Merge branch 'main' into pr-1579 and tighten platform guidance

nanobot/agent/context.py

@@ -62,27 +62,14 @@ Skills with available="false" need dependencies installed first - you can try in
         platform_policy = ""
         if system == "Windows":
             platform_policy = """## Platform Policy (Windows)
-- You are running on Windows. Shell commands executed via the `exec` tool run under the default Windows shell (PowerShell or cmd.exe) unless you explicitly invoke another shell.
+- You are running on Windows. Do not assume GNU tools like `grep`, `sed`, or `awk` exist.
-- Prefer UTF-8 for file I/O and command output. If terminal output is garbled/mojibake, retry with:
+- Prefer Windows-native commands or file tools when they are more reliable.
-  - PowerShell: `[Console]::OutputEncoding = [System.Text.Encoding]::UTF8; <command>`
+- If terminal output is garbled, retry with UTF-8 output enabled.
-  - cmd.exe: `chcp 65001 >NUL & <command>`
-- Do NOT assume GNU tools like `grep`, `sed`, `awk` exist. Prefer Windows built-ins:
-  - Search text: `findstr /i "keyword" path\\to\\file`
-  - List files: `dir`
-  - Show file: `type path\\to\\file`
-- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reliability.
-"""
-        elif system == "Darwin":
-            platform_policy = """## Platform Policy (macOS)
-- You are running on macOS. Prefer POSIX tools and UTF-8.
-- Use forward-slash paths. Prefer `ls`, `cat`, `grep`, `find` for filesystem and text operations.
-- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reproducibility.
 """
         else:
-            platform_policy = """## Platform Policy (Linux)
+            platform_policy = """## Platform Policy (POSIX)
-- You are running on Linux. Prefer POSIX tools and UTF-8.
+- You are running on a POSIX system. Prefer UTF-8 and standard shell tools.
-- Use forward-slash paths. Prefer `ls`, `cat`, `grep`, `find` for filesystem and text operations.
+- Use file tools when they are simpler or more reliable than shell commands.
-- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reproducibility.
 """
 
         return f"""# nanobot 🐈

nanobot/skills/memory/SKILL.md

@@ -13,16 +13,17 @@ always: true
 
 ## Search Past Events
 
-**Recommended approach (cross-platform):**
+Choose the search method based on file size:
-- Use `read_file` to read `memory/HISTORY.md`, then search in-memory
-- This is the most reliable and portable method on all platforms
 
-**Alternative (if you need command-line search):**
+- Small `memory/HISTORY.md`: use `read_file`, then search in-memory
+- Large or long-lived `memory/HISTORY.md`: use the `exec` tool for targeted search
+
+Examples:
 - **Linux/macOS:** `grep -i "keyword" memory/HISTORY.md`
 - **Windows:** `findstr /i "keyword" memory\HISTORY.md`
-- **Python (cross-platform):** `python -c "import re; content=open('memory/HISTORY.md', encoding='utf-8').read(); print('\n'.join([l for l in content.split('\n') if 'keyword' in l.lower()][-20:]))"`
+- **Cross-platform Python:** `python -c "from pathlib import Path; text = Path('memory/HISTORY.md').read_text(encoding='utf-8'); print('\n'.join([l for l in text.splitlines() if 'keyword' in l.lower()][-20:]))"`
 
-Use the `exec` tool to run these commands. For complex searches, prefer `read_file` + in-memory filtering.
+Prefer targeted command-line search for large history files.
 
 ## When to Update MEMORY.md