Adding an Automated Daily Status Workflow#18
Conversation
|
|
📝 WalkthroughWalkthroughThis PR introduces a new daily repository status GitHub Actions workflow, significantly expands TTL (Time to Live) developer documentation, and removes TiSpark-related documentation and references across the repository, reflecting a shift in the HTAP strategy to focus on TiFlash instead. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1d1c195cf6
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| startup_timeout_sec = 120 | ||
| tool_timeout_sec = 60 | ||
| container = "ghcr.io/github/github-mcp-server:v0.31.0" | ||
| env = { "GITHUB_PERSONAL_ACCESS_TOKEN" = "$GH_AW_GITHUB_TOKEN", "GITHUB_READ_ONLY" = "1", "GITHUB_TOOLSETS" = "context,repos,issues,pull_requests" } |
There was a problem hiding this comment.
The mcp_servers.github config injects GITHUB_PERSONAL_ACCESS_TOKEN from $GH_AW_GITHUB_TOKEN, but this job only exports GITHUB_MCP_SERVER_TOKEN and never defines GH_AW_GITHUB_TOKEN, so the GitHub MCP server is launched unauthenticated. In private repositories this prevents data access entirely, and in public repositories it can still cause incomplete reports due to strict unauthenticated rate limits.
Useful? React with 👍 / 👎.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
ecosystem-tool-user-guide.md (1)
9-9:⚠️ Potential issue | 🟡 MinorStale TiSpark reference remains in the introductory paragraph.
Line 9 still mentions "在 TiKV 上运行 Spark SQL", which describes TiSpark — the section that was just removed. The intro now advertises a capability that has no corresponding section or link in the document.
✏️ Proposed fix
-TiDB 提供了丰富的工具，可以帮助你进行部署运维、数据管理（例如，数据迁移、备份恢复、数据校验）、在 TiKV 上运行 Spark SQL。请根据需要选择适用的工具。 +TiDB 提供了丰富的工具，可以帮助你进行部署运维、数据管理（例如，数据迁移、备份恢复、数据校验）。请根据需要选择适用的工具。🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@ecosystem-tool-user-guide.md` at line 9, The intro still advertises "在 TiKV 上运行 Spark SQL" (TiSpark) but the TiSpark section/link was removed; update the introductory sentence in ecosystem-tool-user-guide.md to either remove that phrase or replace it with a current supported capability (e.g., remove "在 TiKV 上运行 Spark SQL" or replace with "在 TiKV 上运行分析查询" and link to the appropriate section), ensuring the intro matches the document's remaining sections and links.
♻️ Duplicate comments (2)
.github/workflows/daily-repo-status.lock.yml (2)
1010-1019: Runner label already flagged.
This job also usesubuntu-slim; please see the earlier runner-label comment.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/daily-repo-status.lock.yml around lines 1010 - 1019, The workflow job safe_outputs is using the already-flagged runner label ubuntu-slim; update the job definition for safe_outputs to use the approved runner label (or the same label used by the other jobs) instead of ubuntu-slim by editing the runs-on value for the safe_outputs job so it matches the project's allowed runner label convention.
814-824: Runner label already flagged.
This job also usesubuntu-slim; please see the earlier runner-label comment.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/daily-repo-status.lock.yml around lines 814 - 824, The 'conclusion' job currently sets runs-on: ubuntu-slim, which duplicates the earlier incorrect runner label; update the runs-on value in the conclusion job to the approved runner label used in the earlier comment (make it consistent across the workflow), and search for any other occurrences of 'ubuntu-slim' in this workflow to replace them with the same approved runner label so all jobs use the consistent runner.
🧹 Nitpick comments (1)
explore-htap.md (1)
66-66: Polish wording: add “地” for adverbial usage.Consider “明显地加速效果” → “明显地加速效果” (or “产生明显的加速效果”) for smoother grammar.
✍️ Suggested edit
- - 如果业务场景以 OLTP 为主，做轻量级的 Ad hoc OLAP 计算，通常部署 1 个或几个 TiFlash 节点就会产生明显的加速效果。 + - 如果业务场景以 OLTP 为主，做轻量级的 Ad hoc OLAP 计算，通常部署 1 个或几个 TiFlash 节点就会产生明显的加速效果。🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@explore-htap.md` at line 66, Summary: wording needs an adverbial form for smoother Chinese. Locate the sentence containing "TiFlash 节点就会产生明显的加速效果" and change the phrase to use the adverbial "明显地" (e.g., "通常部署 1 个或几个 TiFlash 节点就会明显地加速 OLAP 查询。" or rephrase to "通常部署 1 个或几个 TiFlash 节点就会产生明显的加速效果。") so the grammar reads smoothly; update the sentence in the same paragraph accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/daily-repo-status.md:
- Around line 8-31: The workflow frontmatter incorrectly uses a nested "on:"
with "schedule: daily" and "workflow_dispatch:"; replace that block with the
shorthand "on: daily" (i.e., remove the nested "schedule" and
"workflow_dispatch" keys) so the top-level "on" key uses the shorthand form;
update the YAML where the "on", "schedule", and "workflow_dispatch" keys appear
to use "on: daily" while keeping the rest of the document (e.g., "network:
defaults", "tools", "safe-outputs") unchanged.
