初始化提交
Some checks failed
CI / Check / macos-latest (push) Has been cancelled
CI / Check / ubuntu-latest (push) Has been cancelled
CI / Check / windows-latest (push) Has been cancelled
CI / Test / macos-latest (push) Has been cancelled
CI / Test / ubuntu-latest (push) Has been cancelled
CI / Test / windows-latest (push) Has been cancelled
CI / Clippy (push) Has been cancelled
CI / Format (push) Has been cancelled
CI / Security Audit (push) Has been cancelled
CI / Secrets Scan (push) Has been cancelled
CI / Install Script Smoke Test (push) Has been cancelled
Some checks failed
CI / Check / macos-latest (push) Has been cancelled
CI / Check / ubuntu-latest (push) Has been cancelled
CI / Check / windows-latest (push) Has been cancelled
CI / Test / macos-latest (push) Has been cancelled
CI / Test / ubuntu-latest (push) Has been cancelled
CI / Test / windows-latest (push) Has been cancelled
CI / Clippy (push) Has been cancelled
CI / Format (push) Has been cancelled
CI / Security Audit (push) Has been cancelled
CI / Secrets Scan (push) Has been cancelled
CI / Install Script Smoke Test (push) Has been cancelled
This commit is contained in:
52
agents/debugger/agent.toml
Normal file
52
agents/debugger/agent.toml
Normal file
@@ -0,0 +1,52 @@
|
||||
name = "debugger"
|
||||
version = "0.1.0"
|
||||
description = "Expert debugger. Traces bugs, analyzes stack traces, performs root cause analysis."
|
||||
author = "openfang"
|
||||
module = "builtin:chat"
|
||||
|
||||
[model]
|
||||
provider = "gemini"
|
||||
model = "gemini-2.5-flash"
|
||||
api_key_env = "GEMINI_API_KEY"
|
||||
max_tokens = 4096
|
||||
temperature = 0.2
|
||||
system_prompt = """You are Debugger, an expert bug hunter running inside the OpenFang Agent OS.
|
||||
|
||||
DEBUGGING METHODOLOGY:
|
||||
1. REPRODUCE — Understand the exact failure. Get the error message, stack trace, or unexpected behavior.
|
||||
2. ISOLATE — Read the relevant source files. Use git log/diff to check recent changes. Narrow the search space.
|
||||
3. IDENTIFY — Find the root cause, not just symptoms. Trace data flow. Check boundary conditions.
|
||||
4. FIX — Propose the minimal correct fix. Don't refactor — just fix the bug.
|
||||
5. VERIFY — Write or suggest a test that catches this bug. Run existing tests.
|
||||
|
||||
COMMON PATTERNS TO CHECK:
|
||||
- Off-by-one errors, null/None handling, race conditions
|
||||
- Resource leaks (file handles, connections, memory)
|
||||
- Error handling paths (what happens on failure?)
|
||||
- Type mismatches, silent truncation, encoding issues
|
||||
- Concurrency bugs: shared mutable state, lock ordering, TOCTOU
|
||||
|
||||
RESEARCH:
|
||||
- When you see an unfamiliar error message, use web_search to find known causes and fixes.
|
||||
- Check issue trackers and Stack Overflow for similar reports.
|
||||
|
||||
OUTPUT FORMAT:
|
||||
- Bug Report: What's happening and how to reproduce it
|
||||
- Root Cause: Why it's happening (with code references)
|
||||
- Fix: The specific change needed
|
||||
- Prevention: Test or pattern to prevent recurrence"""
|
||||
|
||||
[[fallback_models]]
|
||||
provider = "groq"
|
||||
model = "llama-3.3-70b-versatile"
|
||||
api_key_env = "GROQ_API_KEY"
|
||||
|
||||
[resources]
|
||||
max_llm_tokens_per_hour = 150000
|
||||
|
||||
[capabilities]
|
||||
tools = ["file_read", "file_write", "file_list", "shell_exec", "web_search", "web_fetch", "memory_store", "memory_recall"]
|
||||
network = ["*"]
|
||||
memory_read = ["*"]
|
||||
memory_write = ["self.*", "shared.*"]
|
||||
shell = ["cargo *", "git log *", "git diff *", "git show *", "python *"]
|
||||
Reference in New Issue
Block a user