ci(workflows): 🎡 consolidate comment validation into main jobs

Refactors the comment validation strategy across `bot-reply`, `compliance-check`, and `pr-review` workflows to optimize execution and reduce job overhead.

- Merge standalone `validate-comment` jobs into the primary execution jobs.
- Move initial trigger and bot detection logic into job-level `if` conditions.
- Implement conditional execution for subsequent steps based on validation outputs.
- Ensure validation logic (stripping quotes/code blocks) runs within the main context before processing.

Author: Mirrowel

.github/workflows/bot-reply.yml

@@ -5,48 +5,48 @@ on:
     types: [created]
 
 jobs:
-  # ============================================================================
-  # COMMENT VALIDATION JOB
-  # ============================================================================
-  # Validates that the comment:
-  # 1. Was NOT posted by the bot itself (prevents infinite loops)
-  # 2. Contains trigger words in actual content (not in quotes or code blocks)
-  # ============================================================================
-  validate-comment:
+  continuous-reply:
+    # Skip if comment author is a bot (workflow will show as "skipped")
+    if: |
+      github.event.comment.user.login != 'mirrobot' &&
+      github.event.comment.user.login != 'mirrobot-agent' &&
+      github.event.comment.user.login != 'mirrobot-agent[bot]' &&
+      (contains(github.event.comment.body, '@mirrobot') || 
+       contains(github.event.comment.body, '@mirrobot-agent'))
     runs-on: ubuntu-latest
-    outputs:
-      should_proceed: ${{ steps.validate.outputs.should_proceed }}
+    permissions:
+      contents: write
+      issues: write
+      pull-requests: write
+
     env:
+      THREAD_NUMBER: ${{ github.event.issue.number }}
       BOT_NAMES_JSON: '["mirrobot", "mirrobot-agent", "mirrobot-agent[bot]"]'
+      IGNORE_BOT_NAMES_JSON: '["ellipsis-dev"]'
+      COMMENT_FETCH_LIMIT: '20'
+      REVIEW_FETCH_LIMIT: '15'
+      REVIEW_THREAD_FETCH_LIMIT: '20'
+      THREAD_COMMENT_FETCH_LIMIT: '5'
+
     steps:
+      # ========================================================================
+      # COMMENT VALIDATION STEP
+      # ========================================================================
+      # Validates that trigger words are in actual content (not in quotes/code)
+      # If validation fails, all subsequent steps are skipped
+      # ========================================================================
       - name: Validate comment trigger
         id: validate
         env:
           COMMENT_BODY: ${{ github.event.comment.body }}
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
         run: |
           set -e
           
-          echo "Validating comment from: $COMMENT_AUTHOR"
-          
-          # 1. Check if author is a bot
-          BOT_NAMES=("mirrobot" "mirrobot-agent" "mirrobot-agent[bot]")
-          for bot in "${BOT_NAMES[@]}"; do
-            if [[ "$COMMENT_AUTHOR" == "$bot" ]]; then
-              echo "::notice::Comment author is bot ($COMMENT_AUTHOR). Skipping to prevent loops."
-              echo "should_proceed=false" >> $GITHUB_OUTPUT
-              exit 0
-            fi
-          done
-          
-          echo "Author check passed: $COMMENT_AUTHOR is not a bot"
-          
-          # 2. Strip code blocks and quotes from comment body
-          # First, save comment to a temp file for processing
+          # Save comment to temp file for processing
           TEMP_FILE=$(mktemp)
           echo "$COMMENT_BODY" > "$TEMP_FILE"
           
-          # Remove fenced code blocks (```...```) - handles multiline
+          # Remove fenced code blocks (```...```)
           CLEAN_BODY=$(awk '
             /^```/ { in_code = !in_code; next }
             !in_code { print }
@@ -55,7 +55,7 @@ jobs:
           # Remove inline code (`...`)
           CLEAN_BODY=$(echo "$CLEAN_BODY" | sed 's/`[^`]*`//g')
           
-          # Remove quoted lines (lines starting with > at any level, with optional leading whitespace)
+          # Remove quoted lines (lines starting with >)
           CLEAN_BODY=$(echo "$CLEAN_BODY" | grep -v '^[[:space:]]*>' || true)
           
           rm -f "$TEMP_FILE"
@@ -64,40 +64,22 @@ jobs:
           echo "$CLEAN_BODY"
           echo "---"
           
