release: v0.1.29

Added directory tree example showing how multiple AGENTS.md files are
collected and injected in hierarchical order when reading nested files.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

README.md

@@ -138,7 +138,17 @@ I believe in the right tool for the job. For your wallet's sake, use CLIProxyAPI
   - **Thinking Disabled Violation**: When thinking blocks exist but thinking is disabled → strips thinking blocks
   - **Empty Content Message**: When message has only thinking/meta blocks without actual content → injects "(interrupted)" text via filesystem
 - **Comment Checker**: Detects and reports unnecessary comments after code modifications. Smartly ignores valid patterns (BDD, directives, docstrings, shebangs) to keep the codebase clean from AI-generated artifacts.
-- **Directory AGENTS.md Injector**: Automatically injects `AGENTS.md` contents when reading files. Searches upward from the file's directory to project root, providing directory-level context to the agent. Inspired by Claude Code's CLAUDE.md feature.
+- **Directory AGENTS.md Injector**: Automatically injects `AGENTS.md` contents when reading files. Searches upward from the file's directory to project root, collecting **all** `AGENTS.md` files along the path hierarchy. This enables nested, directory-specific instructions:
+  ```
+  project/
+  ├── AGENTS.md              # Project-wide context
+  ├── src/
+  │   ├── AGENTS.md          # src-specific context
+  │   └── components/
+  │       ├── AGENTS.md      # Component-specific context
+  │       └── Button.tsx     # Reading this injects ALL 3 AGENTS.md files
+  ```
+  When reading `Button.tsx`, the hook injects contexts in order: `project/AGENTS.md` → `src/AGENTS.md` → `components/AGENTS.md`. Each directory's context is injected only once per session. Inspired by Claude Code's CLAUDE.md feature.
 
 ### Agents
 - **oracle** (`openai/gpt-5.1`): The architect. Expert in code reviews and strategy. Uses GPT-5.1 for its unmatched logic and reasoning capabilities. Inspired by AmpCode.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "0.1.27",
+  "version": "0.1.29",
   "description": "OpenCode plugin - custom agents (oracle, librarian) and enhanced features",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

src/hooks/pulse-monitor.ts

@@ -133,10 +133,14 @@ export function createPulseMonitorHook(ctx: PluginInput) {
         stopMonitoring()
     },
     "tool.execute.after": async (input: { sessionID: string }) => {
-        // Resume monitoring after tool finishes
-        if (input.sessionID) {
-            startMonitoring(input.sessionID)
+        // Reset heartbeat after tool execution to prevent false positives
+        // Tools can take arbitrary time, so we need a fresh baseline
+        if (input.sessionID && currentSessionID === input.sessionID) {
+            lastHeartbeat = Date.now()
         }
+        // Don't forcefully restart monitoring here
+        // Monitoring will naturally resume when next session/message event arrives
+        // This prevents stalled detection on legitimately idle sessions
     }
   }
 }

src/hooks/session-recovery/index.ts

@@ -34,11 +34,6 @@ interface ToolUsePart {
   input: Record<string, unknown>
 }
 
-interface ThinkingPart {
-  type: "thinking"
-  thinking: string
-}
-
 interface MessagePart {
   type: string
   id?: string
@@ -186,62 +181,10 @@ async function recoverEmptyContentMessage(
   return anySuccess
 }
 
-async function fallbackRevertStrategy(
-  client: Client,
-  sessionID: string,
-  failedAssistantMsg: MessageData,
-  directory: string
-): Promise<boolean> {
-  const parentMsgID = failedAssistantMsg.info?.parentID
-
-  const messagesResp = await client.session.messages({
-    path: { id: sessionID },
-    query: { directory },
-  })
-  const msgs = (messagesResp as { data?: MessageData[] }).data
-  if (!msgs || msgs.length === 0) {
-    return false
-  }
-
-  let targetUserMsg: MessageData | null = null
-  if (parentMsgID) {
-    targetUserMsg = msgs.find((m) => m.info?.id === parentMsgID) ?? null
-  }
-  if (!targetUserMsg) {
-    for (let i = msgs.length - 1; i >= 0; i--) {
-      if (msgs[i].info?.role === "user") {
-        targetUserMsg = msgs[i]
-        break
-      }
-    }
-  }
-
-  if (!targetUserMsg?.parts?.length) {
-    return false
-  }
-
-  await client.session.revert({
-    path: { id: sessionID },
-    body: { messageID: targetUserMsg.info?.id ?? "" },
-    query: { directory },
-  })
-
-  const textParts = targetUserMsg.parts
-    .filter((p) => p.type === "text" && p.text)
-    .map((p) => ({ type: "text" as const, text: p.text ?? "" }))
-
-  if (textParts.length === 0) {
-    return false
-  }
-
-  await client.session.prompt({
-    path: { id: sessionID },
-    body: { parts: textParts },
-    query: { directory },
-  })
-
-  return true
-}
+// NOTE: fallbackRevertStrategy was removed (2025-12-08)
+// Reason: Function was defined but never called - no error recovery paths used it.
+// All error types have dedicated recovery functions (recoverToolResultMissing,
+// recoverThinkingBlockOrder, recoverThinkingDisabledViolation, recoverEmptyContentMessage).
 
 export function createSessionRecoveryHook(ctx: PluginInput) {
   const processingErrors = new Set<string>()

src/mcp/index.ts

@@ -20,5 +20,3 @@ export function createBuiltinMcps(disabledMcps: McpName[] = []) {
 
   return mcps
 }
-
-export const builtinMcps = allBuiltinMcps

src/tools/lsp/tools.ts

@@ -14,7 +14,6 @@ import {
   formatDiagnostic,
   filterDiagnosticsBySeverity,
   formatPrepareRenameResult,
-  formatWorkspaceEdit,
   formatCodeActions,
   applyWorkspaceEdit,
   formatApplyResult,