SymbX/systemd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ci: Add automatic review thread resolution to claude-review workflow

Browse Source 
Claude now identifies which existing review comment threads should be
resolved (because the issue was addressed or someone disagreed) and
returns their REST API IDs in a new `resolve` array in the structured
output. The post job uses GraphQL to map comment IDs to threads and
resolve them.

Also switches all GitHub data fetching from MCP tools to `gh api` calls,
since the MCP tool strips comment IDs during its GraphQL-to-minimal
conversion and cannot be used for thread resolution.

The thread resolution GraphQL pagination is wrapped in a try/catch so
that a failure to fetch threads degrades gracefully instead of aborting
the entire post job. Unmatched comment IDs are logged for debuggability.

Adds explicit instructions to complete all data fetching before starting
review and to cancel background tasks before returning structured output,
working around a claude-code-action issue where a late-completing
background task triggers a new conversation turn that overwrites the
structured JSON result.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Daan De Meyer
2026-03-17 18:40:32 +01:00
committed by Daan De Meyer
co-authored by Claude Opus 4.6
parent 55bf0766a1
commit 58246e6408
1 changed files with 129 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/claude-review.yml
+129 -22
View File
@@ -172,6 +172,13 @@ jobs:
}
}
}
},
"resolve": {
"type": "array",
"items": {
"type": "integer"
},
"description": "REST API IDs of existing review comments whose threads should be resolved because the issue was addressed or the author left a disagreeing reply"
}
}
}
@@ -187,18 +194,11 @@ jobs:
--model us.anthropic.claude-opus-4-6-v1
--max-turns 100
--allowedTools "
Read,LS,Grep,Glob,Task,
Read,LS,Grep,Glob,Task,TaskStop,
Bash(cat:*),Bash(test:*),Bash(printf:*),Bash(jq:*),Bash(head:*),Bash(tail:*),
Bash(git:*),Bash(grep:*),Bash(find:*),Bash(ls:*),Bash(wc:*),
Bash(gh:api *),
Bash(diff:*),Bash(sed:*),Bash(awk:*),Bash(sort:*),Bash(uniq:*),
mcp__github__get_pull_request,
mcp__github__get_pull_request_files,
mcp__github__get_pull_request_reviews,
mcp__github__get_pull_request_comments,
mcp__github__get_pull_request_review_comments,
mcp__github__get_pull_request_status,
mcp__github__get_issue_comments,
"
--json-schema '${{ env.REVIEW_SCHEMA }}'
prompt: |
@@ -213,22 +213,27 @@ jobs:
## Phase 1: Gather context
Use the GitHub MCP server tools to fetch PR data. For all tools, pass
owner `${{ github.repository_owner }}`, repo `${{ github.event.repository.name }}`,
and pullNumber/issue_number ${{ needs.setup.outputs.pr_number }}:
- `mcp__github__get_pull_request` to get the PR title, body, and metadata
- `mcp__github__get_pull_request_comments` to get top-level PR comments
- `mcp__github__get_pull_request_reviews` to get PR reviews
Use `gh api` to fetch all PR data. The base path for all endpoints is
`repos/${{ github.repository }}/pulls/${{ needs.setup.outputs.pr_number }}`.
Fetch the list of commits in the PR using:
`gh api repos/{owner}/{repo}/pulls/{number}/commits --paginate --jq '.[].sha'`
**IMPORTANT: All data fetching in this phase MUST complete before moving to
Phase 2. Do NOT use `run_in_background` for any commands in this phase. Wait
for all results before proceeding.**
Also fetch issue comments using `mcp__github__get_issue_comments` with
issue_number ${{ needs.setup.outputs.pr_number }}.
Look for an existing tracking comment (containing `<!-- claude-pr-review -->`)
in the issue comments. If one exists, you will use it as the basis for
your `summary` in Phase 3.
Fetch the following in parallel:
- `gh api repos/${{ github.repository }}/pulls/${{ needs.setup.outputs.pr_number }}`
— PR title, body, and metadata
- `gh api repos/${{ github.repository }}/pulls/${{ needs.setup.outputs.pr_number }}/reviews --paginate`
— PR reviews
- `gh api repos/${{ github.repository }}/pulls/${{ needs.setup.outputs.pr_number }}/commits --paginate --jq '.[].sha'`
— list of commit SHAs
- `gh api repos/${{ github.repository }}/issues/${{ needs.setup.outputs.pr_number }}/comments --paginate`
— issue comments (look for the tracking comment containing `<!-- claude-pr-review -->`;
if one exists, use it as the basis for your `summary` in Phase 3)
- `gh api repos/${{ github.repository }}/pulls/${{ needs.setup.outputs.pr_number }}/comments --paginate`
— inline review comments including each comment's numeric `id`, `path`,
`line`, `body`, `user.login`, and `in_reply_to_id`; you will need the
`id` fields in Phase 3 to populate the `resolve` array