In `@ai/integrations/vector-search-integration-overview.md`:
- Around line 45-50: Two Markdown table rows are missing the trailing pipe which
can break rendering: update the rows containing "Python | SQLAlchemy | `pip
install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy]" and "Python | Django | `pip
install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM]" to append a final
'|' at the end of each line so every table row ends with a trailing pipe and the
table is consistent.
In `@br/backup-and-restore-overview.md`:
- Around line 150-151: In the backup-and-restore overview text replace the typo
"目标序规则" with the correct phrase "目标排序规则" wherever it appears (specifically in
the sentence inside the second bullet explaining --sys-check-collation
behavior); update the phrase so the sentence reads that BR verifies system table
data compatibility under the "目标排序规则" of the target cluster.
In `@develop/dev-guide-connection-parameters.md`:
- Around line 39-40:
将文中“常见的连接池库通常提供参数”这句存在副词堆叠的问题改为更通顺的表述，例如将其替换为“常见的连接池库一般提供参数”或“通常有参数可用”；在开发文档段落中查找并替换该原句（即包含“连接池库”和“提供参数”的那一句）并确保句子语义和前后文衔接自然即可。
In `@telemetry.md`:
- Line 23: Replace the incorrect privacy-policy URL
"https://pingkai.cn/legal/privacy-policy" with PingCAP's canonical privacy
policy URL "https://pingcap.com/privacy-policy/" in telemetry.md; update both
occurrences (the string "https://pingkai.cn/legal/privacy-policy" referenced
around the text "在**任何情况**下，集群中用户存储的数据都**不会**被收集。" and the second occurrence
near line 68) so both links point to the correct domain.
---
Outside diff comments:
In `@ecosystem-tool-user-guide.md`:
- Line 9: The intro still advertises "在 TiKV 上运行 Spark SQL" (TiSpark) but the
TiSpark section/link was removed; update the introductory sentence in
ecosystem-tool-user-guide.md to either remove that phrase or replace it with a
current supported capability (e.g., remove "在 TiKV 上运行 Spark SQL" or replace
with "在 TiKV 上运行分析查询" and link to the appropriate section), ensuring the intro
matches the document's remaining sections and links.
---
Duplicate comments:
In @.github/workflows/daily-repo-status.lock.yml:
- Around line 1010-1019: The workflow job safe_outputs is using the
already-flagged runner label ubuntu-slim; update the job definition for
safe_outputs to use the approved runner label (or the same label used by the
other jobs) instead of ubuntu-slim by editing the runs-on value for the
safe_outputs job so it matches the project's allowed runner label convention.
- Around line 814-824: The 'conclusion' job currently sets runs-on: ubuntu-slim,
which duplicates the earlier incorrect runner label; update the runs-on value in
the conclusion job to the approved runner label used in the earlier comment
(make it consistent across the workflow), and search for any other occurrences
of 'ubuntu-slim' in this workflow to replace them with the same approved runner
label so all jobs use the consistent runner.
---
Nitpick comments:
In `@explore-htap.md`:
- Line 66: Summary: wording needs an adverbial form for smoother Chinese. Locate
the sentence containing "TiFlash 节点就会产生明显的加速效果" and change the phrase to use the
adverbial "明显地" (e.g., "通常部署 1 个或几个 TiFlash 节点就会明显地加速 OLAP 查询。" or rephrase to
"通常部署 1 个或几个 TiFlash 节点就会产生明显的加速效果。") so the grammar reads smoothly; update the
sentence in the same paragraph accordingly.
