This is an automated email from the ASF dual-hosted git repository.
zclllyybb pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 88991dc3386 [improvement](ci) Refine Codex review goal completion
prompt (#64658)
88991dc3386 is described below
commit 88991dc3386452818f5dcde44025c839882f0bde
Author: zclllyybb <[email protected]>
AuthorDate: Mon Jun 22 09:45:40 2026 +0800
[improvement](ci) Refine Codex review goal completion prompt (#64658)
### What problem does this PR solve?
Problem Summary: I modified the codex to support the `codex exec --goal`
mode. The Codex review workflow now enters goal mode through the
runner's --goal invocation, so the review instructions should describe
the completion criteria and convergence process instead of telling the
model to create the goal itself.
see modification in
https://github.com/zclllyybb/codex/tree/codex-exec-goal
Verification:
- Before:
https://github.com/apache/doris/pull/63690 got 1 comment when `/review`
- Now:
https://github.com/zclllyybb/doris/pull/49 replicated the same PR,
receiving 8 comments in a single `/review`
---
.claude/skills/code-review/SKILL.md | 10 ++-
.github/workflows/code-review-runner.yml | 135 +++++++++++++++++++++++++++++--
2 files changed, 137 insertions(+), 8 deletions(-)
diff --git a/.claude/skills/code-review/SKILL.md
b/.claude/skills/code-review/SKILL.md
index 539e36224d9..dea95615b8a 100644
--- a/.claude/skills/code-review/SKILL.md
+++ b/.claude/skills/code-review/SKILL.md
@@ -14,9 +14,13 @@ Use this when you need to review code, whether it is code
you just completed or
## How to use me
-1. **Always read and respond to Part 1** (General Principles) — it applies to
all code.
-2. For module-specific review, **read the `AGENTS.md` in the corresponding
source directory** listed in Part 2. Those files contain non-obvious
conventions and traps specific to each subsystem.
-3. Parts 3–7 cover cross-module concerns, testing, high-risk patterns,
functions, and standards — refer as needed.
+0. **MANDATORY GOAL COMPLETION REQUIREMENT:** When the review is running in
Codex goal mode, the goal is complete only after every changed file and
relevant surrounding code path has been examined, every suspicious point has
been accepted as an inline issue or dismissed with evidence, and every accepted
issue has been submitted and verified on GitHub.
+1. **MANDATORY GOAL PROCESS REQUIREMENT:** The goal's progress tracking must
cover instruction loading, subagent spawning, shared-ledger maintenance,
candidate verification/deduplication, final subagent convergence, GitHub review
submission, and GitHub API verification. The goal is not complete until every
live subagent has said `NO_NEW_VALUABLE_FINDINGS` for the same current
ledger/comment set after the last candidate update.
+2. **MANDATORY SUBAGENT REVIEW REQUIREMENT:** Use the available subagent or
multi-agent spawn tool for focused review passes; do not merely simulate
subagent output. The main agent must read the subagent results, independently
verify or dismiss every candidate with concrete code evidence, deduplicate
against existing review threads, submit the final GitHub review itself, and
summarize the subagent conclusions.
+3. **MANDATORY SHARED LEDGER REQUIREMENT:** When a shared subagent review
ledger is provided, every subagent must read the whole ledger and append
findings only to its assigned subagent section. The main agent must use the
ledger as the source of truth for merging, status updates, duplicate
suppression, proposed final comments, and the final convergence round.
Subagents must not edit another subagent section or any main-owned section;
this section-owned append-only rule avoids concurrent [...]
+4. **Always read and respond to Part 1** (General Principles) — it applies to
all code.
+5. For module-specific review, **read the `AGENTS.md` in the corresponding
source directory** listed in Part 2. Those files contain non-obvious
conventions and traps specific to each subsystem.
+6. Parts 3–7 cover cross-module concerns, testing, high-risk patterns,
functions, and standards — refer as needed.
