feat: Add @codebot changelog command for Keep a Changelog format generation

Implements PR changelog generator that analyzes diffs and generates
Keep a Changelog format entries ready for CHANGELOG.md.

Features:
- Generates structured changelog entries (Added/Changed/Fixed/etc.)
- Automatically detects breaking changes
- Includes technical details (files, LOC, components)
- User-focused language filtering out noise
- Ready to copy-paste into CHANGELOG.md

Implementation:
- Added changelog.md prompt template with Keep a Changelog format
- Implemented _handle_changelog_command() in PRAgent
- Added _format_changelog() for markdown formatting
- Updated PRAgent.can_handle() to route changelog commands
- Added 'changelog' to config.yml commands list

Workflow Safety (prevents duplicate runs):
- Added '@codebot changelog' to ai-comment-reply.yml conditions
- Excluded from ai-chat.yml to prevent duplication
- Only triggers on PR comments (not issues)
- Manual command only (no automatic triggering)

Testing:
- 9 comprehensive tests in TestChangelogGeneration class
- Tests command detection, formatting, config validation
- Verifies prompt formatting and Keep a Changelog structure

Documentation:
- Updated README.md with changelog command and examples
- Added detailed implementation guide in CLAUDE.md
- Included example output and use cases

Related: Milestone 2 feature - PR changelog generation for release notes

tools/ai-review/agents/pr_agent.py

@@ -99,7 +99,8 @@ class PRAgent(BaseAgent):
                     f"{mention_prefix} review-again" in comment_body.lower()
                 )
                 has_summarize = f"{mention_prefix} summarize" in comment_body.lower()
-                return is_pr and (has_review_again or has_summarize)
+                has_changelog = f"{mention_prefix} changelog" in comment_body.lower()
+                return is_pr and (has_review_again or has_summarize or has_changelog)
 
         return False
 
@@ -113,6 +114,8 @@ class PRAgent(BaseAgent):
             )
             if f"{mention_prefix} summarize" in comment_body.lower():
                 return self._handle_summarize_command(context)
+            elif f"{mention_prefix} changelog" in comment_body.lower():
+                return self._handle_changelog_command(context)
             elif f"{mention_prefix} review-again" in comment_body.lower():
                 return self._handle_review_again(context)
 
