@cairnkeep/cli 2.5.0 → 2.6.0

package/CHANGELOG.md

@@ -5,6 +5,15 @@ All notable user-facing changes are documented here. This project follows
 
 ## [Unreleased]
 
+## [2.6.0] - 2026-07-29
+
+### Added
+
+- Add Qwen Code as a supported memory client with a generated project launcher,
+  local stdio guidance, and tested authenticated remote HTTP configuration.
+- Expand the harness comparison to cover current native plugin and MCP clients,
+  while keeping memory-only support separate from the full operating layer.
+
 ## [2.5.0] - 2026-07-29
 
 ### Added
@@ -211,7 +220,8 @@ stored memories.
 - Preserve executable permissions and Bash 3.2 portability on macOS.
 - Add backup-first uninstall and SQLite-safe memory export/import guidance.
 
-[Unreleased]: https://github.com/cairnkeep/cairnkeep/compare/v2.5.0...HEAD
+[Unreleased]: https://github.com/cairnkeep/cairnkeep/compare/v2.6.0...HEAD
+[2.6.0]: https://github.com/cairnkeep/cairnkeep/compare/v2.5.0...v2.6.0
 [2.5.0]: https://github.com/cairnkeep/cairnkeep/compare/v2.4.0...v2.5.0
 [2.4.0]: https://github.com/cairnkeep/cairnkeep/compare/v2.3.1...v2.4.0
 [2.3.1]: https://github.com/cairnkeep/cairnkeep/compare/v2.3.0...v2.3.1

package/README.md

@@ -10,7 +10,7 @@ A *cairn* is a stack of stones left as a trail marker for whoever follows; a
 *keep* is where you store what matters. **Cairnkeep** is where coding agents
 stack durable memory — decisions, pitfalls, patterns — and follow the trail
 across sessions, projects, and harnesses (Claude Code, OpenCode, Kimi Code,
-Pi, and other MCP clients).
+Qwen Code, Pi, and other MCP clients).
 
 ## Status
 
@@ -38,6 +38,7 @@ and 20 are end-of-life upstream.
 | Claude Code on Linux/macOS | Memory server plus commands, agents, hooks, and launchers |
 | OpenCode on Linux/macOS | Memory server plus commands, plugins, hooks, and launchers |
 | Kimi Code on Linux/macOS | Memory MCP server plus project launcher; no Cairnkeep operating-layer assets yet |
+| Qwen Code on Linux/macOS | Memory MCP server plus project launcher; no Cairnkeep operating-layer assets yet |
 | Pi on Linux/macOS | Native opt-in trajectory extension and launcher; no bundled MCP bridge |
 | Codex CLI | Memory MCP server; no Cairnkeep operating-layer assets |
 | Other MCP clients | Memory and optional domain-knowledge MCP tools |
@@ -47,7 +48,7 @@ Linux, macOS, Bash 3.2 portability, and clean Node 22/24/26 runtime checks
 are exercised in CI.
 
 See [Harness compatibility](docs/harness-compatibility.md) for exact support
-levels, Kimi configuration, and candidates that are not yet runtime-tested.
+levels, Kimi and Qwen configuration, and candidates that are not yet runtime-tested.
 
 ## Try with Podman
 
@@ -159,6 +160,12 @@ configuration requires a literal URL and supports a token reference through
 `bearerTokenEnvVar`; it does not expand `${VAR}` in the URL. See
 [Harness compatibility](docs/harness-compatibility.md#kimi-code).
 
+For Qwen Code, use project `.qwen/settings.json`: local stdio launches
+`cairn memory-server`, while remote HTTP uses `httpUrl` and environment-expanded
+headers. Review and approve project MCP configuration with
+`qwen mcp approve cairn-memory`, then launch with `./.ai/start-qwen.sh`. See
+[Harness compatibility](docs/harness-compatibility.md#qwen-code).
+
 For Pi, install the local trajectory adapter and use the scaffolded launcher:
 
 ```bash
@@ -208,8 +215,8 @@ unless a wrapper opts in:
   export env (e.g. a provider base URL) or abort the launch by returning
   non-zero. This is where credential refresh / connectivity setup lives.
 - **`CAIRN_EXTRA_SETTINGS`** — path to a settings file layered onto the harness
-  (`--settings` for Claude Code, `OPENCODE_CONFIG` for OpenCode). Pi has no equivalent
-  generic settings-file flag, so its launcher leaves this variable unused.
