"Yes, and manually approve edits" was restoring getPrePlanMode() which
could be YOLO, contradicting the label. Now hardcodes DEFAULT to match
the "manually approve" semantics.
Align with observed provider prompt-cache TTL (~5 min). Add
`context.gapThresholdMinutes` setting so users can tune the threshold
for providers with different cache TTLs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
LLM was putting all findings in the review body (creating a summary
comment) instead of the comments array (inline comments). Added
prominent warning: "Findings go in comments array, NOT in body."
Also: "Do NOT use COMMENT when there are Critical findings."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the two-phase posting (individual gh api comments + separate
gh pr review verdict) with a single Create Review API call that bundles
inline comments + verdict together — same approach as Copilot Code Review.
Benefits:
- No summary comment needed (inline comments ARE the review)
- No "two-phase posting" complexity
- No "STOP for Comment verdict" rules
- No duplicate/orphaned reviews
- One API call instead of N+1
- Verdict (approve/request_changes/comment) correctly attached
Eliminates ~40 lines of complex posting rules replaced by ~30 lines
of straightforward JSON construction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three issues found from real /review output on PR #2921:
1. Critical findings but verdict submitted as --comment instead of
--request-changes. Added explicit: "Do NOT use --comment when
verdict is Request changes — this loses the blocking status."
2. Nice to have findings appeared in PR summary. Added: "Do NOT
include Nice to have findings" to all summary rules.
3. Clarified that failed-inline summary should only contain
Critical/Suggestion, never Nice to have.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two issues found from real review (PR #2826):
1. Multiple /review runs on same PR create duplicate comments. Now
Step 9 checks for existing "via Qwen Code /review" comments
before posting and warns the user about potential duplicates.
2. Comments posted without line numbers appear as orphaned PR
comments. Now enforced: every inline comment MUST reference a
specific line in the diff. Findings that can't be mapped to
diff lines go in the summary instead.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaced 5 numbered rules + example with example-first format.
LLMs pattern-match from examples better than parsing rules.
Rules condensed to 2 sentences after the example.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Inline comments now use ```suggestion blocks when the fix is a direct
line replacement. PR authors can accept fixes with one click instead
of manually copying code. Falls back to regular code blocks when the
fix spans multiple locations.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Logic errors causing incorrect behavior (wrong return values, skipped
code paths) were being classified as Suggestion instead of Critical.
Added explicit examples: "if code does something wrong, it's Critical
— not Suggestion."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three issues found in real review output:
1. Summary repeated findings already posted as inline comments
2. "Review Stats" (agent count, raw/confirmed) is internal noise
3. Summary was too verbose
Fix: partial-failure summary must contain ONLY the failed findings.
Distinguish terminal output (stats OK) from PR comments (no stats).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
GitHub renders #1, #2 as links to issues/PRs with those numbers.
Review summaries using "#1 (logic error)" link to the wrong target.
Added guideline: use (1), [1], or descriptive references instead.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Review comments, findings, and summaries must use the same language
as the PR (title/description/code comments). English PR → English
review. Chinese PR → Chinese review. No language switching.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
LLM was writing detailed analysis in the review summary body despite
"minimal body" instruction. Strengthened to "one-line body only, do
NOT include analysis/findings/explanations" with concrete examples.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add getDefaultPermission() override to GrepToolInvocation in ripGrep.ts
to match the behavior of grep.ts, returning "ask" for paths outside
the workspace and "allow" for workspace-internal paths.
Also pass allowExternalPaths: true to resolveAndValidatePath in both
the execute() and validateToolParamValues() methods, so external paths
are not rejected at the validation layer (permission is deferred to
getDefaultPermission as designed).
Fixes issue where grep searches in arbitrary workspace paths would
fail with "Path is not within workspace" even when the user intended
to search external directories.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
When PR review finds no issues and --comment was not specified, suggest
"post comments" so the user can formally approve the PR on GitHub.
Without this, the LGTM only appears in terminal — no approval status
on the PR.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Loading cached findings from a Markdown report is fragile (unstructured
prose, LLM might misparse). Instead, when --comment is specified on an
unchanged PR, simply run the full review. The user explicitly wants
comments posted — spending 7 LLM calls is acceptable.
Removed reportPath from cache schema (no longer needed).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When --comment is used on an unchanged PR, Step 9 needs prior findings
to post. Cache now stores reportPath pointing to the saved report from
Step 10, allowing findings to be loaded without re-running the review.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
LLM was ignoring the {{model}} template and writing its own footer
("— Qwen Code /review" instead of "— glm-5.1 via Qwen Code /review").
Added explicit warning: footer must appear EXACTLY as shown, do NOT
shorten or rephrase.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The function only checked for string-form type inside anyOf/oneOf variants,
missing the array form (e.g., type: ["array", "null"]). This mirrors the
handling already done at the top-level property schema.
Previously: fetch → create worktree → incremental check → "no changes"
→ delete worktree (wasted time creating it).
