Merge remote-tracking branch 'shareai/main' into fix/pr510-subprocess-output

# Conflicts:
#	s07_skill_loading/code.py
This commit is contained in:
Haoran
2026-08-26 00:45:18 +08:00
408 changed files with 33263 additions and 36787 deletions

View File

@@ -1,38 +1,36 @@
#!/usr/bin/env python3
"""
s07: Skill Loading — two-level on-demand knowledge injection.
s07_skill_loading.py - Skill Loading
Layer 1 (cheap, always present):
SYSTEM prompt includes skill names + one-line descriptions (~100 tokens/skill)
"Skills available: agent-builder, code-review, mcp-builder, pdf"
The system prompt contains a catalog of skill names and descriptions.
The model loads the full SKILL.md only when it calls load_skill.
Layer 2 (expensive, on demand):
Agent calls load_skill("code-review") → full SKILL.md content
injected via tool_result (~2000 tokens/skill)
skills/ Startup
+------------------+ +------------------+
| code-review/ | ----> | SkillLoader |
| SKILL.md | | name + summary |
| pdf/ | +--------+---------+
| SKILL.md | |
+------------------+ v
system prompt catalog
skills/
agent-builder/SKILL.md
code-review/SKILL.md
mcp-builder/SKILL.md
pdf/SKILL.md
Changes from s06:
+ build_system() — scan skills/ dir at startup, inject catalog into SYSTEM
+ load_skill(name) — return full SKILL.md content via tool_result
+ SKILLS_DIR config
Loop unchanged: load_skill auto-dispatches via TOOL_HANDLERS.
Run: python s07_skill_loading/code.py
Needs: pip install anthropic python-dotenv pyyaml + ANTHROPIC_API_KEY in .env
LLM -- load_skill(name) --> full SKILL.md
^ |
+--------- tool_result --------+
"""
import ast, json, os, subprocess
import os
import subprocess
from pathlib import Path
import yaml
try:
import readline
readline.parse_and_bind('set bind-tty-special-chars off')
readline.parse_and_bind('set input-meta on')
readline.parse_and_bind('set output-meta on')
readline.parse_and_bind('set convert-meta off')
except ImportError:
pass
@@ -47,77 +45,98 @@ WORKDIR = Path.cwd()
SKILLS_DIR = WORKDIR / "skills"
client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
MODEL = os.environ["MODEL_ID"]
CURRENT_TODOS: list[dict] = []
# s07: Skill catalog scan (used by build_system below)
def _parse_frontmatter(text: str) -> tuple[dict, str]:
"""Parse YAML frontmatter from SKILL.md. Returns (meta, body)."""
if not text.startswith("---"):
return {}, text
parts = text.split("---", 2)
if len(parts) < 3:
return {}, text
try:
meta = yaml.safe_load(parts[1]) or {}
except yaml.YAMLError:
meta = {}
return meta, parts[2].strip()
# Build skill registry at startup (used for safe lookup in load_skill)
SKILL_REGISTRY: dict[str, dict] = {}
# -- Skill catalog --
def _scan_skills():
"""Scan skills/ dir, populate SKILL_REGISTRY with name/description/content."""
if not SKILLS_DIR.exists():
return
for d in sorted(SKILLS_DIR.iterdir()):
if not d.is_dir():
continue
manifest = d / "SKILL.md"
if manifest.exists():
raw = manifest.read_text()
meta, body = _parse_frontmatter(raw)
name = meta.get("name", d.name)
desc = meta.get("description", raw.split("\n")[0].lstrip("#").strip())
SKILL_REGISTRY[name] = {"name": name, "description": desc, "content": raw}
class SkillLoader:
def __init__(self, skills_dir: Path):
self.skills_dir = skills_dir
self.skills: dict[str, dict[str, str]] = {}
self.scan()
_scan_skills()
@staticmethod
def parse_frontmatter(text: str) -> tuple[dict, str]:
lines = text.splitlines(keepends=True)
if not lines or lines[0].rstrip("\r\n") != "---":
return {}, text
def list_skills() -> str:
"""List all skills (name + one-line description)."""
if not SKILL_REGISTRY:
return "(no skills found)"
return "\n".join(f"- **{s['name']}**: {s['description']}" for s in SKILL_REGISTRY.values())
closing_index = next(
(index for index, line in enumerate(lines[1:], start=1)
if line.rstrip("\r\n") == "---"),
None,
)
if closing_index is None:
return {}, text
# s07: SYSTEM includes skill catalog (cheap — just names + descriptions)
def build_system() -> str:
"""Build SYSTEM prompt with skill catalog injected at startup."""