+  (`--settings` for Claude Code, `OPENCODE_CONFIG` for OpenCode). Kimi, Qwen,
+  and Pi do not interpret this variable in their generic launchers.
   Process env still wins, so an inline value beats the profile.
 - **`.ai/post-exit.sh`** — sourced after the harness exits, with
   `CAIRN_EXIT_STATUS` set to its exit code.

package/docs/building-an-overlay.md

@@ -28,13 +28,13 @@ manifest, profile-lock, private-registry, and rollback contract.
 ## The launcher seams
 
 The generic launchers (`.ai/start-claude.sh`, `.ai/start-opencode.sh`,
-`.ai/start-kimi.sh`, and `.ai/start-pi.sh`, scaffolded by `cairn bootstrap`) run
+`.ai/start-kimi.sh`, `.ai/start-qwen.sh`, and `.ai/start-pi.sh`, scaffolded by `cairn bootstrap`) run
 optional hooks, each a no-op when absent:
 
 | Seam | When | Use it for |
 |---|---|---|
 | `.ai/pre-launch.sh` | sourced after `.env`, before launch | export a provider base URL / credentials, refresh a token, run a connectivity check, or **abort** the launch by returning non-zero |
-| `CAIRN_EXTRA_SETTINGS` | read just before launch | path to a settings file layered onto Claude Code (`--settings`) or OpenCode (`OPENCODE_CONFIG`); Kimi and Pi leave it available to hooks but do not interpret it |
+| `CAIRN_EXTRA_SETTINGS` | read just before launch | path to a settings file layered onto Claude Code (`--settings`) or OpenCode (`OPENCODE_CONFIG`); Kimi, Qwen, and Pi leave it available to hooks but do not interpret it |
 | `.ai/post-exit.sh` | sourced after the harness exits | teardown; `CAIRN_EXIT_STATUS` holds the exit code |
 
 **Typical overlay launcher** — a corporate wrapper needs a non-default provider

package/docs/harness-compatibility.md

@@ -11,14 +11,15 @@ commands, hooks, plugins, or trajectory adapters.
 | Claude Code | Memory MCP, commands, agents, hooks, launcher | Exercised by Cairnkeep tests |
 | OpenCode | Memory MCP, commands, workflows, plugins, launcher | Exercised by Cairnkeep tests |
 | Kimi Code | Memory MCP, `AGENTS.md`, launcher | Launcher tested; remote MCP tested with Kimi Code 0.30.0 |
+| Qwen Code | Memory MCP, launcher | Launcher tested; stdio and remote MCP tested with Qwen Code 0.21.1 |
 | Pi | Native opt-in trajectory extension and launcher | Exercised by Cairnkeep tests; no bundled MCP bridge |
 | Codex CLI | Memory MCP | Configuration supported; no Cairnkeep operating-layer assets or launcher |
 | Other MCP clients | Memory and optional domain-knowledge tools | Protocol-compatible; not automatically runtime-tested |
 
 Only Claude Code and OpenCode currently receive the complete operating layer.
-Kimi skills and hooks require harness-specific adaptation and validation before
-they can be presented as equivalent. In Kimi, call MCP tools directly or use
-ordinary prompts until that work is complete.
+Kimi and Qwen skills and hooks require harness-specific adaptation and
+validation before they can be presented as equivalent. In either client, call
+MCP tools directly or use ordinary prompts until that work is complete.
 
 ## Kimi Code
 
@@ -91,6 +92,72 @@ token value in either file.
 Kimi MCP configuration is documented at
 [Kimi Code MCP](https://www.kimi.com/code/docs/en/kimi-code-cli/customization/mcp.html).
 
+## Qwen Code
+
+Qwen Code can read MCP definitions from user settings, project
+`.qwen/settings.json`, and compatible repository `.mcp.json` files. Use the
+Qwen-specific project settings file for remote HTTP so its `httpUrl` transport
+and environment expansion are explicit.
+
+### Local stdio
+
+Create `.qwen/settings.json` in a trusted project:
+
+```json
+{
+  "mcpServers": {
+    "cairn-memory": {
+      "command": "cairn",
+      "args": ["memory-server"]
+    }
+  }
+}
+```
+
+Project MCP definitions are approval-gated. Review the file, then run:
+
+```bash
+qwen mcp approve cairn-memory
+./.ai/start-qwen.sh
+```
+
+The server is a local child process. Its storage stays on this computer unless
+the operator deliberately replaces this stdio definition with a remote one.