ℹ️ Review info
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (31)
.gitattributes.github/aw/actions-lock.json.github/workflows/daily-repo-status.lock.yml.github/workflows/daily-repo-status.md.lycheeignoreTOC-develop.mdTOC-pingkai.mdTOC.mdai/integrations/vector-search-integration-overview.mdbest-practices/readonly-nodes.mdbr/backup-and-restore-overview.mdcredits.mddashboard/dashboard-slow-query.mddevelop/_index.mddevelop/dev-guide-connection-parameters.mddevelop/dev-guide-delete-data.mddevelop/dev-guide-sample-application-java-jdbc.mddevelop/dev-guide-time-to-live.mdecosystem-tool-user-guide.mdexplore-htap.mdproduction-deployment-using-tiup.mdreleases/release-5.4.0.mdreleases/release-6.6.0.mdtelemetry.mdtiflash/tiflash-overview.mdtiflash/use-tispark-to-read-tiflash.mdtime-to-live.mdtispark-deployment-topology.mdtispark-overview.mdtiup/tiup-cluster-topology-reference.mdtiup/tiup-cluster.md
💤 Files with no reviewable changes (7)
- tiup/tiup-cluster.md
- tispark-deployment-topology.md
- credits.md
- tiflash/use-tispark-to-read-tiflash.md
- tispark-overview.md
- production-deployment-using-tiup.md
- tiup/tiup-cluster-topology-reference.md
| on: | ||
| schedule: daily | ||
| workflow_dispatch: | ||
|
|
||
| permissions: | ||
| contents: read | ||
| issues: read | ||
| pull-requests: read | ||
|
|
||
| network: defaults | ||
|
|
||
| tools: | ||
| github: | ||
| # If in a public repo, setting `lockdown: false` allows | ||
| # reading issues, pull requests and comments from 3rd-parties | ||
| # If in a private repo this has no particular effect. | ||
| lockdown: false | ||
|
|
||
| safe-outputs: | ||
| create-issue: | ||
| title-prefix: "[repo-status] " | ||
| labels: [report, daily-status] | ||
| source: githubnext/agentics/workflows/daily-repo-status.md@b0e9cfd3a20372ce7fe0462bb7bbca2272df4a88 | ||
| engine: codex |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
githubnext agentics workflow schema schedule daily network defaults
💡 Result:
Schedule / daily (GitHub Next Agentic Workflows / gh-aw)
- Recommended “fuzzy” schedule syntax:
on: daily(orweekly,weekly on monday, etc.) runs at a scattered time to avoid load spikes; the scatter is deterministic based on the workflow file path (so it stays consistent per workflow). [1] - Shorthand:
on: dailyexpands to a normal GitHub Actionson.scheduleplusworkflow_dispatch(manual run). [2] - You can also use full cron (fixed times), but the docs note the compiler will warn about schedules that create load spikes and suggest fuzzy alternatives. [2]
Network defaults (what “defaults” means, and what happens if you omit network)
- Network permissions are controlled via frontmatter
network:and an allowlist concept (optionally enforced by the Agent Workflow Firewall / AWF). [3] - Behavior of
network.allowedhandling in the compiler:- If
networkis not set (nil): it falls back to default ecosystem domains for backwards compatibility. [4] - If
network: defaults(ornetwork: { allowed: [defaults] }): it allows the default ecosystem domains (“basic infrastructure”). [4] - If
network: {}ornetwork: { allowed: [] }: it’s deny-all (no network access). [4] - If
network.allowedincludes multiple ecosystems/domains (e.g.,defaults,python,node,example.com): the compiler expands ecosystem identifiers into domain lists and merges/dedupes them. [4]
- If
- The “defaults” ecosystem is described as basic infrastructure (e.g., certificates / JSON schema / OS package mirrors). [3]
Sources: Scheduled workflow examples and syntax [1][2]; network/AWF architecture and configuration [3]; compiler/network default behaviors and ecosystem expansion [4].
Fix the schedule syntax from nested schedule: daily to the shorthand on: daily.
The Agentic workflow schema uses shorthand syntax on: daily (which expands to both schedule and workflow_dispatch), not nested schedule: daily under on:. Update the frontmatter to use on: daily instead of the nested structure. The network: defaults configuration is correct.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/workflows/daily-repo-status.md around lines 8 - 31, The workflow
frontmatter incorrectly uses a nested "on:" with "schedule: daily" and
"workflow_dispatch:"; replace that block with the shorthand "on: daily" (i.e.,
remove the nested "schedule" and "workflow_dispatch" keys) so the top-level "on"
key uses the shorthand form; update the YAML where the "on", "schedule", and
"workflow_dispatch" keys appear to use "on: daily" while keeping the rest of the
document (e.g., "network: defaults", "tools", "safe-outputs") unchanged.
| | 语言 | ORM/客户端 | 安装说明 | 教程 | | ||
| |----------|--------------------|-----------------------------------|----------| | ||
| | Python | TiDB Vector Client | `pip install tidb-vector[client]` | [使用 Python 开始向量搜索](/ai/quickstart-via-python.md) | | ||
| | Python | SQLAlchemy | `pip install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy](/ai/integrations/vector-search-integrate-with-sqlalchemy.md) | ||
| | Python | peewee | `pip install tidb-vector` | [集成 TiDB 向量搜索与 peewee](/ai/integrations/vector-search-integrate-with-peewee.md) | | ||
| | Python | Django | `pip install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM](/ai/integrations/vector-search-integrate-with-django-orm.md) No newline at end of file |
There was a problem hiding this comment.
