docs: document OpenHands Cloud Automations in AGENTS.md by all-hands-bot · Pull Request #3333 · OpenHands/software-agent-sdk

all-hands-bot · 2026-05-20T17:28:07Z

Summary

Documents the three OpenHands Cloud Automations that are now active on this repository for event-driven PR review, so agents working in this repo know what automated review is in place and how it's triggered.

Changes

Adds a bullet to the ## Repository Memory section of AGENTS.md listing the three active automation triggers:
1. OHCloudReview label added
2. Draft PR marked ready for review (pull_request.ready_for_review)
3. all-hands-bot requested as reviewer (pull_request.review_requested)

This PR is also a live test of trigger #2 — converting from draft to ready for review should fire the pr-review automation.

This PR was created by an AI agent (OpenHands) on behalf of the user.

Agent Server images for this PR

• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server

Variants & Base Images

Variant	Architectures	Base Image	Docs / Tags
java	amd64, arm64	`eclipse-temurin:17-jdk`	Link
python	amd64, arm64	`nikolaik/python-nodejs:python3.13-nodejs22-slim`	Link
golang	amd64, arm64	`golang:1.21-bookworm`	Link

Pull (multi-arch manifest)

# Each variant is a multi-arch manifest supporting both amd64 and arm64
docker pull ghcr.io/openhands/agent-server:ea02def-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-ea02def-python \
  ghcr.io/openhands/agent-server:ea02def-python

All tags pushed for this build

ghcr.io/openhands/agent-server:ea02def-golang-amd64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-golang-amd64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-golang-amd64
ghcr.io/openhands/agent-server:ea02def-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:ea02def-golang-arm64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-golang-arm64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-golang-arm64
ghcr.io/openhands/agent-server:ea02def-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:ea02def-java-amd64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-java-amd64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-java-amd64
ghcr.io/openhands/agent-server:ea02def-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:ea02def-java-arm64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-java-arm64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-java-arm64
ghcr.io/openhands/agent-server:ea02def-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:ea02def-python-amd64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-python-amd64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-python-amd64
ghcr.io/openhands/agent-server:ea02def-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-slim-amd64
ghcr.io/openhands/agent-server:ea02def-python-arm64
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-python-arm64
ghcr.io/openhands/agent-server:doc-document-openhands-automations-python-arm64
ghcr.io/openhands/agent-server:ea02def-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-slim-arm64
ghcr.io/openhands/agent-server:ea02def-golang
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-golang
ghcr.io/openhands/agent-server:doc-document-openhands-automations-golang
ghcr.io/openhands/agent-server:ea02def-golang_tag_1.21-bookworm
ghcr.io/openhands/agent-server:ea02def-java
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-java
ghcr.io/openhands/agent-server:doc-document-openhands-automations-java
ghcr.io/openhands/agent-server:ea02def-eclipse-temurin_tag_17-jdk
ghcr.io/openhands/agent-server:ea02def-python
ghcr.io/openhands/agent-server:ea02def4e0326a32a76c2f395511f14e2969b5db-python
ghcr.io/openhands/agent-server:doc-document-openhands-automations-python
ghcr.io/openhands/agent-server:ea02def-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-slim

About Multi-Architecture Support

Each variant tag (e.g., ea02def-python) is a multi-arch manifest supporting both amd64 and arm64
Docker automatically pulls the correct architecture for your platform
Individual architecture tags (e.g., ea02def-python-amd64) are also available if needed

Three event-driven automations are now active on this repo using the pr-review plugin: OHCloudReview label, ready_for_review, and review_requested from all-hands-bot. Co-authored-by: openhands <openhands@all-hands.dev>

github-actions · 2026-05-20T17:28:41Z

REST API breakage checks (OpenAPI) — ✅ PASSED

Result: ✅ PASSED

Action log

github-actions · 2026-05-20T17:29:05Z

Python API breakage checks — ✅ PASSED

Result: ✅ PASSED

Behavioral default changes detected

These public Field(default=...) changes were auto-marked with the release-note-required label:

openhands.sdk.llm.llm.LLM.model: 'claude-sonnet-4-20250514' → 'gpt-5.5'

Action log

all-hands-bot

Clean, useful addition to AGENTS.md — this gives agents the context they need to understand the active PR review automations. One clarity issue on the item count worth addressing before merging.

