Multi-agent v2: completed agent remains resident and prevents replacement spawn after follow-up turns
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
0.153.4
What subscription do you have?
Pro 5x
Which model were you using?
gpt-5.6-sol
What platform is your computer?
Linux 6.18.49-3-lts x86_64 unknown
What terminal emulator and version are you using (if applicable)?
Kitty
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1789000073s since unix epoch",
"overallStatus": "ok",
"codexVersion": "0.153.4",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "/home/eien/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/home/eien/.codex/app-server-daemon",
"mode": "ephemeral",
"pid file": "/home/eien/.codex/app-server-daemon/app-server.pid (missing)",
"settings": "/home/eien/.codex/app-server-daemon/settings.json (missing)",
"status": "not running",
"update-loop pid file": "/home/eien/.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/eien/.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/eien/.codex",
"config.toml": "/home/eien/.codex/config.toml",
"config.toml parse": "ok",
"cwd": "/home/eien",
"enabled feature flags": "shell_tool, view_image, sleep_tool, unified_exec, unified_exec_zsh_fork, shell_snapshot, content_item_kinds, code_mode_host, terminal_resize_reflow, sqlite, hooks, enable_request_compression, unbounded_connection_retries, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, in_app_chat, in_app_dictation, in_app_local_automation, in_app_updates, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, item_ids, skill_mcp_dependency_install, skill_search, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, compaction_image_budget, workspace_dependencies",
"feature flag overrides": "none",
"feature flags enabled": "47",
"log dir": "/home/eien/.codex/log",
"mcp servers": "0",
"model": "gpt-5.6-sol",
"model provider": "openai",
"sqlite home": "/home/eien/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git version 2.55.0",
"details": {
"PATH git #1": "/usr/bin/git",
"PATH git entries": "1",
"git build options": "git version 2.55.0; cpu: x86_64; built from commit: e9019fcafe0040228b8631c30f97ae1adb61bcdc; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh; rust: enabled; feature: fsmonitor--daemon; gettext: enabled; libcurl: 8.21.0; OpenSSL: OpenSSL 3.6.3 9 Jun 2026; zlib-ng: 2.3.3; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
"git exec path": "/usr/lib/git-core",
"git version": "git version 2.55.0",
"repo detected": "false",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 38
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/home/eien/.local/bin/codex",
"current executable": "/home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install context": "npm (package /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"managed by Vite+": "false",
"managed by bun": "false",
"managed by npm": "true",
"managed by pnpm": "false",
"managed package root": "/home/eien/.cache/npm/lib/node_modules/@openai/codex",
"npm update target": "/home/eien/.cache/npm/lib/node_modules/@openai/codex"
},
"remediation": null,
"durationMs": 58
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "no MCP servers configured",
"details": {},
"remediation": null,
"durationMs": 0
},
"network.env": {
"id": "network.env",
"category": "network",
"status": "ok",
"summary": "network-related environment looks readable",
"details": {
"managed proxy": "not configured",
"proxy env vars": "none",
"respect system proxy": "disabled"
},
"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 inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 98
},
"network.websocket_reachability": {
"id": "network.websocket_reachability",
"category": "websocket",
"status": "ok",
"summary": "Responses WebSocket handshake succeeded",
"details": {
"DNS": "2 IPv4, 2 IPv6, first IPv6",
"auth mode": "chatgpt",
"connect timeout": "15000 ms",
"endpoint": "wss://chatgpt.com/backend-api/<redacted>",
"handshake result": "HTTP 101 Switching Protocols",
"model provider": "openai",
"provider name": "OpenAI",
"proxy env vars": "none",
"reasoning header": "false",
"server model present": "false",
"supports websockets": "true",
"wire API": "responses"
},
"remediation": null,
"durationMs": 808
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running npm on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "/home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
"install method": "npm (package /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/eien/.cache/npm/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-x86_64",
"version": "0.153.4"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search is OK (bundled)",
"details": {
"search command": "/home/eien/.cache/npm/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/eien/.codex/tmp/arg0/codex-arg0PhMRfB/codex-linux-sandbox",
"execve wrapper helper": "/home/eien/.codex/tmp/arg0/codex-arg0PhMRfB/codex-execve-wrapper",
"filesystem sandbox": "restricted",
"network sandbox": "restricted"
},
"remediation": null,
"durationMs": 0
},
"security.endpoint": {
"id": "security.endpoint",
"category": "security",
"status": "ok",
"summary": "endpoint protection is not inspected on this platform",
"details": {
"endpoint products": "not inspected on this platform"
},
"remediation": null,
"durationMs": 0
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "/home/eien/.codex (dir)",