Fix Markdown table row delimiters to avoid rendering issues.
Rows at Line 48 and Line 50 are missing the trailing |, which can break table rendering in some Markdown engines. Please add trailing pipes for consistency.
🔧 Suggested fix
-| Python | SQLAlchemy | `pip install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy](/ai/integrations/vector-search-integrate-with-sqlalchemy.md)
+| Python | SQLAlchemy | `pip install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy](/ai/integrations/vector-search-integrate-with-sqlalchemy.md) |
-| Python | Django | `pip install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM](/ai/integrations/vector-search-integrate-with-django-orm.md)
+| Python | Django | `pip install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM](/ai/integrations/vector-search-integrate-with-django-orm.md) |📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| | 语言 | ORM/客户端 | 安装说明 | 教程 | | |
| |----------|--------------------|-----------------------------------|----------| | |
| | Python | TiDB Vector Client | `pip install tidb-vector[client]` | [使用 Python 开始向量搜索](/ai/quickstart-via-python.md) | | |
| | Python | SQLAlchemy | `pip install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy](/ai/integrations/vector-search-integrate-with-sqlalchemy.md) | |
| | Python | peewee | `pip install tidb-vector` | [集成 TiDB 向量搜索与 peewee](/ai/integrations/vector-search-integrate-with-peewee.md) | | |
| | Python | Django | `pip install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM](/ai/integrations/vector-search-integrate-with-django-orm.md) | |
| | 语言 | ORM/客户端 | 安装说明 | 教程 | | |
| |----------|--------------------|-----------------------------------|----------| | |
| | Python | TiDB Vector Client | `pip install tidb-vector[client]` | [使用 Python 开始向量搜索](/ai/quickstart-via-python.md) | | |
| | Python | SQLAlchemy | `pip install tidb-vector` | [集成 TiDB 向量搜索与 SQLAlchemy](/ai/integrations/vector-search-integrate-with-sqlalchemy.md) | | |
| | Python | peewee | `pip install tidb-vector` | [集成 TiDB 向量搜索与 peewee](/ai/integrations/vector-search-integrate-with-peewee.md) | | |
| | Python | Django | `pip install django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM](/ai/integrations/vector-search-integrate-with-django-orm.md) | |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ai/integrations/vector-search-integration-overview.md` around lines 45 - 50,
Two Markdown table rows are missing the trailing pipe which can break rendering:
update the rows containing "Python | SQLAlchemy | `pip install tidb-vector` |
[集成 TiDB 向量搜索与 SQLAlchemy]" and "Python | Django | `pip install
django-tidb[vector]` | [将 TiDB 向量搜索集成到 Django ORM]" to append a final '|' at the
end of each line so every table row ends with a trailing pipe and the table is
consistent.
| > - 已知问题：从 v7.2.0 开始，新建集群的部分系统表字段变为大小写不敏感。然而，对于从 v7.2.0 之前的版本**在线升级**到 v7.2.0 及以上版本的集群，对应的系统表字段仍然大小写敏感。如果在这两类集群之间进行包含系统表的备份和恢复操作，可能会失败。详情参见 [Issue #43717](https://github.com/pingcap/tidb/issues/43717)。 | ||
| > - 从 v8.5.5 起，BR 在恢复系统表时支持通过参数 `--sys-check-collation` 检查排序规则 (Collation) 兼容性。在恢复过程中，BR 会验证系统表数据在目标集群排序规则下是否存在大小写冲突。如果数据在目标序规则下兼容，则可以成功恢复旧版本备份。否则，BR 会报错并终止恢复。 |
There was a problem hiding this comment.
Fix typo: “目标序规则” → “目标排序规则”.
This reads like a typo and may confuse readers.
