After the Codex began implementing its plan, it responded with just a single line immediately after compaction - as if it were completely forgetting all previous context.

What version of Codex CLI is running?

codex-cli 0.147.0

What subscription do you have?

Pro 20x

Which model were you using?

gpt-5.6-luna

What platform is your computer?

Linux 6.18.33.2-microsoft-standard-WSL2 x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

Windows Terminal

Codex doctor report

roku@DESKTOP-U0GHMTQ:~/codex-consultant-20260517$ codex doctor --json
{
  "schemaVersion": 1,
  "generatedAt": "1786084129s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.147.0",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/home/roku/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/home/roku/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/home/roku/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/home/roku/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/home/roku/.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/roku/.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/roku/.codex",
        "config.toml": "/home/roku/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/home/roku/codex-consultant-20260517",
        "enabled feature flags": "<redacted>",
        "feature flag overrides": "<redacted>",
        "feature flags enabled": "52",
        "log dir": "/home/roku/.codex/log",
        "mcp servers": "0",
        "model": "gpt-5.6-luna",
        "model provider": "openai",
        "sqlite home": "/home/roku/.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/roku/codex-consultant-20260517",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 96
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/home/roku/.local/bin/codex",
        "current executable": "/home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/bin/codex",
        "install context": "standalone (unix, package /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl, bin /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/bin, resources /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-resources, path /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-path)",
        "managed by bun": "false",
        "managed by npm": "false",
        "managed by pnpm": "false",
        "managed package root": "not set"
      },
      "remediation": null,
      "durationMs": 7
    },
    "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": {
        "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": 168
    },
    "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": 769
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running standalone on linux-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "/home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/bin/codex",
        "install method": "standalone (unix, package /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl, bin /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/bin, resources /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-resources, path /home/roku/.codex/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-path)",
        "platform": "linux-x86_64",
        "version": "0.147.0"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "/home/roku/.codex/packages/standalone/releases/0.147.0-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": "Never",
        "codex-linux-sandbox helper": "/home/roku/.codex/tmp/arg0/codex-arg0vOvdQ0/codex-linux-sandbox",
        "execve wrapper helper": "/home/roku/.codex/tmp/arg0/codex-arg0vOvdQ0/codex-execve-wrapper",
        "filesystem sandbox": "unrestricted",
        "network sandbox": "enabled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/home/roku/.codex (dir)",
        "active rollout files": "2304 files, 3052739181 total bytes, 1324973 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/home/roku/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/home/roku/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/home/roku/.codex/log (dir)",
        "memories DB": "/home/roku/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "queue DB": "/home/roku/.codex/queue_1.sqlite (file)",
        "queue DB integrity": "ok",
        "sqlite home": "/home/roku/.codex (dir)",
        "standalone release cache": "52 entries in /home/roku/.codex/packages/standalone/releases",
        "state DB": "/home/roku/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok",
        "thread history DB": "/home/roku/.codex/thread_history_1.sqlite (file)",
        "thread history DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 6643
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "warning",
      "summary": "rollout files and state DB thread inventory differ",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "10000",
        "rollout DB active rows": "20737",
        "rollout DB archive mismatches": "skipped (scan cap reached)",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "145",
        "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=18994, openai-https=1887, openai_http=1",
        "rollout DB rows": "20882",
        "rollout DB scan cap reached": "true",
        "rollout DB scan errors": "0",
        "rollout DB sources": "subagent:thread_spawn=10373, exec=7584, cli=2109, subagent:other=638, vscode=164, subagent:review=14",
        "rollout DB stale rows": "skipped (scan cap reached)"
      },
      "issues": [
        {
          "severity": "warning",
          "cause": "rollout scan was incomplete or found bad files",
          "measured": "0 scan errors, 0 malformed names, scan cap reached: true",
          "expected": "rollout directories are fully scannable",
          "remedy": "Check file permissions and unexpected files under CODEX_HOME sessions.",
          "fields": []
        }
      ],
      "remediation": null,
      "durationMs": 13680
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language C",
      "details": {
        "EDITOR": "set",
        "LANG": "C.UTF-8",
        "VISUAL": "set",
        "os": "Ubuntu 24.4.0 (noble) [64-bit]",
        "os language": "C",
        "os type": "Ubuntu",
        "os version": "24.4.0"
      },
      "remediation": null,
      "durationMs": 11
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "DISPLAY": "present",
        "WAYLAND_DISPLAY": "present",
        "WSL_DISTRO_NAME": "present",
        "WSL_INTEROP": "present",
        "WT_SESSION": "present",
        "color output": "enabled",
        "effective locale": "C.UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "Windows Terminal",
        "terminal size": "128x48"
      },
      "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": "codex-consultant-2026...",
        "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": "0.146.1",
        "check for update on startup": "true",
        "last checked at": "2026-08-06T23:11:10.410288557Z",
        "latest version": "0.147.0",
        "latest version status": "current version is not older",
        "update action": "standalone installer",
        "version cache": "/home/roku/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 174
    }
  }
}
roku@DESKTOP-U0GHMTQ:~/codex-consultant-20260517$