@@ -1021,3 +1024,190 @@ class PRAgent(BaseAgent):
                 message=f"Failed to generate PR summary for PR #{pr_number}",
                 error="Summary generation failed",
             )
+
+    def _handle_changelog_command(self, context: AgentContext) -> AgentResult:
+        """Handle @codebot changelog command from PR comments.
+
+        Generates Keep a Changelog format entries for the PR.
+
+        Args:
+            context: Agent context with event data
+
+        Returns:
+            AgentResult with success status and actions taken
+        """
+        issue = context.event_data.get("issue", {})
+        pr_number = issue.get("number")
+        comment_author = (
+            context.event_data.get("comment", {}).get("user", {}).get("login", "user")
+        )
+
+        self.logger.info(f"Generating changelog for PR #{pr_number} at user request")
+
+        try:
+            # Get PR data
+            pr = self.gitea.get_pull_request(context.owner, context.repo, pr_number)
+            pr_title = pr.get("title", "")
+            pr_description = pr.get("body", "")
+
+            # Get PR diff
+            diff = self._get_diff(context.owner, context.repo, pr_number)
+            if not diff.strip():
+                error_msg = (
+                    f"@{comment_author}\n\n"
+                    f"{self.AI_DISCLAIMER}\n\n"
+                    "**⚠️ Changelog Generation Failed**\n\n"
+                    "No changes found in this PR to analyze."
+                )
+                self.gitea.create_issue_comment(
+                    context.owner, context.repo, pr_number, error_msg
+                )
+                return AgentResult(
+                    success=False,
+                    message=f"No diff to generate changelog for PR #{pr_number}",
+                )
+
+            # Load changelog prompt
+            prompt_template = self.load_prompt("changelog")
+            prompt = prompt_template.format(
+                pr_title=pr_title,
+                pr_description=pr_description or "(No description provided)",
+            )
+            prompt = f"{prompt}\n{diff}"
+
+            # Call LLM to generate changelog
+            result = self.call_llm_json(prompt)
+
+            # Format the changelog comment
+            changelog_comment = self._format_changelog(result, pr_number)
+
+            # Post changelog comment
+            self.gitea.create_issue_comment(
+                context.owner, context.repo, pr_number, changelog_comment
+            )
+
+            return AgentResult(
+                success=True,
+                message=f"Generated changelog for PR #{pr_number}",
+                actions_taken=["Posted changelog comment"],
+            )
+
+        except Exception as e:
+            self.logger.error(f"Failed to generate changelog: {e}")
+
+            # Post error message
+            error_msg = (
+                f"@{comment_author}\n\n"
+                f"{self.AI_DISCLAIMER}\n\n"
+                "**⚠️ Changelog Generation Failed**\n\n"
+                f"I encountered an error while generating the changelog: {str(e)}\n\n"
+                "This could be due to:\n"
+                "- The PR is too large to analyze\n"
+                "- The LLM service is temporarily unavailable\n"
+                "- An unexpected error occurred"
+            )
+            self.gitea.create_issue_comment(
+                context.owner, context.repo, pr_number, error_msg
+            )
+
+            return AgentResult(
+                success=False,
+                message=f"Failed to generate changelog for PR #{pr_number}",
+                error=str(e),
+            )
+
+    def _format_changelog(self, changelog_data: dict, pr_number: int) -> str:
+        """Format changelog data into Keep a Changelog format.
+
+        Args:
+            changelog_data: JSON data from LLM containing changelog entries
+            pr_number: PR number for reference
+
+        Returns:
+            Formatted markdown changelog
+        """
+        lines = [
+            self.AI_DISCLAIMER,
+            "",
+            f"## 📋 Changelog for PR #{pr_number}",
+            "",
+        ]
+
+        changelog = changelog_data.get("changelog", {})
+
+        # Added
+        added = changelog.get("added", [])
+        if added:
+            lines.append("### ✨ Added")
+            for item in added:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Changed
+        changed = changelog.get("changed", [])
+        if changed:
+            lines.append("### 🔄 Changed")
+            for item in changed:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Deprecated
+        deprecated = changelog.get("deprecated", [])
+        if deprecated:
+            lines.append("### ⚠️ Deprecated")
+            for item in deprecated:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Removed
+        removed = changelog.get("removed", [])
+        if removed:
+            lines.append("### 🗑️ Removed")
+            for item in removed:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Fixed
+        fixed = changelog.get("fixed", [])
+        if fixed:
+            lines.append("### 🐛 Fixed")
+            for item in fixed:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Security
+        security = changelog.get("security", [])
+        if security:
+            lines.append("### 🔒 Security")
+            for item in security:
+                lines.append(f"- {item}")
+            lines.append("")
+
+        # Breaking changes
+        breaking = changelog_data.get("breaking_changes", [])
+        if breaking:
+            lines.append("---")
+            lines.append("")
+            lines.append("### ⚠️ BREAKING CHANGES")
+            for item in breaking:
+                lines.append(f"- **{item}**")
+            lines.append("")
+
+        # Technical details
+        tech = changelog_data.get("technical_details", {})
+        if tech:
+            lines.append("---")
+            lines.append("")
+            lines.append("### 📊 Technical Details")
+
+            files = tech.get("files_changed", 0)
+            additions = tech.get("insertions", 0)
+            deletions = tech.get("deletions", 0)
+            lines.append(f"- **Files changed:** {files}")
+            lines.append(f"- **Lines:** +{additions} / -{deletions}")
+
+            components = tech.get("main_components", [])
+            if components:
+                lines.append(f"- **Main components:** {', '.join(components)}")
+
+        return "\n".join(lines)