trace-to-skill 0.1.84 → 0.1.85
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +17 -4
- package/dist/src/cli.js +13 -0
- package/dist/src/cli.js.map +1 -1
- package/dist/src/index.d.ts +2 -0
- package/dist/src/index.js +1 -0
- package/dist/src/index.js.map +1 -1
- package/dist/src/issueMap.d.ts +48 -0
- package/dist/src/issueMap.js +311 -0
- package/dist/src/issueMap.js.map +1 -0
- package/dist/src/ossBrief.js +3 -2
- package/dist/src/ossBrief.js.map +1 -1
- package/docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md +115 -0
- package/docs/DISCOVERY.md +3 -0
- package/docs/OPENAI_OSS_BRIEF.md +2 -2
- package/docs/USE_CASES.md +53 -36
- package/fixtures/github-codex-issues-export.json +71 -0
- package/llms.txt +2 -1
- package/package.json +7 -2
package/dist/src/ossBrief.js
CHANGED
|
@@ -13,12 +13,12 @@ export async function runOssBrief(target = process.cwd(), threshold = 85) {
|
|
|
13
13
|
const commandName = packageName ? `npx ${packageName}` : "trace-to-skill";
|
|
14
14
|
const qualificationLong = [
|
|
15
15
|
`${projectName} helps open-source maintainers adopt Codex safely by turning failed coding-agent runs into evidence-backed rules, reusable workflows, and CI gates.`,
|
|
16
|
-
`It supports real maintenance work: PR review, issue
|
|
16
|
+
`It supports real maintenance work: PR review, GitHub issue demand mining, release quality, MCP risk, prompt-injection defense, privacy-preserving trace sharing, and repeat failure reduction.`,
|
|
17
17
|
`The repository is ${scorecard.doctor.status}, scores ${scorecard.doctor.score}/100 on the local Codex readiness doctor, and ships a deterministic benchmark with ${scorecard.benchmark.cases} public fixture cases.`
|
|
18
18
|
].join(" ");
|
|
19
19
|
const apiCreditsLong = [
|
|
20
20
|
"API credits would power optional maintainer workflows on top of the local deterministic scanner:",
|
|
21
|
-
"classifying failed Codex sessions, generating candidate AGENTS.md rules or SKILL.md workflows, comparing before/after runs, and producing PR-ready triage reports.",
|
|
21
|
+
"classifying failed Codex sessions, mining public GitHub issue clusters, generating candidate AGENTS.md rules or SKILL.md workflows, comparing before/after runs, and producing PR-ready triage reports.",
|
|
22
22
|
"The local CLI remains free, dependency-light, and usable without API credits."
|
|
23
23
|
].join(" ");
|
|
24
24
|
return {
|
|
@@ -123,6 +123,7 @@ function buildEvidence(scorecard, commandName, repository, packageName, packageV
|
|
|
123
123
|
license ? `Open-source license: ${license}` : "Add an OSI-approved license such as Apache-2.0 or MIT.",
|
|
124
124
|
`Codex readiness doctor: ${scorecard.doctor.status}, ${scorecard.doctor.score}/100, ${scorecard.doctor.failedChecks} failed checks.`,
|
|
125
125
|
`Public fixture benchmark: ${scorecard.benchmark.status}, ${scorecard.benchmark.cases} cases.`,
|
|
126
|
+
"GitHub issue demand mining: issue-map ranks exported OpenAI/Codex issues by failure class, comments, reactions, and evidence gaps.",
|
|
126
127
|
"Maintainer control: generated rules are suggestions, evidence is line-linked, and secrets can be redacted before sharing."
|
|
127
128
|
];
|
|
128
129
|
}
|
package/dist/src/ossBrief.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"ossBrief.js","sourceRoot":"","sources":["../../src/ossBrief.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,EAAE,YAAY,EAAwB,MAAM,gBAAgB,CAAC;AAmCpE,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,MAAM,GAAG,OAAO,CAAC,GAAG,EAAE,EAAE,SAAS,GAAG,EAAE;IACtE,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;IAClC,MAAM,SAAS,GAAG,MAAM,YAAY,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC;IACtD,MAAM,WAAW,GAAG,MAAM,eAAe,CAAC,IAAI,CAAC,CAAC;IAChD,MAAM,UAAU,GAAG,sBAAsB,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;IACnE,MAAM,WAAW,GAAG,WAAW,EAAE,IAAI,CAAC;IACtC,MAAM,cAAc,GAAG,WAAW,EAAE,OAAO,CAAC;IAC5C,MAAM,OAAO,GAAG,WAAW,EAAE,OAAO,IAAI,uBAAuB,CAAC,SAAS,CAAC,CAAC;IAC3E,MAAM,WAAW,GAAG,WAAW,IAAI,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACvD,MAAM,WAAW,GAAG,WAAW,CAAC,CAAC,CAAC,OAAO,WAAW,EAAE,CAAC,CAAC,CAAC,gBAAgB,CAAC;IAE1E,MAAM,iBAAiB,GAAG;QACxB,GAAG,WAAW,qJAAqJ;QACnK,
|
|
1
|
+
{"version":3,"file":"ossBrief.js","sourceRoot":"","sources":["../../src/ossBrief.