trace-to-skill 0.1.96 → 0.1.98

package/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md

@@ -1,9 +1,9 @@
 # GitHub Issue Pain Map
 
-Generated: 2026-06-01T03:13:15.553Z
+Generated: 2026-06-01T03:41:41.220Z
 
-Issues analyzed: **14**
-Matched issues: **13**
+Issues analyzed: **17**
+Matched issues: **16**
 Unmatched issues: **1**
 
 This report maps GitHub issues onto deterministic `trace-to-skill` failure classes. Fetch a repository directly with `--repo`, or export issues with `gh issue list` / `gh search issues` and pass the JSON file.
@@ -19,10 +19,12 @@ gh issue list --repo openai/codex --state all --limit 100 --json number,title,bo
 
 | Priority | Kind | Severity | Issues | Comments | Reactions | Example |
 | ---: | --- | --- | ---: | ---: | ---: | --- |
+| 1895 | `codex_remote_connection` | high | 1 | 176 | 851 | [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) |
 | 1051 | `codex_token_burn` | high | 2 | 918 | 53 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
+| 508 | `weak_evidence` | medium | 17 | 2186 | 1094 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
+| 434 | `codex_thinking_hang` | high | 2 | 201 | 103 | [#14048 All models - Codex CLI hangs indefinitely on all prompts, no response generated](https://github.com/openai/codex/issues/14048) |
 | 409 | `codex_auth_verification` | high | 2 | 346 | 18 | [#20161 Phone number verification doesn't work](https://github.com/openai/codex/issues/20161) |
 | 304 | `codex_model_routing_mismatch` | high | 3 | 231 | 18 | [#11189 GPT-5.3-Codex being routed to GPT-5.2](https://github.com/openai/codex/issues/11189) |
-| 268 | `weak_evidence` | medium | 14 | 1809 | 140 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
 | 257 | `codex_context_visibility` | high | 3 | 168 | 26 | [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) |
 | 202 | `premature_completion` | high | 1 | 169 | 8 | [#1243 "Sign in With ChatGPT" functionality needs to be robust against all account types](https://github.com/openai/codex/issues/1243) |
 | 137 | `codex_remote_compact` | high | 1 | 90 | 15 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) |
@@ -34,14 +36,24 @@ gh issue list --repo openai/codex --state all --limit 100 --json number,title,bo
 
 | Rank | Next artifact | Why now | Command |
 | ---: | --- | --- | --- |
-| 1 | Usage evidence fixture and support-ready token report | 2 issue(s), 918 comment(s), severity high; top signal: codex_token_burn. | `trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md` |
-| 2 | Auth verification fixture and login support report | 2 issue(s), 346 comment(s), severity high; top signal: codex_auth_verification. | `trace-to-skill codex-report ./runs --output openai-codex-auth-issue.md` |
-| 3 | Model-routing fixture and SSE evidence report | 3 issue(s), 231 comment(s), severity high; top signal: codex_model_routing_mismatch. | `trace-to-skill codex-report ./runs --output openai-codex-model-routing.md` |
-| 4 | Context visibility fixture and Desktop UI evidence report | 3 issue(s), 168 comment(s), severity high; top signal: codex_context_visibility. | `trace-to-skill codex-report ./runs --output openai-codex-context-visibility.md` |
-| 5 | Codex-ready issue report and failure fixture | 1 issue(s), 169 comment(s), severity high; top signal: premature_completion. | `trace-to-skill codex-report ./runs --output openai-codex-issue.md` |
+| 1 | Remote connection fixture and SSH workspace evidence report | 1 issue(s), 176 comment(s), severity high; top signal: codex_remote_connection. | `trace-to-skill codex-report ./runs --output openai-codex-remote-connection.md` |
+| 2 | Usage evidence fixture and support-ready token report | 2 issue(s), 918 comment(s), severity high; top signal: codex_token_burn. | `trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md` |
+| 3 | Codex-ready issue report and failure fixture | 2 issue(s), 201 comment(s), severity high; top signal: codex_thinking_hang. | `trace-to-skill codex-report ./runs --output openai-codex-issue.md` |
+| 4 | Auth verification fixture and login support report | 2 issue(s), 346 comment(s), severity high; top signal: codex_auth_verification. | `trace-to-skill codex-report ./runs --output openai-codex-auth-issue.md` |
+| 5 | Model-routing fixture and SSE evidence report | 3 issue(s), 231 comment(s), severity high; top signal: codex_model_routing_mismatch. | `trace-to-skill codex-report ./runs --output openai-codex-model-routing.md` |
 
 ## Suggested Next Actions
 
+### codex_remote_connection
+
+Priority score: 1895. 1 issue(s), 176 comment(s).
+
+Example issues:
+- [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) (176 comments; labels: enhancement, app)
+
+Evidence rule prompts:
+- When reporting Codex remote connection failures, capture Codex Desktop version, remote Codex CLI/app-server version, local OS, remote OS/architecture, SSH target alias from `~/.ssh/config`, whether `[features].remote_connections = true` is set, Settings > Connections visibility, selected host/path, remote workspace path, whether the remote filesystem is the source of truth, exact tunnel/app-server error, codex-server pid and restart result, `ps -ef | rg 'codex app-server|openai.chatgpt.*/codex'` evidence if available, remote PATH/auth/proxy/API reachability, model list differences versus local, fs/getMetadata or folder listing errors, ForwardAgent/proxy requirements, and whether reconnect/resume or a clean host works.
+
 ### codex_token_burn
 
 Priority score: 1051. 2 issue(s), 918 comment(s).
@@ -53,6 +65,17 @@ Example issues:
 Evidence rule prompts:
 - When reporting Codex token burn, capture plan/workspace, client and version, model and reasoning/speed settings, fast-mode/large-context/subagent/review flags, recent /status and usage-dashboard deltas, local token totals including cached input/output/reasoning if available, background process ids and write_stdin poll cadence, compaction attempts and failures, retry/tool-loop counts, whether the app was idle, and a minimal reproduction with before/after usage percentages.
 
+### codex_thinking_hang
+
+Priority score: 434. 2 issue(s), 201 comment(s).
+
+Example issues:
+- [#14048 All models - Codex CLI hangs indefinitely on all prompts, no response generated](https://github.com/openai/codex/issues/14048) (131 comments; labels: bug, agent)
+- [#7156 Codex hangs during cli command execution](https://github.com/openai/codex/issues/7156) (70 comments; labels: bug, CLI)
+
+Evidence rule prompts:
+- When reporting Codex thinking or CLI no-response hangs, capture app/CLI/extension version, OS/terminal such as WSL, model and reasoning/speed settings, subscription/workspace, turn/thread id, prompt timestamp, whether the prompt is accepted but no streaming output/error/timeout appears, status bar or usage percent such as 100% left, `turn/start` or `task_started` timestamp, last successful tool-call output, first `response_item` or assistant timestamp if it eventually appears, `RUST_LOG`/SSE evidence including unhandled responses events, transport (`responses_http` or websocket), `time.busy`/`time.idle` close metrics, reconnect or stream-disconnect lines, status incident link or cluster mitigation note if relevant, MCP/subagent state, whether stop/Ctrl+C/interrupt works, and whether a new thread, logout/login, downgrade, API billing path, or minimal config without MCPs recovers.
+
 ### codex_auth_verification
 
 Priority score: 409. 2 issue(s), 346 comment(s).
@@ -76,28 +99,6 @@ Example issues:
 Evidence rule prompts:
 - When reporting Codex model-routing mismatches, capture the Codex app/CLI/extension version, subscription/workspace, selected model from config.toml, TUI, command flag, or UI, actual server-side model from SSE `response.created` / `response.model`, the exact `RUST_LOG` or trace command used, timestamp, account or verification state without secrets, whether API and Codex routes differ, whether a warning/fallback notice appeared, and a minimal one-prompt reproduction with redacted logs.
 