+
+### Remote HTTP
+
+Qwen Code 0.21.1 was exercised with environment expansion in project settings:
+
+```json
+{
+  "mcpServers": {
+    "cairn-memory": {
+      "httpUrl": "${CAIRN_MEMORY_REMOTE_URL}",
+      "headers": {
+        "Authorization": "Bearer ${CAIRN_MEMORY_HTTP_TOKEN}",
+        "X-Cairn-Project": "example-project",
+        "X-Cairn-Scopes": "identity,personal,project",
+        "X-Cairn-AnythingLLM-Workspaces": "example-workspace"
+      }
+    }
+  }
+}
+```
+
+Keep the endpoint and token in `.ai/.env` or a machine secret store. The
+generated launcher exports `.ai/.env` before Qwen reads the settings. Re-run
+`qwen mcp approve cairn-memory` after changing the project definition because
+the approval is bound to the configuration digest.
+
+The authenticated recipe above is validated for `.qwen/settings.json`.
+Cairnkeep does not assume that a one-shot `--mcp-config` input performs the same
+environment expansion. A private overlay should write the project settings
+backup-first, preserve unrelated keys, exclude private routing metadata from
+Git, and leave secret values as environment references.
+
+Qwen MCP configuration is documented at
+[Qwen Code MCP](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/).
+
 ## Candidate memory clients
 
 The following clients have documented MCP support and are reasonable adapter
@@ -99,17 +166,28 @@ writers, operating assets, or runtime CI:
 
 | Client | Documented MCP surface | Cairnkeep status |
 |---|---|---|
-| Gemini CLI | `mcpServers` in `settings.json` | Candidate for stdio and HTTP memory tests |
+| Antigravity CLI | Workspace `.agents/mcp_config.json` and plugins | Current successor candidate for memory plus native operating assets |
+| Cursor | Project `.cursor/mcp.json`, plugins, and Agent CLI | Candidate for memory plus native operating assets |
 | GitHub Copilot CLI | `copilot mcp` and `.mcp.json` | Candidate for memory plus shared skills |
-| Qwen Code | `qwen mcp` and MCP configuration | Candidate for stdio and HTTP memory tests |
+| Factory Droid | Native plugin marketplace | Candidate for reusing a compatible operating-layer package |
 | goose | MCP extensions and CLI session extension loading | Candidate for memory and recipe integration |
+| Gemini CLI | `mcpServers` in `settings.json` | Legacy candidate for enterprise or API-key users only |
 
 Primary references:
 
-- [Gemini CLI MCP](https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md)
+- [Antigravity MCP](https://antigravity.google/docs/mcp)
+- [Cursor MCP](https://docs.cursor.com/context/model-context-protocol)
 - [GitHub Copilot CLI MCP](https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-mcp-servers)
-- [Qwen Code MCP](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/)
 - [goose](https://github.com/aaif-goose/goose)
+- [Gemini CLI transition announcement](https://github.com/google-gemini/gemini-cli/discussions/28017)
+- [Superpowers harness integrations](https://github.com/obra/superpowers)
+
+Superpowers is a useful comparison because it keeps shared behavior in one
+source tree and ships thin native adapters through each harness's supported
+plugin, extension, hook, or context mechanism. Cairnkeep follows the same
+principle for future operating-layer ports: reuse common content, map real tool
+names and lifecycle events per harness, and document degraded capabilities
+instead of copying one harness's files into another.
 
 Support should be added one client at a time with a clean install, a local
 stdio handshake, an authenticated HTTP handshake, a real write/recall canary,

package/docs/learning/CURRICULUM-MAP.md

@@ -1,6 +1,6 @@
 # Curriculum Coverage Map
 
-**Baseline:** Cairnkeep 2.5.0
+**Baseline:** Cairnkeep 2.6.0
 **Last reviewed:** 2026-07-29
 
 This map prevents the course from drifting behind the product. It assigns each

package/docs/learning/FEATURE-GUIDE.md

@@ -1,6 +1,6 @@
 # Cairnkeep feature guide
 
-**Baseline:** Cairnkeep 2.5.0
+**Baseline:** Cairnkeep 2.6.0
 
 This is the step-back map for choosing and operating Cairnkeep features. The
 [course labs](https://github.com/cairnkeep/cairnkeep-course-labs) provide one

package/docs/learning/lessons/L00-why-cairnkeep.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 10 minutes
-**Tested with:** Cairnkeep 2.5.0
+**Tested with:** Cairnkeep 2.6.0
 
 ## Outcome
 

package/docs/learning/lessons/L01-safe-trial.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 15 minutes
-**Tested with:** Cairnkeep 2.5.0
+**Tested with:** Cairnkeep 2.6.0
 
 ## Outcome
 
@@ -26,7 +26,7 @@ ephemeral; the named course volume is persistent.