This review was generated by an AI agent (OpenHands) on behalf of the user via OpenHands Automation.

all-hands-bot · 2026-05-20T17:35:03Z

 - AgentSkills progressive disclosure goes through `AgentContext.get_system_message_suffix()` into `<available_skills>`, and `openhands.sdk.context.skills.to_prompt()` truncates each prompt description to 1024 characters because the AgentSkills specification caps `description` at 1-1024 characters.
 - Workspace-wide uv resolver guardrails belong in the repository root `[tool.uv]` table. When `exclude-newer` is configured there, `uv lock` persists it into the root `uv.lock` `[options]` section as both an absolute cutoff and `exclude-newer-span`, and `uv sync --frozen` continues to use that locked workspace state.
 - `pr-review-by-openhands` delegates to `OpenHands/extensions/plugins/pr-review@main`. Repo-specific reviewer instructions live in `.agents/skills/custom-codereview-guide.md`, and because task-trigger matching is substring-based, that `/codereview` skill is also auto-injected for the workflow's `/codereview-roasted` prompt.
+- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):


🟡 Suggestion: The lead-in says "Three OpenHands Cloud Automations" but only two numbered items follow. According to the PR description, triggers #2 (pull_request.ready_for_review) and #3 (pull_request.review_requested) are distinct automations that have been collapsed into a single item #2 here.

Either split them into two separate numbered entries (matching the count), or change the wording to reflect the actual automation count:

Suggested change

- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):

- Two OpenHands Cloud Automations (three trigger events) are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):

Alternatively, if these truly are three separate registered automations, expand to three numbered items so agents reading this file have an accurate mental model.

all-hands-bot

⚠️ QA Report: PASS WITH ISSUES

AGENTS.md now exposes the OpenHands Cloud automation guidance and it renders through GitHub Markdown, but the rendered list is ambiguous about the claimed three automations/triggers.

Does this PR achieve its stated goal?

Partially. The PR does add the automation guidance to AGENTS.md: the baseline origin/main copy did not contain the automation note, while the PR head contains the OHCloudReview, pull_request.labeled, pull_request.ready_for_review, pull_request.review_requested, and all-hands-bot details. GitHub also shows an all-hands-bot review on this PR, which is consistent with the documented pr-review automation behavior. However, the rendered documentation says “Three OpenHands Cloud Automations” but displays only two numbered entries, so a real reader cannot tell whether there are three automations, two automations, or three trigger events.

Phase	Result
Environment Setup	✅ Checked out PR head `ea02def4` and used GitHub/API tooling already available in the workspace; no test suite or lint commands run.
CI Status	🟡 Many checks are green, but at observation time `qa-changes`, several `Build & Push` jobs, Windows binary build, and `coverage-report` were still in progress/queued.
Functional Verification	⚠️ Documentation is present and GitHub-renders, but the visible list structure has a count/clarity issue.

Functional Verification

Test 1: AGENTS.md guidance availability before vs after the PR

Step 1 — Establish baseline without the PR:
Ran a script comparing origin/main:AGENTS.md and HEAD:AGENTS.md for the automation guidance:

Baseline automation guidance present: False
PR automation guidance present: True

This confirms the baseline repository guidance did not include the OpenHands Cloud automation note.

Step 2 — Apply the PR's changes:
The workspace was already checked out at PR head ea02def4e0326a32a76c2f395511f14e2969b5db on doc/document-openhands-automations.

Step 3 — Re-run with the PR in place:
The same verification against HEAD:AGENTS.md found every user-facing detail from the PR goal:

Three OpenHands Cloud Automations are active: FOUND
OHCloudReview label: FOUND
pull_request.labeled: FOUND
Ready for review or review requested: FOUND
pull_request.ready_for_review: FOUND
pull_request.review_requested: FOUND
all-hands-bot: FOUND

This shows the PR adds the intended automation trigger/account details to the repository guidance consumed by future agents.

Test 2: GitHub Markdown rendering of the changed block

Step 1 — Baseline:
The changed block is absent from origin/main, so there is no rendered automation guidance for users/agents to read there.