-### codex_context_visibility
-
-Priority score: 257. 3 issue(s), 168 comment(s).
-
-Example issues:
-- [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) (160 comments; labels: bug, context, app)
-- [#23591 Reimplement visible context/token usage indicator in Codex Desktop App](https://github.com/openai/codex/issues/23591) (7 comments; labels: enhancement, rate-limits, context, app)
-- [#24710 Codex Desktop: hidden context indicator still blocks long-session context management](https://github.com/openai/codex/issues/24710) (1 comments; labels: enhancement, context, app)
-
-Evidence rule prompts:
-- When reporting Codex context-visibility regressions, capture Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
-
-### premature_completion
-
-Priority score: 202. 1 issue(s), 169 comment(s).
-
-Example issues:
-- [#1243 "Sign in With ChatGPT" functionality needs to be robust against all account types](https://github.com/openai/codex/issues/1243) (169 comments; labels: none)
-
-Evidence rule prompts:
-- Before claiming completion, run the relevant validation command or clearly state the exact validation that could not be run and why.
-
 ## Unmatched Issues
 
 - [#99999 Add a fun launch animation](https://github.com/openai/codex/issues/99999) (0 comments; labels: enhancement)

package/docs/CODEX_ISSUE_MAP.md

@@ -35,7 +35,7 @@ npx trace-to-skill lsp-audit . --format json
 | Undo, rewind, and pre-agent checkpoint needs | users want `/undo` or `/rewind`, double-Esc only rewinds chat state, untracked/gitignored files are not protected by commits, and manual recovery needs reviewable pre-agent evidence | workspace checkpoint bundle | `trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex` before agent work |
 | Model routing mismatch | selected `gpt-5.3-codex` in `config.toml`, TUI, or `--model`, but SSE `response.created` / `response.model` shows `gpt-5.2`, silent fallback, no warning, no fallback notice | `codex_model_routing_mismatch` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo model-routing-mismatch` |
 | Latency regressions | GPT-5.5 Fast feels like Standard, simple tasks take 10-20+ minutes, pre-first-token or thinking stalls, slow search/read/compaction, hours for small code changes | `codex_latency_regression` | `trace-to-skill codex-report ./runs` |
-| Thinking or stream hangs | accepted turn, completed local tool output, no streamed assistant follow-up, long gap before first `response_item`, `time.busy` milliseconds with `time.idle` hundreds of seconds, Stop/Ctrl+C cannot interrupt, subagent parent stuck | `codex_thinking_hang` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo thinking-hang` |
+| Thinking or stream hangs | accepted turn, completed local tool output, CLI prompt accepted but no streaming output/error/timeout, status bar `100% left`, unhandled responses events, terminal command execution stuck, long gap before first `response_item`, `time.busy` milliseconds with `time.idle` hundreds of seconds, Stop/Ctrl+C cannot interrupt, status incident or cluster-reroute note, subagent parent stuck | `codex_thinking_hang` | `trace-to-skill codex-report ./runs`, `trace-to-skill demo thinking-hang`, or `trace-to-skill demo cli-no-response` |
 | Clipboard, paste, and generated attachment regressions | `Copy as Markdown` missing, Copy menu only exports metadata, long pasted prompts become `Pasted text.txt`, generated attachments cannot preview/edit/revert, `/goal` ignores non-empty fileAttachments | `codex_clipboard_attachment` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo clipboard-attachment` |
 | Deeplink, OAuth callback, and external launch regressions | `codex://oauth_callback?code=...` fails, `Unable to find Electron app`, `app\oauth_callback?code=...`, notification `type=click&tag=...` becomes an app path, AppX/MSIX protocol evidence, `codex app .` only focuses | `codex_deeplink_launch` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo deeplink-launch` |
 | App connector auth cache and stale link regressions | `401 Reauthentication required`, `refresh token was revoked`, stale `link_*`, `isAccessible: false`, `codex_apps_tools` or `codex_app_directory` cache regeneration keeps broken connector state | `codex_connector_auth_cache` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo connector-auth-cache` |
@@ -61,6 +61,7 @@ npx trace-to-skill lsp-audit . --format json
 | Sandbox and permission blockers | Windows sandbox setup refresh, `os error 740`, ACL/ownership drift, approval-mode mismatch | `sandbox_permission` | `trace-to-skill analyze ./runs` |
 | Auth and connectivity failures | `token_exchange_failed`, `auth.openai.com/oauth/token`, missing CA certificates, proxy/TLS, IPv6, Cloudflare, stream disconnects | `codex_connectivity` | `trace-to-skill codex-report ./runs` |
 | Sign-in and account verification failures | phone verification, SMS/OTP, SSO, ChatGPT sign-in account routing, organization/workspace verification, extension chat initialization | `codex_auth_verification` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo auth-verification` |
+| Remote connection and SSH workspace failures | Codex Desktop remote development, Settings > Connections hidden, `[features].remote_connections`, SSH hosts from `~/.ssh/config`, remote filesystem source of truth, local tunnel not ready, stale remote Codex version, codex-server/app-server restart, fs/getMetadata folder listing timeouts, ForwardAgent or local API proxy needs | `codex_remote_connection` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo remote-connection` |
 | Remote-control routing failures | `Waiting for desktop`, `Directory: Unavailable`, stale listener/enrollment, `127.0.0.1:14567`, empty backend environments | `codex_remote_control` | `trace-to-skill codex-report ./runs` |
 | MCP runtime failures | `user cancelled MCP tool call`, `unsupported call: mcp__...__...`, namespace/serverName loss, `Transport closed` | `codex_mcp_runtime` | `trace-to-skill codex-report ./runs` |
 | Plugin runtime and bundled capability failures | Computer Use native pipe path unavailable, Browser/Computer Use settings fail, plugin/list `unknown variant 'vertical'`, stale plugin cache downgrades | `codex_plugin_runtime` | `trace-to-skill codex-report ./runs` |
@@ -84,13 +85,14 @@ npx trace-to-skill lsp-audit . --format json
 - Include `session-audit` output, largest rollout JSONL sizes, largest line sizes, parse-error counts, `session_index.jsonl` line count, bloated title byte/signal counts, unindexed rollout thread count, recoverable `codex resume <id>` commands, hashed project groups, and state-file presence for resume/session-state failures.
 - Include `diagnostics-bundle` output when the issue spans config plus local session/history state, or when you need one metadata-only folder that excludes raw logs, SQLite databases, raw config, and transcripts.