 1. Pull the public image:
 
    ```bash
-   podman pull ghcr.io/cairnkeep/cairnkeep:2.5.0
+   podman pull ghcr.io/cairnkeep/cairnkeep:2.6.0
    ```
 
 2. Start the stdio server with a read-only root filesystem and no Linux
@@ -38,7 +38,7 @@ ephemeral; the named course volume is persistent.
      --read-only --cap-drop=all --security-opt=no-new-privileges \
      --tmpfs=/tmp:rw,noexec,nosuid,size=64m,mode=1777 \
      --volume cairnkeep-course-data:/data:Z,U \
-     ghcr.io/cairnkeep/cairnkeep:2.5.0 stdio
+     ghcr.io/cairnkeep/cairnkeep:2.6.0 stdio
    ```
 
 3. The process waits quietly for MCP input. Press `Ctrl-C` after confirming it

package/docs/learning/lessons/L02-installation.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 25 minutes
-**Tested with:** Cairnkeep 2.5.0 and Node.js 22 or newer
+**Tested with:** Cairnkeep 2.6.0 and Node.js 22 or newer
 
 ## Outcome
 
@@ -13,7 +13,7 @@ layer, and distinguish a complete installation from a partial one.
 ## Prerequisites
 
 - Node.js 22 or newer and npm.
-- Claude Code installed for the commands below. OpenCode and Kimi Code users
+- Claude Code installed for the commands below. OpenCode, Kimi Code, and Qwen Code users
   should follow the equivalent setup in
   [the operating guide](../../operating.md).
 - Permission to install an npm package globally for your user.
@@ -41,7 +41,7 @@ machine-level steps.
 2. Install Cairnkeep:
 
    ```bash
-   npm install --global @cairnkeep/cli@2.5.0
+   npm install --global @cairnkeep/cli@2.6.0
    cairn --version
    ```
 
@@ -108,6 +108,14 @@ URL rather than `${CAIRN_MEMORY_REMOTE_URL}`. Keep the resolved URL in a private
 `.kimi-code/mcp.json` and keep the bearer token in the environment. See
 [Harness compatibility](../../harness-compatibility.md#kimi-code).
 
+Qwen Code can use the generated `.ai/start-qwen.sh` launcher. Its project
+`.qwen/settings.json` supports environment references for both the remote URL
+and authorization header, so the file can contain names such as
+`${CAIRN_MEMORY_REMOTE_URL}` and `${CAIRN_MEMORY_HTTP_TOKEN}` instead of secret
+values. Keep this project settings file untracked and approve the generated MCP
+entry with `qwen mcp approve cairn-memory`. See
+[Harness compatibility](../../harness-compatibility.md#qwen-code).
+
 ## Clean up if you stop the evaluation
 
 Continue directly to L03 if you are completing the quickstart. If you stop here,

package/docs/learning/lessons/L03-first-project.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 25 minutes
-**Tested with:** Cairnkeep 2.5.0
+**Tested with:** Cairnkeep 2.6.0
 
 ## Outcome
 

package/docs/operating.md

@@ -17,8 +17,9 @@ installs. This guide covers all three in order.
 ## Prerequisites
 
 - Node.js 22 or newer (for the memory server) and a supported harness. Claude
-  Code and OpenCode receive the full operating layer. Kimi Code receives the
-  memory MCP and launcher. Pi receives its native trajectory adapter.
+  Code and OpenCode receive the full operating layer. Kimi Code and Qwen Code
+  receive the memory MCP and launcher. Pi receives its native trajectory
+  adapter.
 - Optional: the `sqlite3` CLI for `cairn memory export`. Runtime memory and
   `cairn memory import` do not require it.