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,EAAE,YAAY,EAAwB,MAAM,gBAAgB,CAAC;AAmCpE,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,MAAM,GAAG,OAAO,CAAC,GAAG,EAAE,EAAE,SAAS,GAAG,EAAE;IACtE,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;IAClC,MAAM,SAAS,GAAG,MAAM,YAAY,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC;IACtD,MAAM,WAAW,GAAG,MAAM,eAAe,CAAC,IAAI,CAAC,CAAC;IAChD,MAAM,UAAU,GAAG,sBAAsB,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;IACnE,MAAM,WAAW,GAAG,WAAW,EAAE,IAAI,CAAC;IACtC,MAAM,cAAc,GAAG,WAAW,EAAE,OAAO,CAAC;IAC5C,MAAM,OAAO,GAAG,WAAW,EAAE,OAAO,IAAI,uBAAuB,CAAC,SAAS,CAAC,CAAC;IAC3E,MAAM,WAAW,GAAG,WAAW,IAAI,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACvD,MAAM,WAAW,GAAG,WAAW,CAAC,CAAC,CAAC,OAAO,WAAW,EAAE,CAAC,CAAC,CAAC,gBAAgB,CAAC;IAE1E,MAAM,iBAAiB,GAAG;QACxB,GAAG,WAAW,qJAAqJ;QACnK,gMAAgM;QAChM,qBAAqB,SAAS,CAAC,MAAM,CAAC,MAAM,YAAY,SAAS,CAAC,MAAM,CAAC,KAAK,sFAAsF,SAAS,CAAC,SAAS,CAAC,KAAK,wBAAwB;KACtN,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IAEZ,MAAM,cAAc,GAAG;QACrB,kGAAkG;QAClG,yMAAyM;QACzM,+EAA+E;KAChF,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IAEZ,OAAO;QACL,WAAW,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACrC,IAAI;QACJ,UAAU;QACV,WAAW;QACX,cAAc;QACd,OAAO;QACP,SAAS,EAAE;YACT,MAAM,EAAE,SAAS,CAAC,MAAM;YACxB,WAAW,EAAE,SAAS,CAAC,MAAM,CAAC,KAAK;YACnC,YAAY,EAAE,SAAS,CAAC,MAAM,CAAC,MAAM;YACrC,eAAe,EAAE,SAAS,CAAC,SAAS,CAAC,MAAM;YAC3C,cAAc,EAAE,SAAS,CAAC,SAAS,CAAC,KAAK;SAC1C;QACD,aAAa,EAAE;YACb,IAAI,EAAE,iBAAiB;YACvB,MAAM,EAAE,MAAM,CAAC,iBAAiB,CAAC;SAClC;QACD,UAAU,EAAE;YACV,IAAI,EAAE,cAAc;YACpB,MAAM,EAAE,MAAM,CAAC,cAAc,CAAC;SAC/B;QACD,QAAQ,EAAE,aAAa,CAAC,SAAS,EAAE,WAAW,EAAE,UAAU,EAAE,WAAW,EAAE,cAAc,EAAE,OAAO,CAAC;QACjG,SAAS,EAAE,cAAc,CAAC,SAAS,CAAC;KACrC,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,MAAsB;IAC3D,MAAM,KAAK,GAAG;QACZ,oBAAoB;QACpB,EAAE;QACF,mBAAmB;QACnB,eAAe;QACf,kBAAkB,MAAM,CAAC,UAAU,IAAI,2BAA2B,IAAI;QACtE,eAAe,MAAM,CAAC,WAAW,CAAC,CAAC,CAAC,GAAG,MAAM,CAAC,WAAW,GAAG,MAAM,CAAC,cAAc,CAAC,CAAC,CAAC,IAAI,MAAM,CAAC,cAAc,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,cAAc,IAAI;QAC3I,eAAe,MAAM,CAAC,OAAO,IAAI,cAAc,IAAI;QACnD,uBAAuB,MAAM,CAAC,SAAS,CAAC,YAAY,KAAK,MAAM,CAAC,SAAS,CAAC,WAAW,SAAS;QAC9F,iBAAiB,MAAM,CAAC,SAAS,CAAC,eAAe,KAAK,MAAM,CAAC,SAAS,CAAC,cAAc,UAAU;QAC/F,EAAE;QACF,kCAAkC;QAClC,EAAE;QACF,MAAM,CAAC,aAAa,CAAC,IAAI;QACzB,EAAE;QACF,2BAA2B;QAC3B,EAAE;QACF,UAAU,CAAC,MAAM,CAAC,aAAa,CAAC,MAAM,CAAC;QACvC,EAAE;QACF,kCAAkC;QAClC,EAAE;QACF,MAAM,CAAC,UAAU,CAAC,IAAI;QACtB,EAAE;QACF,2BAA2B;QAC3B,EAAE;QACF,UAAU,CAAC,MAAM,CAAC,UAAU,CAAC,MAAM,CAAC;QACpC,EAAE;QACF,aAAa;QACb,EAAE;QACF,GAAG,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,CAAC;QAC7C,EAAE;QACF,iCAAiC;QACjC,EAAE;QACF,GAAG,MAAM,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,CAAC;QAC9C,EAAE;QACF,iBAAiB;QACjB,EAAE;QACF,SAAS;QACT,4BAA4B;QAC5B,0CAA0C;QAC1C,KAAK;QACL,EAAE;KACH,CAAC;IAEF,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED,KAAK,UAAU,eAAe,CAAC,IAAY;IACzC,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,cAAc,CAAC,EAAE,MAAM,CAAC,CAAC;QACpE,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAoB,CAAC;IAC5C,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,SAAS,CAAC;IACnB,CAAC;AACH,CAAC;AAED,SAAS,sBAAsB,CAAC,UAAyC;IACvE,MAAM,GAAG,GAAG,OAAO,UAAU,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,UAAU,EAAE,GAAG,CAAC;IAC1E,IAAI,CAAC,GAAG,EAAE,CAAC;QACT,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,OAAO,GAAG;SACP,OAAO,CAAC,QAAQ,EAAE,EAAE,CAAC;SACrB,OAAO,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;AAC3B,CAAC;AAED,SAAS,uBAAuB,CAAC,SAA0B;IACzD,MAAM,OAAO,GAAG,SAAS,CAAC,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,SAAS,CAAC,CAAC;IACxF,MAAM,KAAK,GAAG,OAAO,EAAE,MAAM,CAAC,KAAK,CAAC,yBAAyB,CAAC,CAAC;IAC/D,OAAO,KAAK,EAAE,CAAC,CAAC,CAAC,CAAC;AACpB,CAAC;AAED,SAAS,aAAa,CACpB,SAA0B,EAC1B,WAAmB,EACnB,UAA8B,EAC9B,WAA+B,EAC/B,cAAkC,EAClC,OAA2B;IAE3B,OAAO;QACL,UAAU,CAAC,CAAC,CAAC,sBAAsB,UAAU,EAAE,CAAC,CAAC,CAAC,kDAAkD;QACpG,WAAW,CAAC,CAAC,CAAC,wBAAwB,WAAW,GAAG,cAAc,CAAC,CAAC,CAAC,IAAI,cAAc,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,iEAAiE;QACpK,OAAO,CAAC,CAAC,CAAC,wBAAwB,OAAO,EAAE,CAAC,CAAC,CAAC,wDAAwD;QACtG,2BAA2B,SAAS,CAAC,MAAM,CAAC,MAAM,KAAK,SAAS,CAAC,MAAM,CAAC,KAAK,SAAS,SAAS,CAAC,MAAM,CAAC,YAAY,iBAAiB;QACpI,6BAA6B,SAAS,CAAC,SAAS,CAAC,MAAM,KAAK,SAAS,CAAC,SAAS,CAAC,KAAK,SAAS;QAC9F,oIAAoI;QACpI,2HAA2H;KAC5H,CAAC;AACJ,CAAC;AAED,SAAS,cAAc,CAAC,SAA0B;IAChD,MAAM,KAAK,GAAG;QACZ,4HAA4H;QAC5H,0FAA0F;QAC1F,8HAA8H;KAC/H,CAAC;IAEF,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC;QACtB,KAAK,CAAC,OAAO,CAAC,4FAA4F,CAAC,CAAC;IAC9G,CAAC;IAED,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,MAAM,CAAC,KAAa;IAC3B,IAAI,KAAK,CAAC,MAAM,IAAI,GAAG,EAAE,CAAC;QACxB,OAAO,KAAK,CAAC;IACf,CAAC;IAED,MAAM,MAAM,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IACnC,MAAM,WAAW,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,WAAW,CAAC,IAAI,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,IAAI,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC;IAC3G,MAAM,SAAS,GAAG,WAAW,IAAI,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IAC/F,OAAO,SAAS,CAAC,OAAO,EAAE,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC,GAAG,KAAK,CAAC;AAC5D,CAAC;AAED,SAAS,UAAU,CAAC,KAAa;IAC/B,OAAO,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AACjE,CAAC"}
|
|
@@ -0,0 +1,115 @@
|
|
|
1
|
+
# GitHub Issue Pain Map
|
|
2
|
+
|
|
3
|
+
Generated: 2026-06-01T01:27:18.765Z
|
|
4
|
+
|
|
5
|
+
Issues analyzed: **100**
|
|
6
|
+
Matched issues: **48**
|
|
7
|
+
Unmatched issues: **52**
|
|
8
|
+
|
|
9
|
+
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.
