context-mode 1.0.88 → 1.0.90

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Claude Code plugins by Mert Koseoğlu",
-    "version": "1.0.88"
+    "version": "1.0.90"
   },
   "plugins": [
     {
       "name": "context-mode",
       "source": "./",
       "description": "Claude Code MCP plugin that saves 98% of your context window. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and intent-driven search.",
-      "version": "1.0.88",
+      "version": "1.0.90",
       "author": {
         "name": "Mert Koseoğlu"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "context-mode",
-  "version": "1.0.88",
+  "version": "1.0.90",
   "description": "MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",
   "author": {
     "name": "Mert Koseoğlu",

package/.openclaw-plugin/openclaw.plugin.json

@@ -3,7 +3,7 @@
   "name": "Context Mode",
   "kind": "tool",
   "description": "OpenClaw plugin that saves 98% of your context window. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and intent-driven search.",
-  "version": "1.0.88",
+  "version": "1.0.90",
   "sandbox": {
     "mode": "permissive",
     "filesystem_access": "full",

package/.openclaw-plugin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "context-mode",
-  "version": "1.0.88",
+  "version": "1.0.90",
   "description": "OpenClaw plugin that saves 98% of your context window. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and intent-driven search.",
   "author": {
     "name": "Mert Koseoğlu",

package/README.md

@@ -31,13 +31,24 @@
 
 ## The Problem
 
-Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in progress, and what you last asked for.
+Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in progress, and what you last asked for. On top of that, the agent wastes output tokens on filler, pleasantries, and verbose explanations — burning context from both sides.
 
-Context Mode is an MCP server that solves all three sides of this problem:
+### How Context Mode Solves It
+
+Context Mode is an MCP server that solves all four sides of this problem:
 
 1. **Context Saving** — Sandbox tools keep raw data out of the context window. 315 KB becomes 5.4 KB. 98% reduction.
 2. **Session Continuity** — Every file edit, git operation, task, error, and user decision is tracked in SQLite. When the conversation compacts, context-mode doesn't dump this data back into context — it indexes events into FTS5 and retrieves only what's relevant via BM25 search. The model picks up exactly where you left off. If you don't `--continue`, previous session data is deleted immediately — a fresh session means a clean slate.
-3. **Think in Code** — The LLM should program the analysis, not compute it. Instead of reading 50 files into context to count functions, the agent writes a script that does the counting and `console.log()`s only the result. One script replaces ten tool calls and saves 100x context. This is a mandatory paradigm across all 12 platforms: stop treating the LLM as a data processor, treat it as a code generator.
+3. **Think in Code** — The LLM should program the analysis, not compute it. Instead of reading 50 files into context to count functions, the agent writes a script that does the counting and `console.log()`s only the result. One script replaces ten tool calls and saves 100x context. This is a mandatory paradigm across all 14 platforms: stop treating the LLM as a data processor, treat it as a code generator.
+
+   ```js
+   // Before: 47 × Read() = 700 KB.  After: 1 × ctx_execute() = 3.6 KB.
+   ctx_execute("javascript", `
+     const files = fs.readdirSync('src').filter(f => f.endsWith('.ts'));
+     files.forEach(f => console.log(f + ': ' + fs.readFileSync('src/'+f,'utf8').split('\\n').length + ' lines'));
+   `);
+   ```
+4. **Output Compression** — Terse like caveman. Technical substance exact. Only fluff die. Drop articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged. Pattern: [thing] [action] [reason]. [next step]. Auto-expand for security warnings, irreversible actions, and user confusion. ~65-75% output token reduction with full technical accuracy.
 
 <a href="https://www.youtube.com/watch?v=QUHrntlfPo4">
   <picture>
@@ -158,7 +169,11 @@ This gives you the 6 sandbox tools without automatic routing. The model can stil
 
 You should see `context-mode: ... - Connected`.
 
-**Routing:** Automatic. The SessionStart hook injects routing instructions at runtime — no `GEMINI.md` file is written to your project. All four hooks (BeforeTool, AfterTool, PreCompress, SessionStart) handle enforcement programmatically.
+**Routing:** Automatic via SessionStart hook. Optionally copy routing instructions for full model awareness:
+
+```bash
+cp node_modules/context-mode/configs/gemini-cli/GEMINI.md ./GEMINI.md
+```
 
 > **Why the BeforeTool matcher?** It targets only tools that produce large output (`run_shell_command`, `read_file`, `read_many_files`, `grep_search`, `search_file_content`, `web_fetch`, `activate_skill`) plus context-mode's own tools (`mcp__plugin_context-mode`). This avoids unnecessary hook overhead on lightweight tools while intercepting every tool that could flood your context window.
 
