trace-to-skill 0.1.83 → 0.1.85

package/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md

@@ -0,0 +1,115 @@
+# GitHub Issue Pain Map
+
+Generated: 2026-06-01T01:27:18.765Z
+
+Issues analyzed: **100**
+Matched issues: **48**
+Unmatched issues: **52**
+
+This report maps exported GitHub issues onto deterministic `trace-to-skill` failure classes. Export issues with `gh issue list` or `gh search issues`, then use the highest-priority clusters to decide which fixtures, docs, or support reports to build next.
+
+```bash
+gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
+trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
+```
+
+## Top Clusters
+
+| Priority | Kind | Severity | Issues | Comments | Reactions | Example |
+| ---: | --- | --- | ---: | ---: | ---: | --- |
+| 978 | `codex_token_burn` | high | 9 | 881 | 0 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
+| 778 | `weak_evidence` | medium | 100 | 3746 | 0 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
+| 446 | `premature_completion` | high | 11 | 329 | 0 | [#3962 Play a sound when Codex finishes a prompt / task](https://github.com/openai/codex/issues/3962) | |
+| 307 | `codex_remote_compact` | high | 7 | 230 | 0 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
+| 272 | `context_compaction` | high | 6 | 205 | 0 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
+| 217 | `sandbox_permission` | high | 5 | 160 | 0 | [#10601 Sandbox setup error on Windows](https://github.com/openai/codex/issues/10601) | |
+| 205 | `codex_windows_helper_path` | high | 5 | 148 | 0 | [#18258 Codex app on macOS shows 'Computer Use plugin unavailable'](https://github.com/openai/codex/issues/18258) | |
+| 152 | `codex_latency_regression` | high | 4 | 105 | 0 | [#24422 GPT-5.5 Fast suddenly feels as slow as Standard, with long thinking/context/search stalls](https://github.com/openai/codex/issues/24422) | |
+| 137 | `codex_mcp_discovery_mismatch` | high | 3 | 100 | 0 | [#6465 MCP servers not detected in Codex VS Code extension (but working in Codex CLI)](https://github.com/openai/codex/issues/6465) | |
+| 133 | `codex_approval_friction` | high | 3 | 96 | 0 | [#4212 Windows approval “Allow for this session” isn’t remembered](https://github.com/openai/codex/issues/4212) | |
+| 131 | `codex_resource_leak` | high | 3 | 94 | 0 | [#11981 Codex app 100% CPU Usage even when only one agent is running](https://github.com/openai/codex/issues/11981) | |
+| 130 | `codex_tool_call_integrity` | high | 2 | 103 | 0 | [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) | |
+| 123 | `codex_plugin_runtime` | high | 3 | 86 | 0 | [#18258 Codex app on macOS shows 'Computer Use plugin unavailable'](https://github.com/openai/codex/issues/18258) | |
+| 112 | `mcp_risk` | high | 2 | 85 | 0 | [#6465 MCP servers not detected in Codex VS Code extension (but working in Codex CLI)](https://github.com/openai/codex/issues/6465) | |
+| 110 | `codex_latest_turn_drift` | high | 2 | 83 | 0 | [#8648 Codex replies to earlier messages instead of latest one in conversations](https://github.com/openai/codex/issues/8648) | |
+
+## Suggested Next Actions
+
+### codex_token_burn
+
+Priority score: 978. 9 issue(s), 881 comment(s).
+
+Example issues:
+- [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
+- [#19464 Support 1M token context for GPT-5.5 in Codex](https://github.com/openai/codex/issues/19464) (132 comments; labels: enhancement, context)
+- [#5957 Auto compaction causes GPT-5-Codex to lose the plot. It forgets it is mid-task, forgets it has edited files and stops.](https://github.com/openai/codex/issues/5957) (25 comments; labels: bug, context)
+
+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.
+
+### weak_evidence
+
+Priority score: 778. 100 issue(s), 3746 comment(s).
