User
Write something
GPT-5.5/OpenAI-Codex context crashes?
Is anyone else seeing GPT-5.5/OpenAI-Codex context crashes? I just found out compaction is firing too late because "codex_gpt55_autoraise: true" pushes it near ~85%, while file/context reads were raised from 20k to 100k. So a couple large file reads can blow the session up before compaction catches it. Thinking the fix is lowering reads back to 20k and making summary failures stop the run instead of continuing. Anyone else run into this?
1
0
How I Fixed DeepSeek's Tool Call Failures in 30 Lines
How I Fixed DeepSeek's Tool Call Failures in 30 Lines "How I Fixed DeepSeek's Tool Call Failures in 30 Lines" Posted by: [Your name] The Problem Running Hermes with DeepSeek V4 Pro/Flash. Tool calls fail 50+ times in a row. Same error looped. Context window fills with garbage. Session dies. Sound familiar? It's not the model. It's the harness. What Actually Happens DeepSeek (and GLM, Qwen, etc.) makes the same 4 mistakes on tool calls: Table Mistake Example What Schema Wants null for optional {"file": null} omit the key entirely JSON string as array {"items": '["a","b"]'} {"items": ["a","b"]} Empty {} placeholder {"args": {}} {"args": []} Bare string for array {"name": "foo"} {"name": ["foo"]} Your validator (Zod, Pydantic) rejects it. Error goes back to model. Model sends same bad call again. 56 times average. Then it gives up or hallucinates. The Fix: Repair Harness Don't send the error back. Fix it deterministically, run it, and teach the model what it should have done. This is 4 small repair functions. ~30 lines each. Ordered carefully. Python # repairs/plugin.py — Drop this into your agent import json from dataclasses import dataclass from typing import Dict, Any, List, Optional @dataclass class RepairResult: changed: bool tool_call: Dict[str, Any] repair_id: str description: str before: Optional[str] after: Optional[str] class ToolRepairHarness: def __init__(self): self.repair_stats = {} def repair(self, tool_call: Dict[str, Any], schema: Dict[str, Any]): fixed = json.loads(json.dumps(tool_call)) # deep copy applied = [] # REPAIR 001: null → omit (optional fields) before = json.dumps(fixed.get("arguments", {})) args = dict(fixed.get("arguments", {})) required = schema.get("required", []) for key, value in list(args.items()): if value is None and key not in required: del args[key] if json.dumps(args) != before: fixed["arguments"] = args applied.append(RepairResult(True, fixed, "001",
1
0
1-2 of 2
Agent Empire
skool.com/agentempire
Learn how to build managed AI agents for your business or for clients using Orgo.
Leaderboard (30-day)
Powered by