@@ -213,12 +228,67 @@ Full config reference: [`configs/gemini-cli/settings.json`](configs/gemini-cli/s
 
 **Verify:** Open Copilot Chat and type `ctx stats`. Context-mode tools should appear and respond.
 
-**Routing:** Automatic. The SessionStart hook injects routing instructions at runtime — no `copilot-instructions.md` file is written to your project.
+**Routing:** Automatic via SessionStart hook. Optionally copy routing instructions for full model awareness:
+
+```bash
+cp node_modules/context-mode/configs/vscode-copilot/copilot-instructions.md .github/copilot-instructions.md
+```
 
 Full hook config including PreCompact: [`configs/vscode-copilot/hooks.json`](configs/vscode-copilot/hooks.json)
 
 </details>
 
+<details>
+<summary><strong>JetBrains Copilot</strong> — hooks with SessionStart</summary>
+
+**Prerequisites:** Node.js 18+, JetBrains IDE with GitHub Copilot plugin v1.5.57+.
+
+**Install:**
+
+1. Install context-mode globally:
+
+   ```bash
+   npm install -g context-mode
+   ```
+
+2. Add MCP server via Settings UI: **Settings > Tools > AI Assistant > Model Context Protocol (MCP) > Add Server**:
+   - **Name:** `context-mode`
+   - **Command:** `context-mode`
+
+3. Create `.github/hooks/context-mode.json`:
+
+   ```json
+   {
+     "hooks": {
+       "PreToolUse": [
+         { "type": "command", "command": "context-mode hook jetbrains-copilot pretooluse" }
+       ],
+       "PostToolUse": [
+         { "type": "command", "command": "context-mode hook jetbrains-copilot posttooluse" }
+       ],
+       "SessionStart": [
+         { "type": "command", "command": "context-mode hook jetbrains-copilot sessionstart" }
+       ]
+     }
+   }
+   ```
+
+4. Restart the JetBrains IDE.
+
+**Verify:** Open Copilot Chat and type `ctx stats`. Context-mode tools should appear and respond.
+
+**Routing:** Automatic via SessionStart hook. Optionally copy routing instructions for full model awareness:
+
+```bash
+cp node_modules/context-mode/configs/jetbrains-copilot/copilot-instructions.md .github/copilot-instructions.md
+```
+
+Full hook config including PreCompact: [`configs/jetbrains-copilot/hooks.json`](configs/jetbrains-copilot/hooks.json)
+
+Full setup guide: [`docs/jetbrains-copilot.md`](docs/jetbrains-copilot.md)
+
+</details>
+
 <details>
 <summary><strong>Cursor</strong> — hooks with stop support</summary>
 
@@ -427,7 +497,7 @@ Full documentation: [`docs/adapters/openclaw.md`](docs/adapters/openclaw.md)
 </details>
 
 <details>
-<summary><strong>Codex CLI</strong> — MCP + hooks (waiting for upstream dispatch)</summary>
+<summary><strong>Codex CLI</strong> — MCP + hooks</summary>
 
 **Prerequisites:** Node.js 18+, Codex CLI installed.
 
@@ -446,32 +516,23 @@ Full documentation: [`docs/adapters/openclaw.md`](docs/adapters/openclaw.md)
    command = "context-mode"
    ```
 
-3. *(Waiting for upstream)* Enable the hooks feature flag. Add to `~/.codex/config.toml`:
-
-   ```toml
-   [features]
-   codex_hooks = true
-   ```
-
-   > **Status:** Codex CLI's hook system is implemented in source (`codex-rs/hooks/`) but hook dispatch is not yet wired into the tool execution pipeline (`Stage::UnderDevelopment`). The feature flag is accepted but hooks don't fire during sessions as of v0.118.0. Our hook scripts are ready — they'll work immediately once Codex enables dispatch. Track progress: [openai/codex#16685](https://github.com/openai/codex/issues/16685).
-
-4. *(Prepare for when dispatch is enabled)* Add hooks for routing enforcement and session tracking. Create `~/.codex/hooks.json`:
+3. Add hooks for routing enforcement and session tracking. Create `~/.codex/hooks.json`:
 
    ```json
    {
      "hooks": {
-       "PreToolUse": [{ "hooks": [{ "type": "command", "command": "context-mode hook codex pretooluse" }] }],
+       "PreToolUse": [{ "matcher": "local_shell|shell|shell_command|exec_command|container.exec|Bash|Shell|grep_files|mcp__plugin_context-mode_context-mode__ctx_execute|mcp__plugin_context-mode_context-mode__ctx_execute_file|mcp__plugin_context-mode_context-mode__ctx_batch_execute", "hooks": [{ "type": "command", "command": "context-mode hook codex pretooluse" }] }],
        "PostToolUse": [{ "hooks": [{ "type": "command", "command": "context-mode hook codex posttooluse" }] }],
        "SessionStart": [{ "hooks": [{ "type": "command", "command": "context-mode hook codex sessionstart" }] }]
      }
    }
    ```
 
-   `PreToolUse` enforces sandbox routing (blocks dangerous commands, redirects to MCP tools). `PostToolUse` captures session events. `SessionStart` restores state after compaction.
+   `PreToolUse` enforces deny/block routing today and is prepared for input rewrites once Codex supports them. `PostToolUse` captures session events. `SessionStart` restores state after compaction.
 