+
+Example issues:
+- [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
+- [#19464 Support 1M token context for GPT-5.5 in Codex](https://github.com/openai/codex/issues/19464) (132 comments; labels: enhancement, context)
+- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
+
+Evidence rule prompts:
+- Final responses must include the exact validation evidence used to prove the change, not only a summary of intent.
+
+### premature_completion
+
+Priority score: 446. 11 issue(s), 329 comment(s).
+
+Example issues:
+- [#3962 Play a sound when Codex finishes a prompt / task](https://github.com/openai/codex/issues/3962) (50 comments; labels: enhancement, extension)
+- [#7291 Bug report: VSCode extension failed to revert the changes](https://github.com/openai/codex/issues/7291) (42 comments; labels: bug, extension)
+- [#18341 Mac app shows persistent blurred/translucent overlay below composer](https://github.com/openai/codex/issues/18341) (34 comments; labels: bug, app)
+
+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
+
+Priority score: 307. 7 issue(s), 230 comment(s).
+
+Example issues:
+- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
+- [#9211 Error running remote compact task: timeout waiting for child process to exit](https://github.com/openai/codex/issues/9211) (27 comments; labels: bug, context)
+- [#10823 Unable to compact the context in a VERY long running session](https://github.com/openai/codex/issues/10823) (26 comments; labels: bug, context)
+
+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.
+
+### context_compaction
+
+Priority score: 272. 6 issue(s), 205 comment(s).
+
+Example issues:
+- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
+- [#9211 Error running remote compact task: timeout waiting for child process to exit](https://github.com/openai/codex/issues/9211) (27 comments; labels: bug, context)
+- [#10823 Unable to compact the context in a VERY long running session](https://github.com/openai/codex/issues/10823) (26 comments; labels: bug, context)
+
+Evidence rule prompts:
+- When Codex compaction fails, capture the compact error, model/app version, thread state, and whether the session is recoverable before continuing or reporting success.
+
+## Unmatched Issues
+
+- [#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)
+- [#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)
+- [#11023 Codex desktop app for Linux](https://github.com/openai/codex/issues/11023) (68 comments; labels: enhancement, app)
+- [#13993 Support standalone Windows installer (`codex-setup.exe`)](https://github.com/openai/codex/issues/13993) (58 comments; labels: enhancement, windows-os, app, User Request, Feature)
+- [#8745 LSP integration (auto-detect + auto-install) for Codex CLI](https://github.com/openai/codex/issues/8745) (52 comments; labels: enhancement, agent)
+- [#12661 Markdown file:// links open in default browser (Edge) instead of VS Code editor](https://github.com/openai/codex/issues/12661) (46 comments; labels: bug, windows-os, extension)
+- [#9203 Please make "/undo" back](https://github.com/openai/codex/issues/9203) (46 comments; labels: enhancement, TUI, session)
+- [#6020 MCP client for `X` failed to start: handshaking with MCP server failed: connection closed: initialize response](https://github.com/openai/codex/issues/6020) (40 comments; labels: bug, mcp)
+- [#16857 High GPU usage while the app is “thinking” due to tiny useless animation](https://github.com/openai/codex/issues/16857) (36 comments; labels: bug, app, performance)
+- [#3141 Allow GPU access inside sandbox](https://github.com/openai/codex/issues/3141) (35 comments; labels: enhancement, sandbox)
+- [#3355 Error sending request for url (https://chatgpt.com/backend-api/codex/responses) after macbook sleeps](https://github.com/openai/codex/issues/3355) (35 comments; labels: bug, connectivity)
+- [#2153 ChatGPT integration](https://github.com/openai/codex/issues/2153) (33 comments; labels: enhancement, app, User Request, Feature)
+- [#11626 CLI: Add /rewind checkpoint restore that reverts both chat context and Codex-applied code edits](https://github.com/openai/codex/issues/11626) (33 comments; labels: enhancement, TUI)
+- [#18960 Frequent reconnect loop in Codex App: websocket closed by server before response.completed](https://github.com/openai/codex/issues/18960) (33 comments; labels: bug, connectivity)
+- [#2952 Search @ cannot search from directories excluded by .gitignore](https://github.com/openai/codex/issues/2952) (31 comments; labels: bug, extension)
+

package/docs/CODEX_ISSUE_MAP.md

@@ -24,6 +24,7 @@ npx trace-to-skill lsp-audit . --format json
 | OpenAI/Codex issue cluster | Common signals | Finding kind | Best command |
 | --- | --- | --- | --- |
 | 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` |
 | 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` |
@@ -100,10 +101,12 @@ npx trace-to-skill lsp-audit . --format json
 - For preflight exclusion reports, attach `sensitive-audit` output and recommended exclude globs; use `--format ignore --ignore-target codexignore` when maintainers want a reviewable `.codexignore` candidate. It does not read file contents or follow symlink targets.