 - Include pre-first-token, thinking, tool, search, read, and compaction timings plus model/speed settings for latency regressions.
-- Include `turn/start`, `task_started`, last successful tool output, first `response_item` timestamp, `responses_http` or websocket evidence, `time.busy` / `time.idle`, MCP/subagent state, stop/interrupt behavior, and minimal-config recovery evidence for Thinking hangs.
+- Include `turn/start`, `task_started`, last successful tool output, accepted prompt/no output/no error/no timeout, status bar `100% left`, first `response_item` timestamp, `RUST_LOG` SSE evidence, unhandled responses events, `responses_http` or websocket evidence, `time.busy` / `time.idle`, status incident or cluster note, MCP/subagent state, stop/Ctrl+C/interrupt behavior, and minimal-config recovery evidence for Thinking or CLI no-response hangs.
 - Include exact Copy menu items, paste source size, generated attachment name/path/size, visible editor text, `pasted-text-attachments.json` or fileAttachments metadata, `/goal` or submit path, preview/edit/revert actions, and clipboard payload format for clipboard/attachment regressions.
 - Include exact redacted `codex://` URI shape, connector/plugin, browser, error dialog text, app running state, AppX/MSIX protocol registration evidence such as AppUserModelID and DelegateExecute, HKCU/HKCR `codex` keys, command-line arguments, `Start-Process "codex://test"` repro, and repair/reinstall/re-register attempts for deeplink/OAuth launch regressions.
 - Include connector/plugin name and id, installed plugin root, exact Codex Apps tool name, 401/reauth text, `link_*` id before and after reconnect/cache regeneration, `isAccessible` state, redacted `codex_apps_tools`/`codex_app_directory` metadata, ChatGPT app page state, and external MCP workaround result for connector auth-cache regressions.
 - Include fork source and forked thread ids, fork timestamp, fork boundary marker, `input_tokens` and `cached_input_tokens` before/after fork, `prompt_cache_key` before/after, cache hit rate, duplicated parent-turn/tool-transcript examples, whether new files were read before token growth, compaction state, subagent/`fork_context` history, minimal repro steps, and non-fork control result for context-fork bloat.
 - Include Codex Desktop/app/CLI version, MultiAgentV2 state, OS, model, parent thread id, child thread ids, exact `spawn_agent` arguments, `fork_turns`, role/profile, whether `multi_tool_use.parallel` or same-turn parallel spawning was used, redacted child rollout line order, first user/task message, assistant/commentary envelope lines, sibling prompt excerpts, `wait_agent` and `close_agent` results, unexpected child tool calls, and sequential single-child versus parallel-child controls for subagent prompt leakage.
 - Include effective `CODEX_HOME`, config files considered, redacted MCP sections, trust/profile/default-permissions state, `codex mcp list/get`, CLI-versus-Desktop/VS Code comparison, loaded config path/log lines, WSL/remote/SSH state, and restart/reload/new-conversation results for MCP discovery mismatches.
+- Include Codex Desktop version, remote Codex CLI/app-server version, local OS, remote OS/architecture, SSH alias from `~/.ssh/config`, `[features].remote_connections = true`, Settings > Connections visibility, selected host/path, remote workspace path, remote filesystem source-of-truth expectation, tunnel/app-server error, codex-server pid/restart evidence, remote PATH/auth/proxy/API reachability, model-list differences, fs/getMetadata/folder listing errors, ForwardAgent/proxy needs, and reconnect/resume behavior for remote connection reports.
 - Include Codex version, MCP server name, transport URL without secrets, initialize/tools/list/tools/call results, HTTP status, `Content-Type`, SSE event framing, JSON-RPC message shape, session id before/after restart, auth/OAuth expectations, User-Agent/header requirements, parse/deserialize error, another-client comparison, and reconnect/reinitialize behavior for Streamable HTTP MCP reports.
 - Include app/CLI/extension version, OS, surface, shell/Desktop route, `[features].hooks`, redacted `hooks.json`, hook event type, matcher, handler command/name, expected versus observed fire count, duplicate event ids, deprecation warning text, trust state, live edit/rate-limit/auto-restore timing, Code Mode `exec` versus normal CLI comparison, linked-worktree cwd, Hooks settings UI evidence, and restart/reload/new-session behavior for hooks reports.
 - Include terminal emulator/version, shell, WSL/SSH/tmux/Zellij state, streaming state, exact scroll action, viewport snap behavior, first missing or duplicated line id, raw log/transcript proof, terminal capture, numbered-line harness/control output, terminal dimensions/scrollback settings, and `/resume` or transcript recovery behavior for terminal-output integrity reports.
@@ -119,6 +121,7 @@ npx trace-to-skill lsp-audit . --format json
 - Tool-call integrity and rollback failures: https://github.com/openai/codex/issues/25399, https://github.com/openai/codex/issues/25380, https://github.com/openai/codex/issues/25426, https://github.com/openai/codex/issues/7291
 - Undo, rewind, and pre-agent checkpoint needs: https://github.com/openai/codex/issues/9203, https://github.com/openai/codex/issues/11626
 - Latency regressions: https://github.com/openai/codex/issues/24422, https://github.com/openai/codex/issues/21527, https://github.com/openai/codex/issues/11984, https://github.com/openai/codex/issues/12161
+- CLI no-response and command execution hangs: https://github.com/openai/codex/issues/14048, https://github.com/openai/codex/issues/7156
 - Deeplink, OAuth callback, and external launch regressions: https://github.com/openai/codex/issues/25203, https://github.com/openai/codex/issues/25231, https://github.com/openai/codex/issues/25368, https://github.com/openai/codex/issues/25333
 - App connector auth cache and stale link regressions: https://github.com/openai/codex/issues/24675, https://github.com/openai/codex/issues/25443
 - Context fork bloat and prompt-cache lineage loss: https://github.com/openai/codex/issues/25467, https://github.com/openai/codex/issues/24704, https://github.com/openai/codex/issues/24150, https://github.com/openai/codex/issues/13491, https://github.com/openai/codex/issues/24281

package/docs/CODEX_ISSUE_RADAR.md

@@ -1,10 +1,10 @@
 # GitHub Issue Pain Map
 
-Generated: 2026-06-01T03:13:20.215Z
+Generated: 2026-06-01T03:41:42.598Z
 
 Issues analyzed: **46**
-Matched issues: **20**
-Unmatched issues: **26**
+Matched issues: **23**
+Unmatched issues: **23**
 
 This report maps GitHub issues onto deterministic `trace-to-skill` failure classes. Fetch a repository directly with `--repo`, or export issues with `gh issue list` / `gh search issues` and pass the JSON file.
 