-   > **Note:** PreToolUse routing supports deny rules only (blocks dangerous commands). Context injection (`additionalContext`) is not supported in Codex PreToolUse — it works via PostToolUse and SessionStart instead. This is handled automatically.
+   > **Note:** Codex PreToolUse routing currently supports deny rules only (blocks dangerous commands). It still needs upstream `updatedInput` support before context-mode can rewrite tool input; track [openai/codex#18491](https://github.com/openai/codex/issues/18491). Context injection (`additionalContext`) is not supported in Codex PreToolUse — it works via PostToolUse and SessionStart instead. This is handled automatically.
 
-5. Copy routing instructions (recommended even with hooks for full routing awareness):
+4. Copy routing instructions (recommended even with hooks for full routing awareness):
 
    ```bash
    cp node_modules/context-mode/configs/codex/AGENTS.md ./AGENTS.md
@@ -479,13 +540,65 @@ Full documentation: [`docs/adapters/openclaw.md`](docs/adapters/openclaw.md)
 
    For global use: `cp node_modules/context-mode/configs/codex/AGENTS.md ~/.codex/AGENTS.md`. Global applies to all projects. If both exist, Codex CLI merges them.
 
-6. Restart Codex CLI.
+5. Restart Codex CLI.
 
 **Verify:** Start a session and type `ctx stats`. Context-mode tools should appear and respond.
 
-**Routing:** MCP tools work. Hook-based routing is ready but waiting for Codex to enable hook dispatch. The `AGENTS.md` file provides routing instructions for model awareness in the meantime.
+**Routing:** MCP tools work. Hook-based routing is active when `~/.codex/hooks.json` is configured. The `AGENTS.md` file provides routing instructions for model awareness.
 
-> **Exec mode regression (v0.118.0):** `codex exec` cancels all MCP tool calls with "user cancelled MCP tool call". The `tool_call_mcp_elicitation` flag went stable in 0.118.0, adding an approval prompt that exec-mode can't handle. **Pin to Codex ≤0.116.0 for exec-mode MCP.** Confirmed by upstream: [openai/codex#16685](https://github.com/openai/codex/issues/16685). Interactive mode (`codex` / `codex --full-auto`) is not affected.
+</details>
+
+<details>
+<summary><strong>Qwen Code</strong> — MCP + hooks (identical wire protocol to Claude Code)</summary>
+
+**Prerequisites:** Node.js 18+, Qwen Code installed (`npm install -g @qwen-code/qwen-code`).
+
+1. Install context-mode:
+
+   ```bash
+   npm install -g context-mode
+   ```
+
+2. Add context-mode as an MCP server. Add to `~/.qwen/settings.json`:
+
+   ```json
+   {
+     "mcpServers": {
+       "context-mode": {
+         "command": "context-mode",
+         "args": []
+       }
+     }
+   }
+   ```
+
+3. Add hooks for routing enforcement and session tracking. Add to `~/.qwen/settings.json`:
+
+   ```json
+   {
+     "hooks": {
+       "PreToolUse": [{ "matcher": "run_shell_command|read_file|read_many_files|grep_search|web_fetch|agent|mcp__plugin_context-mode_context-mode__ctx_execute|mcp__plugin_context-mode_context-mode__ctx_execute_file|mcp__plugin_context-mode_context-mode__ctx_batch_execute", "hooks": [{ "type": "command", "command": "context-mode hook qwen-code pretooluse" }] }],
+       "PostToolUse": [{ "matcher": "", "hooks": [{ "type": "command", "command": "context-mode hook qwen-code posttooluse" }] }],
+       "SessionStart": [{ "matcher": "", "hooks": [{ "type": "command", "command": "context-mode hook qwen-code sessionstart" }] }],
+       "PreCompact": [{ "matcher": "", "hooks": [{ "type": "command", "command": "context-mode hook qwen-code precompact" }] }],
+       "UserPromptSubmit": [{ "matcher": "", "hooks": [{ "type": "command", "command": "context-mode hook qwen-code userpromptsubmit" }] }]
+     }
+   }
+   ```
+
+4. Copy routing instructions (recommended for full routing awareness):
+
+   ```bash
+   cp node_modules/context-mode/configs/qwen-code/QWEN.md ./QWEN.md
+   ```
+
+   For global use: `cp node_modules/context-mode/configs/qwen-code/QWEN.md ~/.qwen/QWEN.md`
+
+5. Restart Qwen Code.
+
+**Verify:** Start a session and type `ctx stats`. Context-mode tools should appear and respond.
+
+**Note:** Qwen Code uses the same hook wire protocol as Claude Code (JSON stdin/stdout, same event names). Auto-detected via MCP clientInfo (`qwen-cli-mcp-client-*`) or `QWEN_PROJECT_DIR` env var.
 