Step 2 — Apply the PR's changes:
Rendered the new AGENTS.md automation block through GitHub's Markdown API using GFM mode.

Step 3 — Rendered result with the PR in place:

<ul dir="auto">
<li>Three OpenHands Cloud Automations are active ...
<ol dir="auto">
<li><strong>OHCloudReview label</strong> ... <code>pull_request.labeled</code></li>
<li><strong>Ready for review or review requested</strong> ... <code>pull_request.ready_for_review</code> or <code>pull_request.review_requested</code></li>

The content renders successfully and preserves the important trigger names, but the rendered ordered list has two entries under text claiming three automations/triggers, which creates the QA issue below.

Test 3: GitHub-visible automation outcome on this PR

Queried PR reviews via the GitHub API and found:

user: all-hands-bot
state: COMMENTED
submitted_at: 2026-05-20T17:35:03Z
body: Clean, useful addition to AGENTS.md — this gives agents the context they need...

This confirms a GitHub-visible all-hands-bot review occurred on this PR, matching the documented reviewer account and pr-review automation behavior.

Unable to Verify

I could not inspect the actual OpenHands Cloud automation configuration because no OpenHands Cloud automation API credential was provided in this QA environment. I verified the repository-visible behavior instead: the AGENTS.md guidance is present/rendered, and GitHub shows an all-hands-bot review on this PR.

Issues Found

🟡 Minor: The rendered AGENTS.md block says “Three OpenHands Cloud Automations” but presents only two numbered items, combining ready_for_review and review_requested into one entry. That undercuts the stated goal of clearly documenting the three active triggers/automations.

This review was created by an AI agent (OpenHands) on behalf of the user.

all-hands-bot · 2026-05-20T17:36:22Z

+- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):
+  1. **OHCloudReview label** — fires when the `OHCloudReview` label is added to a PR (`pull_request.labeled`)
+  2. **Ready for review or review requested** — fires when a draft PR is marked ready for review, or when `all-hands-bot` is requested as a reviewer (`pull_request.ready_for_review` or `pull_request.review_requested`)


🟡 Minor: Exercising the docs as rendered by GitHub shows this sentence claims there are three OpenHands Cloud Automations, but the ordered list below has only two entries because pull_request.ready_for_review and pull_request.review_requested are combined. Since the PR goal is to document the three active triggers/automations, please either split these into three numbered entries or reword the intro to make clear that there are two automation entries covering three trigger events.

all-hands-bot

🟡 Taste Rating: Acceptable — docs-only change, but the existing unresolved clarity issue still needs attention: the text says three automations while the rendered ordered list has only two items because ready_for_review and review_requested are combined. No additional issues found.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26468295102

all-hands-bot

The addition is a useful contribution to AGENTS.md — documenting active automations gives future agents the context they need to understand what automated review is already in place.

Already flagged (still unresolved): Two prior reviews have noted that the intro says "Three OpenHands Cloud Automations" but only two numbered items follow. That should be addressed before merging.

New finding: There is a label name discrepancy worth investigating — see inline comment.

This review was generated by an AI agent (OpenHands) on behalf of the user via OpenHands Automation.

all-hands-bot · 2026-05-26T18:51:12Z

 - Workspace-wide uv resolver guardrails belong in the repository root `[tool.uv]` table. When `exclude-newer` is configured there, `uv lock` persists it into the root `uv.lock` `[options]` section as both an absolute cutoff and `exclude-newer-span`, and `uv sync --frozen` continues to use that locked workspace state.
 - `pr-review-by-openhands` delegates to `OpenHands/extensions/plugins/pr-review@main`. Repo-specific reviewer instructions live in `.agents/skills/custom-codereview-guide.md`, and because task-trigger matching is substring-based, that `/codereview` skill is also auto-injected for the workflow's `/codereview-roasted` prompt.
+- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):
+  1. **OHCloudReview label** — fires when the `OHCloudReview` label is added to a PR (`pull_request.labeled`)


🟠 Important: The label documented here is OHCloudReview, but the webhook event that triggered this very review shows the PR was labeled with review-this (visible in the automation event payload). These names don't match.

