oh-my-copilot 4.13.0 → 4.13.2

package/docs/REFERENCE.md

@@ -192,10 +192,14 @@ name: architect
 description: Your custom description
 tools: Read, Grep, Glob, Bash, Edit
 model: opus # or sonnet, haiku
+# Optional: effort inherits from the parent Copilot CLI session unless you add an explicit override.
+# effort: high
 ---
 Your custom system prompt here...
 ```
 
+Bundled OMC agent prompts currently do **not** ship an `effort:` frontmatter field. Any effort language inside `agents/*.md` is behavioral guidance for the prompt body, while runtime effort inherits from the parent Copilot CLI session unless the agent markdown explicitly declares an override.
+
 ### Project-Level Config
 
 Create `.claude/CLAUDE.md` in your project for project-specific instructions:

package/docs/TEAM-WORKTREE-MODE.md

@@ -0,0 +1,86 @@
+# Native Team Worktree Mode
+
+Native team worktree mode is the opt-in rollout path for running `omc team` workers in dedicated git worktrees while keeping one leader-owned team-specific coordination root. It is intended for runtime-v2 team sessions and is designed to make worker edits isolated without fragmenting task, mailbox, status, or manifest state.
+
+## Availability
+
+- The rollout is **opt-in / config-gated** for the first slice. Do not assume worktree mode is the default behavior.
+- The target runtime is `runtime-v2`. Legacy `runtime.ts` remains limited to read/status and cleanup compatibility unless a later plan explicitly expands it.
+- No new dependency is required; lifecycle operations use git worktrees plus the existing team CLI/API surfaces.
+
+## Workspace contract
+
+When worktree mode is active, OMC uses this stable layout:
+
+| Field | Contract |
+| --- | --- |
+| Worktree root | `<repo>/.omc/team/<team-name>/worktrees/<worker-name>` |
+| Team-specific coordination root | `<repo>/.omc/state/team/<team-name>` in the leader workspace |
+| Worker cwd | The worker's `worktree_path` |
+| Worker coordination | `OMC_TEAM_STATE_ROOT` points back to the team-specific leader-owned coordination root |
+| Worker instructions | Worktree-root `AGENTS.md` is installed with backup/restore safeguards |
+
+Workers must keep using `omc team api ...` lifecycle and mailbox operations against the team-specific coordination root. They must not create or mutate a separate local `.omc/state` inside their worker worktree when `OMC_TEAM_STATE_ROOT` is available; for worktree-backed workers it should point at `<repo>/.omc/state/team/<team-name>`.
+
+## Persisted fields
+
+Config, manifest, worker identity, and status surfaces should expose the same locked field set so resume/status/bootstrap paths can reason about worker location without inference:
+
+- `workspace_mode`
+- `worktree_mode`
+- `team_state_root`
+- `working_dir`
+- `worktree_repo_root`
+- `worktree_path`
+- `worktree_branch`
+- `worktree_detached`
+- `worktree_created`
+
+`workspace_mode` should be `worktree` for worktree-backed sessions and `single` for the existing shared-workspace behavior. `team_state_root` means the team-specific coordination root (`<repo>/.omc/state/team/<team-name>`); if a future feature needs the broader `.omc/state` base, use a separately named field such as `state_base_root`.
+
+## Safety rules
+
+- OMC must check the leader workspace before provisioning worktrees. If the leader repo is dirty, startup should refuse worktree provisioning rather than copying an unsafe base state.