|
|
10
|
+
|
|
11
|
+
```bash
|
|
12
|
+
gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
|
|
13
|
+
trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
|
|
14
|
+
```
|
|
15
|
+
|
|
16
|
+
## Top Clusters
|
|
17
|
+
|
|
18
|
+
| Priority | Kind | Severity | Issues | Comments | Reactions | Example |
|
|
19
|
+
| ---: | --- | --- | ---: | ---: | ---: | --- |
|
|
20
|
+
| 978 | `codex_token_burn` | high | 9 | 881 | 0 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
|
|
21
|
+
| 778 | `weak_evidence` | medium | 100 | 3746 | 0 | [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) | |
|
|
22
|
+
| 446 | `premature_completion` | high | 11 | 329 | 0 | [#3962 Play a sound when Codex finishes a prompt / task](https://github.com/openai/codex/issues/3962) | |
|
|
23
|
+
| 307 | `codex_remote_compact` | high | 7 | 230 | 0 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
|
|
24
|
+
| 272 | `context_compaction` | high | 6 | 205 | 0 | [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) | |
|
|
25
|
+
| 217 | `sandbox_permission` | high | 5 | 160 | 0 | [#10601 Sandbox setup error on Windows](https://github.com/openai/codex/issues/10601) | |
|
|
26
|
+
| 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) | |
|
|
27
|
+
| 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) | |
|
|
28
|
+
| 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) | |
|
|
29
|
+
| 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) | |
|
|
30
|
+
| 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) | |
|
|
31
|
+
| 130 | `codex_tool_call_integrity` | high | 2 | 103 | 0 | [#2998 IDE-integrated diff / approval](https://github.com/openai/codex/issues/2998) | |
|
|
32
|
+
| 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) | |
|
|
33
|
+
| 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) | |
|
|
34
|
+
| 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) | |
|
|
35
|
+
|
|
36
|
+
## Suggested Next Actions
|
|
37
|
+
|
|
38
|
+
### codex_token_burn
|
|
39
|
+
|
|
40
|
+
Priority score: 978. 9 issue(s), 881 comment(s).
|
|
41
|
+
|
|
42
|
+
Example issues:
|
|
43
|
+
- [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
|
|
44
|
+
- [#19464 Support 1M token context for GPT-5.5 in Codex](https://github.com/openai/codex/issues/19464) (132 comments; labels: enhancement, context)
|
|
45
|
+
- [#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)
|
|
46
|
+
|
|
47
|
+
Evidence rule prompts:
|
|
48
|
+
- 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.
|
|
49
|
+
|
|
50
|
+
### weak_evidence
|
|
51
|
+
|
|
52
|
+
Priority score: 778. 100 issue(s), 3746 comment(s).
|
|
53
|
+
|
|
54
|
+
Example issues:
|
|
55
|
+
- [#14593 Burning tokens very fast](https://github.com/openai/codex/issues/14593) (593 comments; labels: bug, rate-limits)
|
|
56
|
+
- [#19464 Support 1M token context for GPT-5.5 in Codex](https://github.com/openai/codex/issues/19464) (132 comments; labels: enhancement, context)
|
|
57
|
+
- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
|
|
58
|
+
|
|
59
|
+
Evidence rule prompts:
|
|
60
|
+
- Final responses must include the exact validation evidence used to prove the change, not only a summary of intent.
|
|
61
|
+
|
|
62
|
+
### premature_completion
|
|
63
|
+
|
|
64
|
+
Priority score: 446. 11 issue(s), 329 comment(s).
|
|
65
|
+
|
|
66
|
+
Example issues:
|
|
67
|
+
- [#3962 Play a sound when Codex finishes a prompt / task](https://github.com/openai/codex/issues/3962) (50 comments; labels: enhancement, extension)
|
|
68
|
+
- [#7291 Bug report: VSCode extension failed to revert the changes](https://github.com/openai/codex/issues/7291) (42 comments; labels: bug, extension)
|
|
69
|
+
- [#18341 Mac app shows persistent blurred/translucent overlay below composer](https://github.com/openai/codex/issues/18341) (34 comments; labels: bug, app)
|
|
70
|
+
|
|
71
|
+
Evidence rule prompts:
|
|
72
|
+
- Before claiming completion, run the relevant validation command or clearly state the exact validation that could not be run and why.
|
|
73
|
+
|
|
74
|
+
### codex_remote_compact
|
|
75
|
+
|
|
76
|
+
Priority score: 307. 7 issue(s), 230 comment(s).
|
|
77
|
+
|
|
78
|
+
Example issues:
|
|
79
|
+
- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
|
|
80
|
+
- [#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)
|
|
81
|
+
- [#10823 Unable to compact the context in a VERY long running session](https://github.com/openai/codex/issues/10823) (26 comments; labels: bug, context)
|
|
82
|
+
|
|
83
|
+
Evidence rule prompts:
|
|
84
|
+
- 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.
|
|
85
|
+
|
|
86
|
+
### context_compaction
|
|
87
|
+
|
|
88
|
+
Priority score: 272. 6 issue(s), 205 comment(s).
|
|
89
|
+
|
|
90
|
+
Example issues:
|
|
91
|
+
- [#14860 Error running remote compact task](https://github.com/openai/codex/issues/14860) (90 comments; labels: bug, context)
|
|
92
|
+
- [#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)
|
|
93
|
+
- [#10823 Unable to compact the context in a VERY long running session](https://github.com/openai/codex/issues/10823) (26 comments; labels: bug, context)
|
|
94
|
+
|
|
95
|
+
Evidence rule prompts:
|
|
96
|
+
- When Codex compaction fails, capture the compact error, model/app version, thread state, and whether the session is recoverable before continuing or reporting success.