@@ -21,26 +21,26 @@ gh issue list --repo openai/codex --state all --limit 100 --json number,title,bo
 | ---: | --- | --- | ---: | ---: | ---: | --- |
 | 2438 | `codex_token_burn` | high | 4 | 1151 | 620 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
 | 2221 | `weak_evidence` | medium | 46 | 4755 | 7794 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
+| 1895 | `codex_remote_connection` | high | 1 | 176 | 851 | [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) |
 | 884 | `sensitive_file_access` | high | 1 | 75 | 396 | [#2847 A way to exclude sensitive files](https://github.com/openai/codex/issues/2847) |
 | 805 | `codex_auth_verification` | high | 3 | 436 | 166 | [#20161 Phone number verification doesn't work](https://github.com/openai/codex/issues/20161) |
 | 631 | `codex_context_visibility` | high | 1 | 160 | 227 | [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) |
 | 442 | `codex_tool_call_integrity` | high | 1 | 61 | 182 | [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) |
+| 434 | `codex_thinking_hang` | high | 2 | 201 | 103 | [#14048 All models — Codex CLI hangs indefinitely on all prompts, no response generated](https://github.com/openai/codex/issues/14048) |
 | 376 | `codex_remote_compact` | high | 2 | 147 | 101 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) |
 | 376 | `context_compaction` | high | 2 | 147 | 101 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) |
 | 351 | `codex_terminal_output_integrity` | high | 1 | 66 | 134 | [#2558 Codex client output truncated when scrolling in Zellij](https://github.com/openai/codex/issues/2558) |
 | 324 | `codex_model_routing_mismatch` | high | 1 | 169 | 69 | [#11189 GPT-5.3-Codex being routed to GPT-5.2](https://github.com/openai/codex/issues/11189) |
-| 261 | `premature_completion` | high | 1 | 60 | 92 | [#2448 Codex CLI: Plus users hitting usage limits extremely quickly compared to competitors](https://github.com/openai/codex/issues/2448) |
-| 247 | `codex_connectivity` | high | 2 | 192 | 14 | [#12764 The codex cli giving: 401 unauthorized](https://github.com/openai/codex/issues/12764) |
 
 ## Maintainer Roadmap
 
 | Rank | Next artifact | Why now | Command |
 | ---: | --- | --- | --- |
 | 1 | Usage evidence fixture and support-ready token report | 4 issue(s), 1151 comment(s), severity high; top signal: codex_token_burn. | `trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md` |
-| 2 | Privacy/safety guardrail and redacted support bundle | 1 issue(s), 75 comment(s), severity high; top signal: sensitive_file_access. | `trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics` |
-| 3 | Auth verification fixture and login support report | 3 issue(s), 436 comment(s), severity high; top signal: codex_auth_verification. | `trace-to-skill codex-report ./runs --output openai-codex-auth-issue.md` |
-| 4 | Context visibility fixture and Desktop UI evidence report | 1 issue(s), 160 comment(s), severity high; top signal: codex_context_visibility. | `trace-to-skill codex-report ./runs --output openai-codex-context-visibility.md` |
-| 5 | Patch safety fixture and pre-agent checkpoint workflow | 1 issue(s), 61 comment(s), severity high; top signal: codex_tool_call_integrity. | `trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex` |
+| 2 | Remote connection fixture and SSH workspace evidence report | 1 issue(s), 176 comment(s), severity high; top signal: codex_remote_connection. | `trace-to-skill codex-report ./runs --output openai-codex-remote-connection.md` |
+| 3 | Privacy/safety guardrail and redacted support bundle | 1 issue(s), 75 comment(s), severity high; top signal: sensitive_file_access. | `trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics` |
+| 4 | Auth verification fixture and login support report | 3 issue(s), 436 comment(s), severity high; top signal: codex_auth_verification. | `trace-to-skill codex-report ./runs --output openai-codex-auth-issue.md` |
+| 5 | Context visibility fixture and Desktop UI evidence report | 1 issue(s), 160 comment(s), severity high; top signal: codex_context_visibility. | `trace-to-skill codex-report ./runs --output openai-codex-context-visibility.md` |
 
 ## Suggested Next Actions
 
@@ -56,6 +56,16 @@ Example issues:
 Evidence rule prompts:
 - When reporting Codex token burn, capture plan/workspace, client and version, model and reasoning/speed settings, fast-mode/large-context/subagent/review flags, recent /status and usage-dashboard deltas, local token totals including cached input/output/reasoning if available, background process ids and write_stdin poll cadence, compaction attempts and failures, retry/tool-loop counts, whether the app was idle, and a minimal reproduction with before/after usage percentages.
 
+### codex_remote_connection
+
+Priority score: 1895. 1 issue(s), 176 comment(s).
+
+Example issues:
+- [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) (176 comments; labels: enhancement, app)
+
+Evidence rule prompts:
+- When reporting Codex remote connection failures, capture Codex Desktop version, remote Codex CLI/app-server version, local OS, remote OS/architecture, SSH target alias from `~/.ssh/config`, whether `[features].remote_connections = true` is set, Settings > Connections visibility, selected host/path, remote workspace path, whether the remote filesystem is the source of truth, exact tunnel/app-server error, codex-server pid and restart result, `ps -ef | rg 'codex app-server|openai.chatgpt.*/codex'` evidence if available, remote PATH/auth/proxy/API reachability, model list differences versus local, fs/getMetadata or folder listing errors, ForwardAgent/proxy requirements, and whether reconnect/resume or a clean host works.
+
 ### sensitive_file_access
 
 Priority score: 884. 1 issue(s), 75 comment(s).
@@ -88,27 +98,17 @@ Example issues:
 Evidence rule prompts:
 - When reporting Codex context-visibility regressions, capture Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
 
-### codex_tool_call_integrity
-
-Priority score: 442. 1 issue(s), 61 comment(s).
-
-Example issues:
-- [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) (61 comments; labels: enhancement, extension)
-
-Evidence rule prompts:
-- When reporting Codex tool-call integrity failures, capture the exact tool input and output, app/CLI/extension version, OS/IDE, workspace git state, affected file path and whether it already existed or was a symlink, diff before/after, tool_call_id sequence, durable thread state for subagents, rollback/revert attempts, and whether a clean repo reproduction fails the same way.
-
 ## Unmatched Issues
 
 - [#10410 Codex Desktop App: macOS Intel (x86_64) support](https://github.com/openai/codex/issues/10410) (190 comments; labels: enhancement, app)
-- [#10450 Remote Development in Codex Desktop App](https://github.com/openai/codex/issues/10450) (176 comments; labels: enhancement, app)
-- [#14048 All models — Codex CLI hangs indefinitely on all prompts, no response generated](https://github.com/openai/codex/issues/14048) (131 comments; labels: bug, agent)
 - [#2604 Subagent Support](https://github.com/openai/codex/issues/2604) (103 comments; labels: enhancement, subagent)
 - [#12564 Allow renaming task/thread titles to improve history navigation](https://github.com/openai/codex/issues/12564) (77 comments; labels: enhancement, extension)
 - [#2860 Unusable on Windows due to permission ask for every shell command](https://github.com/openai/codex/issues/2860) (77 comments; labels: bug, windows-os)
 - [#2109 Event Hooks](https://github.com/openai/codex/issues/2109) (76 comments; labels: enhancement, hooks)
 - [#2796 BUG: VSCode IDE Plugin on SSH Connection: "Failed to load tasks."](https://github.com/openai/codex/issues/2796) (71 comments; labels: bug, extension)
 - [#16231 High CPU usage on macOS after updating Codex in VS Code extension to 26.325.31654](https://github.com/openai/codex/issues/16231) (71 comments; labels: bug, extension, regression, performance)
-- [#7156 Codex hangs during cli command execution](https://github.com/openai/codex/issues/7156) (70 comments; labels: bug, CLI)
 - [#4313 Extension for JetBrains IDEs (PyCharm, IntelliJ, etc.)](https://github.com/openai/codex/issues/4313) (70 comments; labels: enhancement)
 - [#13041 WebSocket upgrade succeeds then server closes with 1008 Policy (falls back to HTTPS)](https://github.com/openai/codex/issues/13041) (70 comments; labels: bug, connectivity)
+- [#11701 Subagent configuration and orchestration](https://github.com/openai/codex/issues/11701) (69 comments; labels: enhancement, subagent)
+- [#11023 Codex desktop app for Linux](https://github.com/openai/codex/issues/11023) (68 comments; labels: enhancement, app)
+- [#6172 Hitting rate limits](https://github.com/openai/codex/issues/6172) (66 comments; labels: bug, codex-web, rate-limits)