 </details>
 
@@ -563,7 +676,7 @@ Full configs: [`configs/antigravity/mcp_config.json`](configs/antigravity/mcp_co
      "description": "Context-mode hooks for context window protection",
      "hooks": {
        "preToolUse": [
-         { "matcher": "*", "command": "context-mode hook kiro pretooluse" }
+         { "matcher": "execute_bash|fs_read|@context-mode/ctx_execute|@context-mode/ctx_execute_file|@context-mode/ctx_batch_execute", "command": "context-mode hook kiro pretooluse" }
        ],
        "postToolUse": [
          { "matcher": "*", "command": "context-mode hook kiro posttooluse" }
@@ -638,31 +751,39 @@ Full configs: [`configs/kiro/mcp.json`](configs/kiro/mcp.json) | [`configs/kiro/
 
 **Install:**
 
-1. Clone the extension:
+1. Install context-mode globally:
 
    ```bash
-   git clone https://github.com/mksglu/context-mode.git ~/.pi/extensions/context-mode
-   cd ~/.pi/extensions/context-mode
-   npm install
-   npm run build
+   npm install -g context-mode
    ```
 
-2. Add to `~/.pi/agent/mcp.json` (or `.pi/mcp.json` for project-level):
+2. Install the package into Pi:
+
+   ```bash
+   pi install npm:context-mode
+   ```
+
+   Alternative — add it manually to `~/.pi/agent/settings.json` (or `.pi/settings.json` for project-level):
+
+   ```json
+   {
+     "packages": ["npm:context-mode"]
+   }
+   ```
+
+3. Add to `~/.pi/agent/mcp.json` (or `.pi/mcp.json` for project-level):
 
    ```json
    {
      "mcpServers": {
        "context-mode": {
-         "command": "node",
-         "args": ["/home/youruser/.pi/extensions/context-mode/node_modules/context-mode/start.mjs"]
+         "command": "context-mode"
        }
      }
    }
    ```
 
-   > **Note:** JSON does not expand `~`. Replace `/home/youruser` with your actual home directory (run `echo $HOME` to find it).
-
-3. Restart Pi.
+4. Restart Pi.
 
 **Verify:** In a Pi session, type `ctx stats`. Context-mode tools should appear and respond.
 
@@ -787,16 +908,16 @@ Context Mode captures every meaningful event during your session and persists th
 
 Session continuity requires 4 hooks working together:
 
-| Hook | Role | Claude Code | Gemini CLI | VS Code Copilot | Cursor | OpenCode | KiloCode | OpenClaw | Codex CLI | Antigravity | Kiro | Zed | Pi |
-|---|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| **PreToolUse** | Enforces sandbox routing before tool execution | Yes | -- | -- | Yes | -- | -- | -- | Yes | -- | Yes | -- | ✓ (via tool_call event) |
-| **PostToolUse** | Captures events after each tool call | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | ✓ (via tool_result event) |
-| **UserPromptSubmit** | Captures user decisions and corrections | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
-| **PreCompact** | Builds snapshot before compaction | Yes | Yes | Yes | -- | Plugin | Plugin | Plugin | -- | -- | -- | -- | ✓ (via session_before_compact) |
-| **SessionStart** | Restores state after compaction or resume | Yes | Yes | Yes | -- | -- | -- | Plugin | Yes | -- | -- | -- | ✓ (via session_start event) |
-| | **Session completeness** | **Full** | **High** | **High** | **Partial** | **High** | **High** | **High** | **Partial** | **--** | **Partial** | **--** | **High** |
+| Hook | Role | Claude Code | Gemini CLI | VS Code Copilot | JetBrains Copilot | Cursor | OpenCode | KiloCode | OpenClaw | Codex CLI | Antigravity | Kiro | Zed | Pi |
+|---|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| **PreToolUse** | Enforces sandbox routing before tool execution | Yes | -- | -- | -- | Yes | -- | -- | -- | Yes | -- | Yes | -- | ✓ (via tool_call event) |
+| **PostToolUse** | Captures events after each tool call | Yes | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | ✓ (via tool_result event) |
+| **UserPromptSubmit** | Captures user decisions and corrections | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
+| **PreCompact** | Builds snapshot before compaction | Yes | Yes | Yes | Yes | -- | Plugin | Plugin | Plugin | -- | -- | -- | -- | ✓ (via session_before_compact) |
+| **SessionStart** | Restores state after compaction or resume | Yes | Yes | Yes | Yes | -- | -- | -- | Plugin | Yes | -- | -- | -- | ✓ (via session_start event) |
+| | **Session completeness** | **Full** | **High** | **High** | **High** | **Partial** | **High** | **High** | **High** | **Partial** | **--** | **Partial** | **--** | **High** |
 