## Phase 2: Per-commit review with subagents
@@ -282,6 +287,15 @@ jobs:
comment if one already exists on the same file and line about the same problem.
Also check for author replies that dismiss or reject a previous comment — do NOT
re-raise an issue the PR author has already responded to disagreeing with.
Populate the `resolve` array with the REST API `id` (integer) of existing
review comments whose threads should be resolved. A thread should be resolved if:
- The issue it raised has been addressed in the current PR (i.e. your review
no longer flags it), OR
- The PR author (or another reviewer) left a reply disagreeing with or
dismissing the comment.
Only include the `id` of the **first** comment in each thread (the one that
started the conversation). Do NOT resolve threads for issues that are still
present and unaddressed.
4. Do NOT prefix `body` with a severity tag — the severity is already
captured in the `severity` field and will be added automatically when
posting inline comments.
@@ -332,6 +346,11 @@ jobs:
## CRITICAL: Return structured JSON output
Before returning structured output, cancel ALL running background tasks
using the TaskStop tool. A background task completing after you return
structured output will trigger a new conversation turn that overwrites your
result and causes the workflow to fail.
Your FINAL action must be to return a JSON object matching the following
JSON schema — do NOT end with a text summary or narrative. The `--json-schema`
flag is set, so your last response must be the structured JSON result, not a
@@ -390,12 +409,15 @@ jobs:
console.log(raw || "(empty)");
let comments = [];
let resolveIds = [];
let summary = "";
if (raw) {
try {
const review = JSON.parse(raw);
if (Array.isArray(review.comments))
comments = review.comments;
if (Array.isArray(review.resolve))
resolveIds = review.resolve;
if (typeof review.summary === "string")
summary = review.summary;
} catch (e) {
@@ -442,6 +464,91 @@ jobs:
else
console.log("No inline comments to post.");
/* Resolve review threads that Claude identified as addressed or dismissed. */
if (resolveIds.length > 0) {
const resolveSet = new Set(resolveIds);
/* Fetch all review threads and map first-comment database IDs to thread IDs. */
let threads = [];
try {
let threadCursor = null;
do {
const threadQuery = `
query($owner: String!, $repo: String!, $number: Int!, $cursor: String) {
repository(owner: $owner, name: $repo) {
pullRequest(number: $number) {
reviewThreads(first: 100, after: $cursor) {
pageInfo { hasNextPage endCursor }
nodes {
id
isResolved
comments(first: 1) {
nodes {
databaseId
}
}
}
}
}
}
}
`;
const threadResult = await github.graphql(threadQuery, { owner, repo, number: prNumber, cursor: threadCursor });
const page = threadResult.repository.pullRequest.reviewThreads;
threads.push(...page.nodes);
threadCursor = page.pageInfo.hasNextPage ? page.pageInfo.endCursor : null;
} while (threadCursor);
} catch (e) {
console.log(`Warning: failed to fetch review threads, skipping resolution: ${e.message}`);
threads = [];
}
let resolved = 0;
let alreadyResolved = 0;
const matchedIds = new Set();
for (const thread of threads) {
const firstCommentId = thread.comments.nodes[0]?.databaseId;
if (!firstCommentId || !resolveSet.has(firstCommentId)) continue;
matchedIds.add(firstCommentId);
if (thread.isResolved) {
alreadyResolved++;
continue;
}
try {
await github.graphql(`
mutation($threadId: ID!) {
resolveReviewThread(input: { threadId: $threadId }) {
thread { id }
}
}
`, { threadId: thread.id });
resolved++;
console.log(` Resolved thread for comment ${firstCommentId}`);
} catch (e) {
console.log(` Warning: failed to resolve thread for comment ${firstCommentId}: ${e.message}`);
}
}
const requested = resolveSet.size;
const unmatched = [...resolveSet].filter(id => !matchedIds.has(id));
if (resolved > 0)
console.log(`Resolved ${resolved}/${requested} review thread(s)${alreadyResolved > 0 ? ` (${alreadyResolved} already resolved)` : ""}.`);
else if (alreadyResolved === requested)
console.log(`All ${requested} review thread(s) were already resolved.`);
else if (alreadyResolved > 0)
console.log(`${alreadyResolved}/${requested} review thread(s) were already resolved; could not resolve the rest — see warnings above.`);
else if (threads.length > 0)
console.log(`Could not resolve any of ${requested} review thread(s) — see warnings above.`);
if (unmatched.length > 0)
console.log(` ${unmatched.length} comment ID(s) not found in any thread: ${unmatched.join(", ")}`);
} else {
console.log("No review threads to resolve.");
}
/* Update the tracking comment with Claude's summary. */
if (!summary)
summary = "Claude review: no issues found :tada:\n\n" + MARKER;