|
|
97
|
+
|
|
98
|
+
## Unmatched Issues
|
|
99
|
+
|
|
100
|
+
- [#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)
|
|
101
|
+
- [#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)
|
|
102
|
+
- [#11023 Codex desktop app for Linux](https://github.com/openai/codex/issues/11023) (68 comments; labels: enhancement, app)
|
|
103
|
+
- [#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)
|
|
104
|
+
- [#8745 LSP integration (auto-detect + auto-install) for Codex CLI](https://github.com/openai/codex/issues/8745) (52 comments; labels: enhancement, agent)
|
|
105
|
+
- [#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)
|
|
106
|
+
- [#9203 Please make "/undo" back](https://github.com/openai/codex/issues/9203) (46 comments; labels: enhancement, TUI, session)
|
|
107
|
+
- [#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)
|
|
108
|
+
- [#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)
|
|
109
|
+
- [#3141 Allow GPU access inside sandbox](https://github.com/openai/codex/issues/3141) (35 comments; labels: enhancement, sandbox)
|
|
110
|
+
- [#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)
|
|
111
|
+
- [#2153 ChatGPT integration](https://github.com/openai/codex/issues/2153) (33 comments; labels: enhancement, app, User Request, Feature)
|
|
112
|
+
- [#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)
|
|
113
|
+
- [#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)
|
|
114
|
+
- [#2952 Search @ cannot search from directories excluded by .gitignore](https://github.com/openai/codex/issues/2952) (31 comments; labels: bug, extension)
|
|
115
|
+
|
package/docs/DISCOVERY.md
CHANGED
|
@@ -98,6 +98,7 @@ npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format
|
|
|
98
98
|
npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
|
|
99
99
|
npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
|
|
100
100
|
npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
|
|
101
|
+
npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
|
|
101
102
|
npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
|
|
102
103
|
npx trace-to-skill redact ./runs --output redacted-runs
|
|
103
104
|
npx trace-to-skill analyze ./runs --format json
|
|
@@ -122,12 +123,14 @@ npx trace-to-skill suggest ./runs --target agents-md
|
|
|
122
123
|
- `trace-to-skill diagnostics-bundle --format json`
|
|
123
124
|
- `trace-to-skill usage-evidence --format json`
|
|
124
125
|
- `trace-to-skill process-audit --format json`
|
|
126
|
+
- `trace-to-skill issue-map --format json`
|
|
125
127
|
- `trace-to-skill checkpoint --format json`
|
|
126
128
|
- SARIF from `trace-to-skill analyze --format sarif`
|
|
127
129
|
- OpenAI/Codex issue-ready Markdown from `trace-to-skill codex-report`
|
|
128
130
|
- Packaged zero-setup Codex issue-report demo from `trace-to-skill demo`
|
|
129
131
|
- OpenAI OSS support/application brief from `trace-to-skill oss-brief`
|
|
130
132
|
- Codex issue-cluster mapping in `docs/CODEX_ISSUE_MAP.md`
|
|
133
|
+
- GitHub issue demand mining in `docs/CODEX_GITHUB_ISSUE_PAIN_MAP.md`
|
|
131
134
|
- GitHub Action outputs for doctor, AGENTS lint, GitHub context guard, benchmark, and scorecard modes
|
|
132
135
|
|
|
133
136
|
## Schema Contracts
|
package/docs/OPENAI_OSS_BRIEF.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
| Field | Value |
|
|
4
4
|
| --- | --- |
|
|
5
5
|
| Repository | https://github.com/grnbtqdbyx-create/trace-to-skill |
|
|
6
|
-
| Package | trace-to-skill@0.1.
|
|
6
|
+
| Package | trace-to-skill@0.1.85 |
|
|
7
7
|
| License | Apache-2.0 |
|
|
8
8
|
| Codex readiness | ready (100/100) |
|
|
9
9
|
| Benchmark | pass, 38 cases |
|
|
@@ -27,7 +27,7 @@ API credits would power optional maintainer workflows on top of the local determ
|
|
|
27
27
|
## Evidence
|
|
28
28
|
|
|
29
29
|
- Public repository: https://github.com/grnbtqdbyx-create/trace-to-skill
|
|
30
|
-
- One-command package: npx trace-to-skill@0.1.
|
|
30
|
+
- One-command package: npx trace-to-skill@0.1.85
|
|
31
31
|
- Open-source license: Apache-2.0
|
|
32
32
|
- Codex readiness doctor: ready, 100/100, 0 failed checks.
|
|
33
33
|
- Public fixture benchmark: pass, 38 cases.
|
package/docs/USE_CASES.md
CHANGED
|
@@ -59,7 +59,7 @@ What it proves:
|
|
|
59
59
|
Recommended CI surface:
|
|
60
60
|
|
|
61
61
|
```yaml
|
|
62
|
-
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.
|
|
62
|
+
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.85
|
|
63
63
|
with:
|
|
64
64
|
mode: all
|
|
65
65
|
doctor-threshold: "85"
|
|
@@ -69,7 +69,24 @@ Recommended CI surface:
|
|
|
69
69
|
github-token: ${{ github.token }}
|
|
70
70
|
```
|
|
71
71
|
|
|
72
|
-
## 3.
|
|
72
|
+
## 3. GitHub Issue Demand Mining
|
|
73
|
+
|
|
74
|
+
Use this when you want to see what Codex users are actually complaining about on GitHub before choosing the next fixture, report template, or diagnostic helper.
|
|
75
|
+
|
|
76
|
+
```bash
|
|
77
|
+
gh issue list --repo openai/codex --state open --limit 100 --json number,title,body,url,labels,comments,createdAt,updatedAt > codex-issues.json
|
|
78
|
+
npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
|
|
79
|
+
npx trace-to-skill issue-map codex-issues.json --format json
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
What it proves:
|
|
83
|
+
|
|
84
|
+
- public issue clusters can be ranked without private telemetry
|
|
85
|
+
- high-comment pain points are mapped to deterministic failure classes such as token burn, remote compact, MCP discovery, usage buckets, context drift, sandbox, and resource leaks
|
|
86
|
+
- maintainers get example issue links and evidence-rule prompts for the next support artifact
|
|
87
|
+
- OSS builders can show that new work is grounded in real GitHub demand instead of generic agent demos
|
|
88
|
+
|
|
89
|
+
## 4. AGENTS.md And MCP Hygiene
|
|
73
90
|
|
|
74
91
|
Use this before giving Codex broad repository access.
|
|
75
92
|
|
|
@@ -89,7 +106,7 @@ This checks:
|
|
|
89
106
|
|
|
90
107
|
The goal is not to ban powerful tools. The goal is to make trust boundaries visible before an agent acts.
|
|
91
108
|
|
|
92
|
-
##
|
|
109
|
+
## 5. Language-Server Readiness Before Agent Edits
|
|
93
110
|
|
|
94
111
|
Use this when a repo wants Codex to navigate definitions, references, diagnostics, or rename/refactor flows, but language-server setup differs across machines.
|
|
95
112
|
|
|
@@ -107,7 +124,7 @@ What it proves:
|
|
|
107
124
|
|
|
108
125
|
It does not auto-install anything or grant new permissions; it is a readiness report.
|
|
109
126
|
|
|
110
|
-
##
|
|
127
|
+
## 6. Sandbox And Permission Failure Triage
|
|
111
128
|
|
|
112
129
|
Use this when Codex cannot start tools, apply patches, or write to the workspace because sandbox setup or permissions fail.
|
|
113
130
|
|
|
@@ -128,7 +145,7 @@ For Codex App reports where Speed resets from Fast to Standard after restart, in
|
|
|
128
145
|
|
|
129
146
|
`diagnostics-bundle` combines the config, plugin, and session summaries into a metadata-only support folder with a manifest and README. Use it when OpenAI asks for more evidence but raw `config.toml`, SQLite state, rollout JSONL, and local logs should not be posted publicly.
|
|
130
147
|
|
|
131
|
-
##
|
|
148
|
+
## 7. Codex Auth And Connectivity Triage
|
|
132
149
|
|
|
133
150
|
Use this when Codex cannot log in, exchange an auth token, stream a response, or connect through a container, proxy, VPN, corporate CA, IPv6 network, or Cloudflare challenge.