-          # 3. Check for trigger words in clean text
+          # Check for trigger words in clean text
           # Trigger: @mirrobot or @mirrobot-agent
           if echo "$CLEAN_BODY" | grep -qE '@mirrobot(-agent)?'; then
             echo "::notice::Valid trigger found in non-quoted, non-code text."
             echo "should_proceed=true" >> $GITHUB_OUTPUT
           else
-            echo "::notice::Trigger only found in quotes/code blocks or not present. Skipping."
+            echo "::notice::Trigger only found in quotes/code blocks. Skipping."
             echo "should_proceed=false" >> $GITHUB_OUTPUT
           fi
 
-  continuous-reply:
-    needs: [validate-comment]
-    if: needs.validate-comment.outputs.should_proceed == 'true'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      issues: write
-      pull-requests: write
-
-    env:
-      THREAD_NUMBER: ${{ github.event.issue.number }}
-      BOT_NAMES_JSON: '["mirrobot", "mirrobot-agent", "mirrobot-agent[bot]"]'
-      IGNORE_BOT_NAMES_JSON: '["ellipsis-dev"]'
-      COMMENT_FETCH_LIMIT: '20'
-      REVIEW_FETCH_LIMIT: '15'
-      REVIEW_THREAD_FETCH_LIMIT: '20'
-      THREAD_COMMENT_FETCH_LIMIT: '5'
-
-    steps:
-
       - name: Checkout repository
+        if: steps.validate.outputs.should_proceed == 'true'
         uses: actions/checkout@v4
 
       - name: Bot Setup
+        if: steps.validate.outputs.should_proceed == 'true'
         id: setup
         uses: ./.github/actions/bot-setup
         with:
@@ -109,6 +91,7 @@ jobs:
           custom-providers-json: ${{ secrets.CUSTOM_PROVIDERS_JSON }}
 
       - name: Add reaction to comment
+        if: steps.validate.outputs.should_proceed == 'true'
         env:
           GH_TOKEN: ${{ steps.setup.outputs.token }}
         run: |
@@ -119,6 +102,7 @@ jobs:
             -f content='eyes'
 
       - name: Gather Full Thread Context
+        if: steps.validate.outputs.should_proceed == 'true'
         id: context
         env:
           GH_TOKEN: ${{ steps.setup.outputs.token }}
@@ -474,7 +458,7 @@ jobs:
           fi
 
       - name: Clear pending bot review
-        if: steps.context.outputs.IS_PR == 'true'
+        if: steps.validate.outputs.should_proceed == 'true' && steps.context.outputs.IS_PR == 'true'
         env:
           GH_TOKEN: ${{ steps.setup.outputs.token }}
           BOT_NAMES_JSON: ${{ env.BOT_NAMES_JSON }}
@@ -502,7 +486,7 @@ jobs:
           done <<< "$pending_review_ids"
 
       - name: Determine Review Type and Last Reviewed SHA
-        if: steps.context.outputs.IS_PR == 'true'
+        if: steps.validate.outputs.should_proceed == 'true' && steps.context.outputs.IS_PR == 'true'
         id: review_type
         env:
           GH_TOKEN: ${{ steps.setup.outputs.token }}
@@ -544,18 +528,19 @@ jobs:
           fi
 
       - name: Save secure prompt from base branch
+        if: steps.validate.outputs.should_proceed == 'true'
         run: cp .github/prompts/bot-reply.md /tmp/bot-reply.md
 
       - name: Checkout PR head
-        if: steps.context.outputs.IS_PR == 'true'
+        if: steps.validate.outputs.should_proceed == 'true' && steps.context.outputs.IS_PR == 'true'
         uses: actions/checkout@v4
         with:
           ref: ${{ env.PR_HEAD_SHA }}
           token: ${{ steps.setup.outputs.token }}
           fetch-depth: 0  # Full history needed for git operations and code analysis
 
       - name: Generate PR Diffs (Full and Incremental)
-        if: steps.context.outputs.IS_PR == 'true'
+        if: steps.validate.outputs.should_proceed == 'true' && steps.context.outputs.IS_PR == 'true'
         id: generate_diffs
         env:
           BASE_BRANCH: ${{ env.BASE_BRANCH }}
@@ -610,13 +595,14 @@ jobs:
           fi
 
       - name: Checkout repository (for issues)
-        if: steps.context.outputs.IS_PR == 'false'
+        if: steps.validate.outputs.should_proceed == 'true' && steps.context.outputs.IS_PR == 'false'
         uses: actions/checkout@v4
         with:
           token: ${{ steps.setup.outputs.token }}
           fetch-depth: 0  # Full history needed for git operations and code analysis
 
       - name: Analyze comment and respond
+        if: steps.validate.outputs.should_proceed == 'true'
         env:
           GITHUB_TOKEN: ${{ steps.setup.outputs.token }}
           THREAD_CONTEXT: ${{ env.THREAD_CONTEXT }}