-> **Note:** Full session continuity (capture + snapshot + restore) works on **Claude Code**, **Gemini CLI**, and **VS Code Copilot**. **OpenCode** provides **high** session continuity: it captures tool events and injects compaction snapshots via the plugin, but SessionStart is not yet available ([#14808](https://github.com/sst/opencode/issues/14808)), so startup/resume restore is not supported. **KiloCode** shares the same plugin architecture as OpenCode via the OpenCodeAdapter, so its continuity level depends on KiloCode's SessionStart support. **Cursor** captures tool events via `preToolUse`/`postToolUse`, but `sessionStart` is currently rejected by Cursor's validator ([forum report](https://forum.cursor.com/t/unknown-hook-type-sessionstart/149566)), so session restore after compaction is not available yet. **OpenClaw** uses native gateway plugin hooks (`api.on()`) for full session continuity. **Pi Coding Agent** provides high session continuity via extension hooks (`tool_call`, `tool_result`, `session_start`, `session_before_compact`). **Codex CLI** hook-based session tracking is ready but waiting for upstream hook dispatch (codex_hooks Stage::UnderDevelopment, [openai/codex#16685](https://github.com/openai/codex/issues/16685)). MCP tools work. Once dispatch is enabled, session tracking will activate automatically. **Antigravity**, **Kiro**, and **Zed** have no hook support in the current release, so session tracking is not available.
+> **Note:** Full session continuity (capture + snapshot + restore) works on **Claude Code**, **Gemini CLI**, **VS Code Copilot**, and **JetBrains Copilot**. **OpenCode** provides **high** session continuity: it captures tool events and injects compaction snapshots via the plugin, but SessionStart is not yet available ([#14808](https://github.com/sst/opencode/issues/14808)), so startup/resume restore is not supported. **KiloCode** shares the same plugin architecture as OpenCode via the OpenCodeAdapter, so its continuity level depends on KiloCode's SessionStart support. **Cursor** captures tool events via `preToolUse`/`postToolUse`, but `sessionStart` is currently rejected by Cursor's validator ([forum report](https://forum.cursor.com/t/unknown-hook-type-sessionstart/149566)), so session restore after compaction is not available yet. **OpenClaw** uses native gateway plugin hooks (`api.on()`) for full session continuity. **Pi Coding Agent** provides high session continuity via extension hooks (`tool_call`, `tool_result`, `session_start`, `session_before_compact`). **Codex CLI** provides partial hook-based session tracking through PreToolUse, PostToolUse, and SessionStart; MCP tools work. **Antigravity**, **Kiro**, and **Zed** have no hook support in the current release, so session tracking is not available.
 
 <details>
 <summary><strong>What gets captured</strong></summary>
@@ -871,6 +992,8 @@ Detailed event data is also indexed into FTS5 for on-demand retrieval via `searc
 
 **VS Code Copilot** — High coverage. Same as Gemini CLI — PostToolUse, PreCompact, and SessionStart all fire. User decisions aren't captured but all tool-level events are.
 
+**JetBrains Copilot** — High coverage. Same capabilities as VS Code Copilot — PostToolUse, PreCompact, and SessionStart all fire. Uses the same hook wire protocol and response format. User decisions aren't captured but all tool-level events are.
+
 **Cursor** — Partial coverage. Native `preToolUse` and `postToolUse` hooks capture tool events. `sessionStart` is documented by Cursor but currently rejected by their validator, so session restore is not available. Routing instructions are delivered via MCP server startup instead.
 
 **OpenCode** — Partial. The TypeScript plugin captures PostToolUse events via `tool.execute.after`, but SessionStart is not yet available ([#14808](https://github.com/sst/opencode/issues/14808)). Events are stored but not automatically restored after compaction.
@@ -879,7 +1002,7 @@ Detailed event data is also indexed into FTS5 for on-demand retrieval via `searc
 
 **OpenClaw / Pi Agent** — High coverage. All tool lifecycle hooks (`after_tool_call`, `before_compaction`, `session_start`) fire via the native gateway plugin. User decisions aren't captured but file edits, git ops, errors, and tasks are fully tracked. Falls back to DB snapshot reconstruction if compaction hooks fail on older gateway versions. See [`docs/adapters/openclaw.md`](docs/adapters/openclaw.md).
 
-**Codex CLI** — MCP active, hooks ready. Hook scripts (PreToolUse, PostToolUse, SessionStart) are implemented and tested but Codex CLI doesn't dispatch them yet (Stage::UnderDevelopment). MCP tools work. Track: [openai/codex#16685](https://github.com/openai/codex/issues/16685).
+**Codex CLI** — MCP active, hooks stable. Hook scripts (PreToolUse, PostToolUse, SessionStart) are implemented and tested. PreToolUse deny routing works; input rewriting still depends on upstream `updatedInput` support ([openai/codex#18491](https://github.com/openai/codex/issues/18491)).
 
 **Antigravity** — No session support. No hooks, no event capture. Requires manually copying `GEMINI.md` to your project root. Auto-detected via MCP protocol handshake (`clientInfo.name`).
 
@@ -893,18 +1016,18 @@ Detailed event data is also indexed into FTS5 for on-demand retrieval via `searc
 