package/docs/DEMO.md

@@ -1,10 +1,10 @@
 # trace-to-skill Demo
 
-Scenario: **Codex context or token usage indicator missing**
+Scenario: **Codex CLI no-response or all-model hang**
 
-Desktop context or token usage indicators disappear, leaving long-session compaction pressure invisible.
+Codex CLI accepts prompts but produces no streaming output, no error, no timeout, or hangs during command execution.
 
-Fixture: `fixtures/codex-context-visibility.md`
+Fixture: `fixtures/codex-cli-no-response.md`
 
 This is a packaged public fixture, so you can try the project without collecting a private trace first.
 
@@ -14,7 +14,7 @@ This is a packaged public fixture, so you can try the project without collecting
 
 Score: **75/100**
 
-Likely failure class: **Codex context or token usage indicator missing (codex_context_visibility, high)**
+Likely failure class: **Codex thinking or stream hang (codex_thinking_hang, high)**
 
 Agent workflow needs clearer verification, instruction, or security hardening before broad reuse.
 
@@ -23,25 +23,25 @@ Agent workflow needs clearer verification, instruction, or security hardening be
 ```md
 ### What happened?
 
-trace-to-skill detected Codex context or token usage indicator missing (codex_context_visibility). Desktop users need passive context-pressure visibility during long coding sessions so they can decide when to compact, split a thread, reduce pasted context, or avoid context loss before the app forces compaction.
+trace-to-skill detected Codex thinking or stream hang (codex_thinking_hang). Codex can accept a turn, finish local tool calls, or keep a Responses request open while the UI/CLI remains on Thinking or Working with no streamed follow-up, making users interrupt healthy runs or lose long-session context.
 
 ### Detected failure class
 
-- codex_context_visibility: Codex context or token usage indicator missing (high)
+- codex_thinking_hang: Codex thinking or stream hang (high)
 
 ### Evidence
 
-#### Codex context or token usage indicator missing
-- fixtures/codex-context-visibility.md:5 - - Codex Desktop no longer shows a visible context/token usage indicator in the chat UI after an update.
-- fixtures/codex-context-visibility.md:6 - - Previously the app exposed context usage information, context-window pressure, or a tooltip near the input area.
-- fixtures/codex-context-visibility.md:8 - - `/status` is useful as an explicit command, but it is not a replacement for passive context awareness during long-running desktop threads.
-- fixtures/codex-context-visibility.md:9 - - The missing indicator affects professional coding workflows because users cannot tell when to compact, start a new thread, reduce pasted context, or split work before context loss.
-- fixtures/codex-context-visibility.md:10 - - A related report says the data exists in local session logs, but the app no longer exposes it passively.
-- fixtures/codex-context-visibility.md:15 - - Screenshot or short recording of the chat input area where the context indicator or tooltip used to appear.
+#### Codex thinking or stream hang
+- fixtures/codex-cli-no-response.md:1 - # Codex CLI No-Response Hang
+- fixtures/codex-cli-no-response.md:3 - Public issue cluster: All models - Codex CLI hangs indefinitely on all prompts, no response generated.
+- fixtures/codex-cli-no-response.md:7 - - Codex CLI accepts prompts and displays them, but no streaming output begins.
+- fixtures/codex-cli-no-response.md:8 - - All models tested, including `gpt-5.4 high`, `gpt-5.3-codex`, and `gpt-5.1-codex-max`, show no response, no error, and no timeout.
+- fixtures/codex-cli-no-response.md:9 - - The status bar remains `gpt-5.4 high - 100% left`; no tokens are being consumed while the prompt is stuck.
+- fixtures/codex-cli-no-response.md:10 - - A `status.openai.com/incidents` status incident note says Codex CLI hanging or no response may come from unhealthy clusters and rerouted traffic.
 
 ### Diagnostics to attach
 
-- When reporting Codex context-visibility regressions, capture Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
+- When reporting Codex thinking or CLI no-response hangs, capture app/CLI/extension version, OS/terminal such as WSL, model and reasoning/speed settings, subscription/workspace, turn/thread id, prompt timestamp, whether the prompt is accepted but no streaming output/error/timeout appears, status bar or usage percent such as 100% left, `turn/start` or `task_started` timestamp, last successful tool-call output, first `response_item` or assistant timestamp if it eventually appears, `RUST_LOG`/SSE evidence including unhandled responses events, transport (`responses_http` or websocket), `time.busy`/`time.idle` close metrics, reconnect or stream-disconnect lines, status incident link or cluster mitigation note if relevant, MCP/subagent state, whether stop/Ctrl+C/interrupt works, and whether a new thread, logout/login, downgrade, API billing path, or minimal config without MCPs recovers.
 
 ### Privacy
 
@@ -50,23 +50,25 @@ trace-to-skill detected Codex context or token usage indicator missing (codex_co
 
 ## Findings
 
-### 1. Codex context or token usage indicator missing
+### 1. Codex thinking or stream hang
 
 Severity: **high**
 
-Desktop users need passive context-pressure visibility during long coding sessions so they can decide when to compact, split a thread, reduce pasted context, or avoid context loss before the app forces compaction.
+Codex can accept a turn, finish local tool calls, or keep a Responses request open while the UI/CLI remains on Thinking or Working with no streamed follow-up, making users interrupt healthy runs or lose long-session context.
 
 Evidence:
-- `fixtures/codex-context-visibility.md:5` - Codex Desktop no longer shows a visible context/token usage indicator in the chat UI after an update.
-- `fixtures/codex-context-visibility.md:6` - Previously the app exposed context usage information, context-window pressure, or a tooltip near the input area.
-- `fixtures/codex-context-visibility.md:8` - `/status` is useful as an explicit command, but it is not a replacement for passive context awareness during long-running desktop threads.
-- `fixtures/codex-context-visibility.md:9` - The missing indicator affects professional coding workflows because users cannot tell when to compact, start a new thread, reduce pasted context, or split work before context loss.
-- `fixtures/codex-context-visibility.md:10` - A related report says the data exists in local session logs, but the app no longer exposes it passively.
-- `fixtures/codex-context-visibility.md:15` - Screenshot or short recording of the chat input area where the context indicator or tooltip used to appear.
+- `fixtures/codex-cli-no-response.md:1` # Codex CLI No-Response Hang
+- `fixtures/codex-cli-no-response.md:3` Public issue cluster: All models - Codex CLI hangs indefinitely on all prompts, no response generated.
+- `fixtures/codex-cli-no-response.md:7` - Codex CLI accepts prompts and displays them, but no streaming output begins.
+- `fixtures/codex-cli-no-response.md:8` - All models tested, including `gpt-5.4 high`, `gpt-5.3-codex`, and `gpt-5.1-codex-max`, show no response, no error, and no timeout.
+- `fixtures/codex-cli-no-response.md:9` - The status bar remains `gpt-5.4 high - 100% left`; no tokens are being consumed while the prompt is stuck.
+- `fixtures/codex-cli-no-response.md:10` - A `status.openai.com/incidents` status incident note says Codex CLI hanging or no response may come from unhealthy clusters and rerouted traffic.
+- `fixtures/codex-cli-no-response.md:12` - In another report, Codex hangs during terminal command execution; basic shell commands get stuck, it does half the job then stuck, and the VS Code client remains on Thinking or Working.
+- `fixtures/codex-cli-no-response.md:17` The `codex exec --sandbox read-only --model gpt-5.3-codex 'ping'` run has no output and hangs after MCP startup with `unhandled responses event` SSE lines:
 
 Suggested rule:
 
-> When reporting Codex context-visibility regressions, capture Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
+> When reporting Codex thinking or CLI no-response hangs, capture app/CLI/extension version, OS/terminal such as WSL, model and reasoning/speed settings, subscription/workspace, turn/thread id, prompt timestamp, whether the prompt is accepted but no streaming output/error/timeout appears, status bar or usage percent such as 100% left, `turn/start` or `task_started` timestamp, last successful tool-call output, first `response_item` or assistant timestamp if it eventually appears, `RUST_LOG`/SSE evidence including unhandled responses events, transport (`responses_http` or websocket), `time.busy`/`time.idle` close metrics, reconnect or stream-disconnect lines, status incident link or cluster mitigation note if relevant, MCP/subagent state, whether stop/Ctrl+C/interrupt works, and whether a new thread, logout/login, downgrade, API billing path, or minimal config without MCPs recovers.
 
 
 ## Reporter Notes
@@ -97,6 +99,8 @@ Suggested rule:
 - `terminal-output-integrity`: Terminal scrollback, streamed output, or transcript rendering drops, overwrites, truncates, or makes lines inaccessible.
 - `subagent-lifecycle`: Completed, closed, stale, or interrupted subagents diverge between UI, live registry, persisted state, quota, and parent discoverability.
 - `usage-bucket-confusion`: Usage popovers show 5h and weekly percentages without clear remaining/used, rolling/calendar, or account/workspace scope.
+- `context-visibility`: Desktop context or token usage indicators disappear, leaving long-session compaction pressure invisible.
+- `remote-connection`: Desktop remote SSH workspaces, Settings > Connections, remote app-server, tunnel, or remote filesystem evidence breaks.
 - `token-burn`: Usage drains from background polling, idle activity, compaction loops, retries, or cached-heavy turns.
 - `patch-overwrite`: `apply_patch` accepts `*** Add File` for an existing path, turning a create operation into a silent overwrite.
 - `sensitive-files`: Secrets, local credentials, production env files, or private databases enter agent context.
@@ -112,6 +116,7 @@ trace-to-skill demo subagent-prompt-leakage
 trace-to-skill demo windows-helper-path
 trace-to-skill demo patch-overwrite
 trace-to-skill demo thinking-hang
+trace-to-skill demo cli-no-response
 trace-to-skill demo clipboard-attachment
 trace-to-skill demo deeplink-launch
 trace-to-skill demo connector-auth-cache
@@ -122,6 +127,7 @@ trace-to-skill demo terminal-output-integrity
 trace-to-skill demo subagent-lifecycle
 trace-to-skill demo usage-bucket-confusion
 trace-to-skill demo context-visibility
+trace-to-skill demo remote-connection
 trace-to-skill demo file-tree-ui
 trace-to-skill demo usage-reset-drift
 ```

