fix(pr-review): use list instead of tuple for line_range to fix SDK structured output (#1140)

* fix(pr-review): use list instead of tuple for line_range to fix SDK structured output

The FindingValidationResult.line_range field was using tuple[int, int] which
generates JSON Schema with prefixItems (draft 2020-12 feature). This caused
the Claude Agent SDK to silently fail to capture structured output for
follow-up reviews while returning subtype=success.

Root cause:
- ParallelFollowupResponse schema used prefixItems: True
- ParallelOrchestratorResponse schema used prefixItems: False
- Orchestrator structured output worked; followup didn't

Fix:
- Change line_range from tuple[int, int] to list[int] with min/max length=2
- This generates minItems/maxItems instead of prefixItems
- Schema is now compatible with SDK structured output handling

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(pr-review): only show follow-up when initial review was posted to GitHub

Fixed bug where "Ready for Follow-up" was shown even when the initial
review was never posted to GitHub.

Root cause:
1. Backend set hasCommitsAfterPosting=true when postedAt was null
2. Frontend didn't check if findings were posted before showing follow-up UI

Fixes:
1. Backend (pr-handlers.ts): Return hasCommitsAfterPosting=false when
   postedAt is null - can't be "after posting" if nothing was posted
2. Frontend (ReviewStatusTree.tsx): Add hasPostedFindings check before
   showing follow-up steps (defense-in-depth)

Before: User runs review → doesn't post → new commits → shows "Ready for Follow-up"
After: User runs review → doesn't post → new commits → shows "Pending Post" only

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(ui): use consistent hasPostedFindings check in follow-up logic

Fixed inconsistency where Step 4 only checked postedCount > 0 while Step 3 and previous review checks used postedCount > 0 || reviewResult?.hasPostedFindings. This ensures the follow-up button correctly appears when reviewResult?.hasPostedFindings is true but postedCount is 0 (due to state sync timing issues).

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

apps/backend/runners/github/services/pydantic_models.py

@@ -611,8 +611,10 @@ class FindingValidationResult(BaseModel):
             "This is the proof that determines the validation status."
         ),
     )
-    line_range: tuple[int, int] = Field(
-        description="Start and end line numbers of the examined code"
+    line_range: list[int] = Field(
+        min_length=2,
+        max_length=2,
+        description="Start and end line numbers of the examined code [start, end]",
     )
     explanation: str = Field(
         min_length=20,

apps/frontend/src/main/ipc-handlers/github/pr-handlers.ts

@@ -2102,8 +2102,9 @@ export function registerPRHandlers(getMainWindow: () => BrowserWindow | null): v
               hasCommitsAfterPosting,
             });
           } else if (!postedAt) {
-            // If findings haven't been posted yet, any new commits should trigger follow-up
-            hasCommitsAfterPosting = true;
+            // If findings haven't been posted yet, we can't determine "after posting"
+            // Follow-up should only be available after initial review is posted to GitHub
+            hasCommitsAfterPosting = false;
           }
 
           return {

apps/frontend/src/renderer/components/github-prs/components/ReviewStatusTree.tsx

@@ -178,9 +178,10 @@ export function ReviewStatusTree({
       });
     }
 
-    // Step 4: Follow-up (only show when not currently reviewing AND commits happened after posting)
-    // This prevents showing follow-up prompts for commits that were made during/before the review
-    if (!isReviewing && newCommitsCheck?.hasNewCommits && newCommitsCheck?.hasCommitsAfterPosting) {
+    // Step 4: Follow-up (only show when findings were POSTED and new commits happened after posting)
+    // This prevents showing follow-up prompts when initial review was never posted to GitHub
+    const hasPostedFindings = postedCount > 0 || reviewResult?.hasPostedFindings;
+    if (!isReviewing && hasPostedFindings && newCommitsCheck?.hasNewCommits && newCommitsCheck?.hasCommitsAfterPosting) {
       steps.push({
         id: 'new_commits',
         label: t('prReview.newCommits', { count: newCommitsCheck.newCommitCount }),