|
|
134
151
|
|
|
@@ -138,7 +155,7 @@ npx trace-to-skill analyze ./runs --format json
|
|
|
138
155
|
|
|
139
156
|
This catches signals such as `token_exchange_failed`, `auth.openai.com/oauth/token`, `codex_login::server`, `cf-mitigated: challenge`, missing `ca-certificates`, `update-ca-certificates`, `CODEX_CA_CERTIFICATE`, IPv6 fallback evidence, proxy/MITM TLS failures, and `stream disconnected before completion` on `chatgpt.com/backend-api/codex/responses`.
|
|
140
157
|
|
|
141
|
-
##
|
|
158
|
+
## 8. Codex Remote Compact Failure Triage
|
|
142
159
|
|
|
143
160
|
Use this when `/compact` or auto-compaction fails during a long Codex session and the user cannot continue without recreating context.
|
|
144
161
|
|
|
@@ -148,7 +165,7 @@ npx trace-to-skill codex-report ./runs --output openai-codex-compact-issue.md
|
|
|
148
165
|
|
|
149
166
|
This catches signals such as `Error running remote compact task`, `timeout waiting for child process to exit`, `stream disconnected before completion`, `responses/compact`, `tcp_user_timeout`, `stream_idle_timeout_ms`, provider-id timeout workarounds, Azure provider config drift, and long-running tasks broken by failed compaction.
|
|
150
167
|
|
|
151
|
-
##
|
|
168
|
+
## 9. Codex Context Fork Bloat Evidence
|
|
152
169
|
|
|
153
170
|
Use this when a conversation fork carries duplicate parent context, inflates token counts, or breaks prompt-cache lineage before new work happens.
|
|
154
171
|
|
|
@@ -162,7 +179,7 @@ This catches signals such as forked conversations carrying the full parent trans
|
|
|
162
179
|
|
|
163
180
|
Include 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.
|
|
164
181
|
|
|
165
|
-
##
|
|
182
|
+
## 10. Codex Subagent Prompt Leakage Evidence
|
|
166
183
|
|
|
167
184
|
Use this when `spawn_agent` child tasks are not isolated, especially with `fork_turns: "none"` or same-turn parallel subagent spawning.
|
|
168
185
|
|
|
@@ -176,7 +193,7 @@ This catches signals such as delegated `spawn_agent` messages recorded as assist
|
|
|
176
193
|
|
|
177
194
|
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.
|
|
178
195
|
|
|
179
|
-
##
|
|
196
|
+
## 11. Codex Usage Evidence Packaging
|
|
180
197
|
|
|
181
198
|
Use this when a Codex usage issue has scattered evidence across `/status`, dashboard notes, reset tables, token totals, prompt-cache rows, cached input, and local overhead clues.
|
|
182
199
|
|
|
@@ -196,7 +213,7 @@ The receipt separates:
|
|
|
196
213
|
- orchestration-overhead signals that may burn usage without accepted work
|
|
197
214
|
- suspected cause buckets to keep public reports comparable
|
|
198
215
|
|
|
199
|
-
##
|
|
216
|
+
## 12. Codex Usage Bucket Scope Evidence
|
|
200
217
|
|
|
201
218
|
Use this when Codex usage UI shows 5h and weekly percentages but does not explain the accounting scope.
|
|
202
219
|
|
|
@@ -210,7 +227,7 @@ This catches signals such as `Usage remaining`, `5h 97%`, `Weekly 95%`, reset da
|
|
|
210
227
|
|
|
211
228
|
Include 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.
|
|
212
229
|
|
|
213
|
-
##
|
|
230
|
+
## 13. Codex Windows Helper Path Triage
|
|
214
231
|
|
|
215
232
|
Use this when Codex Desktop on Windows discovers bundled tools or plugin helpers but cannot execute them from the integrated terminal, tool runner, Browser, Chrome, Computer Use, or node_repl path.
|
|
216
233
|
|
|
@@ -220,7 +237,7 @@ npx trace-to-skill codex-report ./runs --output openai-codex-windows-helper-issu
|
|
|
220
237
|
|
|
221
238
|
This catches signals such as `Program 'rg.exe' failed to run`, `Access is denied`, `WindowsApps\OpenAI.Codex...\app\resources`, missing `%LOCALAPPDATA%\OpenAI\Codex\bin`, missing MSIX LocalCache helper bins, `CodexSandboxUsers` ACL/RX problems, `copyfile` failures from WindowsApps bundled plugin manifests, EFS/Application Protected attributes, `windows sandbox failed: spawn setup refresh`, `missing-helper-path`, and unavailable Browser/Chrome/Computer Use plugin helpers.
|
|
222
239
|
|
|
223
|
-
##
|
|
240
|
+
## 14. Codex Mobile And Remote-Control Route Health
|
|
224
241
|
|
|
225
242
|
Use this when Codex mobile, SSH remote, or desktop remote-control says it is connected but commands do not reach the expected host, workspace, or app-server.
|
|
226
243
|
|
|
@@ -230,7 +247,7 @@ npx trace-to-skill analyze ./runs --format json
|
|
|
230
247
|
|
|
231
248
|
This catches signals such as `Waiting for desktop`, `Directory: Unavailable`, stale `server_name` enrollment, stale remote-control listener, `127.0.0.1:14567`, missing cached helper files such as `codex-windows-sandbox-setup.exe` or `codex-command-runner.exe`, empty backend environments, stale Android session lists, and temporary recovery after re-pairing or listener restart.
|
|
232
249
|
|
|
233
|
-
##
|
|
250
|
+
## 15. Codex Terminal Output And Scrollback Integrity
|
|
234
251
|
|
|
235
252
|
Use this when Codex terminal output, streamed assistant text, or scrollback becomes untrustworthy even though raw logs, transcripts, or transaction views still contain the missing lines.
|
|
236
253
|
|
|
@@ -244,7 +261,7 @@ This catches signals such as Windows Terminal scrollback lines disappearing, str
|
|
|
244
261
|
|
|
245
262
|
Include the Codex CLI/app/extension version, OS, shell, terminal emulator and version, WSL/SSH/tmux/Zellij state, model, whether streaming was active, exact scroll action, terminal dimensions and scrollback settings, first missing or duplicated line id, raw log/transcript proof, terminal capture, numbered-line harness output, control run, `/resume` or transcript recovery behavior, and whether another terminal or downgrade changes the result.
|
|
246
263
|
|
|
247
|
-
##
|
|
264
|
+
## 16. Codex Subagent Lifecycle And State Reconciliation
|
|
248
265
|
|
|
249
266
|
Use this when subagents appear completed, closed, stale, or interrupted but Codex cannot reconcile UI state, live handles, persisted spawn edges, parent discoverability, and active spawn quota.
|
|
250
267
|
|
|
@@ -258,7 +275,7 @@ This catches signals such as completed subagents remaining visible in the Subage
|
|
|
258
275
|
|
|
259
276
|
Include Codex app/CLI/extension version, OS, surface, model, subscription/workspace, root thread id, subagent ids/nicknames/roles, spawn/close/list commands, `close_agent` results, `list_agents` or `/agents` output, `thread_spawn_edges` status counts, `agents.max_threads` or registry quota evidence, recent-list/sidebar behavior, child-thread archive/top-level status, last-progress or halt reason, MCP server state, compaction/resume timing, redacted UI evidence, restart/reload behavior, and whether stale agents are UI-only or still block spawns.
