks for todo lifecycle events.
    • ›Adds a new prompt hook type with LLM evaluation support.
    • ›Adds stop hook blocking capability.
    +26 moreshow less

    • ›Adds EnterWorktree and ExitWorktree tools for generic worktree support with agent isolation, plus Phase C session persistence, hooksPath, Footer, WorktreeExitDialog, and three-mode --resume restore.
    • ›Adds /goal command — session-scoped goal setting with judge-driven turn continuation and active goal stream events, including non-interactive goal support; impossible goals are now detected and failed automatically.
    • ›Adds /stuck diagnostic skill for frozen or stalled sessions.
    • ›Adds /doctor command with baseline memory diagnostics and structured memory diagnostics JSON output.
    • ›Adds /diff command with per-turn interactive dialog.
    • ›Adds file restoration support to the /rewind command.
    • ›Adds custom output directory support for /export.
    • ›Adds fork-session --resume flag.
    • ›Adds ModelScope as a built-in third-party API provider.
    • ›Adds Ctrl+P / Ctrl+N readline keybindings for history and selection navigation.
    • ›Adds built-in status line presets with an interactive selection dialog.
    • ›Adds session path status command.
    • ›Adds atomicWriteFile generic write primitive wired into the Write and Edit tools.
    • ›Adds a /demo debug page for the qwen serve daemon.
    • ›Adds Auto approval mode with an LLM classifier.
    • ›Adds image and video support for Qwen3.6-35B-A3B quantized variants.
    • ›Enables progressive MCP availability — MCP no longer blocks the first user input.
    • ›Injects git status into the system prompt and refines Explore/git-log guidance.
    • ›Uses fastModel for the Explore subagent.
    • ›Extends cross-auth fast models to agents.
    • ›Strips inline media before chat compaction summary to reduce token overhead.
    • ›Applies /language output change to the running session without requiring a restart.
    • ›Warns users when rewind is disabled in IDE mode.
    • ›Supports batch deletion of sessions via /delete.
    • ›Unified span creation paths for hierarchical trace trees with interaction span and detailed sensitive attributes.
    • ›Code-splits lowlight syntax highlighting to cut startup V8 parse cost.
70. v0.15.11 May 13, 2026 · issue -098

    Qwen Code v0.15.11 adds structured headless output, codegraph PR risk analysis, runtime session sidecars, and standalone archive installs.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.11 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.11

    └──▷ TRY IT
    Force structured JSON output in a non-interactive CI pipeline by constraining the model response to a schema.
    copy

    $ qwen --headless --json-schema '{"type":"object","properties":{"severity":{"type":"string"},"summary":{"type":"string"}},"required":["severity","summary"]}' 'Review the following diff for security issues: ...'

    Disable tool search for a prefix-caching model to avoid cache invalidation caused by dynamic tool lists.
    yaml copy

    # In your Qwen Code settings file
    # tools.toolSearch.enabled: false

    • ›Adds --json-schema flag to headless mode for structured JSON output constrained to a user-supplied schema.
    • ›Adds tools.toolSearch.enabled setting to control tool-search behavior for prefix-caching models.
    • ›Adds DASHSCOPE_PROXY_BASE_URL environment variable to route DashScope prompt-cache requests through an API gateway.
    • ›Writes a runtime.json sidecar file for active sessions, exposing live session metadata on disk.
    • ›Injects traceId and spanId into debug log files for OpenTelemetry (OTel) correlation.
    +10 moreshow less

    • ›Adds hierarchical session tracing spans to telemetry.
    • ›Adds a codegraph skill for PR review risk analysis and merge-conflict detection.
    • ›Adds standalone archive installation path for environments where npm install is unavailable.
    • ›Adds Ctrl+B keybind to promote context in the CLI.
    • ›Replaces the internal fdir crawler with git ls-files (with ripgrep fallback) for faster, git-aware file enumeration.
    • ›Defers low-frequency built-in tools at startup to reduce initial prompt token size.
    • ›Keeps ask_user_question tool always visible in the tool list to surface clarification UX.
    • ›Improves Anthropic proxy compatibility and enables global prompt cache scope.
    • ›Bounds session-list metadata reads to head/tail 64 KB with pooled buffers and lazy message counts, enabling usable performance on very large session histories.
    • ›Expands core built-in i18n (internationalization) coverage in the CLI.
    └──▷ BREAKING ON UPGRADE

    • !The qwen auth CLI subcommand is removed; authentication is now handled exclusively through the /auth TUI dialog.
    • !The useCollector telemetry setting and TelemetryTarget.QWEN target are removed; configs referencing them will silently lose those values.
71. v0.15.10 May 10, 2026 · issue -101

    Qwen Code v0.15.10 adds /diff command, reactive context compression, autoSkill extraction, QWEN_HOME config, and on-demand tool loading.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.10 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.10

    └──▷ TRY IT
    Use a custom config directory across all Qwen Code sessions, e.g. on a shared machine or in a containerized environment.
    copy

    $ export QWEN_HOME=/opt/qwen-config && qwen

    Review a git diff with statistics without leaving the Qwen Code session.
    copy

    $ /diff

    • ›Adds QWEN_HOME environment variable to customize the configuration directory, replacing the default location.
    • ›Adds /diff command with git diff statistics utility for viewing changes directly in the CLI.
    • ›Adds ToolSearch for on-demand loading of deferred tool schemas, enabling dynamic tool discovery without pre-loading all schemas.
    • ›Adds reactive compression that automatically summarizes context when the conversation overflows the model's context window.
    • ›Adds autoSkill background project skill extraction to the memory system, automatically identifying and storing project-relevant skills.
    +3 moreshow less

    • ›Improves slash command discovery in the CLI, surfacing available commands more effectively.
    • ›Adds message edit/rewind and message metadata UI in the VS Code extension.
    • ›Suppresses OpenTelemetry diagnostics output from the UI in telemetry handling.
72. v0.15.9 May 8, 2026 · issue -103

    Qwen Code v0.15.9 adds /branch conversation forking, a searchable /resume picker, Idealab provider, and per-file AI commit attribution.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.9 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.9

    └──▷ TRY IT
    Fork the current agent conversation to explore an alternative approach without losing the original thread.
    copy

    $ /branch

    Search and resume a previous session by name or keyword from an interactive picker.
    copy

    $ /resume

    • ›Adds /branch slash command to fork the current conversation into a new branch, enabling parallel exploration of agent sessions.
    • ›Adds searchable /resume picker with focus-aware modes for navigating and resuming past sessions.
    • ›Adds Idealab as a new third-party provider in the CLI auth registry.
    • ›Adds per-file AI contribution tracking in commit attribution, recording how much of each file was AI-generated.
    • ›Adds opt-in sensitive span attributes for telemetry, giving users control over what trace data is emitted.
    +2 moreshow less

    • ›Enables foreground-to-background agent promotion, allowing active agents to be moved to background execution.
    • ›Reloads slash commands dynamically when SkillManager fires a change event, so newly added skills are available without restarting.
73. v0.15.8 May 7, 2026 · issue -104

    Qwen Code v0.15.8 adds a light theme toggle to HTML exports and replaces the agent display with an always-on LiveAgentPanel.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.8 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.8

    • ›Adds light theme and theme toggle to /export HTML output via the web-templates feature.
    • ›Replaces the inline AgentExecutionDisplay with an always-on LiveAgentPanel in the CLI for persistent agent status visibility.
74. v0.15.7 May 7, 2026 · issue -104

    Qwen Code v0.15.7 adds a qwen review CLI subcommand, non-interactive model switching, background-agent resume, and expanded TUI markdown rendering.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.7 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.7

    └──▷ TRY IT
    Run an AI-assisted code review on the current working tree using the new review subcommand.
    copy

    $ qwen review

    List and manage all running background agents and monitors, including the new event-monitor tasks.
    copy

    $ /tasks

    • ›Adds qwen review CLI subcommand with an expanded review pipeline for code review workflows.
    • ›Adds ability to switch models non-interactively from the CLI (new model-switch flag/argument).
    • ›Adds FileReadCache in core to short-circuit unchanged file reads, reducing redundant I/O.
    • ›Adds an event monitor tool with throttled stdout streaming, wired into the Background tasks dialog and /tasks command.
    • ›Adds background agent resume and continuation support.
    +16 moreshow less

    • ›Adds MCP health pill to the CLI footer for at-a-glance MCP server status.
    • ›Adds banner area customization (logo, title, hide) via new settings documented in docs(cli).
    • ›Adds HTTP OTLP endpoint behavior and signal routing for telemetry.
    • ›Adds support for reasoning effort 'max' tier as a DeepSeek extension.
    • ›Adds shared permission flow for unified tool-execution authorization.
    • ›Adds path-conditional skill activation and parallelizes skill loading.
    • ›Adds model cost estimation in stats.
    • ›Adds image-sending support for the WeChat (weixin) integration via CDN upload.
    • ›Enforces a prior read before Edit / WriteFile mutates a file, preventing blind overwrites.
    • ›Surfaces and enables cancellation of auto-memory dream tasks from the CLI.
    • ›Routes foreground subagents through the pill-and-dialog UI while running.
    • ›Expands TUI markdown rendering for richer in-terminal output.
    • ›Adds PyPI release workflow for the Python SDK.
    • ›Improves export format completion navigation in the CLI.
    • ›Adds signal.reason convention for ShellExecutionService to carry structured cancellation context.
    • ›Adds hint to background long-running foreground bash commands for better task management.
75. v0.15.5 Apr 29, 2026 · issue -112

    Qwen Code v0.15.5 adds MCP config via CLI, background shell integration with task_stop, and a tmux TUI testing skill.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.5

    • ›Adds MCP (Model Context Protocol) configuration support as a CLI option, enabling MCP setup without editing config files directly.
    • ›Wires background shells into the combined Background Tasks dialog in the CLI UI, giving a unified view of all running background processes.
    • ›Adds a tmux-real-user-testing skill that produces readable TUI test logs for interactive terminal UI testing workflows.
76. v0.15.4 Apr 28, 2026 · issue -113

    Qwen Code v0.15.4 adds OpenRouter auth, background-agent UI, /tasks command, OSC terminal notifications, and agent control tools.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.4

    └──▷ TRY IT
    Set a custom API timeout for slow model endpoints, applied consistently whether using OAuth or a direct API key.
    copy

    $ QWEN_CODE_API_TIMEOUT_MS=60000 qwen

    List and manage background tasks spawned during a session.
    copy

    $ /tasks

    • ›Adds QWEN_CODE_API_TIMEOUT_MS environment variable support across both OAuth and non-OAuth API paths.
    • ›Adds argument-hint support for slash commands in the CLI, showing expected arguments inline.
    • ›Adds /tasks command backed by a managed background shell pool for running and tracking background tasks.
    • ›Adds model-facing agent control tools — task_stop, send_message, and per-agent transcript — enabling the LLM to manage sub-agents directly.
    • ›Adds OpenRouter authentication support (Feat/openrouter auth).
    +6 moreshow less

    • ›Adds API preconnect at startup to reduce first-call latency.
    • ›Adds OSC terminal notification support for iTerm2, Kitty, and Ghostty terminals.
    • ›Adds LLM-generated summary labels for tool-call batches, making multi-step operations easier to follow in the UI.
    • ›Adds background-agent UI with pill indicator, combined dialog, and detail view for monitoring parallel agents.
    • ›Adds tab dot indicator and notification system to the VS Code companion extension.
    • ›Adds Catalan language support.
77. sdk-typescript-v0.1.7 Apr 28, 2026 · issue -113

    Qwen Code SDK TypeScript v0.1.7 adds session resumption, multi-modal input, concurrent batch execution, and a new settings.env config field.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch sdk-typescript-v0.1.7 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout sdk-typescript-v0.1.7

    └──▷ TRY IT
    Resume a previous session by ID to continue work without losing context.
    copy

    $ qwen --session-id <your-session-id>

    Set environment variables for a provider via the settings file instead of the shell environment.
    json copy

    {
      "env": {
        "OPENAI_API_KEY": "sk-...",
        "OPENAI_BASE_URL": "https://api.example.com/v1"
      }
    }

    Pass provider-specific fields through to an OpenAI-compatible endpoint using extra_body.
    json copy

    {
      "extra_body": {
        "enable_thinking": true
      }
    }

    • ›Adds --session-id CLI flag and resume/continue SDK options to resume or continue existing sessions by ID.
    • ›Adds settings.env field in settings configuration for environment variable configuration.
    • ›Adds contextWindowSize configuration support in settings.
    • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
    • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
    +17 moreshow less

    • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
    • ›Adds export command for session history, supporting markdown and HTML output formats.
    • ›Adds concurrent runner for batch CLI execution.
    • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
    • ›Adds MCP tool progress update support in TUI and SDK mode.
    • ›Adds symlink support for the skill manager.
    • ›Adds Coding Plan authentication mode with unified AuthDialog and configuration management.
    • ›Adds experimental LSP support for code intelligence.
    • ›Adds Zed extension for Qwen Code agent server.
    • ›Promotes Agent Skills from experimental to stable.
    • ›Adds TPM throttling error handling with a 1-minute retry delay.
    • ›Adds support for resuming sessions with session ID in query mode.
    • ›Improves retry logic for 429/5xx error handling.
    • ›Adds cache_control for system and last user text messages in the Anthropic content generator to optimize prompt caching.
    • ›Preserves UTF-8 BOM when editing files.
    • ›Routes debug mode console output to a logfile-first debugLogger.
    • ›Adds Java SDK alpha release.
    └──▷ BREAKING ON UPGRADE

    • !Settings renamed from disable* to enable* naming convention — any config keys using the old disable* form will need to be updated.
    • !The read_many_files tool is removed; its functionality is replaced by a readManyFiles utility for user @-commands.
    • !The Smart Edit tool and ClearcutLogger are removed.
    • !Qwen OAuth free quota reduced from 2000 to 1000 requests per day.
78. v0.15.3 Apr 26, 2026 · issue -115

    Qwen Code v0.15.3 adds conversation rewind, a Python SDK, /skills slash command, Traditional Chinese UI, and a 91% cut in sync I/O on the tool hot path.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.3

    └──▷ TRY IT
    Roll back a conversation mid-session after a bad model turn, without restarting the CLI.
    copy

    $ /rewind

    • ›Adds conversation rewind via the /rewind command or double-ESC keypress to roll back the session to a previous state.
    • ›Exposes /skills as a slash command with a secondary picker in the VS Code extension.
    • ›Adds Space-to-preview affordance to the /resume session picker.
    • ›Adds a Python SDK implementation for programmatic access.
    • ›Adds Traditional Chinese (zh-TW) as a selectable UI language option in the CLI.
    +3 moreshow less

    • ›Adds a sticky todo panel to app layouts in the CLI.
    • ›Adds native context menu copy actions for the webview chat in the VS Code extension.
    • ›Cuts runtime sync I/O on the tool hot path by 91%, enabling significantly faster tool execution at scale.
79. v0.15.2 Apr 24, 2026 · issue -117

    Qwen Code v0.15.2 adds auto-titling sessions, /rename --auto, /export command, and MCP-based web search.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.2

    └──▷ TRY IT
    Automatically generate a descriptive title for your current session without typing one manually.
    copy

    $ /rename --auto

    • ›Adds /rename --auto flag to auto-title sessions using a fast model.
    • ›Adds /export session command in the VS Code companion extension.
    • ›Replaces the built-in web_search tool with an MCP-based approach for web search.
    └──▷ BREAKING ON UPGRADE

    • !The built-in web_search tool has been removed; web search now requires an MCP-based configuration.
80. v0.15.1 Apr 23, 2026 · issue -118

    Qwen Code v0.15.1 combines elapsed time and timeout into a single shell time indicator.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.1

    • ›Combines elapsed time and timeout into a unified shell time indicator in the CLI, giving at-a-glance visibility into how long a command has run versus its allowed limit.
81. v0.15.0 Apr 22, 2026 · issue -119

    Qwen Code v0.15.0 adds HTTP/Function/Async hooks, /batch and /doctor slash commands, persistent retry mode, and path-based context rules from .qwen/rules/.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.15.0

    └──▷ USE IT
    Disable specific slash commands project-wide so they are unavailable to all users of the repo.
    json copy

    {
      "slashCommands": {
        "disabled": ["batch", "recap"]
      }
    }

    Run the built-in /doctor command to diagnose environment and configuration issues before starting a session.
    copy

    $ /doctor

    • ›Adds slashCommands.disabled setting to gate individual slash commands from being available.
    • ›Adds refreshInterval to statusLine configuration for periodic status-line refresh.
    • ›Adds OAuth configuration flags to the mcp add subcommand.
    • ›Adds ACP message rewrite timeout as a configurable option.
    • ›Adds path-based context rule injection: rules placed under .qwen/rules/ are automatically injected based on file path.
    +29 moreshow less

    • ›Adds HTTP Hook, Function Hook, and Async Hook support for the hooks system.
    • ›Adds complete hooks support for ACP integration.
    • ›Adds /batch skill for parallel batch operations.
    • ›Adds /doctor diagnostic command for environment troubleshooting.
    • ›Adds /recap slash command and auto-show on session return for session recap.
    • ›Adds /stats rows attributed to the originating subagent for multi-agent token accounting.
    • ›Adds /insight command support in the VS Code IDE companion.
    • ›Adds OSC 52 copy hotkey for OAuth authorization URLs in MCP.
    • ›Adds bare startup mode for the CLI.
    • ›Adds dual-output sidecar mode for the TUI.
    • ›Adds early input capture during CLI startup to prevent keystroke loss.
    • ›Adds tool execution progress messages displayed inline during runs.
    • ›Adds configurable line limit for inline shell output.
    • ›Adds M-d keybinding (Emacs-like) to the CLI input.
    • ›Adds persistent retry mode for unattended CI/CD environments.
    • ›Adds managed auto-memory and auto-dream system.
    • ›Adds enhanced loop detection combining stagnation and validation-retry checks, with automatic stop-directive injection.
    • ›Adds background subagent support with headless and SDK modes.
    • ›Adds session rename, delete, and auto-title generation.
    • ›Adds comparison summary for Arena agent results.
    • ›Adds PDF text extraction fallback and Jupyter notebook parsing.
    • ›Adds Markdown for Agents support to the WebFetch tool.
    • ›Adds dedicated agent execution display in the VS Code IDE companion.
    • ›Enables Plan Mode toggle and approval UI in the VS Code companion.
    • ›Replaces OAuth with Coding Plan / API Key provider setup in the VS Code extension.
    • ›Renders markdown in generic and web-fetch tool outputs in the web UI.
    • ›Displays real-time token consumption during streaming.
    • ›Optimizes compact mode UX with shortcuts, settings sync, and safety improvements.
    • ›Supports multi-line status line output.
82. v0.14.5 Apr 15, 2026 · issue -126

    Qwen Code v0.14.5 adds context-usage exposure in SDK/non-interactive mode, a startup profiler, fork subagent, and LLM-based message rewrite middleware.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.5 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.5

    • ›Exposes /context usage data in non-interactive mode and the SDK API, letting practitioners programmatically inspect context consumption.
    • ›Adds a startup performance profiler to the CLI for measuring and diagnosing launch-time overhead.
    • ›Implements a fork subagent for context sharing in core, enabling subagents to inherit and share context from a parent agent.
    • ›Adds /account command to the VS Code IDE companion for displaying account information.
    • ›Adds LLM-based message rewrite middleware in the ACP layer, supporting custom prompts to transform messages before they reach the model.
    +1 moreshow less

    • ›Discontinues Qwen OAuth free tier with a 2026-04-15 cutoff date.
    └──▷ BREAKING ON UPGRADE

    • !Qwen OAuth free tier is discontinued as of 2026-04-15; setups relying on the qwen-oauth model selection will no longer function after that date.
83. v0.14.4 Apr 13, 2026 · issue -128

    Qwen Code v0.14.4 adds hook events, tool parallelism, voice messages, skill model overrides, and sub-agent disallowed-tools control.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.4

    └──▷ USE IT
    Pin a specific sandbox container image for tool execution instead of relying on the default.
    json copy

    {
      "tools": {
        "sandboxImage": "my-registry.example.com/qwen-sandbox:latest"
      }
    }

    Restrict a sub-agent definition so it cannot invoke file-write or shell tools, limiting blast radius.
    json copy

    {
      "name": "ReadOnlyResearcher",
      "description": "Reads and summarises code, never writes.",
      "disallowedTools": ["write_file", "run_shell_command"]
    }

    Override the model for a specific skill so a lightweight task uses a faster model without changing global settings.
    yaml copy

    ---
    name: quick-summary
    model: qwen3.5-plus
    ---
    Summarise the diff in one paragraph.