---
diff --git a/.github/workflows/code-review-runner.yml
b/.github/workflows/code-review-runner.yml
index f7f299bbf7f..c6bcced9774 100644
--- a/.github/workflows/code-review-runner.yml
+++ b/.github/workflows/code-review-runner.yml
@@ -73,6 +73,32 @@ jobs:
unzip -q "$tmp_dir/ossutil.zip" -d "$tmp_dir"
sudo install -m 0755 "$tmp_dir/ossutil-v1.7.19-linux-amd64/ossutil"
/usr/local/bin/ossutil
+ - name: Install Codex goal binary
+ run: |
+ codex_cmd="$(command -v codex)"
+ codex_target="$(readlink -f "$codex_cmd")"
+ tmp_dir="$(mktemp -d)"
+ trap 'rm -rf "$tmp_dir"' EXIT
+
+ downloaded=false
+ for object in "$OSS_CODEX_GOAL_OBJECT"
"$OSS_CODEX_GOAL_FALLBACK_OBJECT"; do
+ if ossutil -i "$OSS_AK" -k "$OSS_SK" -e "$OSS_ENDPOINT" cp -f
"$object" "$tmp_dir/codex-goal"; then
+ downloaded=true
+ break
+ fi
+ done
+ test "$downloaded" = "true"
+ test -s "$tmp_dir/codex-goal"
+ sudo install -m 0755 "$tmp_dir/codex-goal" "$codex_target"
+ "$codex_cmd" exec --help | grep -q -- '--goal'
+ "$codex_cmd" --version
+ env:
+ OSS_AK: ${{ secrets.OSS_AK }}
+ OSS_SK: ${{ secrets.OSS_SK }}
+ OSS_ENDPOINT: oss-cn-hongkong.aliyuncs.com
+ OSS_CODEX_GOAL_OBJECT: oss://doris-community-ci/codex-goal
+ OSS_CODEX_GOAL_FALLBACK_OBJECT:
oss://doris-community-ci/codex/codex-goal
+
- name: Configure Codex auth
run: |
install -m 700 -d "$RUNNER_TEMP/codex-home"
@@ -241,6 +267,8 @@ jobs:
- name: Prepare review prompt
run: |
cat > "$REVIEW_CONTEXT_DIR/review_prompt.txt" <<'PROMPT'
+ This review task is executed in Codex goal mode. The review goal is
complete only after every changed file and relevant surrounding code path has
been examined, every suspicious point has a clear conclusion, and there is no
remaining possibility of producing any new valuable review comment.
+
You are performing an automated code review inside a GitHub Actions
runner. The gh CLI is available and authenticated via GH_TOKEN.
The current directory is the code repository for the PR to be
reviewed.
You MUST NOT attempt to access any files outside the current
directory. and you DO NOT need to. But this does not prevent you from normally
using any skill or web fetch tools.
@@ -257,8 +285,29 @@ jobs:
- User review focus: PLACEHOLDER_CONTEXT_DIR/review_focus.txt
- PR changed files: PLACEHOLDER_CONTEXT_DIR/pr_changed_files.txt
- Required AGENTS.md files:
PLACEHOLDER_CONTEXT_DIR/required_agents.txt
+ - Shared subagent review ledger:
PLACEHOLDER_CONTEXT_DIR/subagent_review_findings.md
Before reviewing any code, you MUST read and follow the code review
skill in this repository. During review, you must strictly follow those
instructions.
+ The active review goal's progress tracking MUST include, and must
stay current throughout the review:
+ - Read the review prompt, code-review skill, required AGENTS.md
files, existing review threads, user focus, changed-file list, and the shared
subagent review ledger.
+ - Spawn the required focused subagents and assign each subagent a
dedicated section in the shared ledger before it reviews.
+ - Require every subagent to append only to its assigned ledger
section, while reading the whole ledger to avoid duplicate candidates.
+ - Read the shared ledger after every subagent result, then
independently verify, deduplicate, accept, or dismiss every candidate in the
main merged section.
+ - Run at least one final convergence round where every live subagent
reviews the current ledger and proposed final comment set.
+ - Continue reviewing if any subagent reports a new valuable
candidate during convergence; repeat verification and convergence until every
subagent says `NO_NEW_VALUABLE_FINDINGS` for the same current ledger/comment
set.
+ - Submit the final GitHub review and verify that all accepted
comments landed before marking the goal complete.
+ The active review goal MUST remain incomplete until every suspicious
point found during review has a clear conclusion: submitted as an inline issue,
dismissed as already covered by existing review context, or dismissed with
concrete code evidence explaining why it is not a bug.
+ You MUST use the available subagent or multi-agent spawn tool for
this review; do not merely simulate subagent output in your own text. If tool
discovery is needed, search for the subagent/multi-agent tool first. Spawn at
least two subagents before final submission:
+ - one subagent assigned to the `optimizer-rewrite` ledger section
and focused on optimizer/rewrite correctness, semantic equivalence, and
parallel join/aggregate paths.
+ - one subagent assigned to the `tests-session-config` ledger section
and focused on regression tests, expected outputs, session/config propagation,
compatibility, and basic CI/style failures.
