feat(prompt): add Gemini-specific operational guidance for main agent

Adapted from OpenCode's gemini.txt. Gemini models now get both
tool-use enforcement (shared with GPT/Codex) and Gemini-specific
operational directives:
- Absolute paths for all file operations
- Verify file contents before editing (read first)
- Check dependency manifests before importing
- Concise explanatory text
- Parallel tool calls for independent operations
- Non-interactive CLI flags (-y, --yes)
- Autonomous completion (keep going until done)

Only injected into the main agent's system prompt — auxiliary model
calls (vision, compression, session search, etc.) are unaffected.

agent/prompt_builder.py

@@ -187,7 +187,29 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
 
 # Model name substrings that trigger tool-use enforcement guidance.
 # Add new patterns here when a model family needs explicit steering.
-TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex")
+TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini")
+
+# Gemini-specific operational guidance, adapted from OpenCode's gemini.txt.
+# Injected alongside TOOL_USE_ENFORCEMENT_GUIDANCE when the model is Gemini.
+GEMINI_OPERATIONAL_GUIDANCE = (
+    "# Gemini operational directives\n"
+    "Follow these operational rules strictly:\n"
+    "- **Absolute paths:** Always construct and use absolute file paths for all "
+    "file system operations. Combine the project root with relative paths.\n"
+    "- **Verify first:** Use read_file/search_files to check file contents and "
+    "project structure before making changes. Never guess at file contents.\n"
+    "- **Dependency checks:** Never assume a library is available. Check "
+    "package.json, requirements.txt, Cargo.toml, etc. before importing.\n"
+    "- **Conciseness:** Keep explanatory text brief — a few sentences, not "
+    "paragraphs. Focus on actions and results over narration.\n"
+    "- **Parallel tool calls:** When you need to perform multiple independent "
+    "operations (e.g. reading several files), make all the tool calls in a "
+    "single response rather than sequentially.\n"
+    "- **Non-interactive commands:** Use flags like -y, --yes, --non-interactive "
+    "to prevent CLI tools from hanging on prompts.\n"
+    "- **Keep going:** Work autonomously until the task is fully resolved. "
+    "Don't stop with a plan — execute it.\n"
+)
 
 PLATFORM_HINTS = {
     "whatsapp": (

run_agent.py

@@ -79,6 +79,7 @@ from hermes_constants import OPENROUTER_BASE_URL
 from agent.prompt_builder import (
     DEFAULT_AGENT_IDENTITY, PLATFORM_HINTS,
     MEMORY_GUIDANCE, SESSION_SEARCH_GUIDANCE, SKILLS_GUIDANCE,
+    GEMINI_OPERATIONAL_GUIDANCE,
 )
 from agent.model_metadata import (
     fetch_model_metadata,
@@ -2602,6 +2603,10 @@ class AIAgent:
                 _inject = any(p in model_lower for p in TOOL_USE_ENFORCEMENT_MODELS)
             if _inject:
                 prompt_parts.append(TOOL_USE_ENFORCEMENT_GUIDANCE)
+                # Gemini-specific operational guidance (conciseness, absolute
+                # paths, parallel tool calls, etc.)
+                if "gemini" in (self.model or "").lower():
+                    prompt_parts.append(GEMINI_OPERATIONAL_GUIDANCE)
 
         # Honcho CLI awareness: tell Hermes about its own management commands
         # so it can refer the user to them rather than reinventing answers.