    • ›Adds tools.sandboxImage setting to control the sandbox container image used for tool execution.
    • ›Adds disallowedTools field to agent definitions so sub-agents can be restricted to a specific tool subset.
    • ›Adds StopFailure and PostCompact hook events, giving automation pipelines new lifecycle trigger points.
    • ›Adds model override support via skill frontmatter, letting individual skills target a specific model.
    • ›Adds bare exit and bare quit commands so users can exit the CLI without a slash prefix.
    +11 moreshow less

    • ›Warns when a workspace-level config overrides global modelProviders, surfacing silent precedence conflicts.
    • ›Adds a model picker UI for Fast Model in the /settings dialog, replacing the free-text input.
    • ›Shows a description for the active setting in the /settings dialog.
    • ›Propagates approval mode to sub-agents so delegated tasks respect the same permission level as the parent session.
    • ›Adds French (fr-FR) locale support.
    • ›Adds voice message support in the TelegramAdapter channel.
    • ›Adds intelligent tool parallelism with Kind-based batching and shell read-only detection to run compatible tools concurrently.
    • ›Adds a microcompaction mechanism for idle context cleanup, reducing token pressure during long sessions.
    • ›Adds a contextual tips system that surfaces post-response suggestions based on session context.
    • ›Adds CJK word segmentation and Ctrl+Arrow navigation optimisation for East Asian text in the CLI.
    • ›Adds queue input editing — queued messages can be popped for editing via ↑/ESC before submission.
84. v0.14.3 Apr 10, 2026 · issue -131

    Qwen Code v0.14.3 adds a customizable /statusline command and boosts /review with deterministic analysis and autofix.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.3

    └──▷ TRY IT
    Customize the CLI status line during a session to surface the information most relevant to your workflow.
    copy

    $ /statusline

    Run a security-hardened, deterministic code review with autofix suggestions on your current working context.
    copy

    $ /review

    • ›Adds /statusline command to configure a customizable status line in the CLI UI.
    • ›Enhances /review command with deterministic analysis, autofix, and security hardening.
    • ›Adds 'Yes, restore previous mode' option when exiting plan mode, preserving prior workflow state.
    └──▷ BREAKING ON UPGRADE

    • !The verboseMode setting/flag is renamed to compactMode; any configuration or scripts referencing verboseMode will break.
85. v0.14.2 Apr 8, 2026 · issue -133

    Qwen Code v0.14.2 adds /plan command, thinking block retention, adaptive token escalation, and a test-engineer agent.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.2

    └──▷ TRY IT
    Enter plan mode before making changes to review and approve a structured plan without immediate code edits.
    copy

    $ /plan

    • ›Adds /plan command to the CLI for entering plan mode.
    • ›Adds thinking block cross-turn retention with idle cleanup, preserving reasoning context across conversation turns.
    • ›Adds adaptive output token escalation: defaults to 8K tokens and automatically retries at 64K when needed.
    • ›Adds bugfix workflow, test-engineer agent, and debugging skills to the agent toolkit.
    • ›Adds qwen3.6-plus model to the ModelStudio Coding Plan.
86. v0.14.1 Apr 7, 2026 · issue -134

    Qwen Code v0.14.1 adds follow-up suggestions, Ctrl+Y rate-limit skip, Ctrl+O verbosity toggle, and improved /btw side questions.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.1

    └──▷ HOW TO FIND IT
    Skip waiting out a rate-limit backoff immediately so the agent resumes without the full delay.
    📍Ctrl+Y
    Toggle between verbose and compact output display while a session is running to reduce noise during long agent tasks.
    📍Ctrl+O
    • ›Adds Ctrl+Y keyboard shortcut to immediately skip the rate-limit retry delay instead of waiting out the countdown.
    • ›Adds Ctrl+O keyboard shortcut to toggle between verbose and compact output modes mid-session.
    • ›Enhances the /btw side-question command with an improved prompt and support for Ctrl+C/Ctrl+D to cancel.
    • ›Adds follow-up suggestions feature to both the CLI and Web UI after AI responses.
    • ›Adds dangerous-actions behavior guidance in the system prompt to steer agent conduct.
    +2 moreshow less

    • ›Implements mid-turn queue drain for agent execution, allowing queued inputs to be processed during a running agent turn.
    • ›Unifies tool display labels in the Web UI for consistent naming across remaining tools.
87. v0.14.0 Apr 3, 2026 · issue -138

    Qwen Code v0.14.0 adds Channels platform with Telegram/WeChat/DingTalk, cron scheduling, cross-provider subagents, and MCP auto-reconnect.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.14.0

    • ›Adds cron tools for in-session loop scheduling, enabling recurring task automation within a running session.
    • ›Adds an extensible Channels platform with a plugin system supporting Telegram, WeChat, and DingTalk channels out of the box.
    • ›Adds a /mcp reconnect command with auto-reconnect logic for MCP connections.
    • ›Adds npm registry support for extension installation.
    • ›Adds cross-provider model selection for subagents, allowing subagents to use a different model provider than the main agent.
    +3 moreshow less

    • ›Enhances /review with verification, false-positive control, and PR comment posting.
    • ›Promotes hooks out of experimental status and adds a disabled state UI.
    • ›Adds Qwen3.6-Plus model support.
88. v0.13.2 Mar 30, 2026 · issue -142

    Qwen Code v0.13.2 adds a bundled qc-helper skill and qwen-code-claw integration.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.13.2

    • ›Adds bundled qc-helper skill, qwen-code-claw reference, and a README claw guide for extended tool orchestration.
89. sdk-typescript-v0.1.6 Mar 30, 2026 · issue -142

    Qwen Code SDK TypeScript v0.1.6 adds session resumption, multi-modal input, concurrent batch runner, LSP support, and a new settings.env field.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch sdk-typescript-v0.1.6 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout sdk-typescript-v0.1.6

    └──▷ TRY IT
    Resume a previous session by ID to continue a long-running task without losing context.
    copy

    $ qwen --session-id <your-session-id>

    Configure environment variables for the tool directly in settings, avoiding shell profile changes.
    json copy

    {
      "settings": {
        "env": {
          "MY_API_KEY": "abc123",
          "PROXY_URL": "http://proxy.example.com"
        }
      }
    }

    Pass extra body parameters to an OpenAI-compatible provider that requires custom fields.
    json copy

    {
      "provider": "openai-compatible",
      "extra_body": {
        "custom_param": "value"
      }
    }

    • ›Adds --session-id CLI flag and resume/continue SDK options to resume or continue existing sessions by ID.
    • ›Adds settings.env field in settings configuration for environment variable configuration.
    • ›Adds extra_body support for OpenAI-compatible providers to pass additional request body parameters.
    • ›Adds contextWindowSize configuration key for controlling model context window size.
    • ›Adds export command for session history, supporting markdown and HTML output formats.
    +22 moreshow less

    • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
    • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
    • ›Adds symlink support for the skill manager.
    • ›Adds MCP tool progress update support in TUI and SDK mode.
    • ›Adds cache_control for system and last user text messages in the Anthropic content generator to optimize prompt caching.
    • ›Adds Coding Plan authentication mode with a unified AuthDialog and configuration management.
    • ›Adds TPM throttling error handling with a 1-minute retry delay.
    • ›Adds large paste placeholder and improved enter-submit behavior on macOS.
    • ›Adds a concurrent runner for batch CLI execution.
    • ›Adds experimental LSP support for code intelligence.
    • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
    • ›Adds Zed extension for the Qwen Code agent server.
    • ›Promotes Agent Skills from experimental to stable.
    • ›Adds support for model selection through ACP in the VS Code IDE companion.
    • ›Preserves UTF-8 BOM when editing files.
    • ›Improves retry logic for 429/5xx error handling.
    • ›Removes the Smart Edit tool and ClearcutLogger.
    • ›Removes the read_many_files tool and replaces it with a readManyFiles utility for user @-commands.
    • ›Routes debug mode console calls to a logfile-first debugLogger.
    • ›Renames negative settings from disable* to enable* naming convention.
    • ›Clarifies output formats for non-interactive mode.
    • ›Adds source information tracking in telemetry logs.
    └──▷ BREAKING ON UPGRADE

    • !Settings keys previously named with a disable* prefix are renamed to enable* — any existing configuration using the old disable* setting names will need to be updated.
    • !The read_many_files tool is removed; functionality is replaced by a readManyFiles utility available via user @-commands.
    • !The Smart Edit tool is removed; workflows relying on it will need to use alternative edit tools.
90. v0.13.1 Mar 27, 2026 · issue -145

    Qwen Code v0.13.1 adds Alibaba Cloud API key auth, hook execution telemetry, a redesigned hooks UI, and human-readable permission labels.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.13.1

    • ›Adds Alibaba Cloud Standard API Key authentication support via the auth subsystem, giving teams on Alibaba Cloud a native auth path.
    • ›Adds comprehensive hook execution telemetry to the hooks subsystem, enabling visibility into hook run behaviour and outcomes.
    • ›Refactors the hooks UI with a redesigned interface for managing Qwen Code hooks.
    • ›Adds human-readable permission labels, deny-rule feedback, and multi-directory search improvements to the permission flow.
91. v0.13.0 Mar 23, 2026 · issue -149

    Qwen Code v0.13.0 adds hooks, agent arena, skills directories, /btw and /context commands, and system prompt customization.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.13.0

    └──▷ TRY IT
    Ask a quick side question during a session without polluting the main conversation context.
    copy

    $ /btw What does the --dry-run flag do in this codebase?

    Check how your context window tokens are distributed before hitting limits.
    copy

    $ /context

    Authenticate with Qwen Code from the CLI before starting a session.
    copy

    $ qwen auth

    • ›Adds --system-prompt customization options to both the SDK and CLI for overriding the default system prompt.
    • ›Adds /btw slash command for asking ephemeral side questions without affecting the main conversation context.
    • ›Adds /context slash command to display a breakdown of context window token usage.
    • ›Adds auth CLI command for authentication flows.
    • ›Implements a hooks extension mechanism with 10 core event hooks covering session lifecycle and tool execution events.
    +11 moreshow less

    • ›Adds agent collaboration arena (arena) supporting multi-model competitive execution.
    • ›Adds a new Explore agent and renames TaskTool to AgentTool in core.
    • ›Supports skills loaded from the .agents directory and .agents/skills as provider directories.
    • ›Adds support for configurable runtime output directory in storage.
    • ›Adds Tab key fill-only behavior for completions in the VS Code IDE companion.
    • ›Adds image paste support in the VS Code IDE companion.
    • ›Displays token usage inline in the loading/progress indicator.
    • ›Executes task tools concurrently for improved performance.
    • ›Adds metadata and statistics tracking to export.
    • ›Adds support for a permission system.
    • ›Renames QWEN.md to AGENTS.md to follow community best practices.
    └──▷ BREAKING ON UPGRADE

    • !TaskTool is renamed to AgentTool in core — any code or configuration referencing TaskTool by name will need to be updated.
92. v0.12.4 Mar 16, 2026 · issue -156

    Qwen Code v0.12.4 adds bundled /review and docs-audit skills, doubles the default output token limit to 16K.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.4 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.12.4

    └──▷ TRY IT
    Run an instant code review on the current repository without any setup or custom skill configuration.
    copy

    $ /review

    • ›Adds bundled /review slash command skill for out-of-the-box code review with no configuration required.
    • ›Adds docs audit and update helper skills for documentation quality workflows.
    • ›Increases DEFAULT_OUTPUT_TOKEN_LIMIT from 8K to 16K, enabling longer model responses by default.
    • ›Keeps rejected plan content visible in plan mode so users can reference prior proposals.
    • ›Auto-detects max_tokens from the model when not explicitly set by the provider.
93. v0.12.3 Mar 13, 2026 · issue -158

    Qwen Code v0.12.3 improves MCP OAuth UX with post-auth feedback, i18n support, and a clear-auth action.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.3 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.12.3

    • ›Improves MCP OAuth authentication UX with post-auth feedback, internationalization (i18n), and a clear-auth option.
94. v0.12.2 Mar 12, 2026 · issue -159

    Qwen Code v0.12.2 adds truncation support to the LS tool.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.2 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.12.2

    • ›Adds truncation support to the LS tool to prevent oversized directory listings from overwhelming context.
95. v0.12.1 Mar 11, 2026 · issue -160

    Qwen Code v0.12.1 adds a VS Code sidebar view with multi-position chat layout and a CONCAT merge strategy for MCP allowed/excluded lists.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.12.1

    • ›Adds CONCAT merge strategy for MCP allowed/excluded lists, giving practitioners control over how MCP server permission lists are combined across configs.
    • ›Adds sidebar view and multi-position chat layout to the VS Code IDE companion extension.
    • ›Changes temporary filename prefix to qwen-edit- for files opened during edit operations.
96. v0.12.0 Mar 9, 2026 · issue -162

    Qwen Code v0.12.0 adds a hooks system, GIF terminal capture, PTY-by-default shell, AskUserQuestionTool, and richer MCP/extension TUIs.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.12.0

    • ›Implements a hooks system infrastructure (hookConfig) with CLI and UI management, including enable and max turns configuration for lifecycle events such as userPromptSubmit.
    • ›Adds tabWidth support for code highlighting in CodeColorizer, replacing tabs with spaces at a configurable width.
    • ›Enables PTY by default for shell execution, with various shell enhancements.
    • ›Adds streaming terminal capture with GIF generation.
    • ›Adds custom QC commands for GitHub workflows.
    +6 moreshow less

    • ›Adds an export-HTML viewer for tool call results.
    • ›Adds JSON Schema validation for VS Code settings.
    • ›Implements AskUserQuestionTool for interactive user queries during agent runs.
    • ›Enhances the MCP Management TUI with dynamic enable/disable and runtime updates.
    • ›Adds an interactive TUI for extension management.
    • ›Adds support for printable CSI-u keys in KeypressContext.
97. v0.11.1 Mar 3, 2026 · issue -168

    Qwen Code v0.11.1 adds AGENTS.md context support, Ctrl+Y retry shortcut, and improved auth dialog UX.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.1 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.11.1

    └──▷ TRY IT
    Retry a failed API request mid-session without re-entering your prompt — useful when hitting transient rate limits or network errors.
    copy

    $ # When a request fails in the Qwen Code CLI, press:
    Ctrl+Y

    • ›Adds Ctrl+Y keyboard shortcut in the CLI to retry failed requests without retyping.
    • ›Supports AGENTS.md as a default context file, recognized automatically alongside existing context files.
    • ›Improves the auth dialog UX with a clearer three-option layout for easier authentication setup.
98. v0.11.0 Feb 28, 2026 · issue -170

    Qwen Code v0.11.0 adds clipboard image input, a terminal screenshot command, an /insight command, and MCP plan-mode annotations.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.0 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.11.0

    └──▷ TRY IT
    Get personalized programming insights based on your session history directly from the CLI.
    copy

    $ /insight

    • ›Adds /insight CLI command for personalized programming insights, with weighted tips to increase feature discovery.
    • ›Adds clipboard image support and an attachment UI to the CLI, enabling image content to be pasted directly into prompts.
    • ›Supports MCP readOnlyHint annotation in plan mode, allowing read-only MCP tools to run without triggering write restrictions.
    • ›Adds automatic backup of settings.json before any auth modification.
    └──▷ BREAKING ON UPGRADE