 - For LSP readiness reports, attach `lsp-audit` output so maintainers can see detected languages, evidence files, missing server commands, and install hints without auto-installing tools.
 - For token-burn reports, attach `usage-evidence` output so quota-window percentages, rapid drain experiments, local token totals, prompt-cache collapse events, cached input, and orchestration-overhead signals are not collapsed into one ambiguous symptom.
+- For usage bucket confusion, attach subscription plan, account/workspace, app/CLI version, surface, timestamp, redacted popover text or screenshot, 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`, dashboard state, and whether other devices/workspaces show the same values.
 
 ## Related OpenAI/Codex Threads Used For Fixtures
 
 - Token burn, prompt-cache collapse, and usage drain: https://github.com/openai/codex/issues/14593, https://github.com/openai/codex/issues/20301, https://github.com/openai/codex/issues/13733, https://github.com/openai/codex/issues/25420, https://github.com/openai/codex/issues/19585
+- Usage bucket scope and percentage confusion: https://github.com/openai/codex/issues/25471, https://github.com/openai/codex/issues/24860, https://github.com/openai/codex/issues/25343, https://github.com/openai/codex/issues/24274
 - Usage reset schedule drift: https://github.com/openai/codex/issues/9508, https://github.com/openai/codex/issues/5999
 - Remote compact task failures: https://github.com/openai/codex/issues/14860, https://github.com/openai/codex/issues/19009
 - Windows helper and bundled tool path failures: https://github.com/openai/codex/issues/13542, https://github.com/openai/codex/issues/25357, https://github.com/openai/codex/issues/25220

package/docs/DEMO.md

@@ -95,6 +95,7 @@ Suggested rule:
 - `mcp-streamable-http`: Streamable HTTP or SSE MCP servers pass initialize or tools/list but fail parsing, handshakes, auth gating, stale sessions, or reconnects.
 - `hooks-runtime`: Hooks duplicate, stop firing, warn about stale config, skip surfaces, or become hard to manage in Desktop settings.
 - `terminal-output-integrity`: Terminal scrollback, streamed output, or transcript rendering drops, overwrites, truncates, or makes lines inaccessible.
+- `usage-bucket-confusion`: Usage popovers show 5h and weekly percentages without clear remaining/used, rolling/calendar, or account/workspace scope.
 - `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 +119,7 @@ trace-to-skill demo mcp-streamable-http
 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 file-tree-ui
 trace-to-skill demo usage-reset-drift
 ```

package/docs/DISCOVERY.md

@@ -41,6 +41,7 @@ This page is written for maintainers, search engines, package indexes, and AI re
 - Codex app connectors keep stale `link_*` authorization or discovery metadata after `401 Reauthentication required`, plugin reinstall, app restart, or cache regeneration.
 - Codex conversation forks duplicate parent transcript blocks, inflate token counts, break `prompt_cache_key` lineage, drop cache hit rate, or leak `fork_context` subagent history into child context before new work happens.