Possible explanations:

The label name was changed from OHCloudReview to review-this and the docs weren't updated

A separate, undocumented automation fires on review-this in addition to the documented OHCloudReview automation

Please verify the actual label name configured in the OpenHands Cloud Automation trigger and update the docs to reflect the correct label (or add a note if multiple label triggers exist).

all-hands-bot

🟡 Acceptable docs-only change, but I’m leaving this as a comment because the existing unresolved threads still need resolution: the text says three automations while the rendered list has two entries, and the documented OHCloudReview label should be reconciled with the observed review-this trigger. I found no additional issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update; risk is documentation accuracy only.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26468765065

all-hands-bot · 2026-05-26T18:59:04Z

✅ Review complete. · View session

all-hands-bot

🟡 Acceptable — docs-only change, but two existing unresolved accuracy issues should be addressed before merging.

Summary

This PR adds four lines to AGENTS.md documenting the active OpenHands Cloud Automations for PR review. The intention is sound: agents working in this repo need to know that automated review fires and under what conditions. The addition is in the right place and follows the file's established style.

Existing Issues (already flagged — not duplicating inline threads)

Three unresolved inline threads already cover the following, so I'm not re-filing inline comments. They remain blocking for documentation accuracy:

1. Count mismatch (lines 117–119): The intro reads "Three OpenHands Cloud Automations" but only two numbered items follow. The PR description correctly lists three distinct triggers (pull_request.labeled, pull_request.ready_for_review, pull_request.review_requested), but items 2 and 3 were collapsed into a single entry. Fix: either split into three numbered items, or change the intro to "two automation entries covering three trigger events".

2. Label name discrepancy (line 118): The documented trigger label is OHCloudReview, but the webhook event that fired this very review carries the label review-this. Prior reviews have already flagged this with live evidence from the automation event payload. Before merging, verify the actual label name in the automation config and update the docs accordingly — agents reading AGENTS.md will use this to reason about when automated review fires.

No new issues found

No new problems were identified beyond what existing reviews have already flagged. The change is minimal, low-risk, and structurally correct — it just needs the two accuracy fixes above.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update; no code, tests, or runtime behavior is affected. Risk is documentation accuracy only.

VERDICT:
❌ Needs rework — Address the count mismatch and confirm the correct label name before merging.

KEY INSIGHT: Getting the trigger label name wrong means future agents reading AGENTS.md will have incorrect expectations about when automated review fires — worth the one-line fix.

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing.

Re-request a review — the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

Was this review helpful? React with 👍 or 👎 to give feedback.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View session

all-hands-bot · 2026-05-26T19:04:42Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

all-hands-bot

🟡 Acceptable docs-only change, but I’m not approving while the existing unresolved accuracy issues remain: the text says three automations while rendering as a two-item list, and the OHCloudReview label still needs reconciliation with the previously observed review-this trigger. I found no new issues in this diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update; risk is inaccurate repo guidance for future agents.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26469082621

all-hands-bot

Documentation-only PR that captures the active Cloud Automation triggers in AGENTS.md. The intent is correct and the plugin reference is useful — two issues worth addressing before this lands.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

all-hands-bot · 2026-05-26T19:06:44Z

 - AgentSkills progressive disclosure goes through `AgentContext.get_system_message_suffix()` into `<available_skills>`, and `openhands.sdk.context.skills.to_prompt()` truncates each prompt description to 1024 characters because the AgentSkills specification caps `description` at 1-1024 characters.
 - Workspace-wide uv resolver guardrails belong in the repository root `[tool.uv]` table. When `exclude-newer` is configured there, `uv lock` persists it into the root `uv.lock` `[options]` section as both an absolute cutoff and `exclude-newer-span`, and `uv sync --frozen` continues to use that locked workspace state.
 - `pr-review-by-openhands` delegates to `OpenHands/extensions/plugins/pr-review@main`. Repo-specific reviewer instructions live in `.agents/skills/custom-codereview-guide.md`, and because task-trigger matching is substring-based, that `/codereview` skill is also auto-injected for the workflow's `/codereview-roasted` prompt.
+- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):


🟠 Important — count mismatch: The lead sentence says "Three OpenHands Cloud Automations" but the numbered list has only two items. Item 2 quietly folds in two separate event triggers (pull_request.ready_for_review and pull_request.review_requested), which is how this mismatch happens. The PR description itself lists all three as distinct entries. Either:

Change "Three" → "Two" (treating the combined item as one logical trigger), or

Split item 2 into two separate numbered items so the count is accurate.