    • !The coder-model and qwen3.5-plus model entries have been merged, and vision auto-switching has been removed — setups relying on automatic vision model switching will no longer behave as before.
    • !The environment variable GEMINI_CLI_INTEGRATION_TEST is renamed to QWEN_CODE_INTEGRATION_TEST; any CI or scripts that set the old variable must be updated.
99. v0.10.6 Feb 24, 2026 · issue -174

    Qwen Code v0.10.6 adds third-party model support in Coding Plan and an auth_type config key for model authentication.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.10.6 https://github.com/QwenLM/qwen-code.git
    # already have the repo? check out this version:
    $ git checkout v0.10.6

    └──▷ USE IT
    Configure a model runner with a specific authentication type when connecting to a third-party model provider.
    yaml copy

    auth_type: bearer

    • ›Adds auth_type field to model configuration for controlling authentication type per model runner.
    • ›Adds third-party models glm-4.7, kimi-k2.5, and qwen3-coder-next as selectable options in Coding Plan.
    • ›Updates Bailian Coding Plan model list with new model options.
    • ›Excludes .qwen/commands/ and .qwen/skills/ directories from .gitignore, making custom commands and skills trackable in version control.
100. sdk-typescript-v0.1.5 Feb 22, 2026 · issue -176

     Qwen Code SDK TypeScript v0.1.5 adds session resumption, multi-modal input, concurrent batch runner, LSP support, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.5

     └──▷ USE IT
     Inject provider-specific parameters (e.g. thinking budget) to an OpenAI-compatible provider via extra_body in settings.
     json copy

     {
       "extra_body": {
         "enable_thinking": true,
         "thinking_budget": 8192
       }
     }

     Set environment variables for tool use directly inside the settings file instead of the shell environment.
     json copy

     {
       "env": {
         "MY_API_KEY": "sk-...",
         "CUSTOM_ENDPOINT": "https://my-proxy.example.com"
       }
     }

     • ›Adds --session-id CLI flag and resume/continue options in the SDK to resume or continue existing sessions.
     • ›Adds settings.env field in settings configuration for environment variable configuration.
     • ›Adds contextWindowSize configuration support.
     • ›Adds extra_body support for OpenAI-compatible providers.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     +21 moreshow less

     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     • ›Adds an export command for session history with Markdown and HTML output formats.
     • ›Adds a concurrent runner for batch CLI execution.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds experimental LSP support for code intelligence.
     • ›Adds a Zed extension for the Qwen Code agent server.
     • ›Adds MCP tool progress update support in TUI and SDK mode.
     • ›Adds Coding Plan authentication mode with a unified AuthDialog and configuration management.
     • ›Adds symlink support for the skill manager.
     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds cache_control for system and last user text messages in the Anthropic content generator to optimize prompt caching.
     • ›Adds TPM throttling error handling with a 1-minute retry delay.
     • ›Adds source information tracking in telemetry logs.
     • ›Improves retry logic for better 429/5xx error handling.
     • ›Refactors debug mode output to route console calls to a logfile-first debugLogger.
     • ›Adds large paste placeholder and improves enter-submit behavior on macOS.
     • ›Supports model selection through ACP in the VS Code IDE companion.
     • ›Adds hint for installing external source extensions.
     • ›Implements unified UI architecture with shared component library in the web UI.
     • ›Clarifies output formats for non-interactive mode.
     • ›Preserves UTF-8 BOM when editing files.
     └──▷ BREAKING ON UPGRADE

     • !The read_many_files tool is removed; its functionality is replaced by a readManyFiles utility available via user @-commands.
     • !The Smart Edit tool and ClearcutLogger are removed.
     • !Settings keys previously named with disable* prefix are renamed to enable* positive naming.
101. v0.10.5 Feb 18, 2026 · issue -180

     Qwen Code v0.10.5 adds qwen3.5-plus model support for the Coding Plan feature.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.5

     • ›Adds qwen3.5-plus as a supported model for the Coding Plan workflow.
102. v0.10.4-preview.0 Feb 18, 2026 · issue -180

     Qwen Code v0.10.4-preview.0 adds Global/International region support for Coding Plan.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.4-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.4-preview.0

     • ›Adds Global and International region support for the Coding Plan feature.
103. v0.10.2 Feb 14, 2026 · issue -184

     Qwen Code v0.10.2 adds --session-id for CLI/SDK session control and TPM throttling retry handling.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.2

     └──▷ TRY IT
     Resume or correlate a specific agent session by ID — useful when scripting multi-turn workflows or debugging a particular run.
     copy

     $ qwen-code --session-id <your-session-id> 'Continue the refactor we started'

     • ›Adds --session-id flag to the CLI and SDK to attach or resume a specific session by ID.
     • ›Adds TPM throttling error handling with an automatic 1-minute retry delay when rate limits are hit.
104. v0.10.1-nightly.20260214.03c38899 Feb 14, 2026 · issue -184

     Qwen Code v0.10.1-nightly adds --session-id for CLI/SDK and TPM throttling retry handling.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.1-nightly.20260214.03c38899 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.1-nightly.20260214.03c38899

     └──▷ TRY IT
     Resume or correlate a specific conversation session across CLI invocations by pinning a session ID.
     copy

     $ qwen --session-id my-debug-session-001 'Continue analysing the auth module'

     • ›Adds --session-id flag to the CLI and SDK, enabling callers to specify or resume a named session.
     • ›Adds TPM throttling error handling with an automatic 1-minute retry delay when rate limits are hit.
105. v0.10.1 Feb 11, 2026 · issue -187

     Qwen Code v0.10.1 adds MCP tool progress updates and a new Coding Plan authentication mode with configuration management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.1

     • ›Adds Coding Plan configuration management, introducing a new authentication mode with a unified AuthDialog for Coding Plan workflows.
     • ›Adds MCP tool progress update support in TUI and SDK mode, surfacing real-time progress for long-running MCP tool calls.
106. v0.10.0-preview.6 Feb 11, 2026 · issue -187

     Qwen Code v0.10.0-preview.6 adds MCP tool progress updates in TUI/SDK mode and a new Coding Plan authentication mode.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-preview.6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-preview.6

     • ›Adds MCP tool progress update support in TUI and SDK mode, surfacing real-time progress from MCP tools during execution.
     • ›Adds Coding Plan authentication mode with a unified AuthDialog for streamlined login flows.
107. v0.10.0 Feb 9, 2026 · issue -189

     Qwen Code v0.10.0 adds session resume, history export, Java SDK alpha, Agent Skills GA, and a new settings.env config field.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0

     └──▷ USE IT
     Set environment variables for a project directly in settings instead of managing a separate .env file.
     json copy

     {
       "env": {
         "MY_API_KEY": "sk-...",
         "LOG_LEVEL": "debug"
       }
     }

     • ›Adds settings.env field to settings configuration for environment variable configuration directly in settings.
     • ›Adds --resume flag and session-ID support to the query command, allowing interrupted sessions to be continued by ID.
     • ›Adds SDK resume and continue options and extends authType support in the SDK.
     • ›Adds export command for session history, supporting Markdown and HTML output formats.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     +8 moreshow less

     • ›Adds hint UI for installing external-source extensions.
     • ›Adds large-paste placeholder in the CLI input and fixes enter-to-submit on macOS.
     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds Java SDK alpha (Feat/javasdk alpha 202501).
     • ›Refactors debug mode to route all console calls to a logfile-first debugLogger.
     • ›Replaces the read_many_files tool with a readManyFiles utility scoped to user @-commands.
     • ›Renames negative settings flags from disable* to enable* convention.
     • ›Removes the Smart Edit tool and ClearcutLogger.
     └──▷ BREAKING ON UPGRADE

     • !Settings previously named with disable* prefixes are renamed to enable* — any configuration or scripts referencing the old disable* setting names will break.
     • !The read_many_files tool is removed; callers depending on it must migrate to the readManyFiles utility exposed via user @-commands.
     • !The Smart Edit tool and ClearcutLogger are removed — any integrations relying on either will break.
     • !Qwen OAuth free quota is reduced from 2000 to 1000 requests per day — workflows hitting the old limit will now be throttled sooner.
108. v0.10.0-preview.3 Feb 9, 2026 · issue -189

     Qwen Code v0.10.0-preview.3 adds session resume, history export, settings.env, Java SDK alpha, and promotes Agent Skills to stable.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-preview.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-preview.3

     • ›Adds settings.env field to settings configuration for environment variable configuration.
     • ›Adds --resume / --continue options and extended authType support to the SDK.
     • ›Adds session resume support via session ID in query mode.
     • ›Adds export command for session history in Markdown and HTML formats.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     +8 moreshow less

     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds Java SDK alpha release.
     • ›Adds large paste placeholder in the CLI UI and fixes enter-to-submit on macOS.
     • ›Refactors debug mode to route console output to a logfile-first debugLogger.
     • ›Adds source information tracking in telemetry logs.
     • ›Adds hint UI for installing external-source extensions.
     • ›Removes read_many_files tool, replacing it with a readManyFiles utility for user @-commands.
     • ›Removes Smart Edit tool and ClearcutLogger.
     └──▷ BREAKING ON UPGRADE

     • !Settings renamed from disable* to enable* (negative to positive naming convention) — any config referencing the old disable* keys will break.
109. v0.10.0-preview.2 Feb 9, 2026 · issue -189

     Qwen Code v0.10.0-preview.2 adds session resume, history export, Java SDK, and a new settings.env config field.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-preview.2

     └──▷ USE IT
     Set environment variables for a project via the settings file instead of the shell environment.
     json copy

     {
       "env": {
         "MY_API_KEY": "abc123",
         "QWEN_MODEL": "qwen-max"
       }
     }

     • ›Adds settings.env field to settings configuration for environment variable configuration.
     • ›Adds export command for session history, supporting markdown and HTML output formats.
     • ›Adds support for resuming sessions by session ID via the --resume option in the query interface and SDK.
     • ›Adds resume and continue options to the SDK, and extends authType support.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     +7 moreshow less

     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds Java SDK (alpha) support.
     • ›Adds large paste placeholder in the CLI UI.
     • ›Adds source information tracking in telemetry logs.
     • ›Removes Smart Edit tool and ClearcutLogger; replaces read_many_files tool with a readManyFiles utility for user @-commands.
     • ›Adds hint in the UI for installing external source extensions.
     • ›Refactors debug mode to route console output to a logfile-first debugLogger.
     └──▷ BREAKING ON UPGRADE

     • !Settings keys previously named with disable* prefixes are renamed to positive enable* naming — any existing configuration using disable* keys will need to be updated.
     • !The read_many_files tool is removed; functionality is now provided as a readManyFiles utility for user @-commands.
     • !The Smart Edit tool is removed.
     • !Qwen OAuth free quota is reduced from 2000 to 1000 requests per day.
110. v0.10.0-nightly.20260209.36931e1e Feb 9, 2026 · issue -189

     Qwen Code v0.10.0 adds session resume, session-history export to Markdown/HTML, Agent Skills GA, and a Java SDK alpha.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-nightly.20260209.36931e1e https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-nightly.20260209.36931e1e

     └──▷ TRY IT
     Resume a previous coding session by ID so the agent retains full context without re-explaining the task.
     copy

     $ qwen query --resume <session-id> 'Continue implementing the auth middleware'

     • ›Adds support for resuming sessions by session ID via the --resume flag in the query command, keeping context across invocations.
     • ›Adds export command for session history, outputting in Markdown and HTML formats.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     • ›Adds resume and continue options and extends authType support in the SDK (feat(sdk)).
     • ›Adds large-paste placeholder UI when pasting large content into the CLI input.
     +5 moreshow less

     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds Java SDK alpha (Feat/javasdk alpha 202501).
     • ›Adds hint for installing external-source extensions in the UI.
     • ›Routes debug-mode console output to a logfile-first debugLogger for cleaner debug logging.
     • ›Renames disable* settings to enable* (positive naming) in the settings layer.
     └──▷ BREAKING ON UPGRADE

     • !Settings keys previously named with disable* prefix are renamed to enable* — any config or tooling referencing the old disable* names will break.
     • !The read_many_files tool is removed; its functionality moves to a readManyFiles utility available only via user @-commands.
     • !The Smart Edit tool and ClearcutLogger are removed.
111. v0.10.0-nightly.20260208.36931e1e Feb 8, 2026 · issue -190

     Qwen Code v0.10.0 adds session resume, history export (Markdown/HTML), Agent Skills GA, and a Java SDK alpha.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-nightly.20260208.36931e1e https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-nightly.20260208.36931e1e

     └──▷ TRY IT
     Resume a previous conversation in a non-interactive pipeline without losing context.
     copy

     $ qwen query --session-id <your-session-id> 'Continue the refactor from where we left off'

     Archive a finished session as a shareable HTML report or Markdown document.
     copy

     $ qwen export --format html --output session-report.html

     • ›Adds --session-id support to the query command for resuming previous sessions mid-conversation.
     • ›Adds an export command for session history, outputting in Markdown and HTML formats.
     • ›SDK gains resume and continue options plus extended authType support.
     • ›Adds FORK_MODE to ProcessTransport for Electron IPC integration.
     • ›Promotes Agent Skills from experimental to stable.
     +5 moreshow less

     • ›Introduces a Java SDK alpha (Feat/javasdk alpha 202501).
     • ›Adds a large-paste placeholder in the CLI UI to handle oversized input on macOS.
     • ›Debug mode now routes all console calls to a logfile-first debugLogger instead of stdout.
     • ›Removes the read_many_files tool and replaces it with a readManyFiles utility scoped to user @-commands.
     • ›Adds a hint in the UI for installing external-source extensions.
     └──▷ BREAKING ON UPGRADE

     • !Settings previously named with disable* prefixes are renamed to enable* (e.g. disableX becomes enableX); any config referencing the old names will break.
     • !The read_many_files tool is removed; integrations invoking it directly must migrate to the new readManyFiles @-command utility.
     • !The Smart Edit tool and ClearcutLogger are removed; any workflows depending on them will no longer function.
112. v0.10.0-nightly.20260207.36931e1e Feb 7, 2026 · issue -191

     Qwen Code v0.10.0 adds session resume, export to Markdown/HTML, Java SDK alpha, Agent Skills GA, and large-paste UI improvements.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-nightly.20260207.36931e1e https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-nightly.20260207.36931e1e

     └──▷ TRY IT
     Resume a previous conversation session in a scripted or long-running workflow without losing context.
     copy

     $ qwen query --resume <sessionId> 'Continue the refactor we started'

     • ›Adds --resume <sessionId> support to the query command so practitioners can resume previous sessions by session ID.
     • ›Adds export command for session history with markdown and HTML output formats.
     • ›Adds resume and continue options and extends authType support in the SDK.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     • ›Adds Java SDK (alpha) for programmatic access to Qwen Code capabilities.
     +5 moreshow less

     • ›Promotes Agent Skills from experimental to stable.
     • ›Adds a large-paste placeholder in the CLI UI, improving handling of large clipboard input on macOS.
     • ›Adds debug mode output routed logfile-first via debugLogger, replacing direct console calls.
     • ›Adds source information tracking in telemetry logs.
     • ›Adds a UI hint for installing external-source extensions.
     └──▷ BREAKING ON UPGRADE

     • !Settings renamed from disable* to enable* (negative to positive naming) — any configuration or scripts referencing the old disable* setting keys will break.
     • !The Smart Edit tool and ClearcutLogger are removed.
     • !The read_many_files tool is removed; its functionality is replaced by the readManyFiles utility for user @-commands.
     • !Qwen OAuth free quota reduced from 2000 to 1000 requests per day.
113. v0.10.0-preview.1 Feb 6, 2026 · issue -192

     Qwen Code v0.10.0 adds session resume, session history export, Agent Skills GA, Java SDK alpha, and large-paste UI improvements.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-preview.1

     • ›Adds export command to export session history in Markdown and HTML formats.
     • ›Adds resume and continue options to the SDK, plus extended authType support via feat(sdk) changes.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     • ›Adds support for resuming sessions by session ID in the query command.
     • ›Promotes Agent Skills from experimental to stable.
     +5 moreshow less

     • ›Adds Java SDK alpha (Feat/javasdk alpha 202501).
     • ›Adds large-paste placeholder UI and fixes enter-to-submit on macOS for large pastes.
     • ›Routes debug-mode console calls to a logfile-first debugLogger for cleaner debug output.
     • ›Adds source information tracking in telemetry logs.
     • ›Adds a hint in the UI for installing external-source extensions.
     └──▷ BREAKING ON UPGRADE

     • !Settings renamed from disable* to enable* (negative to positive naming); any config or scripts referencing disable* settings will break.
     • !The read_many_files tool is removed; its functionality moves to a readManyFiles utility accessible only via user @-commands.
     • !The Smart Edit tool and ClearcutLogger are removed.
114. v0.10.0-preview.0 Feb 6, 2026 · issue -192

     Qwen Code v0.10.0 adds session resume, session-history export (Markdown/HTML), Java SDK alpha, and FORK_MODE IPC support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0-preview.0

     • ›Adds export command to dump session history in Markdown or HTML format.
     • ›Adds support for resuming sessions by session ID via the --resume flag in the query command.
     • ›Adds resume and continue options to the SDK, and extends authType support.
     • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
     • ›Introduces Java SDK alpha release.
     +3 moreshow less

     • ›Removes the Smart Edit tool and ClearcutLogger; adds readManyFiles utility for user @-commands (replaces the read_many_files tool).
     • ›Routes debug-mode console output through a logfile-first debugLogger instead of stdout.
     • ›Adds hint UI for installing external-source extensions.
     └──▷ BREAKING ON UPGRADE

     • !Settings previously named with disable* prefixes are renamed to enable* (positive naming); any config or scripts referencing the old disable* keys will break.
     • !The read_many_files tool is removed; functionality is replaced by the readManyFiles utility for user @-commands.
     • !The Smart Edit tool is removed.
115. v0.9.1 Feb 5, 2026 · issue -193

     Qwen Code v0.9.1 adds symlink support for the skill manager and preserves UTF-8 BOM during file edits.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.1

     • ›Adds symlink support for the skill manager, allowing skills to be referenced via symbolic links.
     • ›Preserves UTF-8 BOM markers when editing files, preventing BOM stripping on save.
     • ›Adds cache_control headers for system and last user text messages in the Anthropic content generator, optimizing prompt caching.
116. v0.9.0-nightly.20260205.ce7506d6 Feb 5, 2026 · issue -193