package/docs/FAILURE_TAXONOMY.md

@@ -52,9 +52,9 @@ The fix is to capture app/CLI/extension version, model and speed/reasoning setti
 
 Codex can accept a turn, finish a local tool call, or keep a Responses request open while the UI or CLI remains on Thinking/Working with no streamed assistant follow-up. This is more specific than general latency: the session appears structurally accepted but the next visible assistant event never arrives or arrives after a very long gap.
 
-Common signals include `turn/start`, `task_started`, a successful tool output followed by no next assistant action, a long gap before the first `response_item`, `model_client.stream_responses_api` close lines where `time.busy` is milliseconds but `time.idle` is hundreds of seconds, `responses_http` or websocket reconnects, Stop/Ctrl+C not interrupting the stuck turn, a subagent parent thread waiting while a child remains active, and minimal `config.toml` without MCPs changing the behavior.
+Common signals include `turn/start`, `task_started`, a successful tool output followed by no next assistant action, a CLI prompt accepted with no streaming output, no error, and no timeout, status bar `100% left` with no tokens consumed, `codex exec --sandbox read-only --model ... 'ping'` stopping after `mcp startup: no servers`, `unhandled responses event` SSE lines, terminal command execution hanging, a status incident or unhealthy-cluster reroute note, a long gap before the first `response_item`, `model_client.stream_responses_api` close lines where `time.busy` is milliseconds but `time.idle` is hundreds of seconds, `responses_http` or websocket reconnects, Stop/Ctrl+C not interrupting the stuck turn, a subagent parent thread waiting while a child remains active, and minimal `config.toml` without MCPs changing the behavior.
 
-The fix is to capture Codex version, OS, model and speed/reasoning settings, turn or thread id, prompt timestamp, last successful tool output, first `response_item` timestamp, transport evidence, `time.busy` / `time.idle`, reconnect or stream-close lines, MCP/subagent lifecycle state, stop/interrupt behavior, and whether a new thread or minimal config recovers.
+The fix is to capture Codex app/CLI/extension version, OS/terminal such as WSL, model and speed/reasoning settings, subscription/workspace, turn or thread id, prompt timestamp, whether the prompt is accepted but no output/error/timeout appears, status bar or usage percent, last successful tool output, first `response_item` timestamp, `RUST_LOG`/SSE evidence, transport evidence, `time.busy` / `time.idle`, reconnect or stream-close lines, status incident link or cluster mitigation note, MCP/subagent lifecycle state, stop/Ctrl+C/interrupt behavior, and whether a new thread, logout/login, downgrade, API billing path, or minimal config recovers.
 