 - Codex subagents receive assistant/commentary prompt envelopes or sibling prompts despite `fork_turns: "none"`, making independent review, QA, and security lanes cross-contaminated.
+- Codex usage popovers show 5h and weekly percentages without explaining remaining/used, rolling/calendar, or account/workspace/device scope.
 - Codex usage drains unexpectedly because of rapid drain experiments (`1% in 4 minutes`, `22 credits`, `70% weekly in a day`), background `write_stdin` polling, idle app activity, compaction/replay overhead, retry loops, subagent fan-out, fast-mode drift, or cached-token-heavy turns.
 - Codex weekly or 5-hour reset anchors move unexpectedly, saved usage is lost, or `/status` and the dashboard disagree about reset timing or enforcement.
 - Codex usage evidence is scattered across `/status`, dashboard notes, reset tables, usage-limit messages, token totals, prompt-cache rows, cached input, and overhead clues, making high-signal reports hard to file.
@@ -79,6 +80,7 @@ npx trace-to-skill demo deeplink-launch
 npx trace-to-skill demo connector-auth-cache
 npx trace-to-skill demo context-fork-bloat
 npx trace-to-skill demo subagent-prompt-leakage
+npx trace-to-skill demo usage-bucket-confusion
 npx trace-to-skill demo mcp-discovery-mismatch
 npx trace-to-skill demo mcp-streamable-http
 npx trace-to-skill demo hooks-runtime
@@ -96,6 +98,7 @@ npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format
 npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
 npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
 npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
+npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
 npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
 npx trace-to-skill redact ./runs --output redacted-runs
 npx trace-to-skill analyze ./runs --format json
@@ -120,12 +123,14 @@ npx trace-to-skill suggest ./runs --target agents-md
 - `trace-to-skill diagnostics-bundle --format json`
 - `trace-to-skill usage-evidence --format json`
 - `trace-to-skill process-audit --format json`
+- `trace-to-skill issue-map --format json`
 - `trace-to-skill checkpoint --format json`
 - SARIF from `trace-to-skill analyze --format sarif`
 - OpenAI/Codex issue-ready Markdown from `trace-to-skill codex-report`
 - Packaged zero-setup Codex issue-report demo from `trace-to-skill demo`
 - OpenAI OSS support/application brief from `trace-to-skill oss-brief`
 - Codex issue-cluster mapping in `docs/CODEX_ISSUE_MAP.md`
+- GitHub issue demand mining in `docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md`
 - GitHub Action outputs for doctor, AGENTS lint, GitHub context guard, benchmark, and scorecard modes
 
 ## Schema Contracts
@@ -149,7 +154,7 @@ npx trace-to-skill suggest ./runs --target agents-md
 
 ## Related Keywords
 
-Codex, OpenAI Codex, Codex issue report, OpenAI triage, Codex LSP, Codex language server, lsp-audit, language-server readiness, typescript-language-server, pyright-langserver, gopls, rust-analyzer, sourcekit-lsp, clangd, Codex diagnostics bundle, privacy-preserving support bundle, workspace checkpoint, pre-agent checkpoint, Codex undo, Codex rewind, untracked file restore, sensitive path audit, sensitive-audit, agentignore, .agentignore, agentignore generator, codexignore, .codexignore, codexignore generator, aiexclude, .aiexclude, .gitignore candidates, exclude sensitive files, Codex plugin audit, Computer Use unavailable, Codex Browser plugin unavailable, bundled marketplace mismatch, generated runtime marketplace, plugin manifest missing, CODEX_HOME mismatch, Codex CLI, Codex sandbox, Windows sandbox, Codex config audit, Codex config.toml, Codex global state, .codex-global-state.json, Codex Speed reset, Codex Fast resets to Standard, service_tier fast, default-service-tier priority, has-user-changed-service-tier, Codex Preferences unable to save, configVersionConflict, default_permissions missing profile, Codex Windows helper path, Codex WindowsApps, Codex rg Access Denied, Codex