     Qwen Code v0.9.0-nightly adds symlink support for the skill manager and preserves UTF-8 BOM during file edits.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260205.ce7506d6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260205.ce7506d6

     • ›Adds symlink support for the skill manager, allowing skill files to be referenced via symbolic links.
     • ›Preserves UTF-8 BOM markers when editing files, preventing BOM stripping on save.
117. v0.9.1-preview.0 Feb 4, 2026 · issue -194

     Qwen Code v0.9.1-preview.0 adds symlink support for skill manager and preserves UTF-8 BOM on file edits.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.1-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.1-preview.0

     • ›Adds symlink support for the skill manager, allowing skills to be referenced via symbolic links.
     • ›Preserves UTF-8 BOM when editing files, preventing BOM stripping on save for files that require it.
     • ›Adds cache_control to system and last user text messages in the Anthropic content generator, reducing prompt-processing costs on repeated context.
118. v0.9.0-preview.3 Feb 4, 2026 · issue -194

     Qwen Code v0.9.0-preview.3 adds symlink support for the skill manager.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-preview.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-preview.3

     • ›Adds symlink support for the skill manager, enabling skills to be referenced via symbolic links.
119. v0.9.0-nightly.20260204.7fb45c56 Feb 4, 2026 · issue -194

     Qwen Code v0.9.0-nightly adds symlink support for the skill manager.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260204.7fb45c56 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260204.7fb45c56

     • ›Adds symlink support for the skill manager, allowing skill files to be referenced via symbolic links.
120. v0.9.0 Feb 3, 2026 · issue -195

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch execution, LSP support, extra_body for OpenAI providers, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0

     └──▷ USE IT
     Pass custom fields to an OpenAI-compatible provider — useful when the provider requires vendor-specific body parameters (e.g. routing keys or extended options).
     json copy

     {
       "extra_body": {
         "enable_thinking": true,
         "thinking_budget": 8192
       }
     }

     Cap the context window for a model that advertises a large context but needs to be constrained for cost or latency reasons.
     json copy

     {
       "contextWindowSize": 32768
     }

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of custom request body fields.
     • ›Adds contextWindowSize configuration key to control the model context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›New concurrent runner for batch CLI execution, enabling parallel processing of multiple CLI tasks.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     +6 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds Zed extension for the Qwen Code agent server, expanding IDE integration.
     • ›Supports model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic with better handling of 429 and 5xx error responses.
     • ›Clarifies output formats for non-interactive mode.
     • ›Implements unified Web UI architecture with a shared component library.
121. v0.9.0-preview.2 Feb 3, 2026 · issue -195

     Qwen Code v0.9.0-preview.2 adds multi-modal input, concurrent batch execution, LSP support, Zed extension, and extra_body for OpenAI-compatible providers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-preview.2

     └──▷ USE IT
     Set a specific context window size for models that support larger or smaller context limits.
     yaml copy

     contextWindowSize: 32768

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of custom request fields.
     • ›Adds contextWindowSize configuration key to control the model context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds a concurrent runner for batch CLI execution, enabling parallel multi-session runs.
     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     +6 moreshow less

     • ›Adds a Zed extension for the Qwen Code agent server, expanding IDE integration.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling in the core.
     • ›Clarifies output formats for non-interactive mode.
     • ›Implements a unified WebUI architecture with a shared component library.
122. v0.9.0-nightly.20260203.bd900d36 Feb 3, 2026 · issue -195

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch execution, LSP support, Zed extension, and extra_body for OpenAI-compatible providers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260203.bd900d36 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260203.bd900d36

     └──▷ USE IT
     Cap the context window when working with a model that has a smaller effective limit than its advertised maximum.
     yaml copy

     contextWindowSize: 32768

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
     • ›Adds contextWindowSize configuration key to control the model context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds a concurrent runner for batch CLI execution, enabling parallelised non-interactive workloads.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     +6 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds a Zed extension for the Qwen Code agent server, bringing IDE companion support to Zed.
     • ›Adds model selection through ACP in the VS Code IDE companion.
     • ›Implements a unified WebUI architecture with a shared component library.
     • ›Improves retry logic with better handling of 429 and 5xx errors.
     • ›Clarifies output formats for non-interactive mode.
123. v0.9.0-nightly.20260202.bd900d36 Feb 2, 2026 · issue -196

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, LSP code intelligence, Zed extension, and extra_body for OpenAI-compatible providers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260202.bd900d36 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260202.bd900d36

     └──▷ USE IT
     Limit how much context the agent sends per request when working with a model that has a smaller context window.
     yaml copy

     contextWindowSize: 32768

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of arbitrary request body fields.
     • ›Adds contextWindowSize configuration key to control the context window size per model or provider.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds a concurrent runner for batch CLI execution, enabling parallelised non-interactive runs.
     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence inside the agent.
     +6 moreshow less

     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds a Zed editor extension for the Qwen Code agent server.
     • ›Adds model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling in the core request pipeline.
     • ›Clarifies output formats for non-interactive mode.
     • ›Implements a unified WebUI architecture with a shared component library.
124. v0.9.0-nightly.20260201.bd900d36 Feb 1, 2026 · issue -197

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, LSP support, extra_body for OpenAI providers, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260201.bd900d36 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260201.bd900d36

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of custom request fields.
     • ›Adds contextWindowSize configuration key to control context window size per model or provider.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds a concurrent runner for batch CLI execution.
     +7 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds a Zed extension for the Qwen Code agent server.
     • ›Adds model selection through ACP in the VS Code IDE companion.
     • ›Clarifies output formats for non-interactive mode.
     • ›Improves retry logic for 429 and 5xx error handling.
     • ›Implements a unified Web UI architecture with a shared component library.
     • ›Improves error messages when a skill is invoked as a tool.
125. v0.9.0-nightly.20260131.bd900d36 Jan 31, 2026 · issue -198

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, LSP support, extra_body for OpenAI providers, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260131.bd900d36 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260131.bd900d36

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
     • ›Adds contextWindowSize configuration key to control the model context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds a concurrent runner for batch CLI execution, enabling parallel multi-session runs.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     +6 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds a Zed extension for the Qwen Code agent server.
     • ›Supports model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic with better handling of 429 and 5xx errors.
     • ›Clarifies output formats for non-interactive mode.
     • ›Implements a unified web UI architecture with a shared component library.
126. v0.9.0-preview.1 Jan 30, 2026 · issue -199

     Qwen Code v0.9.0-preview.1 adds multi-modal input, concurrent batch CLI, LSP code intelligence, Zed extension, and extra_body for OpenAI-compatible providers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-preview.1

     • ›Adds extra_body support for OpenAI-compatible providers, allowing arbitrary extra parameters to be passed in API requests.
     • ›Adds contextWindowSize configuration key for controlling context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›New concurrent runner for batch CLI execution, enabling parallel processing of multiple tasks.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     +6 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds Zed editor extension for the Qwen Code agent server.
     • ›Supports model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling.
     • ›Implements unified Web UI architecture with shared component library.
     • ›Clarifies output formats for non-interactive mode.
127. v0.9.0-nightly.20260130.0eb94a29 Jan 30, 2026 · issue -199

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, LSP support, extra_body for OpenAI providers, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-nightly.20260130.0eb94a29 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-nightly.20260130.0eb94a29

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request body parameters.
     • ›Adds contextWindowSize configuration key to control the model context window size.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds concurrent runner for batch CLI execution, enabling parallel multi-session workloads.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     +5 moreshow less

     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds Zed extension for Qwen Code agent server, extending IDE integration to Zed.
     • ›Adds model selection support through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling in the core request pipeline.
     • ›Implements unified UI architecture with shared component library for the web UI.
128. v0.9.0-preview.0 Jan 29, 2026 · issue -200

     Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, extra_body for OpenAI providers, LSP support, and a Zed extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0-preview.0

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
     • ›Adds concurrent runner for batch CLI execution, enabling parallel processing of multiple CLI tasks.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     +4 moreshow less

     • ›Adds Zed extension for Qwen Code agent server, enabling Zed IDE integration.
     • ›Adds model selection support through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling in the core.
     • ›Clarifies output formats for non-interactive mode.
129. v0.8.2-preview.2 Jan 29, 2026 · issue -200

     Qwen Code v0.8.2-preview.2 adds multi-modal input, concurrent batch execution, LSP support, Zed extension, and extra_body for OpenAI-compatible providers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.2-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.2-preview.2

     • ›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
     • ›Adds a concurrent runner for batch CLI execution, enabling parallelized non-interactive workloads.
     • ›Adds multi-modal input support (image, PDF, audio) across all content generators.
     • ›Adds experimental LSP (Language Server Protocol) support for code intelligence.
     • ›Adds a Zed extension for the Qwen Code agent server, bringing IDE companion support to Zed.
     +4 moreshow less

     • ›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
     • ›Clarifies output formats for non-interactive mode.
     • ›Supports model selection through ACP in the VS Code IDE companion.
     • ›Improves retry logic for 429 and 5xx error handling.
130. v0.8.2-preview.1 Jan 29, 2026 · issue -200

     Qwen Code v0.8.2-preview.1 adds subagent tracking fields, improved error messages for skills, and smarter 429/5xx retry logic.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.2-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.2-preview.1

     • ›Adds parentToolCallId and subagentType fields to ACP subagent tracking, enabling identification and lineage of subagent calls.
     • ›Improves error messaging when a skill is incorrectly invoked as a tool in core, making misconfiguration easier to diagnose.
     • ›Improves retry logic for 429 (rate-limit) and 5xx (server error) responses in core, reducing failed requests under load.
131. sdk-typescript-v0.1.4 Jan 27, 2026 · issue -202

     Qwen Code SDK TypeScript v0.1.4 adds Japanese and Portuguese locales, extensions detail command, plugin marketplace UI, and /bug in non-interactive mode.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.4

     └──▷ TRY IT
     Report a bug directly from a non-interactive CI/scripting session without dropping into the interactive REPL.
     copy

     $ qwen /bug

     Inspect details and validate a specific installed extension from the command line.
     copy

     $ qwen extensions detail <extension-name>

     • ›Adds /bug command availability to non-interactive mode.
     • ›Adds detail subcommand for extensions with improved extension validation via feat(extensions): add detail command.
     • ›Adds settings support for experimental skills under the experimental namespace in CLI settings.
     • ›Adds ui.showLineNumbers setting respected by the DiffRenderer for diff output.
     • ›Adds plugin selection UI for the Claude marketplace within the extensions workflow.
     +8 moreshow less

     • ›Adds skills and agents display to the extension list with i18n support.
     • ›Adds Japanese language support (ja) with fixed menu labels across other locales.
     • ›Adds Portuguese (pt-BR) language support with complete translations and refactored i18n architecture.
     • ›Adds user feedback dialog with temporary dismissal and persistent re-prompting behaviour.
     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Switches from tiktoken to API-reported token counts, removing the tiktoken dependency.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish the mode.
132. v0.8.1 Jan 27, 2026 · issue -202

     Qwen Code v0.8.1 adds Japanese and Portuguese (pt-BR) UI languages and surfaces skills and agents in the extension list.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.1

     • ›Adds Japanese language support to the UI, including corrected menu labels across other languages.
     • ›Adds Portuguese (pt-BR) language support with complete translations, alongside a refactored i18n architecture for improved language management.
     • ›Adds skills and agents display to the extension list, with i18n support.
133. v0.8.0 Jan 27, 2026 · issue -202

     Qwen Code v0.8.0 adds an extensions system with plugin marketplace UI, /bug in non-interactive mode, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0

     • ›Adds /bug command support to non-interactive (headless) mode.
     • ›Introduces an extensions system with a new detail subcommand and improved extension validation.
     • ›Adds a plugin selection UI for the Claude marketplace via the extensions feature.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Makes DiffRenderer respect the ui.showLineNumbers setting so diff output honors the line-number preference.
     +4 moreshow less

     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that state.
     • ›Switches token counting from the tiktoken local library to API-reported token counts.
     • ›Adds a VSCode IDE Companion release workflow.
134. v0.8.0-preview.4 Jan 27, 2026 · issue -202

     Qwen Code v0.8.0-preview.4 adds extension management commands, /bug in non-interactive mode, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-preview.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-preview.4

     • ›Adds /bug command support to non-interactive (headless) mode.
     • ›Adds an extensions subsystem with a detail command and improved extension validation.
     • ›Adds a plugin selection UI for the Claude marketplace within the extensions feature.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Adds ui.showLineNumbers setting support to the diff renderer so line numbers are respected in diffs.
     +2 moreshow less

     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that mode.
135. v0.8.0-preview.3 Jan 27, 2026 · issue -202

     Qwen Code v0.8.0-preview.3 adds an extensions system, /bug in non-interactive mode, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-preview.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-preview.3

     └──▷ TRY IT
     File a bug report directly from a CI pipeline or script without launching an interactive session.
     copy

     $ qwen /bug

     Inspect a specific installed extension to verify its metadata and configuration.
     copy

     $ qwen extensions detail <extension-name>

     • ›Adds /bug command availability in non-interactive (headless) mode.
     • ›Introduces an extensions system (Feat/extension) with a detail subcommand for inspecting extensions and improved extension validation.
     • ›Adds a plugin selection UI for the Claude marketplace within the extensions system.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Makes DiffRenderer respect the ui.showLineNumbers setting in diffs.
     +2 moreshow less

     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that state.
136. v0.8.0-nightly.20260127.eef9c49e Jan 27, 2026 · issue -202

     Qwen Code v0.8.0-nightly adds /bug command in non-interactive mode, an extensions system with plugin UI, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260127.eef9c49e https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260127.eef9c49e

     • ›Adds /bug command availability in non-interactive (headless/scripted) mode.
     • ›Adds detail subcommand for extensions and improves extension validation via the new extensions system (Feat/extension).
     • ›Adds plugin selection UI for the Claude marketplace within the extensions feature.
     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Redesigns the CLI welcome screen and settings dialog.
     +2 moreshow less

     • ›Makes the diff renderer respect the ui.showLineNumbers setting.
     • ›Uses dim colors for YOLO/auto-accept mode borders in the CLI.
137. v0.8.0-nightly.20260126.829ba9c4 Jan 26, 2026 · issue -203

     Qwen Code v0.8.0 adds a /bug command in non-interactive mode, an extension system with a detail subcommand, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260126.829ba9c4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260126.829ba9c4

     └──▷ TRY IT
     Inspect details and validation status of a loaded extension.
     copy

     $ qwen extensions detail <extension-name>

     • ›Adds /bug command availability in non-interactive (pipeline/scripted) mode.
     • ›Introduces an extensions subsystem (Feat/extension) with an extensions detail subcommand and improved extension validation.
     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers, enabling provider-specific network configuration at runtime.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Uses dim colors for YOLO/auto-accept mode borders, visually distinguishing that mode in the terminal UI.
     +1 moreshow less

     • ›Switches token counting from the local tiktoken dependency to API-reported token counts.
138. v0.8.0-nightly.20260125.829ba9c4 Jan 25, 2026 · issue -204

     Qwen Code v0.8.0 adds an extension system with detail command, /bug in non-interactive mode, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260125.829ba9c4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260125.829ba9c4

     • ›Adds /bug command availability in non-interactive mode.
     • ›Adds a new extensions subsystem (Feat/extension) with a detail command and improved extension validation.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that mode in the terminal UI.
139. v0.8.0-nightly.20260124.829ba9c4 Jan 24, 2026 · issue -205

     Qwen Code v0.8.0 adds /bug in non-interactive mode, an extensions system with a detail command, a redesigned CLI welcome screen, and runtime-aware Anthropic/OpenAI fetch options.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260124.829ba9c4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260124.829ba9c4

     └──▷ TRY IT
     Inspect the details and validation status of a specific installed extension.
     copy

     $ qwen-code extensions detail <extension-name>

     • ›Adds /bug command availability to non-interactive (headless) mode, enabling automated bug-report submission from scripts and CI pipelines.
     • ›Introduces an extensions system (Feat/extension) with an extensions detail subcommand and improved extension validation, letting practitioners inspect and verify installed extensions from the CLI.
     • ›Redesigns the CLI welcome screen and settings dialog for clearer first-run and configuration UX.
     • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers, allowing provider-specific network behaviour to be configured per runtime environment.
     • ›Uses dim colors for YOLO/auto-accept mode borders, giving a distinct visual cue when running in unattended approval mode.
     +1 moreshow less

     • ›Switches token counting from the local tiktoken dependency to API-reported counts, removing a native dependency and improving accuracy with model-native tokenization.
140. v0.8.0-preview.2 Jan 23, 2026 · issue -206

     Qwen Code v0.8.0-preview.2 adds extension management commands, /bug in non-interactive mode, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-preview.2

     • ›Adds /bug command support to non-interactive mode.
     • ›Adds extension management with a detail subcommand and improved extension validation.
     • ›Redesigns the CLI welcome screen and settings dialog.
     • ›Switches token counting to API-reported counts, removing the tiktoken dependency.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish the mode.
141. v0.8.0-nightly.20260123.011f3d23 Jan 23, 2026 · issue -206

     Qwen Code v0.8.0 adds a /bug command for non-interactive mode, an extensions system with a detail subcommand, and a redesigned CLI welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260123.011f3d23 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260123.011f3d23

     • ›Adds /bug command support to non-interactive (headless) mode, enabling automated bug reporting in CI/scripted workflows.
     • ›Introduces an extensions system (Feat/extension) with an extensions detail subcommand and improved extension validation.
     • ›Redesigns the CLI welcome screen and settings dialog with a refreshed layout.
     • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that state in the terminal UI.
142. v0.8.0-preview.1 Jan 22, 2026 · issue -207

     Qwen Code v0.8.0-preview.1 adds /bug in non-interactive mode, a redesigned welcome screen, and YOLO-mode visual cues.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-preview.1