 - Optional: an OpenAI-compatible LLM endpoint for memory extraction and
@@ -189,6 +190,37 @@ parses it before applying its private override. See
 [Harness compatibility](harness-compatibility.md#kimi-code) for the complete
 configuration and trust-boundary guidance.
 
+## Setup order (Qwen Code)
+
+Qwen Code can use the Cairnkeep memory MCP and the generated project launcher.
+It does not yet receive Cairnkeep-specific skills, commands, or hooks.
+
+For local stdio memory, create `.qwen/settings.json` in the project:
+
+```json
+{
+  "mcpServers": {
+    "cairn-memory": {
+      "command": "cairn",
+      "args": ["memory-server"]
+    }
+  }
+}
+```
+
+Review and approve the project server, then launch it:
+
+```bash
+qwen mcp approve cairn-memory
+./.ai/start-qwen.sh
+```
+
+For authenticated remote HTTP, use `httpUrl` plus environment-expanded headers
+in `.qwen/settings.json`. Keep the endpoint and bearer token in `.ai/.env` or a
+machine secret store, not in the JSON file. See
+[Harness compatibility](harness-compatibility.md#qwen-code) for the tested
+configuration, approval behavior, and overlay guidance.
+
 ## Setup order (Pi)
 
 Pi trajectory capture uses the same project scaffold and store, but its source
@@ -663,13 +695,13 @@ maintain a running install — without forking the core. All are opt-in.
 ### Launcher seams
 
 The generic launchers (`.ai/start-claude.sh`, `.ai/start-opencode.sh`,
-`.ai/start-kimi.sh`, and `.ai/start-pi.sh`) run optional hooks around the
+`.ai/start-kimi.sh`, `.ai/start-qwen.sh`, and `.ai/start-pi.sh`) run optional hooks around the
 harness, each a no-op when absent:
 
 | Seam | When | Purpose |
 |---|---|---|
 | `.ai/pre-launch.sh` | sourced after `.env`, before launch | export env (e.g. a provider base URL / auth), refresh credentials, or abort by returning non-zero |
-| `CAIRN_EXTRA_SETTINGS` | read just before launch | path to a settings file layered on Claude Code (`--settings`) or OpenCode (`OPENCODE_CONFIG`); Kimi and Pi leave the variable available to hooks but do not interpret it |
+| `CAIRN_EXTRA_SETTINGS` | read just before launch | path to a settings file layered on Claude Code (`--settings`) or OpenCode (`OPENCODE_CONFIG`); Kimi, Qwen, and Pi leave the variable available to hooks but do not interpret it |
 | `.ai/post-exit.sh` | sourced after the harness exits | teardown; `CAIRN_EXIT_STATUS` holds the exit code |
 
 A wrapper that needs a non-default provider drops a `pre-launch.sh` that renders

package/examples/eval/bundled-fake.json

@@ -1 +1 @@
-{"identifier":"cairn-offline-fake-v1","package_version":"2.5.0","schema_version":1,"task_set_digest":"13e95379f35839593047ec34521a65a8fa3ab92bd3993bca9dc8bf5c4a9ff36f"}
+{"identifier":"cairn-offline-fake-v1","package_version":"2.6.0","schema_version":1,"task_set_digest":"13e95379f35839593047ec34521a65a8fa3ab92bd3993bca9dc8bf5c4a9ff36f"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@cairnkeep/cli",
-  "version": "2.5.0",
-  "description": "A durable, harness-agnostic memory + context layer for coding agents (Claude Code, OpenCode, Pi).",
+  "version": "2.6.0",
+  "description": "A durable, harness-agnostic memory + context layer for coding agents and MCP clients.",
   "license": "Apache-2.0",
   "type": "module",
   "publishConfig": {
@@ -63,6 +63,7 @@
     "agent",
     "claude-code",
     "opencode",
+    "qwen-code",
     "pi-coding-agent",
     "context",
     "rag"

package/scripts/bootstrap.sh

@@ -57,6 +57,7 @@ install_file "$TPL/start-claude.sh.template"   "$target/.ai/start-claude.sh"   0
 install_file "$TPL/start-opencode.sh.template" "$target/.ai/start-opencode.sh" 0755
 install_file "$TPL/start-pi.sh.template"       "$target/.ai/start-pi.sh"       0755
 install_file "$TPL/start-kimi.sh.template"     "$target/.ai/start-kimi.sh"     0755
+install_file "$TPL/start-qwen.sh.template"     "$target/.ai/start-qwen.sh"     0755
 install_file "$TPL/env.example.template"       "$target/.ai/env.example"       0644
 install_file "$TPL/trajectory-redaction.json.template" "$target/.ai/trajectory-redaction.json" 0644
 install_file "$TPL/capabilities.json.template" "$target/.ai/capabilities.json" 0600
@@ -107,3 +108,4 @@ echo "     For Pi trajectory capture, also run: cairn sync-pi --apply"
 echo "     From a source clone, use bin/cairn in place of cairn."