ripgrep, CodexSandboxUsers, LocalCache Local OpenAI Codex bin, node_repl spawn setup refresh, Codex approval friction, Approve for this session, Allow for this session, approval_policy never, MCP approval prompts, default_tools_approval_mode, Playwright MCP approvals, Chrome DevTools MCP approvals, Codex auth, token_exchange_failed, Codex connectivity, stream disconnected, Codex connector auth cache, Codex Apps stale link, codex_apps_tools, codex_app_directory, Reauthentication required, refresh token revoked, isAccessible false, link_ connector, Codex deeplink, Codex OAuth callback, codex://oauth_callback, Unable to find Electron app, Error launching app, type=click&tag, AppUserModelID, DelegateExecute, codex app path, Codex remote compact, responses/compact, /compact timeout, tcp_user_timeout, stream_idle_timeout_ms, Codex context fork, Codex conversation fork, context fork bloat, codex context fork bloat, forked conversation duplicate context, prompt_cache_key lineage, prompt cache lineage, cached_input_tokens fork, cache hit rate fork, fork_context child context, Codex subagent prompt leakage, Codex subagent prompt leak, subagent prompt boundary, MultiAgentV2, spawn_agent fork_turns none, assistant commentary prompt envelope, sibling prompt leakage, parallel child prompt contamination, wait_agent wrong task, close_agent wrong task, Codex remote control, Codex mobile, Waiting for desktop, Directory Unavailable, stale listener, Codex terminal output, Codex scrollback, Codex terminal history, terminal output integrity, missing_count, missing_examples, tmux_scrollback_repro.sh, line_truncation_repro.md, Windows Terminal scrollback, transcript mode, Codex subagent lifecycle, Codex subagent audit, stale subagents, close_agent, wait_agent, spawn_agent, thread_spawn_edges, agent thread limit reached, agents.max_threads, list_agents, /agents, subagent child threads, fork_context, unbiased review, subagent recent conversations, Codex MCP runtime, MCP unsupported call, mcp__node_repl__js, MCP namespace serverName, MCP Transport closed, StdioServerTransport, Codex Streamable HTTP MCP, streamable-http MCP, HTTP/SSE MCP, MCP SSE, Content-Type text/event-stream, JsonRpcMessage deserialize, MCP handshake initialize, stale MCP session id, MCP reconnect, Penpot MCP, n8n MCP, DingTalk MCP, Codex hooks runtime, hooks.json, codex_hooks, features.hooks, PreToolUse, PostToolUse, SessionStart hook, duplicate hooks, Hook N, Hooks settings, command_execution hooks, Code Mode exec hooks, Codex plugin runtime, Computer Use native pipe path unavailable, SKY_CUA_NATIVE_PIPE_DIRECTORY, Plugin loading failed, plugin/list unknown variant vertical, Codex Browser plugin, Codex Computer Use, Codex Chrome plugin, stale plugin cache, codex plugin add, Codex file tree, Toggle File Tree, missing folder icon, floating file panel stale, file preview fails, workspace navigation, Codex project history disappeared, Codex project threads hidden, Codex session index repair, unindexed rollout thread, codex resume thread id, Codex latest-turn drift, Codex replies to earlier messages, stale prompt response, ignoring latest message, previous prompt, auto compaction forgets edits, raw tool payload leak, write_stdin session_id, Codex latency regression, GPT-5.5 Fast slow, Codex too slow, thinking stalls, Codex thinking hang, Codex stuck thinking, Codex Working stuck, no streamed follow-up, first response_item delayed, responses_http time.idle, model_client.stream_responses_api, turn/start, task_started, Codex Copy as Markdown missing, Codex Pasted text.txt, Codex long pasted prompt attachment, Codex clipboard export, Codex paste as text, Codex generated attachment preview edit, Codex goal ignores attachment, pasted-text-attachments.json, fileAttachments promptRaw composer.getText, pre-first-token latency, search/read latency, runtime scheduling latency, Codex resume, Codex session audit, Codex history audit, Codex history map, Codex session index, session_index.jsonl, Codex