catalog = list_skills()
frontmatter = "".join(lines[1:closing_index])
body = "".join(lines[closing_index + 1:]).strip()
try:
metadata = yaml.safe_load(frontmatter) or {}
except yaml.YAMLError:
metadata = {}
if not isinstance(metadata, dict):
metadata = {}
return metadata, body
def scan(self):
self.skills.clear()
if not self.skills_dir.exists():
return
skills_root = self.skills_dir.resolve()
for manifest in sorted(self.skills_dir.glob("*/SKILL.md")):
if (not manifest.is_file()
or not manifest.resolve().is_relative_to(skills_root)):
continue
content = manifest.read_text(encoding="utf-8")
metadata, body = self.parse_frontmatter(content)
raw_name = metadata.get("name")
name = raw_name.strip() if isinstance(raw_name, str) else ""
name = name or manifest.parent.name
raw_description = metadata.get("description")
description = (raw_description.strip()
if isinstance(raw_description, str) else "")
description = description or body.split("\n", 1)[0]
description = " ".join(str(description).lstrip("# ").split())
self.skills[name] = {
"name": name,
"description": description,
"content": content,
}
def catalog(self) -> str:
if not self.skills:
return "(no skills found)"
return "\n".join(
f"- {skill['name']}: {skill['description']}"
for skill in self.skills.values()
)
def load(self, name: str) -> str:
skill = self.skills.get(name)
if skill:
return skill["content"]
available = ", ".join(self.skills) or "none"
return f"Error: Unknown skill '{name}'. Available: {available}"
SKILL_LOADER = SkillLoader(SKILLS_DIR)
def build_system_prompt() -> str:
return (
f"You are a coding agent at {WORKDIR}. "
f"Skills available:\n{catalog}\n"
"Use load_skill to get full details when needed."
f"You are a coding agent at {WORKDIR}. Use tools to solve tasks. "
"Act, don't explain.\n\n"
f"Skills available:\n{SKILL_LOADER.catalog()}\n\n"
"Use load_skill to read the full instructions when a skill applies."
)
SYSTEM = build_system()
# s07: subagent gets its own system prompt — no skill loading, no task
SUB_SYSTEM = (
f"You are a coding agent at {WORKDIR}. "
"Complete the task you were given, then return a concise summary. "
"Do not delegate further."
)
SYSTEM = build_system_prompt()
# ═══════════════════════════════════════════════════════════
# FROM s02-s06 (unchanged): Tool Implementations
# ═══════════════════════════════════════════════════════════
def safe_path(p: str) -> Path:
path = (WORKDIR / p).resolve()
if not path.is_relative_to(WORKDIR):
raise ValueError(f"Path escapes workspace: {p}")
return path
# -- Tools --
# s07: Fix Windows subprocess encoding crash (fallback UTF-8 -> GBK with error replacement)
def safe_decode(data: bytes) -> str:
@@ -140,155 +159,54 @@ def run_bash(command: str) -> str:
except subprocess.TimeoutExpired:
return "Error: Timeout (120s)"
def run_read(path: str, limit: int | None = None) -> str:
try:
lines = safe_path(path).read_text().splitlines()
lines = (WORKDIR / path).resolve().read_text(encoding="utf-8").splitlines()
if limit and limit < len(lines):
lines = lines[:limit] + [f"... ({len(lines) - limit} more lines)"]
return "\n".join(lines)
except Exception as e:
return f"Error: {e}"
def run_write(path: str, content: str) -> str:
try:
file_path = safe_path(path)
file_path = (WORKDIR / path).resolve()
file_path.parent.mkdir(parents=True, exist_ok=True)
file_path.write_text(content)
file_path.write_text(content, encoding="utf-8")
return f"Wrote {len(content)} bytes to {path}"
except Exception as e:
return f"Error: {e}"
def run_edit(path: str, old_text: str, new_text: str) -> str:
try:
file_path = safe_path(path)
text = file_path.read_text()
file_path = (WORKDIR / path).resolve()
text = file_path.read_text(encoding="utf-8")
if old_text not in text:
return f"Error: text not found in {path}"
file_path.write_text(text.replace(old_text, new_text, 1))
file_path.write_text(text.replace(old_text, new_text, 1), encoding="utf-8")
return f"Edited {path}"
except Exception as e:
return f"Error: {e}"
def run_glob(pattern: str) -> str:
import glob as g
import glob
try:
results = []
for match in g.glob(pattern, root_dir=WORKDIR):
if (WORKDIR / match).resolve().is_relative_to(WORKDIR):
results.append(match)