 echo "  4. Launch: $target/.ai/start-claude.sh"
 echo "     Kimi memory-client launch: $target/.ai/start-kimi.sh"
+echo "     Qwen memory-client launch: $target/.ai/start-qwen.sh"

package/scripts/test-bootstrap-untracked.sh

@@ -54,6 +54,7 @@ git -C "$tmp/repo" init -q
 "$ROOT/scripts/bootstrap.sh" --untracked "$tmp/repo" >/dev/null
 [[ -f "$tmp/repo/.ai/start-claude.sh" ]] || fail "scaffold missing"
 [[ -x "$tmp/repo/.ai/start-kimi.sh" ]] || fail "Kimi launcher missing"
+[[ -x "$tmp/repo/.ai/start-qwen.sh" ]] || fail "Qwen launcher missing"
 [[ -f "$tmp/repo/.planning/config.json" ]] || fail "planning layer missing"
 [[ -f "$tmp/repo/.agentfs/.gitignore" ]] || fail "project-memory ignore guard missing"
 [[ -z "$(git -C "$tmp/repo" status --porcelain)" ]] || fail "scaffold visible to git"
@@ -67,7 +68,7 @@ grep -qxF "/.agentfs/" "$tmp/repo/.git/info/exclude" || fail "missing /.agentfs/
 printf '%s\n' '{"schema_version":1,"capabilities":{"wiki":false},"logging":{"callbacks":true}}' >"$tmp/repo/.ai/capabilities.json"
 chmod 600 "$tmp/repo/.ai/capabilities.json"
 printf '%s\n' '# operator-owned environment' >"$tmp/repo/.ai/env.example"
-asset_paths='.ai/start-claude.sh .ai/start-opencode.sh .ai/start-pi.sh .ai/start-kimi.sh .ai/env.example .ai/trajectory-redaction.json .ai/capabilities.json .agentfs/.gitignore .planning/config.json .planning/wiki/index.md .planning/wiki/policy.md .planning/wiki/CONTRADICTIONS.md .planning/wiki/LOG.md .planning/alignment/policy.md .planning/alignment/gap-register.yaml .planning/graphs/policy.md .planning/graphs/.gitignore .planning/security/policy.md'
+asset_paths='.ai/start-claude.sh .ai/start-opencode.sh .ai/start-pi.sh .ai/start-kimi.sh .ai/start-qwen.sh .ai/env.example .ai/trajectory-redaction.json .ai/capabilities.json .agentfs/.gitignore .planning/config.json .planning/wiki/index.md .planning/wiki/policy.md .planning/wiki/CONTRADICTIONS.md .planning/wiki/LOG.md .planning/alignment/policy.md .planning/alignment/gap-register.yaml .planning/graphs/policy.md .planning/graphs/.gitignore .planning/security/policy.md'
 mkdir -p "$tmp/assets-before"
 for path in $asset_paths; do
   cp "$tmp/repo/$path" "$tmp/assets-before/${path//\//__}"

package/scripts/test-launcher-hooks.sh

@@ -425,6 +425,8 @@ pi_launcher="$repo/.ai/start-pi.sh"
 [[ -x "$pi_launcher" ]] || fail "Pi launcher not scaffolded"
 kimi_launcher="$repo/.ai/start-kimi.sh"
 [[ -x "$kimi_launcher" ]] || fail "Kimi launcher not scaffolded"
+qwen_launcher="$repo/.ai/start-qwen.sh"
+[[ -x "$qwen_launcher" ]] || fail "Qwen launcher not scaffolded"
 
 # OpenCode's run mode ends a turn after content-only output. Commands that need
 # owner I/O must therefore make their first response action a tool call rather
@@ -471,12 +473,18 @@ cat > "$tmp/bin/kimi" <<'FAKE'
 { echo "args:$*"; echo "prelaunch:${PRELAUNCH_RAN:-0}"; echo "extra:${CAIRN_EXTRA_SETTINGS:-}"; } > "$KIMI_LOG"
 exit "${FAKE_EXIT:-0}"
 FAKE
-chmod +x "$tmp/bin/claude" "$tmp/bin/opencode" "$tmp/bin/kimi"
+cat > "$tmp/bin/qwen" <<'FAKE'
+#!/usr/bin/env bash