+ The shared subagent review ledger is
PLACEHOLDER_CONTEXT_DIR/subagent_review_findings.md. Before spawning any
subagent, the main agent MUST read this ledger. Every subagent prompt MUST
include this ledger path and the exact ledger section assigned to that
subagent. Subagents must read the whole ledger before reviewing, avoid
duplicating existing candidates, and append their findings only under their
assigned subagent section. They must not rewrite the whole ledger, edit another
[...]
+ Each subagent must record candidate findings in its own ledger
section with stable IDs, path/line, claim, evidence, duplicate relationship if
any, and recommendation. If a candidate overlaps an existing ledger item, the
subagent should add a duplicate note in its own section that references the
existing candidate ID instead of modifying the existing candidate. This
section-owned append-only rule is mandatory to avoid concurrent patch conflicts.
+ The main agent must read the shared ledger after each subagent
result, merge duplicate candidates into the main merged section, update
candidate statuses, and keep a proposed final comment set in the main-owned
ledger sections. Statuses must distinguish at least: proposed_by_subagent,
accepted_for_inline_comment, dismissed_with_evidence,
duplicate_of_existing_thread, duplicate_of_candidate, and needs_more_evidence.
+ Before final submission, the main agent MUST send the current ledger
and proposed final comment set to every live subagent and require a convergence
response. A subagent may either append a new valuable candidate under its
assigned section or reply exactly `NO_NEW_VALUABLE_FINDINGS` for the current
ledger/comment set. The main agent MUST NOT complete the goal, final summary,
or GitHub review until every live subagent has returned
`NO_NEW_VALUABLE_FINDINGS` in the same convergen [...]
+ Subagents must only report candidate findings with evidence. The
main agent must read their results and the shared ledger, independently verify
or dismiss every candidate with concrete code evidence, deduplicate against
existing review threads, and submit the final GitHub review itself. The final
summary must include a short "Subagent conclusions" section describing which
subagent candidates became inline comments, which were dismissed, which
duplicates were merged, and which c [...]
+ If and only if the runtime exposes no subagent or multi-agent tool
after explicit discovery, state that limitation in the final summary and
continue the review manually.
+ You MUST NOT stop after finding the first blocking issue. Keep
reviewing changed files, related control flow, tests, and parallel/special-case
paths until all plausible correctness, lifecycle, configuration, compatibility,
performance, and coverage bugs have been investigated and every bug you can
substantiate has been reported.
+ Before submitting the final review, do one explicit final sweep over
the changed-file list and your unresolved candidate list. Only finish when
there are no unresolved suspicious points and all possible substantiated bugs
have been pointed out in the GitHub review.
Before inspecting the PR diff or related code, you MUST read the
contents of every AGENTS.md file listed below. These paths are computed from
the PR changed file ancestors in this checkout. Searching for or listing paths
is not sufficient; read each listed file directly.
Required AGENTS.md files for this PR:
PLACEHOLDER_REQUIRED_AGENTS_BLOCK
@@ -297,6 +346,82 @@ jobs:
required_agents = required_agents_path.read_text().rstrip()
prompt_path.write_text(prompt.replace("PLACEHOLDER_REQUIRED_AGENTS_BLOCK",
required_agents))
PY
+
+ cat > "$REVIEW_CONTEXT_DIR/subagent_review_findings.md" <<'LEDGER'
+ # Shared Subagent Review Ledger
+
+ This is the shared source of truth for subagent-assisted review.
+
+ Rules:
+ - Subagents must read this whole file before reviewing.
+ - Each subagent may append only to its assigned section under
`Subagent Candidate Sections`.
+ - Subagents must not rewrite this file, edit another subagent
section, edit main-owned sections, edit repository source files, or submit
GitHub comments.
+ - Avoid duplicates. If a candidate overlaps an existing candidate,
add a duplicate note in your own section that references the existing candidate
ID.
+ - The main agent owns final status, final deduplication, GitHub
review submission, and GitHub API verification.
+ - The goal is not complete until all live subagents have reviewed
the current ledger and proposed final comment set in the same convergence round
and replied `NO_NEW_VALUABLE_FINDINGS`.
+
+ Candidate statuses:
+ - proposed_by_subagent
+ - accepted_for_inline_comment
+ - dismissed_with_evidence
+ - duplicate_of_existing_thread
+ - duplicate_of_candidate
+ - needs_more_evidence
+
+ Candidate format:
+
+ - ID:
+ Owner:
+ Status:
+ Path:
+ Line:
+ Claim:
+ Evidence:
+ Duplicate relationship:
+ Recommendation:
+
+ ## Subagent Candidate Sections
+
+ ### optimizer-rewrite
+
+ Subagent assignment: optimizer/rewrite correctness, semantic
equivalence, and parallel join/aggregate paths.