     • ›Adds /bug command support to non-interactive mode, enabling automated bug-report submissions without an interactive session.
     • ›Redesigns the CLI welcome screen and settings dialog with an updated layout.
     • ›Uses dim border colors to visually distinguish YOLO/auto-accept mode from normal operation in the CLI.
143. v0.8.0-nightly.20260122.21b26a40 Jan 22, 2026 · issue -207

     Qwen Code v0.8.0-nightly adds /bug in non-interactive mode and redesigns the CLI welcome screen and settings dialog.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-nightly.20260122.21b26a40 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-nightly.20260122.21b26a40

     • ›Adds /bug command support to non-interactive mode, enabling automated bug reporting from scripts and pipelines.
     • ›Redesigns the CLI welcome screen and settings dialog with a new visual layout.
     • ›Uses dim colors for YOLO/auto-accept mode borders, making unattended-approval sessions visually distinct.
144. v0.8.0-preview.0 Jan 21, 2026 · issue -208

     Qwen Code v0.8.0-preview.0 adds /bug in non-interactive mode, dim YOLO-mode borders, and a redesigned welcome screen.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0-preview.0

     └──▷ TRY IT
     File a bug report from a CI script or automated pipeline without starting an interactive session.
     copy

     $ qwen --non-interactive /bug

     • ›Adds /bug command support to non-interactive mode, enabling automated bug-reporting workflows without an interactive session.
     • ›Redesigns the CLI welcome screen and settings dialog with an updated layout.
     • ›Adds dim colors for YOLO/auto-accept mode borders to visually distinguish that operating mode.
145. v0.7.2 Jan 20, 2026 · issue -209

     Qwen Code v0.7.2 adds experimental skills settings, a user feedback dialog, and improved QWEN.md file loading.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.2

     • ›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
     • ›Adds a user feedback dialog for submitting feedback directly from the CLI.
     • ›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
146. v0.7.2-preview.2 Jan 20, 2026 · issue -209

     Qwen Code v0.7.2-preview.2 adds experimental skills settings, a user feedback dialog, and improved QWEN.md file loading.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.2-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.2-preview.2

     • ›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
     • ›Adds a user feedback dialog for submitting feedback directly from the CLI.
     • ›Improves QWEN.md file loading by filtering out system files and limiting scope.
147. v0.7.2-preview.1 Jan 20, 2026 · issue -209

     Qwen Code v0.7.2-preview.1 adds experimental skills settings, improved QWEN.md loading, and a user feedback dialog.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.2-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.2-preview.1

     • ›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
     • ›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
     • ›Adds a user feedback dialog to the CLI interface.
148. v0.7.1-preview.0 Jan 20, 2026 · issue -209

     Qwen Code v0.7.1-preview.0 adds experimental skills settings, improved QWEN.md loading, and a user feedback dialog.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.1-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.1-preview.0

     • ›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
     • ›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
     • ›Adds a user feedback dialog to the CLI interface.
149. v0.7.2-preview.0 Jan 19, 2026 · issue -210

     Qwen Code v0.7.2-preview.0 adds experimental skills settings and improves QWEN.md file loading scope control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.2-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.2-preview.0

     • ›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
     • ›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
150. v0.7.1-nightly.20260119.0681c718 Jan 19, 2026 · issue -210

     Qwen Code v0.7.1-nightly adds settings support for experimental skills in the CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.1-nightly.20260119.0681c718 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.1-nightly.20260119.0681c718

     • ›Adds settings support for experimental skills via the CLI, enabling configuration of opt-in skill features.
151. v0.7.1-nightly.20260118.0681c718 Jan 18, 2026 · issue -211

     Qwen Code v0.7.1-nightly adds settings support for experimental skills in the CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.1-nightly.20260118.0681c718 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.1-nightly.20260118.0681c718

     • ›Adds settings support for experimental skills via the CLI, enabling configuration of opt-in skill features.
152. v0.7.1-nightly.20260117.0681c718 Jan 17, 2026 · issue -212

     Qwen Code v0.7.1-nightly adds settings support for experimental skills in the CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.1-nightly.20260117.0681c718 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.1-nightly.20260117.0681c718

     • ›Adds settings support for experimental skills via the CLI, enabling configuration of opt-in skill features.
153. v0.7.0 Jan 14, 2026 · issue -215

     Qwen Code v0.7.0 adds multi-provider model config, an experimental /skills command, custom HTTP headers, Jupyter Notebook support, and sandbox customization.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0

     └──▷ TRY IT
     Load skills from a custom directory and iterate on them without restarting — useful when rapidly prototyping agent behaviors.
     copy

     $ /skills

     • ›Adds multi-provider model configuration support, letting users configure and switch between models from multiple providers in a single setup.
     • ›Adds experimental /skills command with hot reload, enabling practitioners to define and iterate on custom agent skills without restarting the CLI.
     • ›Adds custom HTTP headers support for API requests, allowing per-request header injection to downstream model endpoints.
     • ›Adds optional timeout for foreground shell commands, giving users control over runaway command execution.
     • ›Supports Jupyter Notebook (.ipynb) file code selection, extending context-gathering to notebook cells.
     +3 moreshow less

     • ›Adds sandbox environment customization, allowing practitioners to tailor the sandboxed execution context.
     • ›Changes selection order of user settings vs. workspace settings, affecting which config takes precedence when both are present.
     • ›Adds an integration guide for JetBrains IDEs, documenting how to connect Qwen Code as a companion.
154. v0.7.0-preview.1 Jan 14, 2026 · issue -215

     Qwen Code v0.7.0-preview.1 adds multi-provider model config, experimental /skills command, custom HTTP headers, sandbox customization, and Jupyter Notebook support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-preview.1

     └──▷ TRY IT
     Use the new /skills command during a session to list or hot-reload agent skills without restarting the CLI.
     copy

     $ /skills

     • ›Adds experimental /skills command with hot reload support for managing agent skills at runtime.
     • ›Adds multi-provider model configuration support, enabling multiple LLM providers to be configured simultaneously.
     • ›Adds custom HTTP headers support for outbound API requests.
     • ›Adds an optional timeout for foreground shell commands.
     • ›Supports Jupyter Notebook (.ipynb) file code selection in the IDE companion.
     +3 moreshow less

     • ›Adds sandbox environment customization capability.
     • ›Changes the selection order of user settings versus workspace settings.
     • ›Adds integration guide for JetBrains IDEs.
155. v0.7.0-nightly.20260114.d20f2a41 Jan 14, 2026 · issue -215

     Qwen Code v0.7.0-nightly adds multi-provider model config, /skills command, custom headers, sandbox customization, and Jupyter Notebook support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260114.d20f2a41 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260114.d20f2a41

     • ›Adds multi-provider model configuration support, enabling multiple AI provider backends to be configured simultaneously.
     • ›Adds experimental /skills command with hot reload for dynamic skill management at runtime.
     • ›Adds custom HTTP headers support for API requests.
     • ›Adds optional timeout configuration for foreground shell commands.
     • ›Adds sandbox environment customization capability.
     +3 moreshow less

     • ›Supports Jupyter Notebook (.ipynb) file code selection.
     • ›Modifies selection order precedence between user settings and workspace settings.
     • ›Adds JetBrains IDE integration guide.
156. sdk-typescript-v0.1.3 Jan 13, 2026 · issue -216

     Qwen Code SDK TypeScript v0.1.3 adds /skills command, Jupyter Notebook support, custom headers, shell timeouts, and sandbox customization.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.3

     └──▷ TRY IT
     Invoke the new experimental skills command interactively to load or hot-reload agent skills during a session.
     copy

     $ /skills

     • ›Adds experimental /skills command with hot reload support for managing agent skills at runtime.
     • ›Adds optional timeout configuration for foreground shell commands.
     • ›Adds custom HTTP headers support for API requests.
     • ›Supports Jupyter Notebook (.ipynb) file code selection.
     • ›Enables customization of the sandbox environment.
     +1 moreshow less

     • ›Adds integration guide for JetBrains IDEs.
157. v0.7.0-preview.0 Jan 13, 2026 · issue -216

     Qwen Code v0.7.0-preview.0 adds multi-provider model config, an experimental /skills command with hot reload, Jupyter Notebook support, custom headers, and sandbox customization.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-preview.0

     └──▷ TRY IT
     List or manage your loaded skills mid-session without restarting the CLI.
     copy

     $ /skills

     • ›Adds experimental /skills command with hot reload, enabling in-session skill management without restarting the CLI.
     • ›Adds multi-provider model configuration support, allowing multiple AI providers to be defined and selected from a single config.
     • ›Supports Jupyter Notebook (.ipynb) file code selection, enabling context-aware interactions with notebook cells.
     • ›Adds custom HTTP headers support for outbound API requests.
     • ›Adds optional timeout configuration for foreground shell commands.
     +2 moreshow less

     • ›Enables customization of the sandbox environment.
     • ›Changes the selection order of user settings versus workspace settings, giving workspace settings higher or lower precedence.
158. v0.7.0-nightly.20260113.09196c6e Jan 13, 2026 · issue -216

     Qwen Code v0.7.0 adds multi-provider model configuration support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260113.09196c6e https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260113.09196c6e

     • ›Adds multi-provider models config support, enabling configuration of multiple model providers in a single setup.
     • ›Changes the selection order of user settings versus workspace settings, giving workspace settings a new resolution priority.
159. sdk-typescript-v0.1.2 Jan 12, 2026 · issue -217

     Qwen Code SDK TypeScript v0.1.2 adds German UI, a Java SDK, stable --acp flag, multi-provider model config, and direct /approval-mode arguments.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.2

     └──▷ TRY IT
     Run Qwen Code with the now-stable Agent Communication Protocol flag instead of the old experimental one.
     copy

     $ qwen --acp

     • ›Graduates --experimental-acp to the stable --acp flag for Agent Communication Protocol support.
     • ›Adds direct argument support for the /approval-mode command, allowing approval mode to be set inline without a follow-up prompt.
     • ›Adds multi-provider model configuration support, enabling multiple AI provider backends to be defined and selected from config.
     • ›Adds a Java SDK (Feat/javasdk) for programmatic integration with Qwen Code.
     • ›Adds German (de) language support via the i18n system.
     +1 moreshow less

     • ›Changes the selection order of user settings vs. workspace settings, giving workspace settings higher precedence.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by --acp; scripts or configs using --experimental-acp must be updated.
160. v0.7.0-nightly.20260112.bde31d12 Jan 12, 2026 · issue -217

     Qwen Code v0.7.0 adds multi-provider model configuration and revised user/workspace settings selection order.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260112.bde31d12 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260112.bde31d12

     • ›Adds multi-provider models config support, enabling configuration of multiple AI providers within a single Qwen Code setup.
161. v0.7.0-nightly.20260111.bde31d12 Jan 11, 2026 · issue -218

     Qwen Code v0.7.0 adds multi-provider model configuration and changes user/workspace settings selection order.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260111.bde31d12 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260111.bde31d12

     • ›Adds multi-provider models config support, enabling multiple AI provider backends to be configured simultaneously.
     • ›Changes the selection order of user settings and workspace settings resolution.
162. v0.7.0-nightly.20260110.bde31d12 Jan 10, 2026 · issue -219

     Qwen Code v0.7.0 adds multi-provider model configuration and changes workspace settings selection order.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260110.bde31d12 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260110.bde31d12

     • ›Adds multi-provider models config support, enabling multiple AI provider backends to be configured simultaneously.
     • ›Changes the selection order of user settings and workspace settings to give workspace settings proper precedence.
163. v0.7.0-nightly.20260109.f776075a Jan 9, 2026 · issue -220

     Qwen Code v0.7.0 adds multi-provider model configuration support and changes user vs. workspace settings precedence.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260109.f776075a https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260109.f776075a

     • ›Adds multi-provider model configuration support, allowing multiple AI providers to be configured simultaneously.
     • ›Changes the selection order of user settings and workspace settings, giving workspace settings a different precedence relative to user settings.
164. v0.7.0-nightly.20260108.f776075a Jan 8, 2026 · issue -221

     Qwen Code v0.7.0 adds multi-provider model configuration and changes user vs. workspace settings selection order.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0-nightly.20260108.f776075a https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0-nightly.20260108.f776075a

     • ›Adds multi-provider models config support, allowing configuration of multiple model providers within a single Qwen Code setup.
     • ›Changes the selection order between user settings and workspace settings, altering which takes precedence during resolution.
     └──▷ BREAKING ON UPGRADE

     • !The selection order of user settings and workspace settings has changed; setups that relied on the previous precedence order may behave differently after upgrading.
165. v0.6.1 Jan 7, 2026 · issue -222

     Qwen Code v0.6.1 graduates --acp to stable, adds German locale, Java SDK support, and direct /approval-mode arguments.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.1

     └──▷ TRY IT
     Use the now-stable ACP flag to run Qwen Code in Agent Communication Protocol mode without the experimental prefix.
     copy

     $ qwen --acp

     Set approval mode directly from the command prompt without navigating a menu, useful for scripted or quick-switch workflows.
     copy

     $ /approval-mode auto

     • ›Graduates --experimental-acp to the stable --acp flag for Agent Communication Protocol support.
     • ›Adds direct argument support for the /approval-mode command, allowing approval mode to be set inline.
     • ›Adds German language support to the i18n system.
     • ›Auto-detects LLM output language from the system locale.
     • ›Adds Java SDK support (Feat/javasdk).
     +1 moreshow less

     • ›Supports merging ChatCompletionContentPart and adds filterEmptyMessages for cleaner message handling.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by the stable --acp flag; scripts or configs using --experimental-acp must be updated.
166. v0.6.1-nightly.20260107.f6771c08 Jan 7, 2026 · issue -222

     Qwen Code v0.6.1 graduates --acp to stable, adds Java SDK, German locale, and direct /approval-mode arguments.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.1-nightly.20260107.f6771c08 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.1-nightly.20260107.f6771c08

     └──▷ TRY IT
     Run Qwen Code with the now-stable ACP flag instead of the old experimental one.
     copy

     $ qwen --acp

     Set approval mode directly inline with the /approval-mode command instead of waiting for a prompt.
     copy

     $ /approval-mode auto

     • ›Graduates --experimental-acp to the stable --acp flag for Agent Communication Protocol support.
     • ›Adds direct argument support for the /approval-mode command, allowing approval mode to be set inline rather than via a follow-up prompt.
     • ›Adds a Java SDK (Feat/javasdk) for programmatic integration with Qwen Code.
     • ›Supports merging ChatCompletionContentPart and adds filterEmptyMessages for OpenAI-compatible content generation.
     • ›Auto-detects LLM output language from the system locale.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by --acp; scripts or configs using --experimental-acp must be updated.
167. v0.6.1-nightly.20260107.2c285394 Jan 7, 2026 · issue -222

     Qwen Code v0.6.1 graduates --acp to stable, adds German locale, Java SDK support, and direct /approval-mode arguments.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.1-nightly.20260107.2c285394 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.1-nightly.20260107.2c285394

     └──▷ TRY IT
     Run Qwen Code with the now-stable ACP flag instead of the old experimental one.
     copy

     $ qwen --acp

     Set approval mode directly from the slash command without a secondary prompt.
     copy

     $ /approval-mode auto

     • ›Graduates --experimental-acp to the stable --acp flag for Agent Communication Protocol support.
     • ›Adds direct argument support for the /approval-mode command, allowing the mode to be set inline rather than via a follow-up prompt.
     • ›Adds German language support, joining the existing locale set for auto-detected LLM output language.
     • ›Auto-detects LLM output language from the system locale, aligning response language to the user's OS setting.
     • ›Adds a Java SDK (Feat/javasdk) enabling Java-based integration with Qwen Code.
     +1 moreshow less

     • ›Supports merging ChatCompletionContentPart entries and filters empty messages in chat completion requests.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by --acp; any scripts or configs referencing --experimental-acp must be updated.
168. v0.6.0-preview.3 Jan 7, 2026 · issue -222

     Qwen Code v0.6.0-preview.3 graduates --acp to stable, adds German locale, Java SDK, and auto-detects LLM output language from system locale.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-preview.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-preview.3

     └──▷ TRY IT
     Run Qwen Code with the now-stable ACP flag instead of the old experimental one.
     copy

     $ qwen --acp

     • ›Graduates --acp flag from experimental (--experimental-acp) to stable for Agent Communication Protocol support.
     • ›Auto-detects LLM output language from the system locale, aligning model responses to the user's OS language.
     • ›Adds German language support to the i18n system.
     • ›Adds a Java SDK (Feat/javasdk) for programmatic integration with Qwen Code.
     • ›Supports merging ChatCompletionContentPart entries and filters empty messages in chat completion requests.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by --acp; any scripts or configs using --experimental-acp must be updated.
169. v0.6.0-nightly.20260107.b95d9a8d Jan 7, 2026 · issue -222

     Qwen Code v0.6.0-nightly graduates --acp to stable, adds German locale, Java SDK, and merges ChatCompletionContentPart support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260107.b95d9a8d https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260107.b95d9a8d

     └──▷ TRY IT
     Use the now-stable ACP flag instead of the former experimental flag to enable Agent Communication Protocol.
     copy

     $ qwen-code --acp

     • ›Graduates --experimental-acp to the stable --acp flag for Agent Communication Protocol support.
     • ›Adds Java SDK support for Qwen Code integration.
     • ›Supports merging ChatCompletionContentPart objects and filters empty messages in API requests.
     • ›Auto-detects LLM output language from system locale.
     └──▷ BREAKING ON UPGRADE

     • !The --experimental-acp flag is replaced by --acp; scripts or configs using --experimental-acp will need to be updated.
170. v0.6.0-nightly.20260106.b19bb6cb Jan 6, 2026 · issue -223

     Qwen Code v0.6.0-nightly adds German locale support and auto-detects LLM output language from system locale.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260106.b19bb6cb https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260106.b19bb6cb

     • ›Adds German language support for the CLI interface.
     • ›Auto-detects LLM output language from the system locale, so responses match the user's OS language without manual configuration.
     • ›Supports merging ChatCompletionContentPart entries and filters empty messages in API request handling.
171. v0.6.0-nightly.20260105.105ad743 Jan 5, 2026 · issue -224

     Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260105.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260105.105ad743

     • ›Auto-detects the LLM output language from the system locale, eliminating the need to manually configure response language.
     • ›Supports merging ChatCompletionContentPart objects and adds filtering of empty messages in API content handling.
172. v0.6.0-nightly.20260104.105ad743 Jan 4, 2026 · issue -225

     Qwen Code v0.6.0-nightly adds system-locale LLM language auto-detection and ChatCompletionContentPart merging.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260104.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260104.105ad743

     • ›Supports merging ChatCompletionContentPart objects and filters empty messages from chat completion requests.
     • ›Auto-detects the LLM output language from the system locale, removing the need to manually configure response language.
173. v0.6.0-nightly.20260103.105ad743 Jan 3, 2026 · issue -226

     Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and merges ChatCompletionContentPart support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260103.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260103.105ad743

     • ›Supports merging ChatCompletionContentPart objects and filters empty messages in API requests.
     • ›Auto-detects LLM output language from the system locale, removing the need to manually configure response language.
174. v0.6.0-nightly.20260102.105ad743 Jan 2, 2026 · issue -227

     Qwen Code v0.6.0-nightly adds system-locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260102.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260102.105ad743

     • ›Supports merging ChatCompletionContentPart objects and filters empty messages in API content handling.
     • ›Auto-detects the preferred LLM output language from the system locale, removing the need to manually configure language preference.
     • ›Adds Russian translation strings for internationalized UI surfaces.
175. v0.6.0-nightly.20260101.105ad743 Jan 1, 2026 · issue -228

     Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20260101.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20260101.105ad743

     • ›Adds support for merging ChatCompletionContentPart items and filters empty messages in chat completion handling.
     • ›Auto-detects LLM output language from the system locale, eliminating the need to manually configure response language.
176. v0.6.0-preview.2 Dec 31, 2025 · issue -229

     Qwen Code v0.6.0-preview.2 adds locale-based LLM output language detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-preview.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-preview.2

     • ›Supports merging ChatCompletionContentPart payloads and filters empty messages for cleaner API interactions.
     • ›Auto-detects LLM output language from the system locale, eliminating the need to manually configure response language.
177. v0.6.0-nightly.20251231.105ad743 Dec 31, 2025 · issue -229

     Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251231.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251231.105ad743

     • ›Auto-detects the desired LLM output language from the system locale, removing the need to manually configure response language.
     • ›Supports merging ChatCompletionContentPart entries and filters empty messages from API payloads.
     • ›Adds Russian locale translation strings for i18n coverage.
178. v0.6.0-nightly.20251230.105ad743 Dec 30, 2025 · issue -230

     Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251230.105ad743 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251230.105ad743

     • ›Auto-detects the system locale to set the LLM output language, eliminating manual language configuration.
     • ›Supports merging ChatCompletionContentPart objects and filters empty messages from chat completion requests.
179. sdk-typescript-v0.1.1 Dec 29, 2025 · issue -231

     Qwen Code SDK v0.1.1 adds Anthropic/Gemini providers, VSCode extension, /resume command, chat recording, Skills, and terminal bell settings.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.1

     └──▷ TRY IT
     Switch between sessions interactively without leaving the CLI — helpful when managing multiple parallel tasks.
     copy

     $ /resume

     • ›Adds /resume slash command to switch between sessions from the CLI UI.
     • ›Adds --resume and --continue CLI options with -r and -C short aliases for session management.
     • ›Adds gitCoAuthor setting to settings.json to control git co-author tagging in commits.
     • ›Adds chat recording toggle via CLI flag and settings, enabling or disabling session recording.
     • ›Adds terminal bell setting to enable or disable audio notifications.
     +12 moreshow less

     • ›Adds /compress and /summary commands for use in non-interactive mode and ACP.
     • ›Adds Anthropic provider with normalized auth and environment config, enabling Claude models as a backend.
     • ›Adds Gemini provider and removes legacy Google OAuth, with tuned generation parameters.
     • ›Adds experimental Skills feature for extending agent capabilities.
     • ›Implements VSCode Extension with IDE companion support, including clickable bash tool call input/output parts that open as temporary files and context display.
     • ›Adds channel field support in client identification for API requests.
     • ›IDE companion discovery switches to ~/.qwen/ide lock files.
     • ›Adds ACP usage metadata tracking and ACP authentication update messaging.
     • ›Adds Russian language (i18n) support, with auto-detection of LLM output language from system locale.
     • ›Removes vertical borders from the input prompt UI for easier copy/paste.
     • ›Shows session resume command on exit so users can continue from where they left off.
     • ›Bundles CLI into the VSCode release package and into the SDK package, with separate CLI and SDK E2E tests.
     └──▷ BREAKING ON UPGRADE

     • !IDE companion discovery now uses ~/.qwen/ide lock files instead of the previous mechanism — existing IDE companion setups may need to reconnect.
180. v0.6.0-nightly.20251229.2bc80795 Dec 29, 2025 · issue -231

     Qwen Code v0.6.0-nightly now auto-detects LLM output language from the system locale.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251229.2bc80795 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251229.2bc80795

     • ›Auto-detects the system locale to set LLM output language automatically, removing the need for manual language configuration.
     • ›Adds Russian translation strings to the i18n layer.
181. v0.6.0-nightly.20251228.2bc80795 Dec 28, 2025 · issue -232

     Qwen Code v0.6.0-nightly adds automatic LLM output language detection from the system locale.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251228.2bc80795 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251228.2bc80795

     • ›Automatically detects the system locale to set the LLM output language, so responses match the user's OS language without manual configuration.
     • ›Expands Russian translation with new strings for broader i18n coverage.
182. v0.6.0-nightly.20251227.2bc80795 Dec 27, 2025 · issue -233

     Qwen Code v0.6.0-nightly adds automatic LLM output language detection from the system locale.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251227.2bc80795 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251227.2bc80795

     • ›Auto-detects the system locale to set the LLM output language automatically, removing the need for manual language configuration.
183. v0.6.0 Dec 26, 2025 · issue -234

     Qwen Code v0.6.0 adds Gemini and Anthropic providers, an experimental Skills feature, and /compress & /summary commands for non-interactive mode.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0

     • ›Adds /compress and /summary commands for non-interactive and ACP usage.
     • ›Adds Gemini as a supported LLM provider (removes legacy Google OAuth).
     • ›Adds Anthropic as a supported LLM provider, with normalized auth/env config and centralized logging.
     • ›Adds an experimental Skills feature.
     • ›VS Code IDE companion now shows a context-remaining indicator.
     +1 moreshow less

     • ›VS Code IDE companion bash tool-call input/output panels are now clickable to open content in a temporary file.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth support has been removed as part of the Gemini provider addition.
184. v0.6.0-nightly.20251226.17eb20c1 Dec 26, 2025 · issue -234

     Qwen Code v0.6.0 adds Gemini and Anthropic providers, experimental Skills, and /compress & /summary commands for non-interactive mode.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251226.17eb20c1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251226.17eb20c1

     • ›Adds /compress and /summary commands for non-interactive and ACP (Agent Control Protocol) usage.
     • ›Adds Gemini as a provider, with legacy Google OAuth removed and tuned generation settings.
     • ›Adds Anthropic as a provider with normalized auth/environment config and centralized logging.
     • ›Adds an experimental Skills feature.
     • ›VS Code IDE companion now displays a context-remaining indicator.
     +1 moreshow less

     • ›VS Code IDE companion bash tool-call input/output parts are now clickable to open in a temporary file.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth support has been removed; users relying on it must migrate to the new Gemini provider authentication.
185. v0.6.0-nightly.20251226.3787e955 Dec 26, 2025 · issue -234

     Qwen Code v0.6.0-nightly adds Gemini and Anthropic provider support plus an experimental Skills feature.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251226.3787e955 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251226.3787e955

     • ›Adds Gemini provider support, removing legacy Google OAuth in favor of the new provider model.
     • ›Adds Anthropic provider support with normalized auth/env config and centralized logging.
     • ›Adds experimental Skills feature for extended agent capabilities.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth has been removed; users relying on Google OAuth authentication must migrate to the new Gemini provider config.
186. v0.6.0-preview.1 Dec 25, 2025 · issue -235

     Qwen Code v0.6.0-preview.1 adds Gemini and Anthropic providers plus an experimental Skills feature.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-preview.1

     • ›Adds Anthropic as a provider, with normalized auth/env config and centralized logging.
     • ›Adds Gemini as a provider, removing legacy Google OAuth, with tuned generation settings.
     • ›Introduces an experimental Skills feature.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth has been removed as part of the Gemini provider addition.
187. v0.6.0-nightly.20251225.9f65bd3b Dec 25, 2025 · issue -235

     Qwen Code v0.6.0-nightly adds a Gemini provider integration and an experimental Skills feature.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251225.9f65bd3b https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251225.9f65bd3b

     • ›Adds Gemini as a supported AI provider, replacing legacy Google OAuth authentication.
     • ›Introduces an experimental Skills feature for extended agent capabilities.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth support has been removed; users relying on Google OAuth must switch to the new Gemini provider.
188. v0.6.0-preview.0 Dec 24, 2025 · issue -236

     Qwen Code v0.6.0-preview.0 adds Gemini as a provider and removes legacy Google OAuth.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-preview.0

     • ›Adds Gemini as a supported LLM provider, replacing legacy Google OAuth authentication.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth support has been removed; existing setups relying on Google OAuth will need to migrate to the new Gemini provider authentication.
189. v0.6.0-nightly.20251224.bc2a7efc Dec 24, 2025 · issue -236

     Qwen Code v0.6.0-nightly adds Gemini as a provider and removes legacy Google OAuth.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0-nightly.20251224.bc2a7efc https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0-nightly.20251224.bc2a7efc

     • ›Adds Gemini as a supported LLM provider, enabling Qwen Code users to route requests through Gemini models.
     • ›Removes legacy Google OAuth authentication in favour of the new Gemini provider integration.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth support has been removed; users relying on Google OAuth for authentication must migrate to the new Gemini provider.
190. v0.5.1-preview.1 Dec 24, 2025 · issue -236

     Qwen Code v0.5.1-preview.1 adds Gemini as a provider and removes legacy Google OAuth.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-preview.1

     • ›Adds Gemini as a supported LLM provider and removes legacy Google OAuth authentication.
     • ›Adds a link to Gemini CLI Desktop for users who prefer a desktop UI over the CLI.
     └──▷ BREAKING ON UPGRADE

     • !Legacy Google OAuth is removed; any working setup relying on Google OAuth for authentication will break on upgrade.
191. v0.5.1 Dec 19, 2025 · issue -241

     Qwen Code v0.5.1 adds chat recording toggle, a /resume slash command, and exposes gitCoAuthor in settings.json

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1

     └──▷ USE IT
     Enable git co-author attribution so AI-assisted commits credit the model automatically.
     json copy

     {
       "gitCoAuthor": true
     }

     • ›Adds gitCoAuthor setting to settings.json to control git co-author attribution in commits.
     • ›Adds /resume slash command in the CLI to switch between sessions interactively.
     • ›Adds chat recording toggle accessible via CLI flags and the settings UI.
     • ›IDE companion discovery switches to lock files under ~/.qwen/ide, changing where the tool looks for IDE connections.
     └──▷ BREAKING ON UPGRADE

     • !IDE companion discovery now uses ~/.qwen/ide lock files instead of the previous location; existing IDE companion setups may fail to connect until updated.
192. v0.5.1-preview.0 Dec 19, 2025 · issue -241

     Qwen Code v0.5.1 adds chat recording toggle, /resume slash command, and gitCoAuthor setting in settings.json

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-preview.0

     └──▷ USE IT
     Attribute AI-assisted commits to the model by setting gitCoAuthor in your Qwen Code settings.
     json copy

     {
       "gitCoAuthor": true
     }

     • ›Adds gitCoAuthor setting to settings.json to control git co-author attribution in commits.
     • ›Adds /resume slash command in the CLI UI to switch between sessions interactively.
     • ›Adds chat recording toggle available via CLI flag and settings.
     • ›IDE companion discovery switches to ~/.qwen/ide lock files for locating running IDE instances.
193. sdk-typescript-v0.1.1-nightly.20251219.e4468cfc Dec 19, 2025 · issue -241

     Qwen Code SDK gains a VSCode extension, session-resume command, chat recording toggle, Russian i18n, and a terminal bell setting.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch sdk-typescript-v0.1.1-nightly.20251219.e4468cfc https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout sdk-typescript-v0.1.1-nightly.20251219.e4468cfc

     └──▷ TRY IT
     Resume a previous Qwen Code session by name without re-entering the full chat history manually.
     copy

     $ /resume

     Enable git co-author attribution and disable the terminal bell in your personal settings.
     json copy

     {
       "gitCoAuthor": true,
       "terminalBell": false
     }

     • ›Adds gitCoAuthor setting to settings.json to control git co-author behaviour and exposes it in documentation.
     • ›Adds /resume slash command to switch between saved sessions from within the CLI UI.
     • ›Adds chat recording toggle via CLI flag and the settings.json settings interface; recording is disabled in test runs.
     • ›Adds channel field support in client identification requests.
     • ›Adds terminal bell setting to settings.json to enable or disable audio notifications.
     +6 moreshow less

     • ›New VSCode Extension implementation bundled into the VSCode release package, including IDE companion with authentication and completion menu support.
     • ›Shows the session-resume command on CLI exit so users can quickly re-enter a previous session.
     • ›Adds Russian (ru) language support via the /language command.
     • ›Adds ACP usage metadata reporting and an ACP authenticate update message.
     • ›Removes input-prompt vertical borders in the terminal UI for easier copy/paste.
     • ›Adds comprehensive MCP Quick Start guides and examples to documentation.
194. v0.5.1-nightly.20251219.d07ae35c Dec 19, 2025 · issue -241

     Qwen Code v0.5.1 adds chat recording toggle, /resume session switching, and gitCoAuthor settings exposure.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-nightly.20251219.d07ae35c https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-nightly.20251219.d07ae35c

     └──▷ TRY IT
     Resume a previous Qwen Code session quickly from the command line using the new short alias.
     copy

     $ qwen -r

     Set a git co-author for all AI-assisted commits without touching the CLI each time.
     json copy

     {
       "gitCoAuthor": "Pair Partner <[email protected]>"
     }

     • ›Adds gitCoAuthor setting to settings.json, letting users configure co-author attribution for git commits directly from the settings file.
     • ›Adds /resume slash command in the CLI to switch between saved sessions interactively.
     • ›Adds -r and -C as short aliases for the --resume and --continue CLI options.
     • ›Adds a chat recording toggle accessible via both the CLI and the settings UI, with recording disabled automatically during tests.
195. v0.5.1-nightly.20251218.8106a6b0 Dec 18, 2025 · issue -242

     Qwen Code v0.5.1 adds a /resume command for session switching, a chat recording toggle, and a gitCoAuthor setting.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-nightly.20251218.8106a6b0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-nightly.20251218.8106a6b0

     └──▷ USE IT
     Persist a git co-author on all commits made through Qwen Code without typing it each time.
     json copy

     {
       "gitCoAuthor": "Jane Doe <[email protected]>"
     }

     Resume a previous session mid-conversation to continue work without losing context.
     copy

     $ /resume

     • ›Adds gitCoAuthor setting to settings.json to configure git co-author attribution in commits.
     • ›Adds /resume slash command to switch between existing sessions from the CLI.
     • ›Adds a chat recording toggle accessible via CLI and the settings UI.
196. v0.5.1-nightly.20251217.0a39c912 Dec 17, 2025 · issue -243

     Qwen Code v0.5.1 adds a /resume command for session switching, chat recording toggle, and a gitCoAuthor setting.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-nightly.20251217.0a39c912 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-nightly.20251217.0a39c912

     └──▷ USE IT
     Attribute AI assistance in git commits by enabling co-author tagging in your settings file.
     json copy

     {
       "gitCoAuthor": true
     }

     Resume a previous session mid-workflow without restarting the CLI.
     copy

     $ /resume

     • ›Adds gitCoAuthor setting to settings.json to control git co-author attribution in commits.
     • ›Adds /resume slash command to switch between sessions from the CLI.
     • ›Adds a chat recording toggle accessible via CLI and settings UI, allowing recording to be enabled or disabled per session.
197. v0.5.1-nightly.20251216.52faa0da Dec 16, 2025 · issue -244

     Qwen Code v0.5.1 adds a chat recording toggle accessible via CLI and settings.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.1-nightly.20251216.52faa0da https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.1-nightly.20251216.52faa0da

     • ›Adds a chat recording toggle available via both CLI flag and the settings interface, with recording automatically disabled during tests.
198. v0.5.0 Dec 13, 2025 · issue -247

     Qwen Code v0.5.0 adds Russian UI, terminal bell notifications, session resume hints, and bundles the CLI into the VSCode extension.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.0

     • ›Adds a terminal bell setting to enable or disable audio notifications for completed operations.
     • ›Shows the session resume command on exit so users can return to a previous conversation.
     • ›Adds Russian language support to the UI.
     • ›Bundles the CLI directly into the VSCode extension release package, removing the need for a separate CLI install.
     └──▷ BREAKING ON UPGRADE

     • !Removes 'corgi mode' — any configuration or workflow relying on it will no longer function after upgrading.
199. v0.5.0-preview.0 Dec 13, 2025 · issue -247

     Qwen Code v0.5.0-preview.0 adds Russian language support and an ACP authentication update message.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.0-preview.0

     • ›Adds Russian language support via the /language command for localized CLI interactions.
     • ›Adds an ACP authenticate update message to surface authentication status changes.
200. v0.4.1 Dec 12, 2025 · issue -248

     Qwen Code v0.4.1 adds a VSCode extension, ACP usage metadata, and a channel field for client identification.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.1

     • ›Adds a channel field for client identification in requests.
     • ›New VSCode Extension implementation, enabling IDE-integrated Qwen Code workflows.
     • ›Adds ACP usage metadata support for tracking agent-client-protocol consumption.
     • ›Removes vertical borders from the input prompt UI for easier copy/paste.
201. v0.5.0-nightly.20251212.8b29dd13 Dec 12, 2025 · issue -248

