The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
fix(security): provider error taxonomy, tool leak hardening, hook gate, atomic cleanup
Geronimoa3c24818bb28
diff --git a/scripts/hooks/run-with-flags.js b/scripts/hooks/run-with-flags.jsindex 9f6de3722..cd69ed6cc 100755--- a/scripts/hooks/run-with-flags.js+++ b/scripts/hooks/run-with-flags.js@@ -207,7 +207,18 @@ async function main() {// which would interfere with the parent process or cause double execution.let hookModule;const src = fs.readFileSync(scriptPath, 'utf8');- const hasRunExport = /\bmodule\.exports\b/.test(src) && /\brun\b/.test(src);+ // Gate require() on concrete export syntax, not a bare word match: the old+ // /\bmodule\.exports\b/ && /\brun\b/ test fired on comments, strings, and+ // unrelated properties, causing require() — and its module-scope side+ // effects — to run for hooks that export no run(). Still lexical (no parser+ // dependency), but requires an actual export assignment form.+ const RUN_EXPORT_PATTERNS = [+ /module\.exports\s*\.\s*run\s*=/,+ /exports\s*\.\s*run\s*=/,+ /module\.exports\s*=\s*\{[^}]*\brun\b/,+ /module\.exports\s*=\s*(async\s+)?function\s+run\b/,+ ];+ const hasRunExport = RUN_EXPORT_PATTERNS.some(re => re.test(src));if (hasRunExport) {try {diff --git a/scripts/lib/codex-legacy-sync.js b/scripts/lib/codex-legacy-sync.jsindex 5eb92d180..12cdc392b 100644--- a/scripts/lib/codex-legacy-sync.js+++ b/scripts/lib/codex-legacy-sync.js@@ -131,8 +131,15 @@ function removeOpenedRegularFile(filePath, opened) {function atomicWriteJson(filePath, value) {fs.mkdirSync(path.dirname(filePath), { recursive: true, mode: 0o700 });const tempPath = `${filePath}.tmp-${process.pid}-${Date.now()}`;- fs.writeFileSync(tempPath, `${JSON.stringify(value, null, 2)}\n`, { mode: 0o600 });- fs.renameSync(tempPath, filePath);+ try {+ fs.writeFileSync(tempPath, `${JSON.stringify(value, null, 2)}\n`, { mode: 0o600 });+ fs.renameSync(tempPath, filePath);+ } catch (error) {+ // A failed write/rename must not leave a .tmp-<pid>-<timestamp> file+ // beside the canonical state file; repeated failures would accumulate them.+ fs.rmSync(tempPath, { force: true });+ throw error;+ }}function readState(statePath) {diff --git a/src/llm/providers/ollama.py b/src/llm/providers/ollama.pyindex 2f83338d0..793f0aa6b 100644--- a/src/llm/providers/ollama.py+++ b/src/llm/providers/ollama.py@@ -8,6 +8,7 @@ from typing import Anyfrom llm.core.interface import (AuthenticationError,ContextLengthError,+ LLMError,LLMProvider,RateLimitError,)@@ -100,13 +101,33 @@ class OllamaProvider(LLMProvider):)except Exception as e:msg = str(e)- if "401" in msg or "connection" in msg.lower():- raise AuthenticationError(f"Ollama connection failed: {msg}", provider=ProviderType.OLLAMA) from e- if "429" in msg or "rate_limit" in msg.lower():+ lowered = msg.lower()+ if "401" in msg or "unauthorized" in lowered or "forbidden" in lowered:+ raise AuthenticationError(f"Ollama authentication failed: {msg}", provider=ProviderType.OLLAMA) from e+ if "429" in msg or "rate_limit" in lowered:raise RateLimitError(msg, provider=ProviderType.OLLAMA) from e- if "context" in msg.lower() and "length" in msg.lower():+ if "context" in lowered and "length" in lowered:raise ContextLengthError(msg, provider=ProviderType.OLLAMA) from e- raise+ if (+ "connection" in lowered+ or "refused" in lowered+ or "timed out" in lowered+ or "timeout" in lowered+ or "unreachable" in lowered+ or "name resolution" in lowered+ or "nodename nor servname" in lowered+ or isinstance(e, (ConnectionError, TimeoutError))+ ):+ raise LLMError(+ f"Ollama connection failed: {type(e).__name__}",+ provider=ProviderType.OLLAMA,+ code="connection_error",+ ) from e+ raise LLMError(+ f"Ollama request failed: {type(e).__name__}",+ provider=ProviderType.OLLAMA,+ code="provider_error",+ ) from edef list_models(self) -> list[ModelInfo]:return self._models.copy()diff --git a/src/llm/tools/executor.py b/src/llm/tools/executor.pyindex e4a859b34..e59311c1e 100644--- a/src/llm/tools/executor.py+++ b/src/llm/tools/executor.py@@ -2,9 +2,12 @@from __future__ import annotations+import inspect+import loggingfrom collections.abc import Callablefrom typing import Any+from llm.core.interface import LLMErrorfrom llm.core.types import (LLMInput,LLMOutput,@@ -15,6 +18,21 @@ from llm.core.types import (ToolResult,)+logger = logging.getLogger(__name__)++# Model-facing failure text. Raw exception details (credentials, local paths,+# request data, upstream responses) must never reach the model; diagnostics go+# to trusted logs only.