+{ echo "args:$*"; echo "prelaunch:${PRELAUNCH_RAN:-0}"; echo "extra:${CAIRN_EXTRA_SETTINGS:-}"; } > "$QWEN_LOG"
+exit "${FAKE_EXIT:-0}"
+FAKE
+chmod +x "$tmp/bin/claude" "$tmp/bin/opencode" "$tmp/bin/kimi" "$tmp/bin/qwen"
 ln -s "$ROOT/bin/cairn" "$tmp/bin/cairn"
 export PATH="$tmp/bin:$PATH"
 export CLAUDE_LOG="$tmp/claude.log"
 export OPENCODE_LOG="$tmp/opencode.log"
 export KIMI_LOG="$tmp/kimi.log"
+export QWEN_LOG="$tmp/qwen.log"
 
 # Claude sync has three exact installation states. Normal sync and an explicit
 # overlay request with the master off must contain no capability hook bytes or
@@ -540,6 +548,10 @@ grep -qx "capability-registration:0" "$OPENCODE_LOG" || fail "OpenCode baseline
 grep -qx "args:--foo bar" "$KIMI_LOG" || fail "Kimi baseline did not pass args through"
 grep -qx "prelaunch:0" "$KIMI_LOG" || fail "Kimi prelaunch marker leaked without a hook"
 
+"$qwen_launcher" --foo bar >/dev/null 2>&1 || fail "Qwen baseline launch failed"
+grep -qx "args:--foo bar" "$QWEN_LOG" || fail "Qwen baseline did not pass args through"
+grep -qx "prelaunch:0" "$QWEN_LOG" || fail "Qwen prelaunch marker leaked without a hook"
+
 # Invalid/off master values stay on the legacy direct-exec path: one harness
 # process, unchanged argv/config environment, and no isolated assets or store.
 legacy_claude="$tmp/legacy-claude"
@@ -636,6 +648,12 @@ grep -qx "args:--plan" "$KIMI_LOG" || fail "Kimi pre-launch changed harness argv
 grep -qx "prelaunch:1" "$KIMI_LOG" || fail "Kimi pre-launch env not visible to harness"
 grep -qx "extra:$tmp/settings.json" "$KIMI_LOG" || fail "Kimi pre-launch environment was not preserved"
 
+rm -f "$QWEN_LOG"
+"$qwen_launcher" --approval-mode plan >/dev/null 2>&1 || fail "Qwen launch with pre-launch failed"
+grep -qx "args:--approval-mode plan" "$QWEN_LOG" || fail "Qwen pre-launch changed harness argv"
+grep -qx "prelaunch:1" "$QWEN_LOG" || fail "Qwen pre-launch env not visible to harness"
+grep -qx "extra:$tmp/settings.json" "$QWEN_LOG" || fail "Qwen pre-launch environment was not preserved"
+
 # 3. pre-launch.sh non-zero aborts the launch before the harness runs.
 rm -f "$CLAUDE_LOG"
 cat > "$repo/.ai/pre-launch.sh" <<'EOF'
@@ -647,6 +665,9 @@ if "$launcher" >/dev/null 2>&1; then fail "non-zero pre-launch should abort the
 rm -f "$KIMI_LOG"
 if "$kimi_launcher" >/dev/null 2>&1; then fail "non-zero pre-launch should abort Kimi"; fi
 [[ ! -f "$KIMI_LOG" ]] || fail "Kimi ran despite pre-launch abort"
+rm -f "$QWEN_LOG"
+if "$qwen_launcher" >/dev/null 2>&1; then fail "non-zero pre-launch should abort Qwen"; fi
+[[ ! -f "$QWEN_LOG" ]] || fail "Qwen ran despite pre-launch abort"
 rm -f "$repo/.ai/pre-launch.sh"
 
 # 4. post-exit.sh runs after the harness with $CAIRN_EXIT_STATUS.
@@ -666,6 +687,13 @@ status=$?
 grep -qx "args:--auto" "$KIMI_LOG" || fail "Kimi launcher changed arguments"
 grep -qx "post:8" "$tmp/post.log" || fail "Kimi launcher post-exit status missing"
 
+rm -f "$tmp/post.log" "$QWEN_LOG"
+FAKE_EXIT=10 "$qwen_launcher" --output-format json >/dev/null 2>&1 && fail "Qwen launcher should propagate harness exit code"
+status=$?
