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>
Rename the subcommand to accurately reflect its behavior (exits plan
mode and restores previous approval mode, does not trigger execution).
Update source, tests, i18n keys (6 locales), and docs.
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>
Most Qwen OAuth users don't have a fast model configured for this
feature, so it fires a wasted API request on every turn with no
visible benefit. Default to off; users can opt in via settings.
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>
User doc and PR description now include the "PR review, zero findings
→ post comments → approve PR" row in the follow-up actions table.
Also fixed PR description: "Step 4" → "Step 9" for post comments.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.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>
The iLink Bot API requires these headers for session authentication.
Without them, getupdates returns errcode -14 (session timeout).
The protocol version (2.0.0) is tracked independently from our channel
version, matching the current official plugin's API compatibility level.
Closes#2908
Same class of Windows CI timing flake — the backspace keypress
doesn't propagate through the paste/keypress pipeline fast enough
on slow runners, so replaceRangeByOffset is never called (0 calls).
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 test has a stale closure race condition: the 50ms wait between
pressing '2' and Enter may not be enough for React/Ink to re-render
and re-subscribe the useKeypress callback with the updated
selectedIndex, causing it to read the default value (0) instead of
the expected value (1) on slow CI runners (Windows + Node 20).
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.
Remove core dependency from webui by inlining followup controller logic.
This fixes nightly release CI failure where npm version couldn't resolve
the core peer dependency for prerelease versions.
- Move FollowupState type and INITIAL_FOLLOWUP_STATE to src/types/followup.ts
- Inline createFollowupController into src/hooks/useFollowupSuggestions.ts
- Remove separate @qwen-code/webui/followup subpath and vite config
- Export useFollowupSuggestions from main entry
Fixes#2900
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
The vsce package was causing ESM module resolution errors when building
locally due to a dependency cycle between ansi-regex (ESM-only in v6)
and strip-ansi (CommonJS) pulled in by @textlint/linter-formatter.
CI already installs vsce globally before packaging, so this change
aligns local builds with CI behavior. Developers should install vsce
globally: npm install -g @vscode/vsce
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
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>
The broad CODEOWNERS wildcard was adding notification noise without
providing meaningful ownership boundaries. Removing it so that any
team member with write access can provide approving reviews.
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>
