trace-to-skill 0.1.95 → 0.1.97

package/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md

@@ -1,9 +1,9 @@
 # GitHub Issue Pain Map
 
-Generated: 2026-06-01T02:57:23.552Z
+Generated: 2026-06-01T03:25:54.011Z
 
-Issues analyzed: **11**
-Matched issues: **10**
+Issues analyzed: **15**
+Matched issues: **14**
 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) |
+| 460 | `weak_evidence` | medium | 15 | 1985 | 991 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) |
 | 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) |
-| 234 | `weak_evidence` | medium | 11 | 1641 | 114 | [#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) |
 | 137 | `context_compaction` | high | 1 | 90 | 15 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) |
@@ -33,14 +35,24 @@ 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 | 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` |
-| 5 | Compaction/session regression fixture and Codex issue report | 1 issue(s), 90 comment(s), severity high; top signal: codex_remote_compact. | `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 | 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` |
+| 4 | 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` |
+| 5 | 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` |
 
 ## 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).
@@ -75,25 +87,17 @@ 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.
 
-### 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.
-
-### codex_remote_compact
+### codex_context_visibility
 
-Priority score: 137. 1 issue(s), 90 comment(s).
+Priority score: 257. 3 issue(s), 168 comment(s).
 
 Example issues:
-- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
+- [#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 remote compact failures, capture app/CLI/extension version, OS, model and reasoning/speed mode, provider config without secrets, exact /compact or auto-compact error, `responses/compact` endpoint shape, timeout values such as tcp_user_timeout or stream_idle_timeout_ms, context/token level before compaction, whether lowering reasoning/speed changes behavior, whether local fallback or a new session recovers, and related thread/feedback ids.
+- 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.
 
 ## Unmatched Issues
 

package/docs/CODEX_ISSUE_MAP.md

@@ -25,6 +25,7 @@ npx trace-to-skill lsp-audit . --format json
 | --- | --- | --- | --- |
 | Token burn, prompt-cache collapse, and usage drain | `tokens burning very fast`, `1% in 4 minutes`, `22 credits`, large cached input totals, `input_tokens` / `cached_input_tokens` / `cached_tokens` / `prompt_cache_key` rows, websocket reconnect cache drops, `write_stdin` empty polls, idle app usage, compaction tax, retry loops, subagent fan-out | `codex_token_burn` plus usage receipt and `prompt_cache_collapse` | `trace-to-skill usage-evidence ./usage-notes.md` first, then `trace-to-skill codex-report ./runs` for trace reports |
 | Usage bucket scope and percentage confusion | usage popover shows `Usage remaining`, `5h 97%`, `Weekly 95%`, reset date without explaining percent remaining vs percent used, rolling 7-day vs calendar-week, account-wide vs workspace/device/app/CLI scope | `codex_usage_bucket_confusion` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo usage-bucket-confusion` |
+| Context/token indicator visibility | Desktop no longer shows visible context/token usage indicator, context-window pressure display or tooltip is missing, `/status` is not a passive replacement, users cannot tell when to compact or split long sessions | `codex_context_visibility` | `trace-to-skill codex-report ./runs` or `trace-to-skill demo context-visibility` |
 | Usage reset schedule drift | weekly reset time changes, `reset_at` jumps, saved quota is wiped or pushed into the next window, outage compensation reset changes the anchor | `codex_usage_reset_drift` | `trace-to-skill usage-evidence ./usage-notes.md` or `trace-to-skill codex-report ./runs` |
 | Remote compact task failures | `/compact` or auto-compact fails, `responses/compact` stream disconnects, `timeout waiting for child process to exit`, `tcp_user_timeout` or `stream_idle_timeout_ms` workarounds, provider-id timeout drift | `codex_remote_compact` | `trace-to-skill codex-report ./runs` |
 | Windows helper and bundled tool path failures | bundled `rg.exe`, `node_repl.exe`, `codex-command-runner.exe`, Browser, Chrome, or Computer Use helpers resolve through `WindowsApps`, missing `%LOCALAPPDATA%\OpenAI\Codex\bin`, broken LocalCache helper bins, `CodexSandboxUsers` ACL gaps, EFS/copyfile failures | `codex_windows_helper_path` | `trace-to-skill codex-report ./runs` |
@@ -60,6 +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` |
@@ -90,6 +92,7 @@ npx trace-to-skill lsp-audit . --format json
 - 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.

package/docs/CODEX_ISSUE_RADAR.md

@@ -1,10 +1,10 @@
 # GitHub Issue Pain Map
 
-Generated: 2026-06-01T02:57:24.901Z
+Generated: 2026-06-01T03:26:00.188Z
 
 Issues analyzed: **46**
-Matched issues: **19**
-Unmatched issues: **27**
+Matched issues: **21**
+Unmatched issues: **25**
 
 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.
 