+- Existing compatible clean worker worktrees may be reused.
+- Dirty worker worktrees must be preserved and surfaced as warnings/events. Cleanup must not force-remove dirty worker edits.
+- Branch/path mismatches should fail instead of reusing the wrong workspace.
+- Rollback may remove newly created clean worktrees and runtime-created branches when safe; reused worktrees are preserved.
+- `orphan-cleanup` is a destructive escape hatch that may delete worktree recovery metadata and root `AGENTS.md` backups. When that evidence exists, callers must pass `acknowledge_lost_worktree_recovery: true` only after manually preserving or intentionally discarding the affected worker worktrees/backups.
+
+## CLI and status expectations
+
+`omc team status <team-name> --json` should make the workspace contract observable. JSON consumers should be able to find `workspace_mode`, `worktree_mode`, `team_state_root`, and each worker's worktree metadata without reading private files directly.
+
+Human status output should also surface the mode and worktree path/branch details enough for users to understand where worker changes live and whether cleanup preserved a dirty worktree.
+
+## Verification checklist for changes
+
+Use the source PRD/test-spec checklist when modifying this area. At minimum, changes should cover:
+
+1. Worktree planning disabled/no-op and active path modes.
+2. Fresh, reused, dirty, and mismatched worktree lifecycle cases.
+3. Runtime-v2 startup/spawn state: worker cwd, env, config, manifest, and identity all agree.
+4. Bootstrap prompts and trigger paths use `$OMC_TEAM_STATE_ROOT` for worktree-backed workers.
+5. Scale-up workers inherit the same team-specific coordination root and worktree instruction strategy.
+6. Shutdown/cleanup removes safe clean worktrees, preserves dirty ones, and reports warnings.
+7. CLI help/status tests cover the opt-in rollout and locked status field set.
+
+Recommended focused commands:
+
+```bash
+npm test -- --run src/team/__tests__/git-worktree.test.ts
+npm test -- --run src/team/__tests__/worker-bootstrap.test.ts
+npm test -- --run src/team/__tests__/runtime-v2.dispatch.test.ts
+npm test -- --run src/team/__tests__/runtime-v2.shutdown.test.ts
+npm test -- --run src/team/__tests__/api-interop.dispatch.test.ts
+npm test -- --run src/team/__tests__/api-interop.cwd-resolution.test.ts
+npm test -- --run src/team/__tests__/scaling-launch-config.test.ts
+npm test -- --run src/cli/__tests__/team-runtime-boundary.test.ts
+npm run build
+```
+
+## Review notes
+
+- Keep the first slice narrow: runtime-v2 startup/spawn/dispatch/scale-up/resume/status/shutdown/cleanup plus legacy read/cleanup compatibility.
+- Do not reduce scope by omitting status visibility, dirty-worktree preservation, or team-specific coordination-root behavior; those are part of the locked contract.
+- Prefer explicit persisted fields over reconstructing worktree state from paths or branch names.

package/docs/copilot-instructions.md

@@ -1,5 +1,5 @@
 <!-- OMC:START -->
-<!-- OMC:VERSION:4.13.0 -->
+<!-- OMC:VERSION:4.13.2 -->
 
 # oh-my-copilot - Intelligent Multi-Agent Orchestration
 

package/docs/reference/compatibility.md

@@ -180,7 +180,7 @@ tags: tag1, tag2
 Skill documentation here...
 ```
 