return "\n".join(results) if results else "(no matches)"
matches = sorted({
match for match in glob.glob(
pattern, root_dir=WORKDIR, recursive=True)
if (WORKDIR / match).resolve().is_relative_to(WORKDIR)
})
shown = matches[:200]
if len(matches) > 200:
shown.append("... (more matches omitted; narrow the pattern)")
return "\n".join(shown) if shown else "(no matches)"
except Exception as e:
return f"Error: {e}"
def _normalize_todos(todos):
if isinstance(todos, str):
try:
todos = json.loads(todos)
except json.JSONDecodeError:
try:
todos = ast.literal_eval(todos)
except (SyntaxError, ValueError):
return None, "Error: todos must be a list or JSON array string"
if not isinstance(todos, list):
return None, "Error: todos must be a list"
for i, t in enumerate(todos):
if not isinstance(t, dict):
return None, f"Error: todos[{i}] must be an object"
if "content" not in t or "status" not in t:
return None, f"Error: todos[{i}] missing 'content' or 'status'"
if t["status"] not in ("pending", "in_progress", "completed"):
return None, f"Error: todos[{i}] has invalid status '{t['status']}'"
return todos, None
def run_todo_write(todos: list) -> str:
global CURRENT_TODOS
todos, error = _normalize_todos(todos)
if error:
return error
CURRENT_TODOS = todos
lines = ["\n\033[33m## Current Tasks\033[0m"]
for t in CURRENT_TODOS:
icon = {"pending": " ", "in_progress": "\033[36m▸\033[0m", "completed": "\033[32m✓\033[0m"}[t["status"]]
lines.append(f" [{icon}] {t['content']}")
print("\n".join(lines))
return f"Updated {len(CURRENT_TODOS)} tasks"
def extract_text(content) -> str:
if not isinstance(content, list):
return str(content)
return "\n".join(getattr(b, "text", "") for b in content if getattr(b, "type", None) == "text")
# ═══════════════════════════════════════════════════════════
# FROM s06 (unchanged): Subagent
# ═══════════════════════════════════════════════════════════
SUB_TOOLS = [
{"name": "bash", "description": "Run a shell command.",
"input_schema": {"type": "object", "properties": {"command": {"type": "string"}}, "required": ["command"]}},
{"name": "read_file", "description": "Read file contents.",
"input_schema": {"type": "object", "properties": {"path": {"type": "string"}}, "required": ["path"]}},
{"name": "write_file", "description": "Write content to a file.",
"input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "content": {"type": "string"}}, "required": ["path", "content"]}},
{"name": "edit_file", "description": "Replace exact text in a file once.",
"input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "old_text": {"type": "string"}, "new_text": {"type": "string"}}, "required": ["path", "old_text", "new_text"]}},
{"name": "glob", "description": "Find files matching a glob pattern.",
"input_schema": {"type": "object", "properties": {"pattern": {"type": "string"}}, "required": ["pattern"]}},
]
SUB_HANDLERS = {"bash": run_bash, "read_file": run_read, "write_file": run_write,
"edit_file": run_edit, "glob": run_glob}
def spawn_subagent(description: str) -> str:
print(f"\n\033[35m[Subagent spawned]\033[0m")
messages = [{"role": "user", "content": description}]
for _ in range(30):
response = client.messages.create(model=MODEL, system=SUB_SYSTEM,
messages=messages, tools=SUB_TOOLS, max_tokens=8000)
messages.append({"role": "assistant", "content": response.content})
if response.stop_reason != "tool_use":
break
results = []
for block in response.content:
if block.type == "tool_use":
blocked = trigger_hooks("PreToolUse", block)
if blocked:
results.append({"type": "tool_result", "tool_use_id": block.id,
"content": str(blocked)})
continue
handler = SUB_HANDLERS.get(block.name)
output = handler(**block.input) if handler else f"Unknown: {block.name}"
trigger_hooks("PostToolUse", block, output)
print(f" \033[90m[sub] {block.name}: {str(output)[:100]}\033[0m")
results.append({"type": "tool_result", "tool_use_id": block.id, "content": output})
messages.append({"role": "user", "content": results})
result = extract_text(messages[-1]["content"])
if not result:
for msg in reversed(messages):
if msg["role"] == "assistant":
result = extract_text(msg["content"])
if result:
break
if not result:
result = "Subagent stopped after 30 turns without final answer."