session state, rollout JSONL, logs_2.sqlite, codex-tui.log, sandbox.log, thread_goals, state_5.sqlite, goals_1.sqlite, archived chats, Codex token burn, Codex usage evidence, Codex rate-limit evidence, Codex usage drain, prompt cache collapse, prompt_cache_key, cached_input_tokens, cached_tokens, low cache hit rate, websocket reconnect cache drop, Codex usage reset, Codex weekly reset drift, reset_at changed, deterministic reset, rate limit reset, write_stdin polling, cached input tokens, compaction tax, background process polling, Codex process audit, PowerShell polling, powershell.exe Get-CimInstance Win32_Process, Win32_PerfFormattedData_PerfProc_Process, chat_processes.json stale entries, Codex resource leak, Codex performance, high CPU, high GPU, shell-snapshot, Code Helper Renderer, Codex tool-call integrity, apply_patch, apply_patch Add File overwrite, patch guard, guard-patch, Add File symlink, tool_call_id, failed revert changes, patch safety, Codex quota, usage limit, rate limits, sensitive files, Codex privacy, .env, private keys, credential files, AGENTS.md, SKILL.md, Claude Code, Cursor, Copilot coding agent, Gemini CLI, MCP, Model Context Protocol, prompt injection, agent evals, AI code review, open-source maintainers, trace redaction, SARIF, GitHub Actions.
+Codex, OpenAI Codex, Codex issue report, OpenAI triage, Codex LSP, Codex language server, lsp-audit, language-server readiness, typescript-language-server, pyright-langserver, gopls, rust-analyzer, sourcekit-lsp, clangd, Codex diagnostics bundle, privacy-preserving support bundle, workspace checkpoint, pre-agent checkpoint, Codex undo, Codex rewind, untracked file restore, sensitive path audit, sensitive-audit, agentignore, .agentignore, agentignore generator, codexignore, .codexignore, codexignore generator, aiexclude, .aiexclude, .gitignore candidates, exclude sensitive files, Codex plugin audit, Computer Use unavailable, Codex Browser plugin unavailable, bundled marketplace mismatch, generated runtime marketplace, plugin manifest missing, CODEX_HOME mismatch, Codex CLI, Codex sandbox, Windows sandbox, Codex config audit, Codex config.toml, Codex global state, .codex-global-state.json, Codex Speed reset, Codex Fast resets to Standard, service_tier fast, default-service-tier priority, has-user-changed-service-tier, Codex Preferences unable to save, configVersionConflict, default_permissions missing profile, Codex Windows helper path, Codex WindowsApps, Codex rg Access Denied, Codex ripgrep, CodexSandboxUsers, LocalCache Local OpenAI Codex bin, node_repl spawn setup refresh, Codex approval friction, Approve for this session, Allow for this session, approval_policy never, MCP approval prompts, default_tools_approval_mode, Playwright MCP approvals, Chrome DevTools MCP approvals, Codex auth, token_exchange_failed, Codex connectivity, stream disconnected, Codex connector auth cache, Codex Apps stale link, codex_apps_tools, codex_app_directory, Reauthentication required, refresh token revoked, isAccessible false, link_ connector, Codex deeplink, Codex OAuth callback, codex://oauth_callback, Unable to find Electron app, Error launching app, type=click&tag, AppUserModelID, DelegateExecute, codex app path, Codex remote compact, responses/compact, /compact timeout, tcp_user_timeout, stream_idle_timeout_ms, Codex context fork, Codex conversation fork, context fork bloat, codex context fork bloat, forked conversation duplicate context, prompt_cache_key lineage, prompt cache lineage, cached_input_tokens fork, cache hit rate fork, fork_context child context, Codex subagent prompt leakage, Codex subagent prompt leak, subagent prompt boundary, MultiAgentV2, spawn_agent fork_turns none, assistant commentary prompt envelope, sibling prompt leakage, parallel child prompt contamination, wait_agent wrong task, close_agent wrong task, Codex usage bucket, Codex usage popover, Usage remaining, 5h weekly usage, weekly pool, usage percentage confusion, percent remaining, percent used, rolling 