+ Append only below this line and above the next subagent heading.
+
+ ### tests-session-config
+
+ Subagent assignment: regression tests, expected outputs,
session/config propagation, compatibility, and basic CI/style failures.
+ Append only below this line and above the main-owned sections.
+
+ ## Main Merged Findings
+
+ Main-owned format:
+
+ - ID:
+ Source IDs:
+ Owner: main
+ Status:
+ Path:
+ Line:
+ Claim:
+ Evidence:
+ Duplicate relationship:
+ Main verification:
+ Proposed inline body:
+
+ ## Dismissed Or Duplicate Points
+
+ ## Proposed Final Comment Set
+
+ ## Convergence Rounds
+ LEDGER
+
+ cat > "$REVIEW_CONTEXT_DIR/codex_goal_prompt.txt" <<EOF
+ You are performing an automated code review inside a GitHub Actions
runner.
+ This invocation is already running in Codex goal mode. Before
inspecting the PR diff or related code, read
${REVIEW_CONTEXT_REL}/review_prompt.txt verbatim and follow that file as the
complete review instruction set.
+ This review must use the available subagent or multi-agent spawn
tool for focused review passes. All subagents and the main agent must maintain
${REVIEW_CONTEXT_REL}/subagent_review_findings.md as the shared source of
truth. Each subagent may append only to its assigned ledger section; the main
agent owns merged statuses, duplicate suppression, proposed final comments,
GitHub review submission, and GitHub API verification.
+ The review goal's completion process must include shared-ledger
review, subagent spawning with assigned ledger sections, candidate
verification, duplicate merge, a final subagent convergence round, GitHub
review submission, and GitHub API verification. Do not complete the goal unless
every live subagent has replied NO_NEW_VALUABLE_FINDINGS for the same current
ledger/comment set after the last candidate update.
+ Keep reviewing until every suspicious point has a clear conclusion,
every substantiated issue has been submitted as a GitHub inline review comment,
and no new valuable review comment remains possible.
+ EOF
env:
REPO: ${{ github.repository }}
PR_NUMBER: ${{ inputs.pr_number }}
@@ -314,13 +439,13 @@ jobs:
PR_NUMBER: ${{ inputs.pr_number }}
HEAD_SHA: ${{ inputs.head_sha }}
run: |
- PROMPT=$(cat "$REVIEW_CONTEXT_DIR/review_prompt.txt")
+ GOAL_PROMPT="$(cat "$REVIEW_CONTEXT_DIR/codex_goal_prompt.txt")"
review_started_at="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
set +e
# GitHub-hosted runners are ephemeral. Avoid workspace-write here
because
# Codex uses bubblewrap for that mode and uid maps can be
unavailable.
- codex exec "$PROMPT" \
+ codex exec --goal "$GOAL_PROMPT" \
--cd "$GITHUB_WORKSPACE" \
--model "gpt-5.5" \
--config "model_reasoning_effort=\"${REASONING_EFFORT}\"" \
@@ -398,8 +523,8 @@ jobs:
HELPER_REF: ${{ github.workflow_sha || github.sha }}
REASONING_EFFORT: xhigh
run: |
- if [ ! -s "$REVIEW_CONTEXT_DIR/review_prompt.txt" ] || [ ! -s
"$REVIEW_CONTEXT_DIR/codex-events.jsonl" ]; then
- echo "Review prompt or Codex JSONL event stream is missing;
skipping Litefuse I/O recording."
+ if [ ! -s "$REVIEW_CONTEXT_DIR/codex_goal_prompt.txt" ] || [ ! -s
"$REVIEW_CONTEXT_DIR/codex-events.jsonl" ]; then
+ echo "Goal prompt or Codex JSONL event stream is missing; skipping
Litefuse I/O recording."
exit 0
fi
@@ -411,7 +536,7 @@ jobs:
chmod 700 "$helper"
python3 "$helper" \
- --input-file "$REVIEW_CONTEXT_DIR/review_prompt.txt" \
+ --input-file "$REVIEW_CONTEXT_DIR/codex_goal_prompt.txt" \
--events-file "$REVIEW_CONTEXT_DIR/codex-events.jsonl" \
--output-file "$REVIEW_CONTEXT_DIR/codex-final-message.txt" \
--trace-name "doris-ai-review" \
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