|
|
260
277
|
|
|
261
|
-
##
|
|
278
|
+
## 17. Codex MCP Runtime Triage
|
|
262
279
|
|
|
263
280
|
Use this when MCP tools are configured and visible, but Codex cannot actually call them at runtime.
|
|
264
281
|
|
|
@@ -269,7 +286,7 @@ npx trace-to-skill config-audit ~/.codex --format json
|
|
|
269
286
|
|
|
270
287
|
This catches signals such as `user cancelled MCP tool call`, `request_user_input is not supported in exec mode`, `Approve app tool call?`, `tool_call_mcp_elicitation`, routed callable names like `mcp__node_repl__js` becoming `unsupported call`, deferred discovery dropping namespace or `serverName`, `tools/list` succeeding while Codex routing fails, and stdio transport lifecycle failures such as `Transport closed`, `stdin_end`, `stdin_close`, `transport_close`, or stderr backpressure.
|
|
271
288
|
|
|
272
|
-
##
|
|
289
|
+
## 18. Codex Resume And Session State Triage
|
|
273
290
|
|
|
274
291
|
Use this when long Codex sessions become difficult to resume, Desktop history rendering gets sluggish, or local state migrations break goals/projects/history.
|
|
275
292
|
|
|
@@ -286,7 +303,7 @@ This catches signals such as `codex resume` picker hangs, `codex resume <id>` wo
|
|
|
286
303
|
|
|
287
304
|
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.
|
|
288
305
|
|
|
289
|
-
##
|
|
306
|
+
## 19. Codex File Tree UI Evidence
|
|
290
307
|
|
|
291
308
|
Use this when Codex Desktop cannot reveal project files through the native file tree, folder icon, floating file panel, or built-in preview.
|
|
292
309
|
|
|
@@ -297,7 +314,7 @@ npx trace-to-skill codex-report ./runs --output openai-codex-issue.md
|
|
|
297
314
|
|
|
298
315
|
This catches signals such as `View > Toggle File Tree` doing nothing, `Cmd+Shift+E` or `Ctrl+Shift+E` having no visible effect, the folder icon disappearing, the floating file panel showing stale or unclickable entries after add/rename/delete operations, and `.doc`, `.pdf`, or `.ppt` previews failing until restart.
|
|
299
316
|
|
|
300
|
-
##
|
|
317
|
+
## 20. Codex Token Burn Attribution
|
|
301
318
|
|
|
302
319
|
Use this when Codex usage drains faster than expected and the trace needs to separate useful model work from orchestration overhead.
|
|
303
320
|
|
|
@@ -310,7 +327,7 @@ This catches signals such as tokens `burning very fast`, usage dropping by visib
|
|
|
310
327
|
|
|
311
328
|
For public reports, prefer `usage-evidence` first so the quota-window, local-token, and orchestration-overhead layers are visible separately.
|
|
312
329
|
|
|
313
|
-
##
|
|
330
|
+
## 21. Usage Reset Drift Evidence
|
|
314
331
|
|
|
315
332
|
Use this when Codex reset timing changes unexpectedly or users lose the ability to plan paid usage.
|
|
316
333
|
|
|
@@ -321,7 +338,7 @@ npx trace-to-skill codex-report ./runs --output openai-codex-issue.md
|
|
|
321
338
|
|
|
322
339
|
This catches signals such as weekly reset dates moving from one date to another, `reset_at` jumping after the first prompt, saved weekly usage being wiped or pushed into the next window, outage compensation resets changing the anchor, `/status` and dashboard disagreement, and requests for deterministic reset schedules or rollover of unused prior-window usage.
|
|
323
340
|
|
|
324
|
-
##
|
|
341
|
+
## 22. Quota And Usage-Limit Evidence
|
|
325
342
|
|
|
326
343
|
Use this when Codex blocks a prompt with a usage-limit message but another surface still shows remaining quota.
|
|
327
344
|
|
|
@@ -331,7 +348,7 @@ npx trace-to-skill analyze ./runs --format json
|
|
|
331
348
|
|
|
332
349
|
This catches traces where `/status` or the usage page shows remaining 5h or weekly quota, accounts appear to share limits unexpectedly, a Team account inherits a Plus account's limit state, or quota reset times jump after logout/login.
|
|
333
350
|
|
|
334
|
-
##
|
|
351
|
+
## 23. Codex Resource Leak Evidence
|
|
335
352
|
|
|
336
353
|
Use this when Codex Desktop, the VS Code extension, renderer, app-server, GPU process, shell snapshot, or helper process keeps burning local resources after the useful work should be idle.
|
|
337
354
|
|
|
@@ -353,7 +370,7 @@ npx trace-to-skill process-audit ./process-notes.md --format json
|
|
|
353
370
|
|
|
354
371
|
`process-audit` packages Task Manager, System Informer, `Get-CimInstance`, `ps`, `top`, or handwritten process measurement snippets into a smaller public report. It detects PowerShell/pwsh CIM polling such as `Get-CimInstance Win32_Process`, high-CPU Codex/helper/renderer samples, stale `process_manager/chat_processes.json` mentions, and runaway helper signals without inspecting live processes or asking users to post full raw process dumps.
|
|
355
372
|
|
|
356
|
-
##
|
|
373
|
+
## 24. Codex Thinking Hang Evidence
|
|
357
374
|
|
|
358
375
|
Use this when Codex accepts a prompt, finishes a local tool call, or keeps a Responses stream open but the UI/CLI remains on Thinking or Working with no visible assistant follow-up.
|
|
359
376
|
|
|
@@ -367,7 +384,7 @@ This catches signals such as `turn/start`, `task_started`, a completed local too
|
|
|
367
384
|
|
|
368
385
|
Include the Codex version, OS, model and reasoning/speed settings, turn or thread id, prompt timestamp, last successful tool output, first `response_item` timestamp, `responses_http` or websocket transport evidence, `time.busy` / `time.idle`, MCP/subagent state, stop/interrupt behavior, and whether a new thread or minimal config recovers.
|
|
369
386
|
|
|
370
|
-
##
|
|
387
|
+
## 25. Codex Clipboard And Pasted-Text Attachment Evidence
|
|
371
388
|
|
|
372
389
|
Use this when copy/export, long pasted prompts, or generated `Pasted text.txt` attachments break Codex prompt, `/goal`, or support-report workflows.
|
|
373
390
|
|
|
@@ -381,7 +398,7 @@ This catches signals such as `Copy as Markdown` disappearing from the Copy menu,
|
|
|
381
398
|
|
|
382
399
|
Include app version, OS, surface, exact copy menu items, source text size, paste action, visible editor text, generated attachment name/path/size, `pasted-text-attachments.json` or fileAttachments metadata, command path such as `/goal`, preview/edit/revert actions tried, clipboard payload format, and whether paste-as-text, opt-out, explicit file reference, or downgrade changes behavior.
|
|
383
400
|
|
|
384
|
-
##
|
|
401
|
+
## 26. Codex Deeplink And External Launch Evidence
|
|
385
402
|
|
|
386
403
|
Use this when OAuth callbacks, notification clicks, browser extension activation, mobile pairing, or CLI app-open commands fail to route back into Codex.