7-day usage, calendar week usage, account-wide Codex usage, Codex remote control, Codex mobile, Waiting for desktop, Directory Unavailable, stale listener, Codex terminal output, Codex scrollback, Codex terminal history, terminal output integrity, missing_count, missing_examples, tmux_scrollback_repro.sh, line_truncation_repro.md, Windows Terminal scrollback, transcript mode, Codex subagent lifecycle, Codex subagent audit, stale subagents, close_agent, wait_agent, spawn_agent, thread_spawn_edges, agent thread limit reached, agents.max_threads, list_agents, /agents, subagent child threads, fork_context, unbiased review, subagent recent conversations, Codex MCP runtime, MCP unsupported call, mcp__node_repl__js, MCP namespace serverName, MCP Transport closed, StdioServerTransport, Codex Streamable HTTP MCP, streamable-http MCP, HTTP/SSE MCP, MCP SSE, Content-Type text/event-stream, JsonRpcMessage deserialize, MCP handshake initialize, stale MCP session id, MCP reconnect, Penpot MCP, n8n MCP, DingTalk MCP, Codex hooks runtime, hooks.json, codex_hooks, features.hooks, PreToolUse, PostToolUse, SessionStart hook, duplicate hooks, Hook N, Hooks settings, command_execution hooks, Code Mode exec hooks, Codex plugin runtime, Computer Use native pipe path unavailable, SKY_CUA_NATIVE_PIPE_DIRECTORY, Plugin loading failed, plugin/list unknown variant vertical, Codex Browser plugin, Codex Computer Use, Codex Chrome plugin, stale plugin cache, codex plugin add, Codex file tree, Toggle File Tree, missing folder icon, floating file panel stale, file preview fails, workspace navigation, Codex project history disappeared, Codex project threads hidden, Codex session index repair, unindexed rollout thread, codex resume thread id, Codex latest-turn drift, Codex replies to earlier messages, stale prompt response, ignoring latest message, previous prompt, auto compaction forgets edits, raw tool payload leak, write_stdin session_id, Codex latency regression, GPT-5.5 Fast slow, Codex too slow, thinking stalls, Codex thinking hang, Codex stuck thinking, Codex Working stuck, no streamed follow-up, first response_item delayed, responses_http time.idle, model_client.stream_responses_api, turn/start, task_started, Codex Copy as Markdown missing, Codex Pasted text.txt, Codex long pasted prompt attachment, Codex clipboard export, Codex paste as text, Codex generated attachment preview edit, Codex goal ignores attachment, pasted-text-attachments.json, fileAttachments promptRaw composer.getText, pre-first-token latency, search/read latency, runtime scheduling latency, Codex resume, Codex session audit, Codex history audit, Codex history map, Codex session index, session_index.jsonl, Codex session state, rollout JSONL, logs_2.sqlite, codex-tui.log, sandbox.log, thread_goals, state_5.sqlite, goals_1.sqlite, archived chats, Codex token burn, Codex usage evidence, Codex rate-limit evidence, Codex usage drain, prompt cache collapse, prompt_cache_key, cached_input_tokens, cached_tokens, low cache hit rate, websocket reconnect cache drop, Codex usage reset, Codex weekly reset drift, reset_at changed, deterministic reset, rate limit reset, write_stdin polling, cached input tokens, compaction tax, background process polling, Codex process audit, PowerShell polling, powershell.exe Get-CimInstance Win32_Process, Win32_PerfFormattedData_PerfProc_Process, chat_processes.json stale entries, Codex resource leak, Codex performance, high CPU, high GPU, shell-snapshot, Code Helper Renderer, Codex tool-call integrity, apply_patch, apply_patch Add File overwrite, patch guard, guard-patch, Add File symlink, tool_call_id, failed revert changes, patch safety, Codex quota, usage limit, rate limits, sensitive files, Codex privacy, .env, private keys, credential files, AGENTS.md, SKILL.md, Claude Code, Cursor, Copilot coding agent, Gemini CLI, MCP, Model Context Protocol, prompt injection, agent evals, AI code review, open-source maintainers, trace redaction, SARIF, GitHub Actions.
