GPT 5.6 Sol Ultra is horrible
Resolved 💬 3 comments Opened Jul 10, 2026 by juanqui Closed Jul 10, 2026
What version of Codex CLI is running?
0.144.0
What subscription do you have?
Pro 20x
Which model were you using?
gpt-5.6-sol ultra
What platform is your computer?
Linux 6.17.0-35-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
herdr remote in iTerm2
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1783696162s since unix epoch",
"overallStatus": "ok",
"codexVersion": "0.144.0",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "/home/juanqui/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/home/juanqui/.codex/app-server-daemon",
"mode": "ephemeral",
"pid file": "/home/juanqui/.codex/app-server-daemon/app-server.pid (missing)",
"settings": "/home/juanqui/.codex/app-server-daemon/settings.json (missing)",
"status": "not running",
"update-loop pid file": "/home/juanqui/.codex/app-server-daemon/app-server-updater.pid (missing)"
},
"remediation": null,
"durationMs": 0
},
"auth.credentials": {
"id": "auth.credentials",
"category": "auth",
"status": "ok",
"summary": "auth is configured",
"details": {
"auth file": "/home/juanqui/.codex/auth.json",
"auth storage mode": "File",
"stored API key": "false",
"stored ChatGPT tokens": "true",
"stored agent identity": "false",
"stored auth mode": "chatgpt"
},
"remediation": null,
"durationMs": 0
},
"config.load": {
"id": "config.load",
"category": "config",
"status": "ok",
"summary": "config loaded",
"details": {
"CODEX_HOME": "/home/juanqui/.codex",
"config.toml": "/home/juanqui/.codex/config.toml",
"config.toml parse": "ok",
"cwd": "/home/juanqui/Git/exp-socraticresearch",
"enabled feature flags": "shell_tool, unified_exec, shell_snapshot, code_mode_host, terminal_resize_reflow, sqlite, memories, hooks, enable_request_compression, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, skill_mcp_dependency_install, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, workspace_dependencies",
"feature flag overrides": "memories=true",
"feature flags enabled": "36",
"log dir": "/home/juanqui/.codex/log",
"mcp servers": "3",
"model": "gpt-5.6-sol",
"model provider": "openai",
"sqlite home": "/home/juanqui/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git version 2.43.0",
"details": {
".git entry": "directory",
"PATH git #1": "/usr/bin/git",
"PATH git #2": "/bin/git",
"PATH git entries": "2",
"git branch": "main",
"git build options": "git version 2.43.0; cpu: x86_64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh",
"git exec path": "/usr/lib/git-core",
"git version": "git version 2.43.0",
"repo detected": "true",
"repo root": "/home/juanqui/Git/exp-socraticresearch",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 27
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/home/juanqui/.npm-global/bin/codex",
"current executable": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install context": "npm (package /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"managed by bun": "false",
"managed by npm": "true",
"managed by pnpm": "false",
"managed package root": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex",
"npm update target": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex"
},
"remediation": null,
"durationMs": 60
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "MCP configuration is locally consistent",
"details": {
"configured servers": "3",
"disabled servers": "0",
"stdio servers": "2",
"streamable_http servers": "1"
},
"remediation": null,
"durationMs": 210
},
"network.env": {
"id": "network.env",
"category": "network",
"status": "ok",
"summary": "network-related environment looks readable",
"details": {
"proxy env vars": "none"
},
"remediation": null,
"durationMs": 0
},
"network.provider_reachability": {
"id": "network.provider_reachability",
"category": "reachability",
"status": "ok",
"summary": "active provider endpoints are reachable over HTTP",
"details": {
"ChatGPT base URL": "https://chatgpt.com/backend-api/ reachable (HTTP 404)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 310
},
"network.websocket_reachability": {
"id": "network.websocket_reachability",
"category": "websocket",
"status": "ok",
"summary": "Responses WebSocket handshake succeeded",
"details": {
"DNS": "2 IPv4, 2 IPv6, first IPv4",
"auth mode": "chatgpt",
"connect timeout": "15000 ms",
"endpoint": "wss://chatgpt.com/backend-api/<redacted>",
"handshake result": "HTTP 101 Switching Protocols",
"model provider": "openai",
"models etag present": "true",
"provider name": "OpenAI",
"proxy env vars": "none",
"reasoning header": "false",
"server model present": "false",
"supports websockets": "true",
"wire API": "responses"
},
"remediation": null,
"durationMs": 936
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running npm on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install method": "npm (package /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-x86_64",
"version": "0.144.0"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search is OK (bundled)",
"details": {
"search command": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path/rg",
"search command readiness": "file exists",
"search provider": "bundled"
},
"remediation": null,
"durationMs": 0
},
"sandbox.helpers": {
"id": "sandbox.helpers",
"category": "sandbox",
