improve agent reliability: behavioral constraints, full tool history, error hints

nanobot/agent/context.py

@@ -96,14 +96,18 @@ Your workspace is at: {workspace_path}
 - History log: {workspace_path}/memory/HISTORY.md (grep-searchable)
 - Custom skills: {workspace_path}/skills/{{skill-name}}/SKILL.md
 
-IMPORTANT: When responding to direct questions or conversations, reply directly with your text response.
-Only use the 'message' tool when you need to send a message to a specific chat channel (like WhatsApp).
-For normal conversation, just respond with text - do not call the message tool.
+Reply directly with text for conversations. Only use the 'message' tool to send to a specific chat channel.
 
-Always be helpful, accurate, and concise. Before calling tools, briefly tell the user what you're about to do (one short sentence in the user's language).
-If you need to use tools, call them directly — never send a preliminary message like "Let me check" without actually calling a tool.
-When remembering something important, write to {workspace_path}/memory/MEMORY.md
-To recall past events, grep {workspace_path}/memory/HISTORY.md"""
+## Tool Call Guidelines
+- Before calling tools, you may briefly state your intent (e.g. "Let me check that"), but NEVER predict or describe the expected result before receiving it.
+- Before modifying a file, read it first to confirm its current content.
+- Do not assume a file or directory exists — use list_dir or read_file to verify.
+- After writing or editing a file, re-read it if accuracy matters.
+- If a tool call fails, analyze the error before retrying with a different approach.
+
+## Memory
+- Remember important facts: write to {workspace_path}/memory/MEMORY.md
+- Recall past events: grep {workspace_path}/memory/HISTORY.md"""
     
     def _load_bootstrap_files(self) -> str:
         """Load all bootstrap files from workspace."""