@@ -20,27 +20,27 @@ gh issue list --repo openai/codex --state all --limit 100 --json number,title,bo
 | Priority | Kind | Severity | Issues | Comments | Reactions | Example |
 | ---: | --- | --- | ---: | ---: | ---: | --- |
 | 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 | 7793 | [#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) |
 | 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) |
-| 181 | `codex_latest_turn_drift` | high | 1 | 58 | 53 | [#8648 Codex replies to earlier messages instead of latest one in conversations](https://github.com/openai/codex/issues/8648) |
 
 ## 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 | 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` |
-| 5 | Compaction/session regression fixture and Codex issue report | 2 issue(s), 147 comment(s), severity high; top signal: codex_remote_compact. | `trace-to-skill codex-report ./runs --output openai-codex-issue.md` |
+| 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).
@@ -78,32 +88,19 @@ Example issues:
 Evidence rule prompts:
 - When reporting Codex sign-in or account-verification failures, capture the Codex app/CLI/extension version, surface, OS, account type without secrets, workspace or organization context, SSO provider, whether the flow is ChatGPT sign-in, phone/SMS/OTP verification, or extension chat initialization, exact redacted error text, timestamps, whether another device/browser/account works, logout/login attempts, and screenshots with phone numbers, tokens, and email addresses redacted.
 
-### codex_tool_call_integrity
-
-Priority score: 442. 1 issue(s), 61 comment(s).
+### codex_context_visibility
 
-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.
-
-### codex_remote_compact
-
-Priority score: 376. 2 issue(s), 147 comment(s).
+Priority score: 631. 1 issue(s), 160 comment(s).
 
 Example issues:
-- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
-- [#9544 Error running remote compact task: stream disconnected before completion](https://github.com/openai/codex/issues/9544) (57 comments; labels: bug, context)
+- [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) (160 comments; labels: bug, context, app)
 
 Evidence rule prompts:
-- When reporting Codex remote compact failures, capture app/CLI/extension version, OS, model and reasoning/speed mode, provider config without secrets, exact /compact or auto-compact error, `responses/compact` endpoint shape, timeout values such as tcp_user_timeout or stream_idle_timeout_ms, context/token level before compaction, whether lowering reasoning/speed changes behavior, whether local fallback or a new session recovers, and related thread/feedback ids.
+- 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.
 
 ## 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)
-- [#23794 Codex Desktop no longer shows visible context/token usage indicator](https://github.com/openai/codex/issues/23794) (160 comments; labels: bug, context, 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)
@@ -113,3 +110,5 @@ Evidence rule prompts:
 - [#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)

package/docs/DEMO.md

@@ -1,10 +1,10 @@
 # trace-to-skill Demo
 
-Scenario: **Codex selected model differs from actual routed model**
+Scenario: **Codex remote connection or SSH workspace failure**
 
-Codex shows one selected model while SSE response evidence shows a different server-side model was used.
+Desktop remote SSH workspaces, Settings > Connections, remote app-server, tunnel, or remote filesystem evidence breaks.
 
-Fixture: `fixtures/codex-model-routing-mismatch.md`
+Fixture: `fixtures/codex-remote-connection.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 selected model differs from actual routed model (codex_model_routing_mismatch, high)**
+Likely failure class: **Codex remote connection or SSH workspace failure (codex_remote_connection, high)**
 
 Agent workflow needs clearer verification, instruction, or security hardening before broad reuse.
 