Suggested change

- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):

- Two OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):

all-hands-bot · 2026-05-26T19:06:44Z

 - Workspace-wide uv resolver guardrails belong in the repository root `[tool.uv]` table. When `exclude-newer` is configured there, `uv lock` persists it into the root `uv.lock` `[options]` section as both an absolute cutoff and `exclude-newer-span`, and `uv sync --frozen` continues to use that locked workspace state.
 - `pr-review-by-openhands` delegates to `OpenHands/extensions/plugins/pr-review@main`. Repo-specific reviewer instructions live in `.agents/skills/custom-codereview-guide.md`, and because task-trigger matching is substring-based, that `/codereview` skill is also auto-injected for the workflow's `/codereview-roasted` prompt.
+- Three OpenHands Cloud Automations are active on this repository for event-driven PR review using the `pr-review` plugin (`github:OpenHands/extensions`, `repo_path: plugins/pr-review`):
+  1. **OHCloudReview label** — fires when the `OHCloudReview` label is added to a PR (`pull_request.labeled`)


🟡 Suggestion — verify trigger label name: This documentation says the trigger label is OHCloudReview, but the webhook event that fired this review run carries the label review-this. If the actual automation filter matches review-this (or both labels), the label name here should be corrected or expanded to reflect what is really configured. Worth double-checking the automation definition to confirm the exact filter expression.

all-hands-bot

🟡 Taste Rating: Acceptable — useful docs-only addition, but I’m not approving while the existing unresolved accuracy threads still apply: the text says three automations while the rendered list has two entries, and the OHCloudReview label should be reconciled with the observed review-this trigger. I found no additional issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update; the main risk is inaccurate repo guidance for future agents.

VERDICT:
❌ Needs follow-up: address or explicitly resolve the existing accuracy threads before merging.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26469450743

all-hands-bot

🟡 Acceptable — docs-only change, but I’m not approving while the existing unresolved accuracy threads remain: the text says three automations while the rendered list has two entries, and the OHCloudReview label should be reconciled with the observed review-this trigger. I found no new issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — AGENTS.md documentation-only update; risk is inaccurate repo guidance for future agents.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26469608423

all-hands-bot

🟡 Acceptable docs-only update, but I’m leaving this as a comment because the existing unresolved accuracy threads still need resolution: the “three automations” lead-in renders as only two numbered items, and the documented OHCloudReview label still conflicts with the observed review-this trigger. I found no new issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — documentation-only change; risk is inaccurate repo guidance for future agents.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26469710678

all-hands-bot

🟡 Acceptable — docs-only change, but I’m leaving this as a COMMENT because the existing unresolved accuracy threads still need resolution: the text says three automations while the rendered list has two entries, and the OHCloudReview label discrepancy with the observed review-this trigger remains unresolved. I found no new issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — documentation-only update; the risk is inaccurate repo guidance for future agents.

VERDICT:
❌ Needs rework: Resolve the existing documentation accuracy threads before merging.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26471450913

all-hands-bot · 2026-05-26T19:52:23Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

all-hands-bot

🟡 Acceptable intent, but two accuracy issues need resolution before merge.

This docs-only PR adds automation documentation to AGENTS.md — a worthwhile contribution that gives future agents context about the active review infrastructure. The change is small and scoped correctly. However, two factual inaccuracies in the added text (already called out in multiple existing unresolved review threads) need to be fixed before this is merged.

[CRITICAL ISSUES]

Count mismatch — "Three" vs two numbered items: The lead sentence claims "Three OpenHands Cloud Automations" but the ordered list has only two entries. Item 2 quietly bundles two distinct triggers ( and ) into a single bullet, which is the likely source of the count claim — but that still only yields two numbered entries in the list, not three. Fix: either split Item 2 into two distinct numbered entries (making the count accurate), or change "Three" to "Two" and keep the combined entry.
**Label name unverified — vs **: The documentation states the trigger label is , but the webhook event that triggered this very review shows the PR was labeled . If is the actual automation trigger label, the documentation is wrong at the one concrete fact it is trying to establish. Please verify the correct label name against the live automation configuration (the automation definition on app.all-hands.dev) and update accordingly.