"status": "ok",
"summary": "sandbox configuration is readable",
"details": {
"approval policy": "OnRequest",
"codex-linux-sandbox helper": "/home/juanqui/.codex/tmp/arg0/codex-arg0wjLH6Z/codex-linux-sandbox",
"execve wrapper helper": "/home/juanqui/.codex/tmp/arg0/codex-arg0wjLH6Z/codex-execve-wrapper",
"filesystem sandbox": "restricted",
"network sandbox": "restricted"
},
"remediation": null,
"durationMs": 0
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "/home/juanqui/.codex (dir)",
"active rollout files": "81 files, 715751335 total bytes, 8836436 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "/home/juanqui/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/home/juanqui/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/home/juanqui/.codex/log (dir)",
"memories DB": "/home/juanqui/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"sqlite home": "/home/juanqui/.codex (dir)",
"state DB": "/home/juanqui/.codex/state_5.sqlite (file)",
"state DB integrity": "ok"
},
"remediation": null,
"durationMs": 188
},
"state.rollout_db_parity": {
"id": "state.rollout_db_parity",
"category": "threads",
"status": "ok",
"summary": "rollout files and state DB thread inventory agree",
"details": {
"default model provider": "openai",
"rollout DB active files": "81",
"rollout DB active rows": "81",
"rollout DB archive mismatches": "0",
"rollout DB archived files": "0",
"rollout DB archived rows": "0",
"rollout DB duplicate DB paths": "0",
"rollout DB duplicate rollout thread ids": "0",
"rollout DB malformed file names": "0",
"rollout DB missing active rows": "0",
"rollout DB missing archived rows": "0",
"rollout DB model providers": "openai=81",
"rollout DB rows": "81",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "subagent:thread_spawn=51, cli=30",
"rollout DB stale rows": "0"
},
"remediation": null,
"durationMs": 5107
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language en-US",
"details": {
"EDITOR": "not set",
"LANG": "en_US.UTF-8",
"VISUAL": "not set",
"os": "Ubuntu 24.4.0 (noble) [64-bit]",
"os language": "en-US",
"os type": "Ubuntu",
"os version": "24.4.0"
},
"remediation": null,
"durationMs": 8
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"COLORTERM": "truecolor",
"SSH_CLIENT": "present",
"SSH_CONNECTION": "present",
"TERM": "xterm-256color",
"color output": "enabled",
"effective locale": "en_US.UTF-8",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout is terminal": "true",
"terminal": "unknown",
"terminal size": "213x47"
},
"remediation": null,
"durationMs": 0
},
"terminal.title": {
"id": "terminal.title",
"category": "title",
"status": "ok",
"summary": "terminal title default",
"details": {
"terminal title activity": "true",
"terminal title items": "activity, project-name",
"terminal title project source": "git repo root",
"terminal title project value": "exp-socraticresearch",
"terminal title source": "default"
},
"remediation": null,
"durationMs": 0
},
"updates.status": {
"id": "updates.status",
"category": "updates",
"status": "ok",
"summary": "update configuration is locally consistent",
"details": {
"cached latest version": "0.143.0",
"check for update on startup": "true",
"last checked at": "2026-07-09T02:50:16.647336370Z",
"latest version": "0.144.1",
"latest version status": "newer version is available",
"npm update target": "/home/juanqui/.npm-global/lib/node_modules/@openai/codex",
"update action": "npm install -g @openai/codex",
"version cache": "/home/juanqui/.codex/version.json"
},
"remediation": null,
"durationMs": 476
}
}
}What issue are you seeing?
I am very disappointed with GPT 5.6 Sol Ultra. It has completely broken an application after spending 12+ hours working on a clear task. See thread id 019f4892-739f-7f73-ab16-e6b512e913f3.
(For privacy reasons I am not including the original prompt here. It should be on that thread for the OpenAI team to analyze).
GPT 5.6 Sol Ultra becomes EXTREMELY fixated on whatever random thing it decides to do next and endlessly pursues a rabbit trail that becomes increasingly more disconnected and unrelated to the original task the longer I let it run without interrupting it. I had to interrupt it multiple times to bring it back on track.
I made the mistake of letting it run overnight thinking it was almost done. I woke up to a completely broken application. It was working on a COMPLETELY DIFFERENT TASK than what I had tasked it with. I tasked it with improving visualizations in our tutor agent and I woke up to it re-engineering how lessons are generated and how progress is displayed.
This model has ZERO ability to stay on track. I cannot trust it on a short horizon task, let alone a long horizon task. Fable 5 is CONSIDERABLY better at this and I am now tasking it with salvaging any useful work that GPT 5.6 Sol Ultra might have done (if there is any here).
This was just a test of GPT 5.6 Sol Ultra's capabilities. I upgraded from 5x to 20x to really hit this hard and I am honestly very disappointed with the performance. I am surprised this behavior was not caught by OpenAI before releasing to the public.
What steps can reproduce the bug?
Uploaded thread: 019f4892-739f-7f73-ab16-e6b512e913f3
What is the expected behavior?
_No response_
Additional information
_No response_
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