@@ -23,24 +23,25 @@ Agent workflow needs clearer verification, instruction, or security hardening be
 ```md
 ### What happened?
 
-trace-to-skill detected Codex selected model differs from actual routed model (codex_model_routing_mismatch). Silent model fallback, misrouting, or response.model mismatch makes Codex model access, benchmarks, billing expectations, and user trust hard to debug unless reports preserve both the selected model and the actual server-side model evidence.
+trace-to-skill detected Codex remote connection or SSH workspace failure (codex_remote_connection). Remote-first developers need Codex Desktop to open SSH, server, VM, WSL, container, or cloud workspaces as the source of truth, with reliable remote file browsing, command execution, model availability, app-server health, and reconnect behavior.
 
 ### Detected failure class
 
-- codex_model_routing_mismatch: Codex selected model differs from actual routed model (high)
+- codex_remote_connection: Codex remote connection or SSH workspace failure (high)
 
 ### Evidence
 
-#### Codex selected model differs from actual routed model
-- fixtures/codex-model-routing-mismatch.md:5 - - GPT-5.3-Codex is being routed to GPT-5.2.
-- fixtures/codex-model-routing-mismatch.md:6 - - Both `config.toml` and the TUI are set to `gpt-5.3-codex`, but SSE captures show the actual `response.model` is `gpt-5.2-2025-12-11`.
-- fixtures/codex-model-routing-mismatch.md:7 - - Running `RUST_LOG='codex_tui::chatwidget=info,codex_api::sse::responses=trace' codex` and sending a prompt shows `response.created` with `response.model=gpt-5.2-2025-12-11`.
-- fixtures/codex-model-routing-mismatch.md:9 - - The user sees no warning or fallback notice that a different model version is being used internally.
-- fixtures/codex-model-routing-mismatch.md:10 - - Some reports mention ChatGPT Pro, WSL, macOS, recent CLI versions, and verification briefly restoring GPT-5.3-Codex before silently rerouting back to GPT-5.2.
+#### Codex remote connection or SSH workspace failure
+- fixtures/codex-remote-connection.md:5 - - Remote Development in Codex Desktop App is a high-demand workflow because many users work on SSH hosts, cloud instances, GPU machines, WSL boxes, containers, or remote Linux servers.
+- fixtures/codex-remote-connection.md:7 - - Users expect Settings > Connections to show SSH hosts from `~/.ssh/config` after enabling `[features] remote_connections = true`.
+- fixtures/codex-remote-connection.md:8 - - A common setup mistake is using `remote_control = true` instead of `remote_connections = true`, so the Connections subheading never appears in the Desktop app.
+- fixtures/codex-remote-connection.md:9 - - The local tunnel can fail with "local tunnel not ready" even when the SSH host is reachable.
+- fixtures/codex-remote-connection.md:10 - - Remote folder browsing can fail with `Unable to load folder contents: Timed out waiting for MCP response to fs/getMetadata while listing directories/files`.
+- fixtures/codex-remote-connection.md:12 - - Killing a stale `codex-server` or app-server on the remote host can force the Desktop app to reattach.
 
 ### Diagnostics to attach
 
-- 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.
+- 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.
 
 ### Privacy
 
@@ -49,22 +50,25 @@ trace-to-skill detected Codex selected model differs from actual routed model (c
 
 ## Findings
 
-### 1. Codex selected model differs from actual routed model
+### 1. Codex remote connection or SSH workspace failure
 
 Severity: **high**
 
-Silent model fallback, misrouting, or response.model mismatch makes Codex model access, benchmarks, billing expectations, and user trust hard to debug unless reports preserve both the selected model and the actual server-side model evidence.
+Remote-first developers need Codex Desktop to open SSH, server, VM, WSL, container, or cloud workspaces as the source of truth, with reliable remote file browsing, command execution, model availability, app-server health, and reconnect behavior.
 
 Evidence:
-- `fixtures/codex-model-routing-mismatch.md:5` - GPT-5.3-Codex is being routed to GPT-5.2.
-- `fixtures/codex-model-routing-mismatch.md:6` - Both `config.toml` and the TUI are set to `gpt-5.3-codex`, but SSE captures show the actual `response.model` is `gpt-5.2-2025-12-11`.
-- `fixtures/codex-model-routing-mismatch.md:7` - Running `RUST_LOG='codex_tui::chatwidget=info,codex_api::sse::responses=trace' codex` and sending a prompt shows `response.created` with `response.model=gpt-5.2-2025-12-11`.
-- `fixtures/codex-model-routing-mismatch.md:9` - The user sees no warning or fallback notice that a different model version is being used internally.
-- `fixtures/codex-model-routing-mismatch.md:10` - Some reports mention ChatGPT Pro, WSL, macOS, recent CLI versions, and verification briefly restoring GPT-5.3-Codex before silently rerouting back to GPT-5.2.