Both issues have had open threads from previous reviews for some time and remain unresolved.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — docs-only change, no code execution impact. That said, incorrect automation documentation actively misleads agents about when reviews will fire, which undermines the entire purpose of the addition.

VERDICT:
❌ Needs rework: Verify the actual trigger label name and reconcile the automation count with the numbered list before merging.

KEY INSIGHT:
The documentation contains two factual errors about its own subject matter — the automation that triggered this review used label , not , and the text claims three automations while listing only two.

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing. See the customization docs for the required frontmatter format.

Re-request a review — the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

Was this review helpful? React with 👍 or 👎 to give feedback.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

all-hands-bot · 2026-05-26T20:05:02Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

all-hands-bot · 2026-05-26T20:05:11Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

all-hands-bot

🟡 Acceptable — docs-only change, but I’m leaving a COMMENT because the existing unresolved accuracy threads still apply: the text says three automations while the rendered list has two items, and the OHCloudReview label still needs reconciliation with the observed trigger discrepancy. I found no new issues in the current diff.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — documentation-only update; risk is inaccurate repo guidance for future agents.

This review was generated by an AI agent (OpenHands) on behalf of the user.

Was this automated review useful? React with 👍 or 👎 to this review to help us measure review quality.
Workflow run: https://github.com/OpenHands/software-agent-sdk/actions/runs/26472096480

all-hands-bot

🟡 Acceptable — docs-only change, but the two existing accuracy issues still need resolution before this lands.

Summary

This PR adds four lines to AGENTS.md documenting the active OpenHands Cloud Automations for event-driven PR review, using the pr-review plugin (github:OpenHands/extensions, repo_path: plugins/pr-review). The intent is correct and useful — giving future agents the context they need to understand what automated review is already in place.

Issues to Fix

Two accuracy problems have been flagged in existing unresolved review threads and remain unaddressed:

1. Count mismatch (existing inline thread on line 117)
The lead sentence claims "Three OpenHands Cloud Automations" but the ordered list has only two items. Item 2 folds pull_request.ready_for_review and pull_request.review_requested into one bullet, which is how the count becomes inconsistent. Fix: either expand to three numbered items (keeping each trigger as its own entry) or change the lead sentence to say "Two OpenHands Cloud Automations" if a single combined entry is the intended design.

2. Label name mismatch (existing inline thread on line 118)
The documentation says the labeled-trigger uses the OHCloudReview label, but the webhook event that triggered this very review run carries the label review-this — not OHCloudReview. One of these is wrong. The author should verify the actual label filter configured in the automation and update the docs to match. If both OHCloudReview and review-this are valid trigger labels, that should be stated explicitly.

What's Good

Placement in AGENTS.md is correct — right after the existing pr-review-by-openhands note.
The plugin reference format (github:OpenHands/extensions, repo_path: plugins/pr-review) is clear and matches the SDK's plugin source syntax.
The attribution note ("Reviews posted by these automations are from the all-hands-bot GitHub account") is a helpful disambiguation for reviewers.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW
Documentation-only change to AGENTS.md. No code paths are modified. No risk of regression or breaking changes. The only risk is documentation inaccuracy, which the two flagged issues represent.

VERDICT:
❌ Not approving yet — the two accuracy issues (count mismatch and label name) must be fixed before merge. Once resolved, this is a straightforward approval.

KEY INSIGHT: The PR is self-referentially inconsistent: the automation that triggered this very review was labeled review-this, yet the docs being added say the trigger label is OHCloudReview — the label name error is immediately verifiable from the event payload.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing. See the customization docs for the required frontmatter format.

Re-request a review - the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

Resolve with AI? Install the iterate skill in your agent and run /iterate to automatically drive this PR through CI, review, and QA until it's merge-ready.