 ## Platform Compatibility
 
-| Feature | Claude Code | Gemini CLI | VS Code Copilot | Cursor | OpenCode | KiloCode | OpenClaw | Codex CLI | Antigravity | Kiro | Zed | Pi |
-|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| MCP Server | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
-| PreToolUse Hook | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
-| PostToolUse Hook | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
-| SessionStart Hook | Yes | Yes | Yes | -- | -- | -- | Plugin | Yes | -- | -- | -- | Yes (extension) |
-| PreCompact Hook | Yes | Yes | Yes | -- | Plugin | Plugin | Plugin | -- | -- | -- | -- | Yes (extension) |
-| Can Modify Args | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | -- | -- | Yes (extension) |
-| Can Block Tools | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
-| Utility Commands (ctx) | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes (/ctx-stats, /ctx-doctor) |
-| Slash Commands | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
-| Plugin Marketplace | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
+| Feature | Claude Code | Qwen Code | Gemini CLI | VS Code Copilot | JetBrains Copilot | Cursor | OpenCode | KiloCode | OpenClaw | Codex CLI | Antigravity | Kiro | Zed | Pi |
+|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| MCP Server | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
+| PreToolUse Hook | Yes | Yes | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
+| PostToolUse Hook | Yes | Yes | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
+| SessionStart Hook | Yes | Yes | Yes | Yes | Yes | -- | -- | -- | Plugin | Yes | -- | -- | -- | Yes (extension) |
+| PreCompact Hook | Yes | Yes | Yes | Yes | Yes | -- | Plugin | Plugin | Plugin | -- | -- | -- | -- | Yes (extension) |
+| Can Modify Args | Yes | Yes | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | -- | -- | -- | -- | Yes (extension) |
+| Can Block Tools | Yes | Yes | Yes | Yes | Yes | Yes | Plugin | Plugin | Plugin | Yes | -- | Yes | -- | Yes (extension) |
+| Utility Commands (ctx) | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes (/ctx-stats, /ctx-doctor) |
+| Slash Commands | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
+| Plugin Marketplace | Yes | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
 
 > **OpenCode** uses a TypeScript plugin paradigm — hooks run as in-process functions via `tool.execute.before`, `tool.execute.after`, and `experimental.session.compacting`, providing the same routing enforcement and session continuity as shell-based hooks. SessionStart is not yet available ([#14808](https://github.com/sst/opencode/issues/14808)), but compaction recovery works via the plugin's compacting hook.
 >
@@ -912,7 +1035,7 @@ Detailed event data is also indexed into FTS5 for on-demand retrieval via `searc
 >
 > **OpenClaw** runs context-mode as a native gateway plugin targeting Pi Agent sessions. Hooks register via `api.on()` (tool/lifecycle) and `api.registerHook()` (commands). All tool interception and compaction hooks are supported. See [`docs/adapters/openclaw.md`](docs/adapters/openclaw.md).
 >
-> **Codex CLI** hooks are implemented but dispatch is not yet active (`codex_hooks` is `Stage::UnderDevelopment`). MCP tools work. Hook scripts are ready and will activate once Codex enables dispatch ([openai/codex#16685](https://github.com/openai/codex/issues/16685)). PreToolUse supports `permissionDecision: "deny"` only — `additionalContext` is not supported in PreToolUse (context injection works via PostToolUse and SessionStart instead; the codex formatter handles this automatically). See the Codex install section for setup. **Antigravity** and **Zed** do not support hooks. They rely solely on manually-copied routing instruction files (`AGENTS.md` / `GEMINI.md`) for enforcement (~60% compliance). See each platform's install section for copy instructions. Antigravity and Zed are auto-detected via MCP protocol handshake — no manual platform configuration needed.
+> **Codex CLI** hooks are stable. MCP tools work, and hook scripts activate through `~/.codex/hooks.json`. PreToolUse supports `permissionDecision: "deny"` only; input modification still needs upstream `updatedInput` support ([openai/codex#18491](https://github.com/openai/codex/issues/18491)). `additionalContext` is not supported in PreToolUse (context injection works via PostToolUse and SessionStart instead; the codex formatter handles this automatically). See the Codex install section for setup. **Antigravity** and **Zed** do not support hooks. They rely solely on manually-copied routing instruction files (`AGENTS.md` / `GEMINI.md`) for enforcement (~60% compliance). See each platform's install section for copy instructions. Antigravity and Zed are auto-detected via MCP protocol handshake — no manual platform configuration needed.
 >
 > **Kiro** supports native `preToolUse` and `postToolUse` hooks for routing enforcement and tool event capture. `agentSpawn` (SessionStart equivalent) and `stop` are not yet wired. Requires manually copying `KIRO.md` to your project root. Kiro is auto-detected via MCP protocol handshake (`clientInfo.name`).
 >
@@ -922,13 +1045,14 @@ Detailed event data is also indexed into FTS5 for on-demand retrieval via `searc
 
 Hooks intercept tool calls programmatically — they can block dangerous commands and redirect them to the sandbox before execution. Instruction files guide the model via prompt instructions but cannot block anything. **Always enable hooks where supported.**
 
-> **Note:** Routing instruction files were previously auto-written to project directories on first session start. This was disabled to prevent git tree pollution ([#158](https://github.com/mksglu/context-mode/issues/158), [#164](https://github.com/mksglu/context-mode/issues/164)). Hook-capable platforms (Claude Code, Gemini CLI, VS Code Copilot, Cursor, OpenCode, OpenClaw, Codex CLI) inject routing via hooks and need no file. Non-hook platforms (Zed, Kiro, Antigravity) require a one-time manual copy — see each platform's install section.
+> **Note:** Routing instruction files were previously auto-written to project directories on first session start. This was disabled to prevent git tree pollution ([#158](https://github.com/mksglu/context-mode/issues/158), [#164](https://github.com/mksglu/context-mode/issues/164)). Hook-capable platforms (Claude Code, Gemini CLI, VS Code Copilot, JetBrains Copilot, Cursor, OpenCode, OpenClaw, Codex CLI) inject routing via hooks and need no file. Non-hook platforms (Zed, Kiro, Antigravity) require a one-time manual copy — see each platform's install section.
 