print(f"\033[35m[Subagent done]\033[0m")
return result
# ═══════════════════════════════════════════════════════════
# NEW in s07: load_skill — runtime full content loading
# ═══════════════════════════════════════════════════════════
def load_skill(name: str) -> str:
"""Load full skill content. Lookup via registry — no path traversal."""
skill = SKILL_REGISTRY.get(name)
if not skill:
return f"Skill not found: {name}"
return skill["content"]
# ═══════════════════════════════════════════════════════════
# Tool Registry — all tools from s02-s07
# ═══════════════════════════════════════════════════════════
TOOLS = [
{"name": "bash", "description": "Run a shell command.",
@@ -299,33 +217,31 @@ TOOLS = [
"input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "content": {"type": "string"}}, "required": ["path", "content"]}},
{"name": "edit_file", "description": "Replace exact text in a file once.",
"input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "old_text": {"type": "string"}, "new_text": {"type": "string"}}, "required": ["path", "old_text", "new_text"]}},
{"name": "glob", "description": "Find files matching a glob pattern.",
{"name": "glob", "description": "Find files matching a glob pattern; ** matches recursively.",
"input_schema": {"type": "object", "properties": {"pattern": {"type": "string"}}, "required": ["pattern"]}},
{"name": "todo_write", "description": "Create and manage a task list for your current coding session.",
"input_schema": {"type": "object", "properties": {"todos": {"type": "array", "items": {"type": "object", "properties": {"content": {"type": "string"}, "status": {"type": "string", "enum": ["pending", "in_progress", "completed"]}}, "required": ["content", "status"]}}}, "required": ["todos"]}},
{"name": "task", "description": "Launch a subagent to handle a complex subtask. Returns only the final conclusion.",
"input_schema": {"type": "object", "properties": {"description": {"type": "string"}}, "required": ["description"]}},
# s07: skill tool (catalog is already in SYSTEM prompt, this loads full content)
{"name": "load_skill", "description": "Load the full content of a skill by name.",
{"name": "load_skill", "description": "Load the full SKILL.md content by skill name.",
"input_schema": {"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]}},
]
TOOL_HANDLERS = {
"bash": run_bash, "read_file": run_read, "write_file": run_write,
"edit_file": run_edit, "glob": run_glob, "todo_write": run_todo_write,
"task": spawn_subagent, "load_skill": load_skill,
"bash": run_bash,
"read_file": run_read,
"write_file": run_write,
"edit_file": run_edit,
"glob": run_glob,
"load_skill": SKILL_LOADER.load,
}
# ═══════════════════════════════════════════════════════════
# FROM s04 (unchanged): Hook System
# ═══════════════════════════════════════════════════════════
# -- Hooks --
HOOKS = {"UserPromptSubmit": [], "PreToolUse": [], "PostToolUse": [], "Stop": []}
def register_hook(event: str, callback):
HOOKS[event].append(callback)
def trigger_hooks(event: str, *args):
for callback in HOOKS[event]:
result = callback(*args)
@@ -333,96 +249,137 @@ def trigger_hooks(event: str, *args):
return result
return None
DENY_LIST = ["rm -rf /", "sudo", "shutdown", "reboot", "mkfs", "dd if="]
DESTRUCTIVE = ["rm ", "> /etc/", "chmod 777"]
def permission_hook(block):
"""PreToolUse: block denied operations and ask about risky ones."""
if block.name == "bash":
for p in DENY_LIST:
if p in block.input.get("command", ""):
print(f"\n\033[31m⛔ Blocked: '{p}'\033[0m")
return "Permission denied"
command = block.input.get("command", "")
for pattern in DENY_LIST:
if pattern in command:
print(f"\n\033[31m[blocked] '{pattern}'\033[0m")
return "Permission denied by deny list"
for keyword in DESTRUCTIVE:
if keyword in command:
print("\n\033[33m[permission] Potentially destructive command\033[0m")
print(f" Tool: {block.name}({block.input})")
choice = input(" Allow? [y/N] ").strip().lower()
if choice not in ("y", "yes"):
return "Permission denied by user"
if block.name in ("read_file", "write_file", "edit_file"):
path = block.input.get("path", "")
if not (WORKDIR / path).resolve().is_relative_to(WORKDIR):
print("\n\033[33m[permission] Access outside workspace\033[0m")
print(f" Tool: {block.name}({block.input})")
choice = input(" Allow? [y/N] ").strip().lower()
if choice not in ("y", "yes"):
return "Permission denied by user"
return None
def log_hook(block):
print(f"\033[90m[HOOK] {block.name}\033[0m")
"""PreToolUse: log every tool call."""