✍️ Suggested edit
-否则，BR 会报错并终止恢复。
+否则，BR 会报错并终止恢复。🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@br/backup-and-restore-overview.md` around lines 150 - 151, In the
backup-and-restore overview text replace the typo "目标序规则" with the correct
phrase "目标排序规则" wherever it appears (specifically in the sentence inside the
second bullet explaining --sys-check-collation behavior); update the phrase so
the sentence reads that BR verifies system table data compatibility under the
"目标排序规则" of the target cluster.
| 常见的连接池库通常提供参数，用于控制连接的最长存活时间。 | ||
|
|
There was a problem hiding this comment.
修正文案中的副词用法以避免语病。
“常见的连接池库通常提供参数”可调整为更通顺的表达（如“常见的连接池库一般提供参数”或“通常有参数可用”）。
✏️ 建议修改
-常见的连接池库通常提供参数，用于控制连接的最长存活时间。
+常见的连接池库一般提供参数，用于控制连接的最长存活时间。📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| 常见的连接池库通常提供参数，用于控制连接的最长存活时间。 | |
| 常见的连接池库一般提供参数，用于控制连接的最长存活时间。 |
🧰 Tools
🪛 LanguageTool
[uncategorized] ~39-~39: 动词的修饰一般为‘形容词（副词）+地+动词’。您的意思是否是：常见"地"连接
Context: ...问题，对于长期保持的数据库连接，建议每天至少主动关闭并重新建立一次连接。 常见的连接池库通常提供参数，用于控制连接的最长存活时间。 <...
(wb4)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@develop/dev-guide-connection-parameters.md` around lines 39 - 40,
将文中“常见的连接池库通常提供参数”这句存在副词堆叠的问题改为更通顺的表述，例如将其替换为“常见的连接池库一般提供参数”或“通常有参数可用”；在开发文档段落中查找并替换该原句（即包含“连接池库”和“提供参数”的那一句）并确保句子语义和前后文衔接自然即可。
|
|
||
| > **注意：** | ||
| > | ||
| > 在**任何情况**下，集群中用户存储的数据都**不会**被收集。另请参阅[隐私政策](https://pingkai.cn/legal/privacy-policy)。 |
There was a problem hiding this comment.
Broken privacy-policy URL: pingkai.cn should be pingcap.cn.
Both occurrences link to https://pingkai.cn/legal/privacy-policy, but PingCAP's official domain is pingcap.com / pingcap.cn. https://pingcap.com/privacy-policy/ is the canonical URL used in PingCAP's own terms of service. pingkai.cn is a misspelling that sends readers to a non-PingCAP domain.
🐛 Proposed fix (apply to both line 23 and line 68)
-可参阅[隐私政策](https://pingkai.cn/legal/privacy-policy)
+可参阅[隐私政策](https://pingcap.cn/legal/privacy-policy)Also applies to: 68-68
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@telemetry.md` at line 23, Replace the incorrect privacy-policy URL
"https://pingkai.cn/legal/privacy-policy" with PingCAP's canonical privacy
policy URL "https://pingcap.com/privacy-policy/" in telemetry.md; update both
occurrences (the string "https://pingkai.cn/legal/privacy-policy" referenced
around the text "在**任何情况**下，集群中用户存储的数据都**不会**被收集。" and the second occurrence
near line 68) so both links point to the correct domain.
qiancai
force-pushed
the
codex/adding-automated-daily-status-workflow
branch
from
13e3f31 to
ee53362
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ee53362dc9
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| startup_timeout_sec = 120 | ||
| tool_timeout_sec = 60 | ||
| container = "ghcr.io/github/github-mcp-server:v0.31.0" | ||
| env = { "GITHUB_PERSONAL_ACCESS_TOKEN" = "$GH_AW_GITHUB_TOKEN", "GITHUB_READ_ONLY" = "1", "GITHUB_TOOLSETS" = "context,repos,issues,pull_requests" } |
There was a problem hiding this comment.
In Start MCP Gateway, the TOML config for mcp_servers.github sets GITHUB_PERSONAL_ACCESS_TOKEN to $GH_AW_GITHUB_TOKEN, but this step only exports GITHUB_MCP_SERVER_TOKEN (line 591) and never defines GH_AW_GITHUB_TOKEN. That leaves the GitHub MCP server unauthenticated for the Codex run that consumes this config, which can block private-repo access entirely and cause incomplete daily reports in public repos due to strict anonymous rate limits.
Useful? React with 👍 / 👎.
2 participants
Summary
\n- add GitHub Agentic Workflow markdown for daily repo status reporting\n- compile and add the generated lock workflow YAML\n- add gh-aw lock metadata files (.github/aw/actions-lock.json and .gitattributes)\n\n## Notes\n- workflow source: githubnext/agentics/daily-repo-status\n- engine configured: codex
Summary by CodeRabbit
Release Notes
Documentation
Chores