"active rollout files": "171 files, 350971549 total bytes, 2052465 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "/home/eien/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/home/eien/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/home/eien/.codex/log (dir)",
"memories DB": "/home/eien/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"queue DB": "/home/eien/.codex/queue_1.sqlite (file)",
"queue DB integrity": "ok",
"sqlite home": "/home/eien/.codex (dir)",
"state DB": "/home/eien/.codex/state_5.sqlite (file)",
"state DB integrity": "ok",
"thread history DB": "/home/eien/.codex/thread_history_1.sqlite (file)",
"thread history DB integrity": "ok"
},
"remediation": null,
"durationMs": 288
},
"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": "171",
"rollout DB active rows": "171",
"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=171",
"rollout DB rows": "171",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "cli=82, subagent:thread_spawn=71, exec=17, subagent:review=1",
"rollout DB stale rows": "0"
},
"remediation": null,
"durationMs": 90
},
"system.disk": {
"id": "system.disk",
"category": "disk",
"status": "ok",
"summary": "sufficient free disk space (1159.4 GiB)",
"details": {
"CODEX_HOME available": "1159.4 GiB",
"failure threshold": "1.0 GiB",
"warning threshold": "5.0 GiB",
"worktree available": "1159.4 GiB"
},
"remediation": null,
"durationMs": 0
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language en-US",
"details": {
"EDITOR": "set",
"LANG": "en_US.UTF-8",
"LESS": "set",
"PAGER": "set",
"VISUAL": "set",
"os": "Arch Linux Rolling Release [64-bit]",
"os language": "en-US",
"os type": "Arch Linux",
"os version": "Rolling Release"
},
"remediation": null,
"durationMs": 7
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"COLORTERM": "truecolor",
"DISPLAY": "present",
"TERMINFO": "/usr/lib/kitty/terminfo (dir)",
"WAYLAND_DISPLAY": "present",
"color output": "disabled (stdout is not a terminal)",
"effective locale": "en_US.UTF-8",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout is terminal": "false",
"terminal": "kitty",
"terminal size": "212x65"
},
"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": "cwd",
"terminal title project value": "eien",
"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": "0.153.4",
"check for update on startup": "true",
"last checked at": "2026-09-09T22:03:17.549438631Z",
"latest version": "0.154.0",
"latest version status": "newer version is available",
"npm update target": "/home/eien/.cache/npm/lib/node_modules/@openai/codex",
"update action": "npm install -g @openai/codex",
"version cache": "/home/eien/.codex/version.json"
},
"remediation": null,
"durationMs": 164
}
}
}
What issue are you seeing?
- multi_agent_version: v2
- Three-worker capacity was full.
- One worker completed after receiving repeated followup_task calls.
- list_agents reported it completed.
- After roughly 80 seconds, spawn_agent still failed with:
collab spawn failed: agent thread limit reached
What steps can reproduce the bug?
Candidate Reproducer
Configuration
Use multi-agent v2 with four total resident threads: root plus three workers.
[features.multi_agent_v2]
enabled = true
[agents]
enabled = true
max_concurrent_threads_per_session = 4
Start a new root session so the configuration is definitely applied.
Reproduction sequence
-
Spawn two long-running workers, B and C, so they continue occupying residency slots.
Example task:
Run
sleep 180, then reply DONE. Do not spawn agents. -
Spawn a short worker A:
Reply with A0.
Residency is now full: root + A + B + C.
-
Wait until A reports completed.
-
Reuse A with followup_task:
Reply with A1.
-
Wait until A reports completed again.
-
Reuse A a second time:
Reply with A2.
-
Wait until A reports completed.
-
Call list_agents and confirm:
- A is completed.
- B and C are running.
-
Wait another 30–90 seconds to rule out an ordinary completion-cleanup race.
-
Spawn a new agent D using a unique task name:
Reply with D0.
Expected result
A is terminal and idle, so the v2 residency manager evicts A and successfully creates D.
Buggy result
The spawn fails:
collab spawn failed: agent thread limit reached
Despite list_agents reporting A as completed.
This mirrors the observed session almost exactly:
- A completed its initial task.
- A completed two subsequent followup_task turns.
- list_agents showed A completed.
- A replacement spawn roughly 80 seconds later failed.
- B and C were still running.
Control experiment
Repeat the sequence without reusing A:
- Spawn A, B, and C.
- Let A complete once.
- Spawn D.
What is the expected behavior?
If list_agents reports a worker as completed and no new work was sent to it, spawn_agent should be able to reclaim its slot.
If internal cleanup is still underway, completed may remain technically accurate—but returning only agent thread limit reached is inadequate. It should say that completed residents are temporarily non- evictable, preferably with the reason.
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the multi-agent flow described in the title: complete an agent, send follow-up turns, and attempt to spawn a replacement. Trace the multi_agent feature and subagent:thread_spawn activity shown in the report; done means completed agents no longer remain resident and replacement agents can spawn successfully.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- cli, devtools
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100