Now: fetch → incremental check (via git rev-parse on fetched ref) →
if no changes, delete ref and stop (no worktree ever created).
Worktree only created when review will actually proceed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Step 9 --comment guard blocked "post comments" follow-up path.
Fixed: allow entry via either --comment flag OR follow-up request.
2. Cross-repo gh pr review needs -R {owner}/{repo}. Added note.
3. "post comments" tip shown even when --comment already set (double
posting risk). Fixed: tip only shown when --comment NOT specified.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
LLM ignored the "do not submit summary for Comment verdict" rule
despite it being written. Restructured: warning emoji + STOP instruction
first, then the exception cases. The default is "don't post", not
"decide whether to post."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: LLM was calling gh pr review for each inline comment
instead of using gh api for comments and gh pr review once for the
verdict. Added explicit "Two-phase posting" instruction: complete ALL
inline comments (gh api) first, THEN submit verdict (gh pr review)
ONCE. Do NOT call gh pr review per comment.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Commands were hardcoded as ./mvnw and ./gradlew despite text saying
"prefer wrapper if exists, else mvn/gradle". Changed to explicit
conditional: "use ./mvnw if it exists, otherwise mvn" with {mvn}
placeholder in examples. Applied to Step 3 and Agent 5.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two rejected alternatives added from real debugging:
1. Verbose agent prompts → exceed output token budget → serial fallback
2. Relaxed "try 3+2" instruction → model always takes the fallback
Key constraint: each agent prompt ≤200 words for all 5 to fit in
one response and launch in parallel.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each agent prompt must be under 200 words. With 5 verbose prompts,
the total output exceeds the model's output token limit, forcing
serial execution. Shorter prompts = all 5 fit in one response =
parallel execution.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Cross-repo lightweight mode has no local codebase — Agent 5 (build/test)
is pointless. Now launches 4 agents instead of 5 in cross-repo mode.
Updated token count tables in SKILL.md, user doc, and DESIGN.md:
same-repo = 7 LLM calls, cross-repo = 6.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The relaxed "if you cannot fit 5, try 3+2" gave the model a fallback
that it always took (serial execution). Restored strict requirement:
MUST include all 5 tool calls in one response. The runtime confirms
concurrent agent execution is supported.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The strict "all 5 in one response" requirement may exceed the model's
output token limit. Changed to: prefer all 5 in one response, but
allow splitting (e.g., 3+2) as long as agents launch without waiting
for previous ones to finish. Runtime confirms parallel execution is
supported (coreToolScheduler tests).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. When verdict is Comment and SOME inline comments fail, submit
a summary with the failed findings (not lost). Only skip summary
when ALL inline comments succeed.
2. Accept *italic* for model attribution in prose — prettier
normalizes _italic_ to *italic* in markdown, both render the same.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Many repos rely on wrappers and don't require global Maven/Gradle
installed. Now prefers ./mvnw over mvn and ./gradlew over gradle
in both Step 3 (linter) and Agent 5 (build/test).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Step 11: conditional worktree removal — skip if Step 8 flagged
preservation (autofix commit/push failure)
2. Standardize model attribution to _italic_ (was mixed *italic*)
3. Cache stores pre-autofix headRefOid (not worktree HEAD which may
include the autofix commit)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Previously, rule 7 (CI config auto-discovery) only ran for "unrecognized
projects." Java/Makefile (e.g., OpenJDK) and C/C++/Makefile matched
earlier rules that said "skip," so CI config was never read.
Now: language-specific rules 1-6 run first for known tools, then rule 7
runs for ALL projects to discover additional CI-defined checks. OpenJDK
will now discover jcheck and custom targets from .github/workflows/*.yml.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Step 9 code block: annotate Comment template applies only when
no inline comments were posted (avoids LLM confusion)
2. Step 11: fix stale rationale — Step 9 uses API calls, not worktree
3. Verdict: explicitly based on high-confidence findings only —
low-confidence findings don't influence PR approval status
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When verdict is "Comment" and inline comments were posted successfully,
do NOT submit an additional gh pr review — the inline comments are
sufficient. Only submit summary for Approve/Request changes (which
carry approval status) or when no inline comments were posted.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Each inline PR comment now includes model attribution footer
(e.g., "— qwen3-coder") so reviewers know which model produced
each comment.
2. When inline comments are posted successfully, the review summary
is minimal (verdict + model only, no repeated findings). Full
summary is only used when no inline comments were posted.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- User doc: added "Other" row to language table + explanation that
CI config is read for unrecognized projects
- DESIGN.md: added "Why auto-discover from CI config" decision
section + added .qwen/review-tools.md to rejected alternatives
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
For projects that don't match standard tool patterns (e.g., OpenJDK),
Step 3 and Agent 5 now read CI configuration files (.github/workflows,
.gitlab-ci.yml, Jenkinsfile, Makefile) to discover what lint/build/test
commands the project uses. No user configuration needed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