What issue are you seeing?

Despite having been coding according to the plan up until the very last moment, immediately after Compaction, no context remained at all.

• 回帰テストを先に変更し、現状の resolveAllowedPath が ~/file.txt を /workspace/~/file.txt とし
  て扱うため赤くなることを確認しました。次に共通解決関数だけを最小変更し、同じテストを緑にしま
  す。

• Edited src/roots.ts (+1 -1)
    43  export function resolveAllowedPath(inputPath: string, cwd: string, allowedRoots: string[
        ]): string {
    44 -  const absolutePath = resolve(cwd, inputPath);
    44 +  const absolutePath = resolve(cwd, expandHomePath(inputPath));
    45    return assertAllowedPath(absolutePath, allowedRoots);

• Ran npx tsx src/roots.test.ts
  └ (no output)

• Edited src/skills.test.ts (+16 -0)
     11  } from "./skills.js";
     12 +import { WorkspaceRegistry } from "./workspaces.js";
     13
        ⋮
    240
    241 +  const workspaceRegistry = new WorkspaceRegistry(config);
    242 +  const workspaceContext = await workspaceRegistry.openWorkspace(projectRoot);
    243 +  const globalSkill = workspaceContext.workspace.skills.find(
    244 +    (skill) => skill.name === "agent-global-skill",
    245 +  );
    246 +  assert.ok(globalSkill);
    247 +  const displayedSkillPath = formatPathForPrompt(globalSkill.filePath);
    248 +  assert.match(displayedSkillPath, /^~\//);
    249 +  const resolvedDisplayedSkill = workspaceRegistry.resolveReadPath(
    250 +    workspaceContext.workspace,
    251 +    displayedSkillPath,
    252 +  );
    253 +  assert.equal(resolvedDisplayedSkill.absolutePath, globalSkill.filePath);
    254 +  assert.deepEqual(resolvedDisplayedSkill.readRoots, [projectRoot, globalSkill.baseDir]
         );
    255 +
    256    const skillFileRead = resolveSkillReadPath(loaded.skills, new Set(), projectSkill.fil
         ePath);

• Ran npx tsx src/skills.test.ts
  └ (no output)

• Ran git diff --unified=30 -- docs/chatgpt-coding-workflow.md src/server.ts src/roots.ts src/
  │ roots.test.ts src/skills.test.ts
  └ diff --git a/docs/chatgpt-coding-workflow.md b/docs/chatgpt-coding-workflow.md
    index 6606262..54bb8df 100644
    … +740 lines (ctrl + t to view transcript)
       await rm(root, { recursive: true, force: true });
     }