+[[ "$status" -eq 10 ]] || fail "expected exit 10 from Qwen launcher, got $status"
+grep -qx "args:--output-format json" "$QWEN_LOG" || fail "Qwen launcher changed arguments"
+grep -qx "post:10" "$tmp/post.log" || fail "Qwen launcher post-exit status missing"
+
 # 5. Pi launcher preserves the same env/pre/post seams and passes arguments
 # unchanged; Pi has no generic settings-file flag so CAIRN_EXTRA_SETTINGS is ignored.
 rm -f "$repo/.ai/pre-launch.sh" "$repo/.ai/post-exit.sh"

package/scripts/test-package-install.sh

@@ -44,6 +44,7 @@ bootstrap_output=$(cairn bootstrap "$tmp/project")
 [[ -x "$tmp/project/.ai/start-claude.sh" ]] || fail "bootstrap did not install an executable Claude launcher"
 [[ -x "$tmp/project/.ai/start-pi.sh" ]] || fail "bootstrap did not install an executable Pi launcher"
 [[ -x "$tmp/project/.ai/start-kimi.sh" ]] || fail "bootstrap did not install an executable Kimi launcher"
+[[ -x "$tmp/project/.ai/start-qwen.sh" ]] || fail "bootstrap did not install an executable Qwen launcher"
 [[ -f "$tmp/project/.planning/config.json" ]] || fail "bootstrap did not install the planning scaffold"
 
 (cd "$tmp/project" && cairn doctor) >/dev/null || fail "installed package failed cairn doctor"
@@ -223,6 +224,8 @@ NODE
   fail "npm tarball omitted the Pi launcher template"
 [[ -f "$installed_root/templates/start-kimi.sh.template" ]] || \
   fail "npm tarball omitted the Kimi launcher template"
+[[ -f "$installed_root/templates/start-qwen.sh.template" ]] || \
+  fail "npm tarball omitted the Qwen launcher template"
 [[ -f "$installed_root/schemas/note.schema.json" ]] || \
   fail "npm tarball omitted the note schema"
 [[ -f "$installed_root/schemas/memory-node.schema.json" ]] || \

package/scripts/uninstall.sh

@@ -40,6 +40,7 @@ PROJECT_AI_FILES=(
   start-opencode.sh
   start-pi.sh
   start-kimi.sh
+  start-qwen.sh
   env.example
   trajectory-redaction.json
   capabilities.json

package/templates/start-qwen.sh.template

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+# Cairnkeep launcher for Qwen Code. Loads this repo's private .ai/.env, runs
+# the optional pre/post seams, and launches Qwen from the project root. Qwen
+# reads user ~/.qwen/settings.json plus project .qwen/settings.json and
+# .mcp.json configuration.
+set -euo pipefail
+ROOT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)
+
+if [[ -f "$ROOT_DIR/.ai/.env" ]]; then
+  set -a
+  # shellcheck disable=SC1091
+  . "$ROOT_DIR/.ai/.env"
+  set +a
+fi
+if [[ -f "$ROOT_DIR/.ai/pre-launch.sh" ]]; then
+  # shellcheck disable=SC1091
+  . "$ROOT_DIR/.ai/pre-launch.sh"
+fi
+
+cd "$ROOT_DIR"
+
+if [[ -f "$ROOT_DIR/.ai/post-exit.sh" ]]; then
+  set +e
+  qwen "$@"
+  CAIRN_EXIT_STATUS=$?
+  set -e
+  export CAIRN_EXIT_STATUS
+  # shellcheck disable=SC1091
+  . "$ROOT_DIR/.ai/post-exit.sh" || true
+  exit "$CAIRN_EXIT_STATUS"
+fi
+exec qwen "$@"