     Qwen Code v0.5.0 adds a VSCode Extension and ACP usage metadata tracking alongside UI copy/paste improvements.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.0-nightly.20251212.8b29dd13 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.5.0-nightly.20251212.8b29dd13

     • ›Adds a channel field to client identification headers/payloads for tracking request sources.
     • ›New VSCode Extension implementation connects Qwen Code to the IDE as a companion.
     • ›Adds ACP usage metadata reporting to track token/usage telemetry.
     • ›Removes vertical borders from the input prompt UI, making it easier to copy/paste multi-line content.
202. v0.4.1-nightly.20251212.58d3a9c2 Dec 12, 2025 · issue -248

     Qwen Code v0.4.1-nightly adds a VSCode extension and ACP usage metadata support alongside UI copy/paste improvements.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.1-nightly.20251212.58d3a9c2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.1-nightly.20251212.58d3a9c2

     • ›Adds ACP usage metadata tracking via the Feat/acp usage metadata feature.
     • ›New VSCode Extension implementation brings Qwen Code capabilities directly into the editor.
     • ›Removes vertical borders from the input prompt UI, making it easier to copy/paste multi-line content.
203. v0.4.1-nightly.20251211.a02c4b27 Dec 11, 2025 · issue -249

     Qwen Code v0.4.1-nightly adds a VSCode extension and a cleaner input prompt UI for easier copy/paste.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.1-nightly.20251211.a02c4b27 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.1-nightly.20251211.a02c4b27

     • ›Adds a VSCode Extension, bringing Qwen Code capabilities directly into the editor.
     • ›Removes vertical borders from the input prompt UI, making it easier to copy and paste prompts.
204. v0.4.0 Dec 6, 2025 · issue -254

     Qwen Code v0.4.0 adds a TypeScript SDK, DeepSeek V3.2 thinking mode, SDK-controlled MCP custom tools, and session-level conversation history.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0

     • ›Adds a basic TypeScript SDK, enabling programmatic integration with Qwen Code from TypeScript applications.
     • ›Integrates DeepSeek V3.2 Thinking Mode, surfacing chain-of-thought reasoning within the CLI.
     • ›Supports custom tools via SDK-controlled MCP servers, allowing callers to supply their own tool definitions through the SDK.
     • ›Introduces session-level conversation history management, giving users control over conversation context within a session.
     └──▷ BREAKING ON UPGRADE

     • !The /quit-confirm flow has been removed; any workflow or scripting that relied on the /quit-confirm command will break on upgrade.
205. v0.4.0-nightly.20251206.ab228c68 Dec 6, 2025 · issue -254

     Qwen Code v0.4.0 adds a TypeScript SDK, DeepSeek V3.2 thinking mode, custom MCP tool support, and session-level conversation history management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0-nightly.20251206.ab228c68 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0-nightly.20251206.ab228c68

     • ›Adds a basic TypeScript SDK (feat: basic TypeScript SDK) for programmatic integration with Qwen Code.
     • ›Supports custom tools via SDK-controlled MCP (Model Context Protocol) servers, enabling tool injection through the SDK.
     • ›Integrates DeepSeek V3.2 Thinking Mode, adding reasoning/thinking model support to the tool.
     • ›Adds session-level conversation history management, giving users control over per-session chat context.
     └──▷ BREAKING ON UPGRADE

     • !The /quit-confirm flow has been removed; any workflow or integration relying on that confirmation step will no longer function.
206. v0.4.0-preview.1 Dec 5, 2025 · issue -255

     Qwen Code v0.4.0-preview.1 adds a TypeScript SDK, DeepSeek V3.2 thinking mode, session-level conversation history management, and custom tool support via SDK-controlled MCP servers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0-preview.1

     • ›Adds a basic TypeScript SDK (feat: basic TypeScript SDK) enabling programmatic integration with Qwen Code.
     • ›Supports custom tools via SDK-controlled MCP servers, allowing SDK consumers to register and surface their own tooling to the agent.
     • ›Integrates DeepSeek V3.2 thinking mode, enabling reasoning-trace-style responses from the DeepSeek V3.2 model.
     • ›Adds session-level conversation history management, giving users control over per-session context across a conversation.
     └──▷ BREAKING ON UPGRADE

     • !The /quit-confirm flow has been removed; any workflow or script that relied on the /quit-confirm command will no longer work.
207. v0.4.0-preview.0 Dec 4, 2025 · issue -256

     Qwen Code v0.4.0-preview.0 adds session-level conversation history management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0-preview.0

     • ›Adds session-level conversation history management, enabling practitioners to view and control conversation context within a session.
208. v0.4.0-nightly.20251204.6729980b Dec 4, 2025 · issue -256

     Qwen Code v0.4.0-nightly adds session-level conversation history management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0-nightly.20251204.6729980b https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0-nightly.20251204.6729980b

     • ›Adds session-level conversation history management, enabling users to control and review conversation context within a session.
209. v0.3.0 Nov 28, 2025 · issue -262

     Qwen Code v0.3.0 adds stream-json I/O format for headless programmatic use and full internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0

     └──▷ TRY IT
     Pipe structured prompts into Qwen Code and consume streaming JSON responses in a script or CI pipeline.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format in headless mode, enabling programmatic, machine-readable streaming I/O.
     • ›Adds internationalization (i18n) support for both UI text and LLM output.
210. v0.3.0-nightly.20251128.c9af7481 Nov 28, 2025 · issue -262

     Qwen Code v0.3.0-nightly adds stream-json I/O format for headless programmatic use and full internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251128.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251128.c9af7481

     └──▷ TRY IT
     Drive Qwen Code headlessly from a script, piping newline-delimited JSON commands in and reading structured JSON responses out.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format flags in headless mode, enabling programmatic/machine-readable streaming JSON I/O.
     • ›Adds internationalization (i18n) support for both the UI and LLM output.
211. v0.3.0-nightly.20251127.c9af7481 Nov 27, 2025 · issue -263

     Qwen Code v0.3.0-nightly adds stream-json I/O format for headless/programmatic use and internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251127.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251127.c9af7481

     └──▷ TRY IT
     Pipe structured commands into Qwen Code headlessly and receive machine-parseable streaming JSON output for CI/automation pipelines.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format options, enabling programmatic/headless use of Qwen Code via streaming JSON I/O.
     • ›Adds internationalization (i18n) support for both UI text and LLM output.
212. v0.3.0-preview.1 Nov 26, 2025 · issue -264

     Qwen Code v0.3.0-preview.1 adds stream-JSON I/O for headless use and internationalization for UI and LLM output.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-preview.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-preview.1

     └──▷ TRY IT
     Drive Qwen Code non-interactively from a script by piping stream-JSON input and capturing stream-JSON output.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format flags, enabling programmatic headless use of Qwen Code via structured streaming JSON.
     • ›Adds internationalization (i18n) support for both UI text and LLM output.
213. v0.3.0-nightly.20251126.c9af7481 Nov 26, 2025 · issue -264

     Qwen Code v0.3.0-nightly adds stream-json I/O format for headless use and full internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251126.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251126.c9af7481

     └──▷ TRY IT
     Drive Qwen Code programmatically from a script by piping stream-JSON input and capturing stream-JSON output.
     copy

     $ qwen-code --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format to enable programmatic (headless) use of the CLI.
     • ›Adds internationalization (i18n) support for both UI text and LLM output.
214. v0.3.0-nightly.20251125.c9af7481 Nov 25, 2025 · issue -265

     Qwen Code v0.3.0-nightly adds stream-json I/O format for headless programmatic use and full i18n support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251125.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251125.c9af7481

     └──▷ TRY IT
     Drive Qwen Code non-interactively from a script, piping structured JSON in and reading streaming JSON responses out.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format to enable programmatic, headless use of Qwen Code via structured streaming JSON.
     • ›Adds internationalization (i18n) support for UI text and LLM output, enabling localized experiences across languages.
215. v0.3.0-preview.0 Nov 24, 2025 · issue -266

     Qwen Code v0.3.0-preview.0 adds stream-JSON I/O for programmatic headless use and full internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-preview.0

     └──▷ TRY IT
     Pipe structured JSON commands into Qwen Code headlessly and receive stream-JSON responses for programmatic integration in a CI pipeline or script.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format in headless mode, enabling programmatic machine-readable I/O.
     • ›Adds internationalization (i18n) support for both UI strings and LLM output.
216. v0.3.0-nightly.20251124.c9af7481 Nov 24, 2025 · issue -266

     Qwen Code v0.3.0-nightly adds stream-json format for programmatic headless use and full internationalization support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251124.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251124.c9af7481

     └──▷ TRY IT
     Pipe structured commands into Qwen Code headlessly and receive streaming JSON output — useful for driving the tool from scripts or CI pipelines.
     copy

     $ qwen --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format in headless mode, enabling programmatic/machine-readable streaming JSON I/O.
     • ›Adds internationalization (i18n) support for both UI strings and LLM output.
217. v0.3.0-nightly.20251123.c9af7481 Nov 23, 2025 · issue -267

     Qwen Code v0.3.0-nightly adds stream-json I/O format and internationalization support for UI and LLM output.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0-nightly.20251123.c9af7481 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0-nightly.20251123.c9af7481

     └──▷ TRY IT
     Pipe structured prompts into Qwen Code headlessly and receive streaming JSON responses for integration into automated pipelines.
     copy

     $ qwen-code --input-format stream-json --output-format stream-json

     • ›Adds stream-json as a supported value for --input-format and --output-format flags, enabling programmatic (headless) use of the CLI via streaming JSON.
     • ›Adds internationalization (i18n) support for UI labels and LLM output.
218. v0.2.2 Nov 19, 2025 · issue -271

     Qwen Code v0.2.2 adds Trae editor support, ACP slash commands, configurable OpenAPI window, and terminal attention notifications.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.2

     • ›Adds slash command support for ACP (Agent Communication Protocol) integration.
     • ›Adds support for the Trae editor.
     • ›Makes the OpenAPI context window configurable.
     • ›Adds support for alternative cached_tokens format in OpenAI-compatible conversations.
     • ›Enhances QwenLogger to capture OS platform and version metadata alongside log entries.
     +1 moreshow less

     • ›Adds terminal attention notifications to alert users to events requiring action.
219. v0.2.2-nightly.20251119.97bf48b1 Nov 19, 2025 · issue -271

     Qwen Code v0.2.2-nightly adds configurable OpenAPI window, Trae editor support, ACP slash commands, and terminal attention notifications.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.2-nightly.20251119.97bf48b1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.2-nightly.20251119.97bf48b1

     • ›Adds slash command support for ACP (Agent Communication Protocol) integration.
     • ›Adds configurable window size for the OpenAPI provider.
     • ›Adds support for the alternative cached_tokens format in OpenAI-compatible conversation contexts.
     • ›Adds support for the Trae editor as a recognized environment.
     • ›Enhances QwenLogger to capture OS platform and version metadata for richer diagnostic context.
     +1 moreshow less

     • ›Adds terminal attention notifications to alert users when the tool requires input or action.
220. v0.2.1 Nov 13, 2025 · issue -277

     Qwen Code v0.2.1 adds interactive approval mode, fuzzy edit matching, and expanded Zed integration with TodoWriteTool and TaskTool.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.1

     • ›Adds TodoWriteTool and TaskTool support to the Zed editor integration.
     • ›Adds an interactive approval mode dialog, giving users a prompt-level gate before tool actions are executed.
     • ›Improves Edit Tool reliability with a fuzzy matching pipeline to handle inexact file-content matches.
221. v0.2.1-nightly.20251113.d5d96c72 Nov 13, 2025 · issue -277

     Qwen Code v0.2.1-nightly adds TodoWriteTool and TaskTool support in the Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.1-nightly.20251113.d5d96c72 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.1-nightly.20251113.d5d96c72

     • ›Adds TodoWriteTool and TaskTool support to the Zed editor integration, expanding agentic task and todo tracking workflows within Zed.
     • ›Standardizes tool naming and configuration system across the codebase.
222. v0.2.0-preview.0 Nov 12, 2025 · issue -278

     Qwen Code v0.2.0-preview.0 adds TodoWriteTool and TaskTool support to the Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0-preview.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0-preview.0

     • ›Adds TodoWriteTool and TaskTool support to the Zed editor integration, enabling task and to-do management workflows within Zed.
223. v0.2.1-nightly.20251112.22edef0c Nov 12, 2025 · issue -278

     Qwen Code v0.2.1-nightly adds TodoWriteTool and TaskTool support to its Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.1-nightly.20251112.22edef0c https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.1-nightly.20251112.22edef0c

     • ›Adds TodoWriteTool and TaskTool support to the Zed editor integration, enabling task and to-do management workflows from within Zed.
224. v0.2.0-nightly.20251110.3c01c715 Nov 10, 2025 · issue -280

     Qwen Code v0.2.0-nightly adds TodoWriteTool and TaskTool support to the Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0-nightly.20251110.3c01c715 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0-nightly.20251110.3c01c715

     • ›Extends the Zed editor integration with TodoWriteTool and TaskTool support, enabling todo and task management surfaces inside Zed.
225. v0.2.0-nightly.20251109.3c01c715 Nov 9, 2025 · issue -281

     Qwen Code v0.2.0-nightly adds TodoWriteTool and TaskTool support to its Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0-nightly.20251109.3c01c715 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0-nightly.20251109.3c01c715

     • ›Extends the Zed editor integration to support TodoWriteTool and TaskTool, enabling todo and task management surfaces within Zed.
226. v0.2.0-nightly.20251108.3c01c715 Nov 8, 2025 · issue -282

     Qwen Code v0.2.0-nightly adds TodoWriteTool and TaskTool support to the Zed editor integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0-nightly.20251108.3c01c715 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0-nightly.20251108.3c01c715

     • ›Adds TodoWriteTool and TaskTool support to the Zed editor integration.
227. v0.2.0 Nov 7, 2025 · issue -283

     Qwen Code v0.2.0 adds ripgrep support for search tools and introduces customizable model training and tool output management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0

     • ›Adds ripgrep integration alongside glob and grep for faster, more capable file search within the tool.
     • ›Introduces customizable model training and tool output management controls.
228. v0.1.5 Nov 7, 2025 · issue -283

     Qwen Code v0.1.5 improves search tooling and adds customizable model training and tool output management.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.5

     • ›Simplifies and improves the glob, grep, and ripgrep search tools for more reliable file and content search.
     • ›Adds customizable model training and tool output management capabilities.
229. v0.1.5-nightly.20251107.d17c37af Nov 7, 2025 · issue -283

     Qwen Code v0.1.5 simplifies and improves glob, grep, and ripgrep search tools.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.5-nightly.20251107.d17c37af https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.5-nightly.20251107.d17c37af

     • ›Simplifies and improves the glob, grep, and ripgrep search tools for faster file and content discovery.
230. v0.1.4 Nov 5, 2025 · issue -285

     Qwen Code v0.1.4 adds configurable OpenAI logging directory support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.4

     • ›Adds support for custom OpenAI logging directory configuration, letting users control where OpenAI API interaction logs are stored.
231. v0.1.0 Oct 27, 2025 · issue -294

     Qwen Code v0.1.0 ships a standalone bundled package, upstream Gemini-CLI v0.8.2 sync, and standardized tool output format.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0

     • ›Packages the Qwen Code CLI as a standalone bundled package, enabling installation and use without requiring a full Node.js/npm development environment.
     • ›Syncs upstream Gemini-CLI v0.8.2 changes into Qwen Code, bringing all capability improvements from that release.
     • ›Standardizes tool output format for improved LLM communication, making tool call results more reliably parseable by the model.
     • ›Adds /model command documentation, indicating the /model command is a supported interactive subcommand for switching models mid-session.
232. v0.1.0-nightly.20251027.2a5577e5 Oct 27, 2025 · issue -294

     Qwen Code v0.1.0-nightly ships a standalone bundled package and syncs upstream Gemini-CLI v0.8.2 features.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0-nightly.20251027.2a5577e5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0-nightly.20251027.2a5577e5

     • ›Releases the Qwen Code CLI as a standalone bundled package, enabling installation without requiring a full Node.js toolchain.
     • ›Syncs upstream Gemini-CLI v0.8.2 changes into the Qwen Code codebase.
233. v0.1.0-nightly.20251026.2a5577e5 Oct 26, 2025 · issue -295

     Qwen Code v0.1.0-nightly ships a standalone bundled CLI package and syncs upstream Gemini-CLI v0.8.2 features.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0-nightly.20251026.2a5577e5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0-nightly.20251026.2a5577e5

     • ›Releases the qwen-code CLI as a standalone bundled package, enabling installation without separate dependency management.
     • ›Syncs upstream Gemini-CLI v0.8.2 changes into Qwen Code.
234. v0.1.0-nightly.20251025.2a5577e5 Oct 25, 2025 · issue -296

     Qwen Code v0.1.0-nightly ships a standalone bundled package release and syncs upstream Gemini-CLI v0.8.2.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0-nightly.20251025.2a5577e5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0-nightly.20251025.2a5577e5

     • ›Releases the Qwen Code CLI as a standalone bundled package, enabling installation and distribution without separate dependency resolution.
     • ›Syncs upstream Gemini-CLI v0.8.2 changes into Qwen Code.
     └──▷ BREAKING ON UPGRADE

     • !Removes default topp and temperature values, so configurations that relied on those implicit defaults will now behave differently.
235. v0.0.14 Sep 29, 2025 · issue -321

     Qwen Code v0.0.14 adds Plan Mode for safe code planning, Qwen3-VL-Plus token limits, and DashScope cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.14 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.14

     • ›Adds support for Qwen3-VL-Plus model with token limits of 256K input and 32K output.
     • ›Implements Plan Mode for safe code planning, allowing the agent to plan changes before executing them.
     • ›Enhances DashScope cache control for improved API caching behavior.
236. v0.0.14-nightly.2 Sep 29, 2025 · issue -321

     Qwen Code v0.0.14-nightly.2 adds Plan Mode for safe code planning and Qwen3-VL-Plus support with 256K input / 32K output token limits.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.14-nightly.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.14-nightly.2