-**Agents** are discovered from `.md` files in the agents directory with similar frontmatter structure.
+**Agents** are discovered from `.md` files in the agents directory with similar frontmatter structure. Supported runtime fields depend on Copilot CLI; OMC's bundled agent files currently rely on `name`, `description`, `model`, optional tool restrictions, and prompt body guidance. They do not currently ship an `effort:` frontmatter override, so effort inherits from the parent Copilot CLI session unless a custom agent explicitly adds one.
 
 ## MCP Server Discovery
 

package/hooks/hooks.json

@@ -1,16 +1,17 @@
 {
   "version": 1,
-  "description": "OMC orchestration hooks with async capabilities",
   "hooks": {
     "userPromptSubmitted": [
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/keyword-detector.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/keyword-detector.mjs\"",
         "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/skill-injector.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/skill-injector.mjs\"",
         "timeoutSec": 3
       }
     ],
@@ -18,26 +19,31 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/session-start.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/session-start.mjs\"",
         "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-session.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-session.mjs\"",
         "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-session-start.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-session-start.mjs\"",
         "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/setup-init.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/setup-init.mjs\"",
         "timeoutSec": 30
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/setup-maintenance.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/setup-maintenance.mjs\"",
         "timeoutSec": 60
       }
     ],
@@ -45,16 +51,25 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" start",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" start",
+        "timeoutSec": 3
+      },
+      {
+        "type": "command",
+        "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/safe-command-approver.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/safe-command-approver.mjs\"",
         "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/pre-tool-enforcer.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/pre-tool-enforcer.mjs\"",
         "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/context-safety.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/context-safety.mjs\"",
         "timeoutSec": 3
       }
     ],
@@ -62,11 +77,13 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/post-tool-verifier.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/post-tool-verifier.mjs\"",
         "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-posttool.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-posttool.mjs\"",
         "timeoutSec": 3
       }
     ],
@@ -74,6 +91,7 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/post-tool-use-failure.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/post-tool-use-failure.mjs\"",
         "timeoutSec": 3
       }
     ],
@@ -81,11 +99,13 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" stop",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" stop",
         "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/verify-deliverables.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/verify-deliverables.mjs\"",
         "timeoutSec": 5
       }
     ],
@@ -93,52 +113,53 @@
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/pre-compact.mjs\"",
-        "timeoutSec": 10
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/pre-compact.mjs\"",
+        "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-precompact.mjs\"",
-        "timeoutSec": 5
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/project-memory-precompact.mjs\"",
+        "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-pre-compact.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-pre-compact.mjs\"",
         "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/context-guard-stop.mjs\"",
-        "timeoutSec": 5
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/context-guard-stop.mjs\"",
+        "timeoutSec": 3
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/persistent-mode.cjs\"",
-        "timeoutSec": 10
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/persistent-mode.cjs\"",
+        "timeoutSec": 5
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/code-simplifier.mjs\"",
-        "timeoutSec": 5
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/code-simplifier.mjs\"",
+        "timeoutSec": 3
       }
     ],
     "sessionEnd": [
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/session-end.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/session-end.mjs\"",
         "timeoutSec": 10
       },
       {
         "type": "command",
         "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-session-end.mjs\"",
+        "powershell": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/wiki-session-end.mjs\"",
         "timeoutSec": 30
       }
-    ],
-    "permissionRequest": [
-      {
-        "type": "command",
-        "bash": "node \"${PLUGIN_ROOT}/scripts/run.cjs\" \"${PLUGIN_ROOT}/scripts/permission-handler.mjs\"",
-        "timeoutSec": 3
-      }
     ]
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-copilot",
-  "version": "4.13.0",
+  "version": "4.13.2",
   "description": "Multi-agent orchestration system for Copilot CLI - Inspired by oh-my-opencode",
   "type": "module",
   "main": "dist/index.js",

package/scripts/cleanup-orphans.mjs

@@ -127,7 +127,21 @@ function teamConfigExists(name) {
 }
 
 /**
- * Kill a process: SIGTERM first, SIGKILL after 5s if still alive.
+ * Kill a process.
+ *
+ * On Windows: `taskkill /F` terminates synchronously.
+ *
+ * On Unix: issue SIGTERM for graceful exit. A best-effort SIGKILL escalation
+ * is scheduled 5s later, but the timer is `.unref()`ed so it does not block
+ * the Node event loop — main() exits promptly after SIGTERM and does not
+ * hang waiting for the escalation window to elapse. In practice, OMC agent
+ * processes (claude/codex/gemini/omc) respect SIGTERM and exit within
+ * milliseconds; the SIGKILL path is a safety net that only fires if the
+ * caller's event loop stays alive long enough (e.g., another timer or I/O
+ * keeps the process running past 5s). Callers that need guaranteed
+ * escalation should poll `process.kill(pid, 0)` themselves or re-run this
+ * script. See commit message for the rationale behind removing the implicit
+ * 5s hang this function previously caused.
  */
 function killProcess(pid) {
   // Validate PID is a positive integer (prevent command injection)
@@ -140,7 +154,10 @@ function killProcess(pid) {
       // Send SIGTERM
       process.kill(pid, 'SIGTERM');
 