Was this review helpful? React with 👍 or 👎 to give feedback.

all-hands-bot

Review: `docs: document OpenHands Cloud Automations in AGENTS.md`

🟡 Acceptable intent — this docs-only PR correctly captures the active Cloud Automation triggers in AGENTS.md so future agents understand the review automation landscape. The structure is consistent with surrounding entries and the information is genuinely useful.

However, two factual accuracy issues in the added text remain unresolved across all prior review runs and should be fixed before merge:

1. Numerical mismatch — "Three" vs. two numbered items (line 117)
The lead-in states "Three OpenHands Cloud Automations" but the ordered list has only two numbered entries because pull_request.ready_for_review and pull_request.review_requested are folded into a single item 2. Fix by either:

Splitting item 2 into two separate numbered entries to match the stated count of three, or
Changing the count to "Two" with a parenthetical like (covering three trigger events) for clarity

2. Label name discrepancy — OHCloudReview vs. review-this (line 118)
The documented trigger label is OHCloudReview, but the webhook event that triggered this very review run carries the label review-this. These don't match. The docs should reflect the exact label name(s) configured in the automation filter. Please verify the automation definition and update accordingly.

These are factual accuracy issues in a file that agents use as authoritative repository memory — incorrect information here will actively mislead future agents working in this repo.

Both issues have inline comment threads already open on this PR; no new inline comments are added here to avoid duplication.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — documentation-only update; risk is propagating inaccurate agent guidance into repo memory.

VERDICT:
⏸ Comment — fix the two accuracy issues (number count and label name) before merging.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing. See the customization docs for the required frontmatter format.

Re-request a review — the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

When your PR is merged, the guideline file goes through normal code review by repository maintainers.

Resolve with AI? Install the iterate skill in your agent and run /iterate to automatically drive this PR through CI, review, and QA until it's merge-ready.

Was this review helpful? React with 👍 or 👎 to give feedback.

all-hands-bot

Review: `docs: document OpenHands Cloud Automations in AGENTS.md`

🟡 Acceptable intent — this docs-only PR correctly captures the active Cloud Automation triggers in AGENTS.md so future agents understand the review automation landscape. The structure is consistent with surrounding entries and the information is genuinely useful.

However, two factual accuracy issues in the added text remain unresolved across all prior review runs and should be fixed before merge:

1. Numerical mismatch — "Three" vs. two numbered items (line 117)
The lead-in states "Three OpenHands Cloud Automations" but the ordered list has only two numbered entries because pull_request.ready_for_review and pull_request.review_requested are folded into a single item 2. Fix by either:

Splitting item 2 into two separate numbered entries to match the stated count of three, or
Changing the count to "Two" with a parenthetical like (covering three trigger events) for clarity

2. Label name discrepancy — OHCloudReview vs. review-this (line 118)
The documented trigger label is OHCloudReview, but the webhook event that triggered this very review run carries the label review-this. These don't match. The docs should reflect the exact label name(s) configured in the automation filter. Please verify the automation definition and update accordingly.

These are factual accuracy issues in a file that agents use as authoritative repository memory — incorrect information here will actively mislead future agents working in this repo.

Both issues have inline comment threads already open on this PR; no new inline comments are added here to avoid duplication.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW — documentation-only update; risk is propagating inaccurate agent guidance into repo memory.

VERDICT:
⏸ Comment — fix the two accuracy issues (number count and label name) before merging.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing. See the customization docs for the required frontmatter format.

Re-request a review — the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

When your PR is merged, the guideline file goes through normal code review by repository maintainers.

Resolve with AI? Install the iterate skill in your agent and run /iterate to automatically drive this PR through CI, review, and QA until it's merge-ready.

Was this review helpful? React with 👍 or 👎 to give feedback.

docs: document OpenHands Cloud Automations in AGENTS.md

ea02def

Three event-driven automations are now active on this repo using the pr-review plugin: OHCloudReview label, ready_for_review, and review_requested from all-hands-bot. Co-authored-by: openhands <openhands@all-hands.dev>

github-actions Bot added the release-note-required PR requires explicit release-note coverage for behavioral or default changes label May 20, 2026

all-hands-bot marked this pull request as ready for review May 20, 2026 17:32

all-hands-bot commented May 20, 2026

View reviewed changes

all-hands-bot added the review-this This label triggers a PR review by OpenHands label May 26, 2026