 | Platform | Hooks | Instruction File | With Hooks | Without Hooks |
 |---|:---:|---|:---:|:---:|
 | Claude Code | Yes (auto) | [`CLAUDE.md`](configs/claude-code/CLAUDE.md) | **~98% saved** | ~60% saved |
 | Gemini CLI | Yes | [`GEMINI.md`](configs/gemini-cli/GEMINI.md) | **~98% saved** | ~60% saved |
 | VS Code Copilot | Yes | [`copilot-instructions.md`](configs/vscode-copilot/copilot-instructions.md) | **~98% saved** | ~60% saved |
+| JetBrains Copilot | Yes | [`copilot-instructions.md`](configs/vscode-copilot/copilot-instructions.md) | **~98% saved** | ~60% saved |
 | Cursor | Yes | [`context-mode.mdc`](configs/cursor/context-mode.mdc) | **~98% saved** | ~60% saved |
 | OpenCode | Plugin | [`AGENTS.md`](configs/opencode/AGENTS.md) | **~98% saved** | ~60% saved |
 | OpenClaw | Plugin | [`AGENTS.md`](configs/openclaw/AGENTS.md) | **~98% saved** | ~60% saved |
@@ -1059,7 +1183,7 @@ Context Mode enforces the same permission rules you already use — but extends
 }
 ```
 
-Add this to your project's `.claude/settings.json` (or `~/.claude/settings.json` for global rules). All platforms read security policies from Claude Code's settings format — even on Gemini CLI, VS Code Copilot, and OpenCode. Codex CLI security enforcement requires the `codex_hooks` feature flag to be enabled.
+Add this to your project's `.claude/settings.json` (or `~/.claude/settings.json` for global rules). All platforms read security policies from Claude Code's settings format — even on Gemini CLI, VS Code Copilot, and OpenCode. Codex CLI security enforcement requires the Codex hooks in `~/.codex/hooks.json` to be configured.
 
 The pattern is `Tool(what to match)` where `*` means "anything".
 

package/build/adapters/antigravity/index.d.ts

@@ -16,8 +16,10 @@
  *   - MCP support: https://antigravity.google/docs/mcp
  *   - Tool list: System prompt leak (21 verified tools)
  */
+import { BaseAdapter } from "../base.js";
 import type { HookAdapter, HookParadigm, PlatformCapabilities, DiagnosticResult, PreToolUseEvent, PostToolUseEvent, PreCompactEvent, SessionStartEvent, PreToolUseResponse, PostToolUseResponse, PreCompactResponse, SessionStartResponse, HookRegistration } from "../types.js";
-export declare class AntigravityAdapter implements HookAdapter {
+export declare class AntigravityAdapter extends BaseAdapter implements HookAdapter {
+    constructor();
     readonly name = "Antigravity";
     readonly paradigm: HookParadigm;
     readonly capabilities: PlatformCapabilities;
@@ -30,9 +32,6 @@ export declare class AntigravityAdapter implements HookAdapter {
     formatPreCompactResponse(_response: PreCompactResponse): unknown;
     formatSessionStartResponse(_response: SessionStartResponse): unknown;
     getSettingsPath(): string;
-    getSessionDir(): string;
-    getSessionDBPath(projectDir: string): string;
-    getSessionEventsPath(projectDir: string): string;
     generateHookConfig(_pluginRoot: string): HookRegistration;
     readSettings(): Record<string, unknown> | null;
     writeSettings(settings: Record<string, unknown>): void;
@@ -40,7 +39,6 @@ export declare class AntigravityAdapter implements HookAdapter {
     checkPluginRegistration(): DiagnosticResult;
     getInstalledVersion(): string;
     configureAllHooks(_pluginRoot: string): string[];
-    backupSettings(): string | null;
     setHookPermissions(_pluginRoot: string): string[];
     updatePluginRegistry(_pluginRoot: string, _version: string): void;
     getRoutingInstructions(): string;

package/build/adapters/antigravity/index.js

@@ -16,15 +16,18 @@
  *   - MCP support: https://antigravity.google/docs/mcp
  *   - Tool list: System prompt leak (21 verified tools)
  */
-import { createHash } from "node:crypto";
-import { readFileSync, writeFileSync, mkdirSync, copyFileSync, accessSync, constants, } from "node:fs";
-import { resolve, join, dirname } from "node:path";
+import { readFileSync, writeFileSync, mkdirSync, } from "node:fs";
+import { resolve, dirname } from "node:path";
 import { fileURLToPath } from "node:url";
 import { homedir } from "node:os";
+import { BaseAdapter } from "../base.js";
 // ─────────────────────────────────────────────────────────
 // Adapter implementation
 // ─────────────────────────────────────────────────────────
-export class AntigravityAdapter {
+export class AntigravityAdapter extends BaseAdapter {
+    constructor() {
+        super([".gemini"]);
+    }
     name = "Antigravity";
     paradigm = "mcp-only";
     capabilities = {
@@ -69,25 +72,6 @@ export class AntigravityAdapter {
     getSettingsPath() {
         return resolve(homedir(), ".gemini", "antigravity", "mcp_config.json");
     }
-    getSessionDir() {
-        const dir = join(homedir(), ".gemini", "context-mode", "sessions");