+GENERIC_TOOL_FAILURE = "Error executing {name}: tool failed"+++def _generic_failure(tool_call: ToolCall) -> ToolResult:+ return ToolResult(+ tool_call_id=tool_call.id,+ content=GENERIC_TOOL_FAILURE.format(name=tool_call.name),+ is_error=True,+ )+ToolFunc = Callable[..., Any]@@ -55,18 +73,50 @@ class ToolExecutor:try:result = func(**tool_call.arguments)+ if inspect.isawaitable(result):+ logger.warning(+ "Async tool '%s' called via sync execute(); use execute_async()",+ tool_call.name,+ )+ return ToolResult(+ tool_call_id=tool_call.id,+ content=GENERIC_TOOL_FAILURE.format(name=tool_call.name),+ is_error=True,+ )content = result if isinstance(result, str) else str(result)return ToolResult(tool_call_id=tool_call.id, content=content)- except Exception as e:+ except Exception:+ logger.exception("Tool '%s' failed", tool_call.name)+ return _generic_failure(tool_call)++ async def execute_async(self, tool_call: ToolCall) -> ToolResult:+ func = self.registry.get(tool_call.name)+ if not func:return ToolResult(tool_call_id=tool_call.id,- content=f"Error executing {tool_call.name}: {e}",+ content=f"Error: Tool '{tool_call.name}' not found",is_error=True,)+ try:+ result = func(**tool_call.arguments)+ if inspect.isawaitable(result):+ result = await result+ content = result if isinstance(result, str) else str(result)+ return ToolResult(tool_call_id=tool_call.id, content=content)+ except Exception:+ logger.exception("Tool '%s' failed", tool_call.name)+ return _generic_failure(tool_call)+def execute_all(self, tool_calls: list[ToolCall]) -> list[ToolResult]:return [self.execute(tc) for tc in tool_calls]+ async def execute_all_async(self, tool_calls: list[ToolCall]) -> list[ToolResult]:+ results: list[ToolResult] = []+ for tc in tool_calls:+ results.append(await self.execute_async(tc))+ return results+class ReActAgent:def __init__(@@ -92,7 +142,14 @@ class ReActAgent:tools=tools,)- output: LLMOutput = self.provider.generate(input_copy)+ try:+ output: LLMOutput = self.provider.generate(input_copy)+ except LLMError as e:+ logger.warning("Provider failed during agent run: %s", e.code or type(e).__name__)+ return LLMOutput(+ content=f"Provider error: {e.code or type(e).__name__}",+ stop_reason="provider_error",+ )if not output.has_tool_calls:return output@@ -105,7 +162,7 @@ class ReActAgent:))- results = self.executor.execute_all(output.tool_calls or [])+ results = await self.executor.execute_all_async(output.tool_calls or [])for result in results:messages.append(diff --git a/tests/test_executor.py b/tests/test_executor.pyindex 749c4d1b4..75f522ff7 100644--- a/tests/test_executor.py+++ b/tests/test_executor.py@@ -1,5 +1,5 @@-from llm.core.types import ToolCall, ToolDefinition-from llm.tools import ToolExecutor, ToolRegistry+from llm.core.types import LLMInput, LLMOutput, Message, Role, ToolCall, ToolDefinition+from llm.tools import ReActAgent, ToolExecutor, ToolRegistryclass TestToolRegistry:@@ -83,3 +83,55 @@ class TestToolExecutor:assert len(results) == 2assert results[0].content == "result1"assert results[1].content == "result2"+++class TestAsyncTools:+ def test_execute_async_awaits_coroutine(self):+ import asyncio++ registry = ToolRegistry()++ async def fetch(url: str = "") -> str:+ return f"fetched:{url}"++ registry.register(ToolDefinition(name="fetch", description="", parameters={}), fetch)++ executor = ToolExecutor(registry)+ result = asyncio.run(+ executor.execute_async(ToolCall(id="1", name="fetch", arguments={"url": "x"}))+ )++ assert result.tool_call_id == "1"+ assert result.content == "fetched:x"+ assert result.is_error is False++ def test_react_agent_runs_awaitable_tool(self):+ import asyncio++ async def lookup(key: str = "") -> str:+ return f"value:{key}"++ registry = ToolRegistry()+ registry.register(ToolDefinition(name="lookup", description="", parameters={}), lookup)++ seen = {}++ class FakeProvider:+ def generate(self, agent_input):+ if "done" not in seen:+ seen["done"] = True+ return LLMOutput(+ content="",+ tool_calls=[ToolCall(id="1", name="lookup", arguments={"key": "k"})],+ )+ tool_messages = [m for m in agent_input.messages if m.role == Role.TOOL]+ assert len(tool_messages) == 1+ assert tool_messages[0].content == "value:k"+ return LLMOutput(content="done")++ agent = ReActAgent(provider=FakeProvider(), executor=ToolExecutor(registry))+ output = asyncio.run(+ agent.run(LLMInput(messages=[Message(role=Role.USER, content="hi")]))+ )++ assert output.content == "done"