+- `fixtures/codex-remote-connection.md:5` - Remote Development in Codex Desktop App is a high-demand workflow because many users work on SSH hosts, cloud instances, GPU machines, WSL boxes, containers, or remote Linux servers.
+- `fixtures/codex-remote-connection.md:7` - Users expect Settings > Connections to show SSH hosts from `~/.ssh/config` after enabling `[features] remote_connections = true`.
+- `fixtures/codex-remote-connection.md:8` - A common setup mistake is using `remote_control = true` instead of `remote_connections = true`, so the Connections subheading never appears in the Desktop app.
+- `fixtures/codex-remote-connection.md:9` - The local tunnel can fail with "local tunnel not ready" even when the SSH host is reachable.
+- `fixtures/codex-remote-connection.md:10` - Remote folder browsing can fail with `Unable to load folder contents: Timed out waiting for MCP response to fs/getMetadata while listing directories/files`.
+- `fixtures/codex-remote-connection.md:12` - Killing a stale `codex-server` or app-server on the remote host can force the Desktop app to reattach.
+- `fixtures/codex-remote-connection.md:13` - Some remote machines cannot directly access the Codex API, so reports need to mention proxy, local-machine request routing, or ForwardAgent SSH remote server requirements.
+- `fixtures/codex-remote-connection.md:22` - Exact local tunnel, app-server, codex-server, fs/getMetadata, folder listing, model list, auth, proxy, or API reachability error.
 
 Suggested rule:
 
-> 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.
+> 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.
 
 
 ## Reporter Notes
@@ -83,6 +87,7 @@ Suggested rule:
 - `windows-helper-path`: Windows Desktop exposes bundled rg/node/plugin helpers from WindowsApps or missing LocalCache paths that cannot execute.
 - `approval-friction`: Repeated approval prompts, Approve for this session misses, and noisy trusted MCP tool approvals.
 - `latency-regression`: Fast mode feels like Standard, with long thinking, search, read, or compaction stalls.
+- `model-routing-mismatch`: Codex shows one selected model while SSE response evidence shows a different server-side model was used.
 - `thinking-hang`: A turn or tool call completes, but the session stays on Thinking or Working with no streamed follow-up.
 - `clipboard-attachment`: Copy as Markdown, long-paste conversion, or generated Pasted text.txt attachments break prompt and report workflows.
 - `deeplink-launch`: OAuth callbacks, notification clicks, mobile links, or `codex app <path>` external activation fail to route into Codex.
@@ -94,6 +99,7 @@ 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.
 - `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.
@@ -118,6 +124,8 @@ trace-to-skill demo hooks-runtime
 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

@@ -152,6 +152,22 @@ Common signals include `Usage remaining`, compact rows like `5h 97%` and `Weekly
 
 The fix is to capture subscription plan, account/workspace, app/CLI version, surface, timestamp, screenshot or redacted popover text, 5h percentage, weekly percentage, reset time/date, whether values are used or remaining, whether weekly is rolling or calendar-based, whether weekly includes app/CLI/cloud/review usage, `/status` output, usage dashboard state, and whether other devices or workspaces show the same values.
 
+## Codex Context Or Token Usage Indicator Missing
+
+Codex Desktop can regress by hiding or removing passive context/token usage visibility from the chat UI. This is different from confusing quota percentages: the issue is that users cannot see context-window pressure at all during long desktop threads.
+
+Common signals include `visible context/token usage indicator`, `context-window pressure`, missing context usage tooltip near the input area, `Context N% used` or `Context N% remaining` requests, `/status` not being a replacement for passive context awareness, local session logs still containing context data, and users being unable to decide when to compact, split a thread, reduce pasted context, or avoid context loss.
+
+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@0.1.95 |
+| Package | trace-to-skill@0.1.97 |
 | License | Apache-2.0 |
 | Codex readiness | ready (100/100) |
-| Benchmark | pass, 40 cases |
+| Benchmark | pass, 42 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 40 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 42 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@0.1.95
+- One-command package: npx trace-to-skill@0.1.97
 - Open-source license: Apache-2.0
 - Codex readiness doctor: ready, 100/100, 0 failed checks.
-- Public fixture benchmark: pass, 40 cases.
+- Public fixture benchmark: pass, 42 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 | 40 |
+| Benchmark cases | 42 |
 
 ## Doctor Summary
 
@@ -54,8 +54,10 @@ 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@v0.1.95
+- uses: grnbtqdbyx-create/trace-to-skill@v0.1.97
   with:
     mode: all
     doctor-threshold: "85"