 
 ## Non-Goals
 

package/docs/FAILURE_TAXONOMY.md

@@ -128,6 +128,14 @@ Common signals include a forked conversation carrying the full parent transcript
 
 The fix is to capture Codex app/CLI/extension version, surface, model, fork source thread id, forked thread id, fork action timestamp, fork boundary marker, `input_tokens` and `cached_input_tokens` before and after the fork, `prompt_cache_key` before and after, cache hit rate, duplicated parent-turn or tool-transcript examples with line ids, whether new files were read before the token jump, compaction state, subagent or `fork_context` history, minimal reproduction steps, and whether a fresh thread or non-fork continuation avoids the bloat.
 
+## Codex Usage Bucket Confusion
+
+Codex usage reports can be technically correct but still impossible for users to interpret. When a popover shows 5h and weekly percentages without saying whether they are used or remaining, rolling or calendar-based, account-wide or workspace-local, users cannot tell whether the display is a metering bug or expected quota accounting.
+
+Common signals include `Usage remaining`, compact rows like `5h 97%` and `Weekly 95%`, reset dates such as `Jun 7`, first-window-of-week confusion, labels that do not say percent remaining versus percent used, unclear rolling 7-day versus natural-week semantics, and uncertainty about whether app, CLI, cloud tasks, reviews, other devices, or other workspaces share the weekly pool.
+
+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 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

@@ -3,18 +3,18 @@
 | Field | Value |
 | --- | --- |
 | Repository | https://github.com/grnbtqdbyx-create/trace-to-skill |
-| Package | trace-to-skill@0.1.83 |
+| Package | trace-to-skill@0.1.85 |
 | License | Apache-2.0 |
 | Codex readiness | ready (100/100) |
-| Benchmark | pass, 37 cases |
+| Benchmark | pass, 38 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, and CI gates. 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 37 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, and CI gates. 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 38 public fixture cases.
 
 ### 500-Character Version
 
-> trace-to-skill helps open-source maintainers adopt Codex safely by turning failed coding-agent runs into evidence-backed rules, reusable workflows, and CI gates. 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 37 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, and CI gates. 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 38 public fixture cases.
 
 ## How API Credits Would Be Used
 
@@ -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@0.1.83
+- One-command package: npx trace-to-skill@0.1.85
 - Open-source license: Apache-2.0
 - Codex readiness doctor: ready, 100/100, 0 failed checks.
-- Public fixture benchmark: pass, 37 cases.
+- Public fixture benchmark: pass, 38 cases.
 - Maintainer control: generated rules are suggestions, evidence is line-linked, and secrets can be redacted before sharing.
 
 ## Next Steps Before Submitting

package/docs/SCORECARD.md

@@ -9,7 +9,7 @@ Status: **pass**
 | Failed doctor checks | 0 |
 | Critical findings | 0 |
 | Built-in benchmark | pass |
-| Benchmark cases | 37 |
+| Benchmark cases | 38 |
 
 ## Doctor Summary
 
@@ -53,6 +53,7 @@ This benchmark runs the public fixture pack that ships with the repository and p
 | 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 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 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 |