-        mkdirSync(dir, { recursive: true });
-        return dir;
-    }
-    getSessionDBPath(projectDir) {
-        const hash = createHash("sha256")
-            .update(projectDir)
-            .digest("hex")
-            .slice(0, 16);
-        return join(this.getSessionDir(), `${hash}.db`);
-    }
-    getSessionEventsPath(projectDir) {
-        const hash = createHash("sha256")
-            .update(projectDir)
-            .digest("hex")
-            .slice(0, 16);
-        return join(this.getSessionDir(), `${hash}-events.md`);
-    }
     generateHookConfig(_pluginRoot) {
         return {};
     }
@@ -157,18 +141,6 @@ export class AntigravityAdapter {
     configureAllHooks(_pluginRoot) {
         return [];
     }
-    backupSettings() {
-        const settingsPath = this.getSettingsPath();
-        try {
-            accessSync(settingsPath, constants.R_OK);
-            const backupPath = settingsPath + ".bak";
-            copyFileSync(settingsPath, backupPath);
-            return backupPath;
-        }
-        catch {
-            return null;
-        }
-    }
     setHookPermissions(_pluginRoot) {
         return [];
     }

package/build/adapters/base.d.ts

@@ -0,0 +1,27 @@
+/**
+ * BaseAdapter — shared implementation for methods identical across all adapters.
+ *
+ * Eliminates ~288 lines of duplication across 12 adapters.
+ * Each concrete adapter extends this and provides platform-specific logic.
+ *
+ * Shared methods:
+ *   - getSessionDir()       — builds session dir from sessionDirSegments
+ *   - getSessionDBPath()    — SHA-256 hash of projectDir → .db file
+ *   - getSessionEventsPath()— SHA-256 hash of projectDir → -events.md file
+ *   - backupSettings()      — copies settings file to .bak
+ *
+ * Adapters with custom logic override the relevant method:
+ *   - vscode-copilot: overrides getSessionDir (checks .github dir)
+ *   - opencode: overrides getSessionDir (XDG_CONFIG_HOME / APPDATA)
+ *              and backupSettings (calls checkPluginRegistration first)
+ *   - openclaw: overrides backupSettings (searches 3 config paths)
+ */
+export declare abstract class BaseAdapter {
+    protected readonly sessionDirSegments: string[];
+    constructor(sessionDirSegments: string[]);
+    getSessionDir(): string;
+    getSessionDBPath(projectDir: string): string;
+    getSessionEventsPath(projectDir: string): string;
+    backupSettings(): string | null;
+    abstract getSettingsPath(): string;
+}

package/build/adapters/base.js

@@ -0,0 +1,59 @@
+/**
+ * BaseAdapter — shared implementation for methods identical across all adapters.
+ *
+ * Eliminates ~288 lines of duplication across 12 adapters.
+ * Each concrete adapter extends this and provides platform-specific logic.
+ *
+ * Shared methods:
+ *   - getSessionDir()       — builds session dir from sessionDirSegments
+ *   - getSessionDBPath()    — SHA-256 hash of projectDir → .db file
+ *   - getSessionEventsPath()— SHA-256 hash of projectDir → -events.md file
+ *   - backupSettings()      — copies settings file to .bak
+ *
+ * Adapters with custom logic override the relevant method:
+ *   - vscode-copilot: overrides getSessionDir (checks .github dir)
+ *   - opencode: overrides getSessionDir (XDG_CONFIG_HOME / APPDATA)
+ *              and backupSettings (calls checkPluginRegistration first)
+ *   - openclaw: overrides backupSettings (searches 3 config paths)
+ */
+import { createHash } from "node:crypto";
+import { join } from "node:path";
+import { accessSync, copyFileSync, constants, mkdirSync } from "node:fs";
+import { homedir } from "node:os";
+export class BaseAdapter {
+    sessionDirSegments;
+    constructor(sessionDirSegments) {
+        this.sessionDirSegments = sessionDirSegments;
+    }
+    getSessionDir() {
+        const dir = join(homedir(), ...this.sessionDirSegments, "context-mode", "sessions");
+        mkdirSync(dir, { recursive: true });
+        return dir;
+    }
+    getSessionDBPath(projectDir) {
+        const hash = createHash("sha256")
+            .update(projectDir)
+            .digest("hex")
+            .slice(0, 16);
+        return join(this.getSessionDir(), `${hash}.db`);
+    }
+    getSessionEventsPath(projectDir) {
+        const hash = createHash("sha256")
+            .update(projectDir)
+            .digest("hex")
+            .slice(0, 16);
+        return join(this.getSessionDir(), `${hash}-events.md`);
+    }
+    backupSettings() {
+        const settingsPath = this.getSettingsPath();
+        try {
+            accessSync(settingsPath, constants.R_OK);
+            const backupPath = settingsPath + ".bak";
+            copyFileSync(settingsPath, backupPath);
+            return backupPath;
+        }
+        catch {
+            return null;
+        }
+    }
+}