• Edited 2 files (+9 -2)
  └ docs/chatgpt-coding-workflow.md (+7 -0)
    19
    20 +Workspace path arguments are relative to the opened workspace by default. A
    21 +leading `~` is expanded before containment checks, so paths such as
    22 +`~/.codex/skills/example/SKILL.md` can be reused when `open_workspace` advertises
    23 +them as skills. Paths outside the workspace remain unavailable to ordinary file,
    24 +search, and directory tools; only advertised skills and their activated files are
    25 +readable outside it.
    26 +
    27  Do not reopen the same folder unless:

  └ src/server.ts (+2 -2)
    925            config.skillsEnabled
    926 -            ? "If available skills were returned and a task matches one, read that skil
         l's path before proceeding. Skill paths may be outside the workspace; only advertised S
         KILL.md files and files under already-loaded skill directories are readable."
    926 +            ? "If available skills were returned and a task matches one, read that skil
         l's path before proceeding. Skill paths may be outside the workspace; only advertised S
         KILL.md files and files under already-loaded skill directories are readable. Leading ~
         in an advertised skill path is expanded to the user's home directory."
    927              : "",
        ⋮
    938              config.skillsEnabled
    939 -              ? "File path to read, relative to the workspace root. May also be an adve
         rtised skill path from open_workspace skills."
    939 +              ? "File path to read, relative to the workspace root. May also be an adve
         rtised skill path from open_workspace skills; leading ~ is expanded for those paths."
    940                : "File path to read, relative to the workspace root.",

• Ran npx tsx src/roots.test.ts
  └ (no output)

• Ran npx tsx src/skills.test.ts
  └ (no output)

• Ran npx tsx src/workspaces.test.ts
  └ (no output)

• Ran npx tsc -p tsconfig.json --noEmit
  └ (no output)

────────────────────────────────────────────────────────────────────────────────────────────────

• 中心修正とスキル経路の回帰テストは緑になり、型チェックも通過しました。次に全テストと差分監査を
  行い、問題がなければ build 前にログを退避して常駐サービスへ反映します。

• Waited for background terminal · npm test

• Ran npm test
  └ {"ts":"2026-08-07T05:54:40.076Z","level":"error","event":"process_uncaught_exception","error
    ":"uncaught boom","stack":"Error: uncaught boom\n    at <anonymous> (/tmp/
    … +25 lines (ctrl + t to view transcript)
    opencode, pi, cursor, or copilot: /tmp/devspace-agent-profiles-test-d8jkKV/
    project/.devspace/agents/custom.md

• Ran git diff --check && git diff --stat && git diff --unified=8 -- src/roots.ts src/
  │ roots.test.ts src/skills.test.ts src/server.ts docs/chatgpt-coding-workflow.md
  └  docs/chatgpt-coding-workflow.md |  9 +++++
     docs/configuration.md           | 11 ++++++
    … +412 lines (ctrl + t to view transcript)
       assert.equal(resolveSkillReadPath(loaded.skills, new Set(), resourcePath), undefined);
       assert.equal(

• Ran npm run build
  └
    > @waishnav/devspace@1.0.5 clean
    … +335 lines (ctrl + t to view transcript)
    https://rolldown.rs/reference/OutputOptions.codeSplitting
    - Adjust chunk size limit for this warning via build.chunkSizeWarningLimit.

• Context compacted

────────────────────────────────────────────────────────────────────────────────────────────────

• Understood. I’ll follow these DevSpace repository instructions and preserve the stated
  security, lifecycle, and verification boundaries.

─ Worked for 3m 04s ────────────────────────────────────────────────────────────────────────────


› Continue.


• What would you like me to continue with?

• Feedback uploaded. Please open an issue using the following URL:

  https://github.com/openai/codex/issues/new?template=3-cli.yml&steps=Uploaded%20thread:%20019fda50-2d5a-7232-a7bd-10786216dd07

  Or mention your thread ID 019fda50-2d5a-7232-a7bd-10786216dd07 in an existing issue.

What steps can reproduce the bug?

Uploaded thread: 019fda50-2d5a-7232-a7bd-10786216dd07

What is the expected behavior?

The post-compaction continuation should proceed as normal.

Additional information

_No response_