args_preview = str(list(block.input.values())[:2])[:60]
print(f"\033[90m[HOOK] {block.name}({args_preview})\033[0m")
return None
def large_output_hook(block, output):
"""PostToolUse: warn on large output."""
if len(str(output)) > 100000:
print(f"\033[33m[HOOK] Large output from {block.name}: {len(str(output))} chars\033[0m")
return None
def context_inject_hook(query: str):
"""UserPromptSubmit: log the working directory."""
print(f"\033[90m[HOOK] UserPromptSubmit: working in {WORKDIR}\033[0m")
return None
def summary_hook(messages: list):
tool_count = sum(1 for m in messages
for b in (m.get("content") if isinstance(m.get("content"), list) else [])
if isinstance(b, dict) and b.get("type") == "tool_result")
"""Stop: print the number of tool results in this message list."""
tool_count = sum(
1
for message in messages
for block in (
message.get("content")
if isinstance(message.get("content"), list)
else []
)
if isinstance(block, dict) and block.get("type") == "tool_result"
)
print(f"\033[90m[HOOK] Stop: session used {tool_count} tool calls\033[0m")
return None
register_hook("UserPromptSubmit", context_inject_hook)
register_hook("PreToolUse", permission_hook)
register_hook("PreToolUse", log_hook)
register_hook("PostToolUse", large_output_hook)
register_hook("Stop", summary_hook)
# ═══════════════════════════════════════════════════════════
# agent_loop — same as s05-s06 + nag reminder
# ═══════════════════════════════════════════════════════════
def execute_tool(block) -> str:
blocked = trigger_hooks("PreToolUse", block)
if blocked:
return str(blocked)
handler = TOOL_HANDLERS.get(block.name)
try:
output = handler(**block.input) if handler else f"Unknown: {block.name}"
except Exception as e:
output = f"Error: {e}"
trigger_hooks("PostToolUse", block, output)
return str(output)
def agent_loop(messages: list):
rounds_since_todo = 0
while True:
if rounds_since_todo >= 3 and messages:
messages.append({"role": "user",
"content": "<reminder>Update your todos.</reminder>"})
rounds_since_todo = 0
response = client.messages.create(
model=MODEL, system=SYSTEM, messages=messages,
tools=TOOLS, max_tokens=8000,
model=MODEL,
system=SYSTEM,
messages=messages,
tools=TOOLS,
max_tokens=8000,
)
messages.append({"role": "assistant", "content": response.content})
if response.stop_reason != "tool_use":
tool_calls = [
block for block in response.content if block.type == "tool_use"
]
if not tool_calls:
force = trigger_hooks("Stop", messages)
if force:
messages.append({"role": "user", "content": force})
continue
return
rounds_since_todo += 1
results = []
for block in response.content:
if block.type != "tool_use":
continue
blocked = trigger_hooks("PreToolUse", block)
if blocked:
results.append({"type": "tool_result", "tool_use_id": block.id,
"content": str(blocked)})
continue
handler = TOOL_HANDLERS.get(block.name)
output = handler(**block.input) if handler else f"Unknown: {block.name}"
trigger_hooks("PostToolUse", block, output)
if block.name == "todo_write":
rounds_since_todo = 0
results.append({"type": "tool_result", "tool_use_id": block.id,
"content": output})
for block in tool_calls:
output = execute_tool(block)
results.append({
"type": "tool_result",
"tool_use_id": block.id,
"content": output,
})
messages.append({"role": "user", "content": results})
if __name__ == "__main__":
print("s07: Skill Loading catalog in SYSTEM, content on demand")
print("Type a question, press Enter. Type q to quit.\n")
print("s07: Skill Loading - catalog first, full content on demand")
print("Enter a question, press Enter to send. Type q to quit.\n")
history = []
while True:
try:
query = input("\033[36ms07 >> \033[0m")
# \001/\002 tell Readline the ANSI escapes have zero display width.
query = input("\001\033[36m\002s07 >> \001\033[0m\002")
except (EOFError, KeyboardInterrupt):
break
if query.strip().lower() in ("q", "exit", ""):