|
|
387
404
|
|
|
@@ -395,7 +412,7 @@ This catches signals such as `codex://oauth_callback?code=...` opening an Electr
|
|
|
395
412
|
|
|
396
413
|
Include app/CLI/extension version, OS/build, install source, package id/path, affected surface, exact redacted URI shape, browser and connector/plugin name, error dialog text, whether the app was already running, AppX/MSIX evidence such as AppUserModelID and DelegateExecute, HKCU/HKCR `codex` keys, command-line arguments, repair/reinstall/re-register attempts, and whether manual `codex://test` or `Start-Process` reproduces.
|
|
397
414
|
|
|
398
|
-
##
|
|
415
|
+
## 27. Codex App Connector Auth Cache Evidence
|
|
399
416
|
|
|
400
417
|
Use this when Codex app connectors appear installed but keep stale auth or discovery metadata after a reauth-required response.
|
|
401
418
|
|
|
@@ -409,7 +426,7 @@ This catches signals such as `401: "Server returned 401: 'Reauthentication requi
|
|
|
409
426
|
|
|
410
427
|
Include app/CLI version, OS, connector/plugin name and id, installed plugin root, exact tool name, redacted `codex_apps_tools` and `codex_app_directory` metadata, `link_*` id before/after reconnect, `isAccessible` state, restart/remove/re-add/cache-clear/sign-in attempts, ChatGPT app page state, and whether an external MCP workaround succeeds.
|
|
411
428
|
|
|
412
|
-
##
|
|
429
|
+
## 28. Codex MCP Discovery And Config Scope Evidence
|
|
413
430
|
|
|
414
431
|
Use this when MCP servers work in Codex CLI or one config scope but are missing in VS Code, Desktop, WSL, remote sessions, project-local config, or an older conversation.
|
|
415
432
|
|
|
@@ -423,7 +440,7 @@ This catches signals such as `MCP servers not detected in Codex VS Code extensio
|
|
|
423
440
|
|
|
424
441
|
Include app/CLI/extension version, OS, IDE, remote/WSL/SSH state, workspace root, effective `CODEX_HOME`, all config files considered (`~/.codex/config.toml`, project `.codex/config.toml`, `.vscode/mcp.json`, `.mcp.json`), redacted MCP sections, trust/profile/default-permissions state, `codex mcp list`, `codex mcp get <server>`, CLI-versus-Desktop/VS Code comparison, loaded config path/log lines, whether moving the same server to user-global config fixes it, and whether the current session exposes `mcp__*` tools.
|
|
425
442
|
|
|
426
|
-
##
|
|
443
|
+
## 29. Codex Streamable HTTP MCP Evidence
|
|
427
444
|
|
|
428
445
|
Use this when a Streamable HTTP or SSE MCP server is reachable but Codex fails during JSON-RPC parsing, handshake, auth gating, stale session reuse, or reconnect.
|
|
429
446
|
|
|
@@ -437,7 +454,7 @@ This catches signals such as Penpot `JsonRpcMessage deserialize` or response-par
|
|
|
437
454
|
|
|
438
455
|
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 and after reconnect or server restart, auth/OAuth expectations, User-Agent/header requirements, exact parse/deserialize error, whether curl or another MCP client succeeds, and whether restarting Codex or reinitializing the transport recovers.
|
|
439
456
|
|
|
440
|
-
##
|
|
457
|
+
## 30. Codex Hooks Runtime Evidence
|
|
441
458
|
|
|
442
459
|
Use this when Codex hooks duplicate, stop firing, emit stale deprecation warnings, behave differently across CLI/Desktop/Code Mode/Windows, or become hard to inspect in settings.
|
|
443
460
|
|
|
@@ -451,7 +468,7 @@ This catches signals such as duplicate Hooks entries for one tool call, `PostToo
|
|
|
451
468
|
|
|
452
469
|
Include Codex app/CLI/extension version, OS, surface, shell or Desktop route, `[features].hooks` and `hooks.json` snippets without secrets, hook event type, matcher, handler command/name, expected versus observed fire count, duplicate event ids, exact deprecation warning, trust state, live-edit/rate-limit/auto-restore timing, Code Mode `exec` versus normal CLI comparison, linked-worktree cwd, Hooks settings UI screenshot if relevant, and whether restart/reload/new session restores behavior.
|
|
453
470
|
|
|
454
|
-
##
|
|
471
|
+
## 31. Patch Overwrite Guard
|
|
455
472
|
|
|
456
473
|
Use this before applying a generated patch when you want create/update/delete semantics checked against the actual workspace.
|
|
457
474
|
|
|
@@ -468,7 +485,7 @@ For a public demo report:
|
|
|
468
485
|
npx trace-to-skill demo patch-overwrite
|
|
469
486
|
```
|
|
470
487
|
|
|
471
|
-
##
|
|
488
|
+
## 32. Sensitive Path Preflight Before Agent Runs
|
|
472
489
|
|
|
473
490
|
Use this before giving an AI coding agent a repository.
|
|
474
491
|
|
|
@@ -483,7 +500,7 @@ This finds sensitive-looking paths such as `.env`, `.env.*`, `.npmrc`, `.pypirc`
|
|
|
483
500
|
|
|
484
501
|
The output includes a stable JSON schema plus recommended exclude globs that can seed `.agentignore`, `.aiexclude`, `.codexignore`, `.gitignore`, local sandbox permission profiles, or team security review checklists. `--format ignore` renders a reviewable generated file candidate and still does not mutate the repo. It is a preflight report, not a sandbox boundary.
|
|
485
502
|
|
|
486
|
-
##
|
|
503
|
+
## 33. Workspace Checkpoint Before Agent Runs
|
|
487
504
|
|
|
488
505
|
Use this before giving Codex, Claude, Cursor, or another coding agent a dirty repository where untracked local work matters.
|
|
489
506
|
|
|
@@ -496,7 +513,7 @@ This writes a local checkpoint bundle with `status.txt`, staged and unstaged bin
|
|
|
496
513
|
|
|
497
514
|
This is useful for OpenAI/Codex `/undo` and `/rewind` discussions where users need workspace protection beyond conversation rewind, especially when untracked files are outside normal commit history.
|
|
498
515
|
|
|
499
|
-
##
|
|
516
|
+
## 34. OpenAI Codex Issue Report
|
|
500
517
|
|
|
501
518
|
Use this when you want to file or update an OpenAI/Codex issue with a concise, evidence-backed report instead of pasting a full transcript.
|
|
502
519
|
|
|
@@ -509,7 +526,7 @@ The report includes the likely Codex failure class, line-linked evidence, diagno
|
|
|
509
526
|
|
|
510
527
|
For a cluster-to-command map of current Codex issue patterns, see [CODEX_ISSUE_MAP.md](CODEX_ISSUE_MAP.md).
|
|
511
528
|
|
|
512
|
-
##
|
|
529
|
+
## 35. Sensitive File Access Evidence
|
|
513
530
|
|
|
514
531
|
Use this when a trace suggests an agent read, attached, uploaded, diffed, or indexed credential-bearing files.
|
|
515
532
|
|
|
@@ -522,7 +539,7 @@ This catches signals such as `.env`, `.env.production`, `.npmrc`, `.pypirc`, `.n
|
|
|
522
539
|
|
|
523
540
|
Before publishing evidence, run `trace-to-skill redact` and attach only redacted excerpts plus the file path/class.
