LLM Integration Guide

┌─────────────────────────────────────┐
│ LLM Request                         │
├─────────────────────────────────────┤
│ System Prompt (from workflow/preset)│
│ ─────────────────────────────────── │
│ Message History (thread context)    │
│   - User messages                   │
│   - Assistant responses             │
│   - Tool calls & results            │
│ ─────────────────────────────────── │
│ Available Tools (definitions)       │
│ ─────────────────────────────────── │
│ Parameters (temperature, etc.)      │
└─────────────────────────────────────┘

# This will fail if 'bash' isn't in the tools list
- id: call_llm
  action: CallLLM
  inputs:
    tools: ["view", "edit"]  # bash not included!
    # If LLM tries to call 'bash', it will error

# Include all default tools
tools: true

# Or be explicit
tool_filter: ["tag:default", "tag:mcp"]

system_prompt: |
  # Role
  You are a code reviewer focusing on security.
  
  # Rules
  - Always check for injection vulnerabilities
  - Flag hardcoded credentials
  - Suggest secure alternatives
  
  # Output Format
  Provide findings in markdown with severity levels.

# Problem: LLM might call tools not in the list
tools: ["view", "grep"]

# Solution: Include all tools the LLM might need
tools: true
# or
tool_filter: ["tag:default"]

# Problem: Large tool results fill context
- id: search
  run: grep -r "pattern" .  # Could return megabytes

# Solution: Limit results or filter
- id: search
  run: grep -r "pattern" . | head -100

# Problem: No termination condition
while: "true"

# Solution: Always include iteration limit
while: "iter.iteration < inputs.max_turns && ..."

# Problem: Assuming tool_calls is never null
condition: size(nodes.llm.tool_calls) > 0

# Solution: Check for null first
condition: nodes.llm.tool_calls != null && size(nodes.llm.tool_calls) > 0

# Problem: Thinking end_turn means "done with tools"
# Reality: end_turn just means LLM stopped responding

# The LLM might stop because:
# - It's truly done (no more tool calls)
# - It hit max_tokens (output truncated)
# - It wants to explain before continuing

# Solution: Check tool_calls presence, not just stop_reason
condition: nodes.llm.tool_calls != null && size(nodes.llm.tool_calls) > 0

response_tool:
  name: decision
  description: Report your decision
  options:
    approve: "Code looks good - explain why"
    reject: "Issues found - describe them"

{
  "choice": "approve",
  "value": "The code follows all conventions and has good test coverage."
}