@@ -335,6 +335,32 @@ This catches signals such as `codex resume` picker hangs, `codex resume <id>` wo
 
 For mixed resume, crash, config, plugin, or history issues, `diagnostics-bundle` writes the session, config, and plugin reports together with a checklist of files not to attach publicly.
 
+## 18.1. Codex Context Visibility Evidence
+
+Use this when Codex Desktop no longer shows passive context/token usage visibility in the chat UI and long-session compaction pressure becomes invisible.
+
+```bash
+npx trace-to-skill demo context-visibility
+npx trace-to-skill codex-report ./runs --output openai-codex-context-visibility.md
+```
+
+This catches signals such as a missing visible context/token usage indicator, hidden context-window pressure display, missing tooltip near the input area, `/status` not being a replacement for passive context awareness, local session logs still containing context data, and users being unable to tell when to compact, start a new thread, reduce pasted context, or split work before context loss.
+
+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.
+
 ## 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-context-visibility.md

@@ -0,0 +1,18 @@
+# Codex context visibility fixture
+
+## Public-style issue signals
+
+- Codex Desktop no longer shows a visible context/token usage indicator in the chat UI after an update.
+- Previously the app exposed context usage information, context-window pressure, or a tooltip near the input area.
+- The current desktop app experience makes it difficult to understand how much context is being used, when compaction is likely, or whether a long-running session is approaching a practical context limit.
+- `/status` is useful as an explicit command, but it is not a replacement for passive context awareness during long-running desktop threads.
+- 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.
+- A related report says the data exists in local session logs, but the app no longer exposes it passively.
+
+## Evidence checklist
+
+- Codex Desktop version, OS, subscription, and surface.
+- Screenshot or short recording of the chat input area where the context indicator or tooltip used to appear.
+- Prior version where the context/token indicator was visible, current version where it is hidden or missing, and whether CLI/TUI still exposes a statusline.
+- Local session metadata or `/status` output if available, with private paths and account details redacted.
+- How the missing indicator affects long-session compaction, context-loss, or thread-splitting decisions.

package/fixtures/codex-remote-connection.md

@@ -0,0 +1,24 @@
+# Codex remote connection fixture
+
+## Public-style issue signals
+
+- Remote Development in Codex Desktop App is a high-demand workflow because many users work on SSH hosts, cloud instances, GPU machines, WSL boxes, containers, or remote Linux servers.
+- The remote workspace should be the single source of truth: no local clone, git/rsync/sshfs sync workaround, or stale local copy should be required.
+- Users expect Settings > Connections to show SSH hosts from `~/.ssh/config` after enabling `[features] remote_connections = true`.
+- A common setup mistake is using `remote_control = true` instead of `remote_connections = true`, so the Connections subheading never appears in the Desktop app.
+- The local tunnel can fail with "local tunnel not ready" even when the SSH host is reachable.
+- Remote folder browsing can fail with `Unable to load folder contents: Timed out waiting for MCP response to fs/getMetadata while listing directories/files`.
+- The app can show a stale remote Codex version even after the host has the expected Codex CLI version installed.
+- Killing a stale `codex-server` or app-server on the remote host can force the Desktop app to reattach.
+- Some remote machines cannot directly access the Codex API, so reports need to mention proxy, local-machine request routing, or ForwardAgent SSH remote server requirements.
+- Long-running remote tasks often depend on tmux-like persistence, reconnect/resume behavior, and background sessions after the Desktop app closes.
+
+## Evidence checklist
+
+- Codex Desktop version, local OS, remote OS/architecture, and remote Codex CLI/app-server version.
+- SSH target alias from `~/.ssh/config`, selected host/path, and whether Settings > Connections is visible.
+- Redacted `[features].remote_connections = true` config evidence and confirmation that `remote_control = true` was not the mistaken feature flag.
+- Remote workspace path and whether the remote filesystem is the source of truth.
+- Exact local tunnel, app-server, codex-server, fs/getMetadata, folder listing, model list, auth, proxy, or API reachability error.
+- `ps -ef | rg 'codex app-server|openai.chatgpt.*/codex'` or equivalent process evidence when a stale remote server is suspected.
+- Whether killing codex-server, reinstalling/updating remote Codex, reconnecting, or trying a clean host changes the result.