|
|
524
541
|
|
|
525
|
-
##
|
|
542
|
+
## 36. GitHub Context Guard
|
|
526
543
|
|
|
527
544
|
Use this before an agent reads untrusted GitHub text.
|
|
528
545
|
|
|
@@ -539,7 +556,7 @@ Use it when:
|
|
|
539
556
|
- a bot asks Codex to triage untrusted user reports
|
|
540
557
|
- logs or comments might contain instructions like "ignore previous instructions" or "print secrets"
|
|
541
558
|
|
|
542
|
-
##
|
|
559
|
+
## 37. Failed Agent Run To Reviewable Rule
|
|
543
560
|
|
|
544
561
|
Use this when a coding agent made a repeated workflow mistake.
|
|
545
562
|
|
|
@@ -557,7 +574,7 @@ Recommended maintainer loop:
|
|
|
557
574
|
4. Copy only evidence-backed rules into the real policy file.
|
|
558
575
|
5. Run `eval` or `scorecard` in CI so the same failure does not silently return.
|
|
559
576
|
|
|
560
|
-
##
|
|
577
|
+
## 38. Privacy-Preserving Adoption
|
|
561
578
|
|
|
562
579
|
Use this when you want public evidence without leaking private traces.
|
|
563
580
|
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
[
|
|
2
|
+
{
|
|
3
|
+
"number": 14593,
|
|
4
|
+
"title": "Burning tokens very fast",
|
|
5
|
+
"body": "Codex is burning tokens very fast while idle. Weekly usage drops 70% in one day with repeated compaction loops, retries, background polling, and no accepted edits. /status disagrees with the dashboard and cached input tokens keep replaying.",
|
|
6
|
+
"url": "https://github.com/openai/codex/issues/14593",
|
|
7
|
+
"labels": [
|
|
8
|
+
{ "name": "bug" },
|
|
9
|
+
{ "name": "rate-limits" }
|
|
10
|
+
],
|
|
11
|
+
"commentsCount": 593,
|
|
12
|
+
"reactions": { "totalCount": 41 },
|
|
13
|
+
"updatedAt": "2026-06-01T00:00:00Z"
|
|
14
|
+
},
|
|
15
|
+
{
|
|
16
|
+
"number": 14860,
|
|
17
|
+
"title": "Error running remote compact task",
|
|
18
|
+
"body": "The long Codex session fails during /compact. The client prints Error running remote compact task, responses/compact, stream disconnected before completion, and timeout waiting for child process to exit. A provider config workaround only changes the failure timing.",
|
|
19
|
+
"url": "https://github.com/openai/codex/issues/14860",
|
|
20
|
+
"labels": [
|
|
21
|
+
{ "name": "bug" },
|
|
22
|
+
{ "name": "context" }
|
|
23
|
+
],
|
|
24
|
+
"commentsCount": 90,
|
|
25
|
+
"reactions": { "+1": 15 },
|
|
26
|
+
"updatedAt": "2026-05-31T22:00:00Z"
|
|
27
|
+
},
|
|
28
|
+
{
|
|
29
|
+
"number": 6465,
|
|
30
|
+
"title": "MCP servers not detected in Codex VS Code extension but working in Codex CLI",
|
|
31
|
+
"body": "MCP servers not detected in the VS Code extension or Desktop, but working in Codex CLI from ~/.codex/config.toml. tools/list is empty in one surface, project .codex/config.toml is ignored, and serverName metadata is missing.",
|
|
32
|
+
"url": "https://github.com/openai/codex/issues/6465",
|
|
33
|
+
"labels": [
|
|
34
|
+
{ "name": "bug" },
|
|
35
|
+
{ "name": "extension" },
|
|
36
|
+
{ "name": "mcp" }
|
|
37
|
+
],
|
|
38
|
+
"comments": [
|
|
39
|
+
{ "body": "I can reproduce this across WSL and Desktop with the same config scope mismatch." }
|
|
40
|
+
],
|
|
41
|
+
"commentsCount": 55,
|
|
42
|
+
"reactions": { "totalCount": 8 },
|
|
43
|
+
"updatedAt": "2026-05-30T20:00:00Z"
|
|
44
|
+
},
|
|
45
|
+
{
|
|
46
|
+
"number": 25471,
|
|
47
|
+
"title": "Codex usage popover shows confusing remaining percentages for 5h vs weekly buckets",
|
|
48
|
+
"body": "Usage remaining shows 5h 97% and Weekly 95% Jun 7. The popover does not say whether the percentages are percent remaining or percent used, whether weekly is rolling 7-day or calendar week, or whether app, CLI, cloud tasks, reviews, devices, and workspaces share the same pool.",
|
|
49
|
+
"url": "https://github.com/openai/codex/issues/25471",
|
|
50
|
+
"labels": [
|
|
51
|
+
{ "name": "enhancement" },
|
|
52
|
+
{ "name": "rate-limits" },
|
|
53
|
+
{ "name": "app" }
|
|
54
|
+
],
|
|
55
|
+
"commentsCount": 1,
|
|
56
|
+
"reactions": 2,
|
|
57
|
+
"updatedAt": "2026-06-01T01:00:00Z"
|
|
58
|
+
},
|
|
59
|
+
{
|
|
60
|
+
"number": 99999,
|
|
61
|
+
"title": "Add a fun launch animation",
|
|
62
|
+
"body": "This is a cosmetic request with no evidence of a failed agent run.",
|
|
63
|
+
"url": "https://github.com/openai/codex/issues/99999",
|
|
64
|
+
"labels": [
|
|
65
|
+
{ "name": "enhancement" }
|
|
66
|
+
],
|
|
67
|
+
"commentsCount": 0,
|
|
68
|
+
"reactions": 0,
|
|
69
|
+
"updatedAt": "2026-05-01T00:00:00Z"
|
|
70
|
+
}
|
|
71
|
+
]
|
package/llms.txt
CHANGED
|
@@ -102,6 +102,7 @@ npx trace-to-skill plugin-audit ~/.codex --app /Applications/Codex.app --format
|
|
|
102
102
|
npx trace-to-skill diagnostics-bundle ~/.codex --output codex-diagnostics
|
|
103
103
|
npx trace-to-skill usage-evidence ./usage-notes.md --output usage-evidence.md
|
|
104
104
|
npx trace-to-skill process-audit ./process-notes.md --output process-audit.md
|
|
105
|
+
npx trace-to-skill issue-map codex-issues.json --output codex-issue-map.md
|
|
105
106
|
npx trace-to-skill checkpoint . --output .trace-to-skill/checkpoints/before-codex
|
|
106
107
|
npx trace-to-skill redact ./runs --output redacted-runs
|
|
107
108
|
npx trace-to-skill sensitive-audit . --format json
|
|
@@ -119,7 +120,7 @@ npx trace-to-skill init --comment --sarif
|
|
|
119
120
|
## GitHub Action
|
|
120
121
|
|
|
121
122
|
```yaml
|
|
122
|
-
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.
|
|
123
|
+
- uses: grnbtqdbyx-create/trace-to-skill@v0.1.85
|
|
123
124
|
with:
|
|
124
125
|
mode: all
|
|
125
126
|
doctor-threshold: "85"
|