 ## Codex Clipboard Attachment
 
@@ -160,6 +160,14 @@ Common signals include `visible context/token usage indicator`, `context-window
 
 The fix is to capture Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
 
+## Codex Remote Connection Or SSH Workspace Failure
+
+Codex Desktop remote connections can fail after the feature exists: the app may not show Settings > Connections, the wrong feature flag may be set, the SSH host may connect but the local tunnel or remote app-server may be unhealthy, the remote filesystem may fail to list, or the remote Codex version/model list may be stale.
+
+Common signals include `Remote Development in Codex Desktop App`, `Remote SSH`, remote workspaces as the single source of truth, `remote_connections = true`, `remote_control = true` used as a mistaken flag, Settings > Connections missing, `local tunnel not ready`, stale remote Codex versions, `codex-server` or app-server restarts, `fs/getMetadata` folder listing timeouts, ForwardAgent requirements, proxying Codex API traffic through the local machine, and tmux-like reconnect/resume expectations.
+
+The fix is to capture Codex Desktop version, remote Codex CLI/app-server version, local OS, remote OS/architecture, SSH alias from `~/.ssh/config`, whether `[features].remote_connections = true` is set, Settings > Connections visibility, selected host/path, remote workspace path, whether the remote filesystem is the source of truth, exact tunnel/app-server error, codex-server pid and restart result, remote PATH/auth/proxy/API reachability, model list differences versus local, fs/getMetadata or folder listing errors, ForwardAgent/proxy requirements, and whether reconnect/resume or a clean host works.
+
 ## Codex Subagent Prompt Leakage
 
 Codex MultiAgentV2 child agents can fail the task boundary even when the parent asks for isolated children. When `spawn_agent` with `fork_turns: "none"` records the delegated task as an assistant/commentary JSON envelope, or a same-turn parallel child sees a sibling prompt, independent review, QA, and security lanes are no longer independent.

package/docs/OPENAI_OSS_BRIEF.md

@@ -3,14 +3,14 @@
 | Field | Value |
 | --- | --- |
 | Repository | https://github.com/grnbtqdbyx-create/trace-to-skill |
-| Package | trace-to-skill@0.1.96 |
+| Package | trace-to-skill@0.1.98 |
 | License | Apache-2.0 |
 | Codex readiness | ready (100/100) |
-| Benchmark | pass, 41 cases |
+| Benchmark | pass, 43 cases |
 
 ## Why This Repository Qualifies
 
-trace-to-skill helps open-source maintainers adopt Codex safely by turning failed coding-agent runs into evidence-backed rules, reusable workflows, CI gates, and a weekly Codex Issue Radar for live GitHub issue demand. It supports real maintenance work: PR review, issue triage, release quality, MCP risk, prompt-injection defense, privacy-preserving trace sharing, and repeat failure reduction. The repository is ready, scores 100/100 on the local Codex readiness doctor, and ships a deterministic benchmark with 41 public fixture cases.
+trace-to-skill helps open-source maintainers adopt Codex safely by turning failed coding-agent runs into evidence-backed rules, reusable workflows, CI gates, and a weekly Codex Issue Radar for live GitHub issue demand. It supports real maintenance work: PR review, issue triage, release quality, MCP risk, prompt-injection defense, privacy-preserving trace sharing, and repeat failure reduction. The repository is ready, scores 100/100 on the local Codex readiness doctor, and ships a deterministic benchmark with 43 public fixture cases.
 
 ### 500-Character Version
 
@@ -27,10 +27,10 @@ API credits would power optional maintainer workflows on top of the local determ
 ## Evidence
 
 - Public repository: https://github.com/grnbtqdbyx-create/trace-to-skill
-- One-command package: npx trace-to-skill@0.1.96
+- One-command package: npx trace-to-skill@0.1.98
 - Open-source license: Apache-2.0
 - Codex readiness doctor: ready, 100/100, 0 failed checks.
-- Public fixture benchmark: pass, 41 cases.
+- Public fixture benchmark: pass, 43 cases.
 - GitHub issue demand mining: issue-map fetches or reads piped GitHub CLI issue JSON, then ranks OpenAI/Codex issues by failure class, comments, reactions, evidence gaps, and Maintainer Roadmap next artifacts.
 - Weekly Codex Issue Radar: init --issue-map-repo owner/name scaffolds a scheduled Action that fetches live GitHub issues and publishes the pain map to the job summary or a stable tracking issue comment.
 - Maintainer control: generated rules are suggestions, evidence is line-linked, and secrets can be redacted before sharing.

package/docs/SCORECARD.md

@@ -9,7 +9,7 @@ Status: **pass**
 | Failed doctor checks | 0 |
 | Critical findings | 0 |
 | Built-in benchmark | pass |
-| Benchmark cases | 41 |
+| Benchmark cases | 43 |
 
 ## Doctor Summary
 
@@ -34,6 +34,7 @@ This benchmark runs the public fixture pack that ships with the repository and p
 | Codex selected model differs from actual routed model | `fixtures/codex-model-routing-mismatch.md` | 75 | 2 | 0 | `codex_model_routing_mismatch`, `weak_evidence` | pass |
 | Codex model and runtime latency regression | `fixtures/codex-latency-regression.md` | 75 | 2 | 0 | `codex_latency_regression`, `weak_evidence` | pass |
 | Codex thinking and stream hang | `fixtures/codex-thinking-hang.md` | 75 | 2 | 0 | `codex_thinking_hang`, `weak_evidence` | pass |
+| Codex CLI no-response and command execution hang | `fixtures/codex-cli-no-response.md` | 75 | 2 | 0 | `codex_thinking_hang`, `weak_evidence` | pass |
 | Codex clipboard, paste, and attachment workflow regression | `fixtures/codex-clipboard-attachment.md` | 75 | 2 | 0 | `codex_clipboard_attachment`, `weak_evidence` | pass |
 | Codex deeplink, OAuth callback, and external launch regression | `fixtures/codex-deeplink-launch.md` | 50 | 4 | 0 | `codex_deeplink_launch`, `codex_remote_control`, `hallucinated_file`, `weak_evidence` | pass |
 | Codex app connector auth cache and stale link regression | `fixtures/codex-connector-auth-cache.md` | 75 | 2 | 0 | `codex_connector_auth_cache`, `weak_evidence` | pass |
@@ -54,9 +55,10 @@ This benchmark runs the public fixture pack that ships with the repository and p
 | Codex MCP discovery and config-scope mismatch | `fixtures/codex-mcp-discovery-mismatch.md` | 75 | 2 | 0 | `codex_mcp_discovery_mismatch`, `weak_evidence` | pass |
 | Codex plugin runtime and bundled capability failure | `fixtures/codex-plugin-runtime.md` | 59 | 3 | 0 | `codex_plugin_runtime`, `codex_windows_helper_path`, `weak_evidence` | pass |
 | Codex file tree and workspace navigation UI failure | `fixtures/codex-file-tree-ui.md` | 75 | 2 | 0 | `codex_file_tree_ui`, `weak_evidence` | pass |
-| Codex session resume and state failure | `fixtures/codex-session-state.md` | 59 | 3 | 0 | `codex_resource_leak`, `codex_session_state`, `weak_evidence` | pass |
+| Codex session resume and state failure | `fixtures/codex-session-state.md` | 75 | 2 | 0 | `codex_session_state`, `weak_evidence` | pass |
 | Codex usage bucket scope and percentage confusion | `fixtures/codex-usage-bucket-confusion.md` | 59 | 3 | 0 | `codex_token_burn`, `codex_usage_bucket_confusion`, `weak_evidence` | pass |
 | Codex context or token usage indicator missing | `fixtures/codex-context-visibility.md` | 75 | 2 | 0 | `codex_context_visibility`, `weak_evidence` | pass |
+| Codex remote connection or SSH workspace failure | `fixtures/codex-remote-connection.md` | 75 | 2 | 0 | `codex_remote_connection`, `weak_evidence` | pass |
 | Codex token burn and usage-drain loop | `fixtures/codex-token-burn.md` | 75 | 2 | 0 | `codex_token_burn`, `weak_evidence` | pass |
 | Codex resource leak and runaway process | `fixtures/codex-resource-leak.md` | 75 | 2 | 0 | `codex_resource_leak`, `weak_evidence` | pass |
 | Codex tool-call integrity and rollback failure | `fixtures/codex-tool-call-integrity.md` | 43 | 4 | 0 | `codex_resource_leak`, `codex_subagent_lifecycle`, `codex_tool_call_integrity`, `weak_evidence` | pass |