-      // Wait 5s, then SIGKILL if still alive
+      // Schedule a best-effort SIGKILL escalation after 5s.
+      // .unref() ensures this pending timer does not keep the Node event
+      // loop alive — without it, main() would appear to "hang" for 5s per
+      // orphan after printing the JSON result.
       setTimeout(() => {
         try {
           process.kill(pid, 0); // Check if still running
@@ -148,7 +165,7 @@ function killProcess(pid) {
         } catch {
           // Process already exited
         }
-      }, 5000);
+      }, 5000).unref();
     }
     return true;
   } catch {
@@ -201,6 +218,10 @@ function main() {
       ? `Found ${orphans.length} orphan(s). Re-run without --dry-run to clean up.`
       : `Cleaned up ${results.filter(r => r.action === 'killed').length}/${orphans.length} orphan(s).`,
   }));
+
+  // Explicit exit: any pending .unref()ed SIGKILL timers should not pin the
+  // event loop, but exit(0) here makes the completion intent unambiguous.
+  process.exit(0);
 }
 
 main();

package/scripts/context-safety.mjs

@@ -10,9 +10,9 @@
  *
  * Configurable via OMC_CONTEXT_SAFETY_THRESHOLD env var (default: 55%).
  *
- * Hook output:
- *   - Block (exit 2 + stderr message) when context too high for the tool
- *   - Allow ({ continue: true, suppressOutput: true }) otherwise
+ * Hook output (preToolUse — Copilot CLI compliant):
+ *   - Deny ({ permissionDecision: "deny", permissionDecisionReason: "..." }) when context too high
+ *   - Allow ({ permissionDecision: "allow" }) otherwise
  */
 
 import { existsSync, statSync, openSync, readSync, closeSync } from 'node:fs';
@@ -139,7 +139,7 @@ async function main() {
     const toolName = data.tool_name || data.toolName || '';
 
     if (!BLOCKED_TOOLS.has(toolName)) {
-      console.log(JSON.stringify({ continue: true, suppressOutput: true }));
+      console.log(JSON.stringify({ permissionDecision: 'allow' }));
       return;
     }
 
@@ -148,17 +148,16 @@ async function main() {
     const pct = estimateContextPercent(transcriptPath);
 
     if (pct >= THRESHOLD) {
-      process.stderr.write(
-        `[OMC] Context at ${pct}% (threshold: ${THRESHOLD}%). ` +
-        `Too high for ${toolName}. Run /compact or start a fresh session to free context.\n`
-      );
-      process.exit(2);
+      const reason = `[OMC] Context at ${pct}% (threshold: ${THRESHOLD}%). ` +
+        `Too high for ${toolName}. Run /compact or start a fresh session to free context.`;
+      console.log(JSON.stringify({ permissionDecision: 'deny', permissionDecisionReason: reason }));
+      return;
     }
 
-    console.log(JSON.stringify({ continue: true, suppressOutput: true }));
+    console.log(JSON.stringify({ permissionDecision: 'allow' }));
   } catch {
     // On any error, allow the tool to proceed (never block on hook failure)
-    console.log(JSON.stringify({ continue: true, suppressOutput: true }));
+    console.log(JSON.stringify({ permissionDecision: 'allow' }));
   }
 }
 

package/scripts/keyword-detector.debug.mjs

@@ -31,8 +31,8 @@ import { fileURLToPath } from 'url';
 import { getCopilotConfigDir } from './lib/config-dir.mjs';
 import { readStdin } from './lib/stdin.mjs';
 
-// Resolve OMC package root: CLAUDE_PLUGIN_ROOT (plugin system) or derive from this script's location
-const _omcRoot = process.env.CLAUDE_PLUGIN_ROOT ||
+// Resolve OMC package root: PLUGIN_ROOT (plugin system) or derive from this script's location
+const _omcRoot = process.env.PLUGIN_ROOT || process.env.CLAUDE_PLUGIN_ROOT ||
   join(dirname(fileURLToPath(import.meta.url)), '..');
 
 /**