     • ›Adds Qwen3-VL-Plus model support with 256K input and 32K output token limits.
     • ›Implements Plan Mode for safe code planning, letting the agent plan changes before executing them.
237. v0.0.14-nightly.1 Sep 26, 2025 · issue -324

     Qwen Code v0.0.14-nightly.1 adds Plan Mode for safe, non-destructive code planning before execution.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.14-nightly.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.14-nightly.1

     • ›Adds Plan Mode, a safe code-planning workflow that lets the agent reason and propose changes without executing them.
238. v0.0.14-nightly.0 Sep 25, 2025 · issue -325

     Qwen Code v0.0.14-nightly.0 adds Plan Mode for safe, non-destructive code planning before execution.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.14-nightly.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.14-nightly.0

     • ›Adds Plan Mode, a safe code-planning workflow that lets the model reason and propose changes before any code is executed or modified.
239. v0.0.13 Sep 24, 2025 · issue -326

     Qwen Code v0.0.13 adds OpenAI/Qwen OAuth auth for Zed ACP and yolo-mode auto vision model switching.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.13 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.13

     • ›Adds yolo mode support to automatic vision model switching, enabling hands-free model selection when processing images.
     • ›Adds OpenAI and Qwen OAuth authentication support to the Zed ACP integration.
240. v0.1.0-preview Sep 24, 2025 · issue -326

     Qwen Code v0.1.0-preview adds OpenAI and Qwen OAuth authentication support for the Zed ACP integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0-preview https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0-preview

     • ›Adds OpenAI and Qwen OAuth authentication support to the Zed ACP integration.
241. v0.0.13-nightly.4 Sep 24, 2025 · issue -326

     Qwen Code v0.0.13-nightly.4 adds OpenAI and Qwen OAuth authentication to the Zed ACP integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.13-nightly.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.13-nightly.4

     • ›Adds OpenAI and Qwen OAuth authentication support to the Zed ACP integration.
242. v0.0.13-nightly.3 Sep 23, 2025 · issue -327

     Qwen Code v0.0.13-nightly.3 adds OpenAI and Qwen OAuth authentication to the Zed ACP integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.13-nightly.3 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.13-nightly.3

     • ›Adds OpenAI and Qwen OAuth authentication support to the Zed ACP integration.
243. v0.0.13-nightly.2 Sep 23, 2025 · issue -327

     Qwen Code v0.0.13-nightly.2 adds OpenAI and Qwen OAuth authentication to the Zed ACP integration.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.13-nightly.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.13-nightly.2

     • ›Adds OpenAI and Qwen OAuth authentication support to the Zed ACP integration.
244. v0.0.12 Sep 19, 2025 · issue -331

     Qwen Code v0.0.12 adds skipLoopDetection config option, vision model support for Qwen-OAuth, and an enhanced /init command.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.12 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.12

     └──▷ USE IT
     Disable loop detection when running long autonomous tasks that would otherwise be incorrectly flagged as stuck.
     json copy

     {
       "skipLoopDetection": true
     }

     • ›Adds skipLoopDetection configuration option to disable agentic loop detection.
     • ›Adds vision model support for Qwen-OAuth authentication flows.
     • ›Enhances the /init command with a confirmation prompt before writing files.
     • ›Enables tool call type coercion so mismatched argument types from model responses are automatically cast to the expected type.
245. v0.0.12-nightly.2 Sep 19, 2025 · issue -331

     Qwen Code v0.0.12-nightly.2 adds skipLoopDetection config, vision model support, and an enhanced /init confirmation prompt.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.12-nightly.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.12-nightly.2

     └──▷ USE IT
     Disable loop detection when running long autonomous agent tasks that would otherwise be interrupted by false positives.
     json copy

     {
       "skipLoopDetection": true
     }

     • ›Adds skipLoopDetection configuration option to allow users to disable agent loop detection.
     • ›Adds vision model support for Qwen-OAuth authentication flows.
     • ›Enhances the /init command with a confirmation prompt before initializing.
     • ›Enables tool call type coercion so mismatched argument types in tool calls are automatically corrected.
246. v0.0.12-nightly.1 Sep 18, 2025 · issue -332

     Qwen Code v0.0.12-nightly.1 adds skipLoopDetection config option and a confirmation prompt to /init.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.12-nightly.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.12-nightly.1

     • ›Adds skipLoopDetection configuration option to disable loop detection during agentic runs.
     • ›Enhances /init command with a confirmation prompt before executing initialization.
247. v0.0.11 Sep 12, 2025 · issue -338

     Qwen Code v0.0.11 adds a Subagents feature, a Welcome Back dialog with project summary, and configurable cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11

     • ›Adds Subagents feature, enabling agent delegation and multi-agent workflows.
     • ›Adds Welcome Back dialog with project summary and enhanced quit options on session resume.
     • ›Adds configurable cache control for API interactions.
248. v0.0.11-nightly.6 Sep 12, 2025 · issue -338

     Qwen Code v0.0.11-nightly.6 adds a Subagents feature, a Welcome Back dialog with project summary, and configurable cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11-nightly.6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11-nightly.6

     • ›Adds configurable cache control via a new configuration option.
     • ›Introduces a Subagents feature, enabling multi-agent task delegation within Qwen Code.
     • ›Adds a Welcome Back dialog, project summary view, and enhanced quit options to the CLI UI.
     • ›Re-implements the tokenLimits class to correctly handle token accounting for Qwen and related models.
     • ›Makes the ReadManyFiles tool apply the DEFAULT_MAX_LINES_TEXT_FILE limit shared across all files rather than per-file independently.
249. v0.0.11-nightly.5 Sep 12, 2025 · issue -338

     Qwen Code v0.0.11-nightly.5 adds a Subagents feature, Welcome Back Dialog with project summary, and configurable cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11-nightly.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11-nightly.5

     • ›Adds configurable cache control via new configuration support (chore: add configurable cache control).
     • ›Introduces a Subagents feature, enabling agent delegation and multi-agent task handling.
     • ›Adds a Welcome Back Dialog with project summary and enhanced quit options to the CLI UI.
     • ›Applies the DEFAULT_MAX_LINES_TEXT_FILE limit across all files when using the ReadManyFiles tool, preventing unbounded reads across multiple files.
250. v0.0.11-nightly.4 Sep 12, 2025 · issue -338

     Qwen Code v0.0.11-nightly.4 adds a Subagents feature, a Welcome Back dialog with project summary, and configurable cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11-nightly.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11-nightly.4

     • ›Introduces Subagents feature, enabling multi-agent task delegation within Qwen Code workflows.
     • ›Adds a Welcome Back dialog with project summary and enhanced quit options on session resume.
     • ›Adds configurable cache control for API interactions.
     • ›Applies the DEFAULT_MAX_LINES_TEXT_FILE limit consistently across all files read by the ReadManyFiles tool.
251. v0.0.11-nightly.2 Sep 9, 2025 · issue -341

     Qwen Code v0.0.11-nightly.2 adds configurable cache control and corrected token limits for Qwen models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11-nightly.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11-nightly.2

     • ›Adds configurable cache control via new configuration support, enabling tuning of caching behavior.
     • ›Re-implements the tokenLimits class to work correctly for Qwen and related models, unlocking accurate context-window management.
252. v0.0.10 Sep 2, 2025 · issue -348

     Qwen Code v0.0.10 adds a Todo Write tool for in-session task management and syncs upstream Gemini CLI v0.2.1 features.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.10 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.10

     • ›Adds a Todo Write tool for task management and progress tracking during coding sessions.
     • ›Syncs features from Gemini CLI v0.2.1 upstream.
253. v0.0.10-nightly.2 Sep 2, 2025 · issue -348

     Qwen Code v0.0.10-nightly.2 adds a Todo Write tool for task tracking and configurable cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.10-nightly.2 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.10-nightly.2

     • ›Adds a Todo Write tool for in-session task management and progress tracking.
     • ›Adds configurable cache control settings.
254. v0.0.10-nightly.1 Sep 1, 2025 · issue -349

     Qwen Code v0.0.10-nightly.1 adds a Todo Write tool for in-session task management and progress tracking.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.10-nightly.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.10-nightly.1

     • ›Adds a Todo Write tool enabling task management and progress tracking within coding sessions.
255. v0.0.9 Aug 27, 2025 · issue -354

     Qwen Code v0.0.9 adds subcommand-based switching between project and global memory operations.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.9 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.9

     • ›Adds subcommands to /memory to switch between project-level and global memory operations.
256. v0.0.9-nightly.4 Aug 27, 2025 · issue -354

     Qwen Code v0.0.9-nightly.4 adds subcommands to switch between project and global memory operations.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.9-nightly.4 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.9-nightly.4

     • ›Adds subcommands to switch between project-level and global memory operations, replacing a single undifferentiated memory command.
257. v0.0.8 Aug 22, 2025 · issue -359

     Qwen Code v0.0.8 adds .geminiignore support in grep, project/global save location options, and deterministic cache control.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.8 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.8

     • ›Adds project/global save location option to control where settings are persisted.
     • ›Adds deterministic cache control for LLM requests.
     • ›Grep tool now respects .geminiignore to exclude files from search results.
258. v0.0.8-nightly.7 Aug 22, 2025 · issue -359

     Qwen Code v0.0.8-nightly.7 adds .geminiignore support in grep, grep result limits, deterministic cache control, and save location options.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.8-nightly.7 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.8-nightly.7

     • ›Grep tool now respects .geminiignore to exclude files and directories from search results, consistent with other tool behaviors.
     • ›Adds a project/global save location option, letting users control where session data is persisted.
     • ›Adds deterministic cache control for LLM requests.
259. v0.0.8-nightly.6 Aug 21, 2025 · issue -360

     Qwen Code v0.0.8-nightly.6 adds .geminiignore support in grep and project/global save location options.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.8-nightly.6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.8-nightly.6

     • ›Adds project/global save location option, letting users control where conversation or session data is persisted.
     • ›Applies .geminiignore rules to the grep tool, so files excluded from Gemini/Qwen Code context are also excluded from grep searches.
260. v0.0.8-nightly.5 Aug 20, 2025 · issue -361

     Qwen Code v0.0.8-nightly.5 adds .geminiignore support in grep and a project/global save location option.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.8-nightly.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.8-nightly.5

     └──▷ USE IT
     Exclude build artifacts and secrets from grep results by listing them in .geminiignore at the repo root.
     yaml copy

     # .geminiignore
     dist/
     *.env
     node_modules/
     *.log

     • ›Adds .geminiignore support to the grep tool, so files and paths listed in .geminiignore are excluded from grep searches.
     • ›Adds a project/global save location option, letting users choose whether settings are saved at the project or global scope.
261. v0.0.7 Aug 15, 2025 · issue -363

     Qwen Code v0.0.7 migrates web search to Tavily API and removes Google GenAI dependency from web-fetch

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.7 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.7

     • ›Migrates web search from Google/Gemini to the Tavily API, replacing the previous search backend.
     • ›Refactors the web-fetch tool to remove the google genai dependency, making it provider-independent.
     • ›Adds a GitHub Actions workflow to build the sandbox image.
     • ›Adds an API request logger for observability into outbound model requests.
     └──▷ BREAKING ON UPGRADE

     • !Web search is now routed through the Tavily API instead of Google/Gemini — existing setups relying on Google/Gemini for web search will no longer work without a Tavily API key.
262. v0.0.6-nightly.1 Aug 13, 2025 · issue -363

     Qwen Code v0.0.6-nightly.1 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.6-nightly.1 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.6-nightly.1

     • ›Adds systemPromptMappings configuration feature to map system prompts per context.
     • ›Adds Qwen OAuth integration for authentication flows.
     • ›Supports OpenRouter as a model backend provider.
     • ›Adds telemetry service for usage tracking.
     • ›Makes /init respect the configured context filename, aligning with QWEN.md.
     +3 moreshow less

     • ›Adds usage statistics logging for the Qwen integration.
     • ›Adds GitHub Actions workflow to build the sandbox image.
     • ›Updates /bug command to point to the Qwen-Code repository.
     └──▷ BREAKING ON UPGRADE

     • !GEMINI.md is renamed to QWEN.md across the codebase — any tooling or scripts referencing GEMINI.md as the context filename will break.
263. v0.0.6-nightly.0 Aug 13, 2025 · issue -363

     Qwen Code v0.0.6-nightly.0 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.6-nightly.0 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.6-nightly.0

     • ›Adds systemPromptMappings configuration feature to map system prompts per context.
     • ›Adds Qwen OAuth integration for authenticated sessions.
     • ›Supports OpenRouter as a model provider backend.
     • ›Adds telemetry service for usage tracking.
     • ›Adds usage statistics logging for the Qwen integration.
     +2 moreshow less

     • ›Updates /bug command to point to the Qwen-Code repository.
     • ›Makes /init respect the configured context filename and aligns docs with QWEN.md.
     └──▷ BREAKING ON UPGRADE

     • !Context filename documentation and /init command behavior now align with QWEN.md (renamed from GEMINI.md) — any workflows or scripts referencing GEMINI.md as the context file will need to be updated.
264. v0.0.6 Aug 12, 2025 · issue -363

     Qwen Code v0.0.6 adds usage statistics logging and makes /init respect configured context filenames.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.6

     • ›Adds usage statistics logging for Qwen API integration to track token and request consumption.
     • ›Makes /init command respect the configured context filename (e.g., QWEN.md) rather than hardcoding a default.
265. v0.0.5-nightly.12 Aug 12, 2025 · issue -363

     Qwen Code v0.0.5-nightly.12 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and usage statistics logging.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.12 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.12

     • ›Adds systemPromptMappings configuration feature to map system prompts per context.
     • ›Adds Qwen OAuth integration for authenticated sessions.
     • ›Supports OpenRouter as a model provider backend.
     • ›Adds telemetry service for usage tracking.
     • ›Adds usage statistics logging for Qwen integration.
     +2 moreshow less

     • ›Updates /bug command to point to the Qwen-Code repository.
     • ›Makes /init respect the configured context filename, aligned with QWEN.md.
     └──▷ BREAKING ON UPGRADE

     • !GEMINI.md is renamed to QWEN.md across the codebase — any tooling or scripts that reference GEMINI.md will break.
266. v0.0.5-nightly.11 Aug 12, 2025 · issue -363

     Qwen Code v0.0.5-nightly.11 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.11 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.11

     • ›Adds systemPromptMappings configuration feature to map models to custom system prompts.
     • ›Adds OpenRouter as a supported inference provider.
     • ›Adds Qwen OAuth integration for authentication.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code repository.
     +1 moreshow less

     • ›Adds ModelScope inference API as a supported backend.
267. v0.0.5-nightly.10 Aug 11, 2025 · issue -363

     Qwen Code v0.0.5-nightly.10 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.10 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.10

     • ›Adds systemPromptMappings configuration feature, enabling per-context system prompt overrides via config.
     • ›Adds Qwen OAuth integration for authenticated access to Qwen services.
     • ›Adds support for OpenRouter as a model provider backend.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug slash command to point to the Qwen-Code issue tracker instead of the upstream repo.
268. v0.0.5-nightly.9 Aug 10, 2025 · issue -363

     Qwen Code v0.0.5-nightly.9 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.9 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.9

     • ›Adds systemPromptMappings configuration feature, enabling per-context system prompt overrides.
     • ›Adds Qwen OAuth integration for authenticated sessions.
     • ›Adds support for OpenRouter as a model provider backend.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code repository.
269. v0.0.5-nightly.8 Aug 9, 2025 · issue -363

     Qwen Code v0.0.5-nightly.8 adds OAuth, OpenRouter support, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.8 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.8

     • ›Adds systemPromptMappings configuration feature, enabling per-context system prompt customization.
     • ›Adds Qwen OAuth integration for authentication flows.
     • ›Adds support for OpenRouter as a model provider.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code issue tracker.
270. v0.0.5 Aug 8, 2025 · issue -363

     Qwen Code v0.0.5 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5

     • ›Adds systemPromptMappings configuration feature to map system prompts conditionally.
     • ›Adds Qwen OAuth integration for authenticated access.
     • ›Supports OpenRouter as a model provider backend.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates /bug command to point to the Qwen-Code repository.
271. v0.0.5-nightly.7 Aug 8, 2025 · issue -363

     Qwen Code v0.0.5-nightly.7 adds OAuth login, OpenRouter support, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.7 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.7

     • ›Adds systemPromptMappings configuration feature, enabling per-context system prompt overrides.
     • ›Adds Qwen OAuth integration for authenticated access.
     • ›Adds support for OpenRouter as a model provider.
     • ›Adds a telemetry service for usage data collection.
     • ›Updates the /bug command to point to the Qwen-Code repository.
272. v0.0.5-nightly.6 Aug 8, 2025 · issue -363

     Qwen Code v0.0.5-nightly.6 adds OpenRouter support, Qwen OAuth, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.6 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.6

     • ›Adds systemPromptMappings configuration feature, enabling per-context system prompt customization.
     • ›Adds Qwen OAuth integration for authentication flows.
     • ›Adds support for OpenRouter as a model provider.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code repository.
273. v0.0.5-nightly.5 Aug 8, 2025 · issue -363

     Qwen Code v0.0.5-nightly.5 adds OpenRouter support, systemPromptMappings config, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.5-nightly.5 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.5-nightly.5

     • ›Adds systemPromptMappings configuration feature, allowing per-context system prompt overrides.
     • ›Adds support for OpenRouter as a model provider backend.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code repository.
274. v0.0.1-alpha.14 Aug 1, 2025 · issue -363

     Qwen Code alpha.14 adds systemPromptMappings config, OpenRouter support, and a telemetry service.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.1-alpha.14 https://github.com/QwenLM/qwen-code.git
     # already have the repo? check out this version:
     $ git checkout v0.0.1-alpha.14

     • ›Adds systemPromptMappings configuration feature, allowing per-model or per-context system prompt overrides.
     • ›Supports OpenRouter as a new model provider integration.
     • ›Adds a telemetry service for usage tracking.
     • ›Updates the /bug command to point to the Qwen-Code repository.