package/docs/USE_CASES.md

@@ -59,7 +59,7 @@ What it proves:
 Recommended CI surface:
 
 ```yaml
-- uses: grnbtqdbyx-create/trace-to-skill@v0.1.96
+- uses: grnbtqdbyx-create/trace-to-skill@v0.1.98
   with:
     mode: all
     doctor-threshold: "85"
@@ -348,6 +348,32 @@ This catches signals such as a missing visible context/token usage indicator, hi
 
 Include Codex Desktop version, OS, surface, screenshot or short recording of the chat input area, whether the prior context/token indicator or tooltip was visible before the update, exact UI route where it disappeared, local session metadata showing context/window pressure if available, `/status` output if relevant, compaction timing, whether CLI/TUI still exposes a statusline, and how the missing indicator affects long-session decisions.
 
+## 18.2. Codex Remote Connection Evidence
+
+Use this when Codex Desktop remote SSH workspaces, Settings > Connections, remote app-server, tunnel, model list, or remote filesystem browsing fails.
+
+```bash
+npx trace-to-skill demo remote-connection
+npx trace-to-skill codex-report ./runs --output openai-codex-remote-connection.md
+```
+
+This catches signals such as `Remote Development in Codex Desktop App`, missing Settings > Connections, `[features].remote_connections = true`, mistaken `remote_control = true`, SSH hosts from `~/.ssh/config`, remote filesystem source-of-truth expectations, `local tunnel not ready`, stale remote Codex versions, `codex-server` restart evidence, `fs/getMetadata` timeouts while listing remote folders, ForwardAgent needs, and local-machine proxy expectations for remote hosts that cannot reach the Codex API directly.
+
+Include Codex Desktop version, remote Codex CLI/app-server version, local OS, remote OS/architecture, selected SSH host/path, whether the remote filesystem is the source of truth, exact tunnel/app-server/folder-listing/model-list/auth/proxy error, process evidence such as `ps -ef | rg 'codex app-server|openai.chatgpt.*/codex'` when available, and whether killing codex-server, reinstalling remote Codex, reconnecting, or trying a clean host changes the result.
+
+## 18.3. Codex CLI No-Response Evidence
+
+Use this when Codex CLI accepts prompts but produces no streaming output, no error, no timeout, or hangs during command execution.
+
+```bash
+npx trace-to-skill demo cli-no-response
+npx trace-to-skill codex-report ./runs --output openai-codex-cli-no-response.md
+```
+
+This catches signals such as all-model hangs, `gpt-5.4 high - 100% left`, no tokens consumed, simple prompts like `Hello` or `ping` never producing output, `codex exec --sandbox read-only --model gpt-5.3-codex 'ping'`, `mcp startup: no servers`, unhandled responses events, CLI/VS Code stuck on Thinking or Working, terminal command execution hangs, status incidents, unhealthy cluster reroutes, and Ctrl+C or `/exit` delays.
+
+Include CLI/app/extension version, OS/terminal/WSL, subscription/workspace, model and reasoning/speed settings, prompt timestamp, exact prompt, whether the prompt was accepted but no stream/error/timeout appeared, status bar or usage percent, `RUST_LOG` SSE snippets, transport, first `response_item` or assistant timestamp if it appears later, reconnect or stream-disconnect lines, status incident link, and recovery attempts such as new thread, downgrade, logout/login, API billing path, or minimal config without MCPs.
+
 ## 19. Codex File Tree UI Evidence
 
 Use this when Codex Desktop cannot reveal project files through the native file tree, folder icon, floating file panel, or built-in preview.

package/fixtures/codex-cli-no-response.md

@@ -0,0 +1,46 @@
+# Codex CLI No-Response Hang
+
+Public issue cluster: All models - Codex CLI hangs indefinitely on all prompts, no response generated.
+
+## Symptoms
+
+- Codex CLI accepts prompts and displays them, but no streaming output begins.
+- All models tested, including `gpt-5.4 high`, `gpt-5.3-codex`, and `gpt-5.1-codex-max`, show no response, no error, and no timeout.
+- The status bar remains `gpt-5.4 high - 100% left`; no tokens are being consumed while the prompt is stuck.
+- A `status.openai.com/incidents` status incident note says Codex CLI hanging or no response may come from unhealthy clusters and rerouted traffic.
+- Simple greetings, questions, codebase analysis, and every message hang the same way.
+- In another report, Codex hangs during terminal command execution; basic shell commands get stuck, it does half the job then stuck, and the VS Code client remains on Thinking or Working.
+- `/exit`, Stop, or Ctrl+C does not respond for minutes, so the user has to kill the Codex process.
+
+## Minimal Reproduction
+
+The `codex exec --sandbox read-only --model gpt-5.3-codex 'ping'` run has no output and hangs after MCP startup with `unhandled responses event` SSE lines:
+
+```bash
+RUST_LOG='codex_api::sse::responses=trace' codex exec --sandbox read-only --model gpt-5.3-codex 'ping'
+```
+
+Observed output stops after:
+
+```text
+mcp startup: no servers
+unhandled responses event: response.in_progress
+unhandled responses event: response.content_part.added
+unhandled responses event: response.output_text.done
+unhandled responses event: response.content_part.done
+```
+
+## Status and Recovery Notes
+
+- A collaborator note linked a status incident and said unhealthy clusters were rerouted.
+- Users still reported Codex is down, Reconnecting, stream disconnected before completion, and no response in both CLI and VS Code after the incident note.
+- Downgrading, starting a new thread, logout/login, API billing path, or a minimal config without MCPs should be recorded as separate recovery attempts.
+
+## Evidence Checklist
+
+- CLI/app/extension version and whether it is Terminal, WSL, VS Code, or Desktop.
+- OS, shell, subscription/workspace, selected model, reasoning effort, and speed/service tier.
+- Prompt timestamp, exact prompt, and whether the prompt is accepted but no streaming output, error, or timeout appears.
+- Status bar or usage percent such as `100% left`, first assistant timestamp if it eventually appears, and whether tokens were consumed.
+- `RUST_LOG` SSE snippets, transport (`responses_http` or websocket), first `response_item`, unhandled responses events, reconnect or stream-disconnect lines, and status incident link.
+- Stop, Ctrl+C, `/exit`, forced kill, new thread, downgrade, logout/login, API billing path, and minimal-config recovery results.