chore(qodo-reviewer): add new agentic reviewer

[naorpeled]

PR Type

Enhancement, Configuration changes

---

Description

• Add GitHub App configuration with PR and push commands

• Enable agentic review functionality with output publishing

• Configure automated commands for describe, improve, and agentic_review

---

Diagram Walkthrough

flowchart LR
  A["PR Agent Config"] --> B["GitHub App Settings"]
  B --> C["PR Commands"]
  B --> D["Push Commands"]
  A --> E["Review Agent"]
  E --> F["Enable & Publish"]
  C --> G["describe, improve, agentic_review"]
  D --> H["improve, agentic_review"]

Loading

File Walkthrough

Relevant files

Configuration changes

.pr_agent.toml Add GitHub App and review agent configuration                        .pr_agent.toml Added GitHub App configuration section with PR and push command triggers Configured PR commands including describe with comment publishing, improve, and agentic_review Configured push commands for improve and agentic_review workflows Added review_agent section with enabled and publish_output settings +17/-0

---

[qodo-free-for-open-source-projects]

PR Compliance Guide 🔍

Below is a summary of compliance checks for this PR:

Security Compliance
⚪	Push trigger abuse risk Description: Enabling handle_push_trigger with automated commands like /improve and /agentic_review on every push could allow malicious actors to trigger resource-intensive operations repeatedly, potentially leading to denial of service or excessive API consumption. .pr_agent.toml [12-16] Referred Code handle_push_trigger = true push_commands = [ "/improve", "/agentic_review" ]
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Consistent Naming Conventions Objective: All new variables, functions, and classes must follow the project's established naming standards Status: Passed
	No Dead or Commented-Out Code Objective: Keep the codebase clean by ensuring all submitted code is active and necessary Status: Passed
	Robust Error Handling Objective: Ensure potential errors and edge cases are anticipated and handled gracefully throughout the code Status: Passed
	Single Responsibility for Functions Objective: Each function should have a single, well-defined responsibility Status: Passed
	When relevant, utilize early return Objective: In a code snippet containing multiple logic conditions (such as 'if-else'), prefer an early return on edge cases than deep nesting Status: Passed

Compliance status legend

🟢 - Fully Compliant
🟡 - Partial Compliant
🔴 - Not Compliant
⚪ - Requires Further Human Verification
🏷️ - Compliance label

[qodo-free-for-open-source-projects]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Disable resource-intensive on-push triggers To prevent excessive resource usage and costs, consider disabling the handle_push_trigger. This setting currently runs /improve and /agentic_review on every push to any branch. .pr_agent.toml [12-16] -handle_push_trigger = true +handle_push_trigger = false push_commands = [ "/improve", "/agentic_review" ] Apply / Chat Suggestion importance[1-10]: 8 __ Why: The suggestion correctly highlights a significant operational risk of high resource consumption and cost by enabling agentic tools on every push, which is a critical consideration for the user.	Medium
More

• Author self-review: I have reviewed the PR code suggestions, and addressed the relevant ones.

[Copilot]

Pull request overview

This pull request attempts to configure an "agentic reviewer" feature for the PR-Agent tool by adding new commands and configuration sections to .pr_agent.toml.

Changes:

• Adds /agentic_review command to both pr_commands and push_commands arrays
• Adds /improve to push trigger commands alongside /agentic_review
• Introduces a new [review_agent] configuration section with enabled and publish_output settings

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The configuration section '[review_agent]' does not exist in the default configuration file (pr_agent/settings/configuration.toml). No code in the codebase references this configuration section. This configuration will be ignored at runtime and will have no effect. Either remove this section or ensure the corresponding feature implementation exists.

Suggested change

	[review_agent]
	enabled = true
	publish_output = true

[ofir-frd]

/agentic_review

[qodo-free-for-open-source-projects]

Code Review by Qodo (Alpha)

🐞 Bugs (2) 📘 Rule Violations (0) 📎 Requirement Gaps (0) 💡 Suggestions (0)

1. Non-existent Command Causes Automation Failure 🐞 Bug

Description

• The configuration references '/agentic_review' command in both pr_commands and push_commands
  arrays, but this command does not exist in the codebase
• When executed, the command will fail with 'Unknown command' warning and return False, causing
  silent automation failures
• This will occur on every PR creation and every push event, wasting CI/CD resources without
  providing any value to users

correctness

Code

.pr_agent.toml[9]

+    "/agentic_review"

Evidence

The command2class dictionary in pr_agent.py defines all valid commands. Searching this dictionary
shows that 'agentic_review' is not registered. When an unknown command is encountered, the code logs
a warning and returns False without executing any action. The configuration file shows this
non-existent command is used in both pr_commands (line 9) and push_commands (line 15).

pr_agent/agent/pr_agent.py[24-44]
pr_agent/agent/pr_agent.py[100-103]
.pr_agent.toml[9-9]
.pr_agent.toml[15-15]

Agent Prompt

## Issue Description
The configuration file `.pr_agent.toml` references a command '/agentic_review' that does not exist in the codebase. This command is not registered in the command2class mapping in pr_agent/agent/pr_agent.py, which means it will fail silently when executed during PR automation or push triggers.

## Issue Context
The PR-Agent system uses a command registry (command2class dictionary) to map command names to their implementation classes. Only commands registered in this dictionary can be executed. When an unregistered command is encountered, the system logs a warning and returns False, causing the automation to fail without providing feedback to users.

## Fix Focus Areas
- .pr_agent.toml[9-9] - Remove '/agentic_review' from pr_commands array
- .pr_agent.toml[15-15] - Remove '/agentic_review' from push_commands array

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

2. Unused Configuration Section Added 🐞 Bug

Description

• A new [review_agent] section with 'enabled' and 'publish_output' settings is added to the
  configuration
• No code in the codebase reads or uses these settings via get_settings().review_agent
• This creates dead configuration that may confuse users or lead to incorrect assumptions about
  system behavior

correctness

Code

.pr_agent.toml[R18-20]

+[review_agent]
+enabled = true
+publish_output = true

Evidence

The configuration.toml file defines all supported configuration sections for the PR-Agent system.
The [review_agent] section does not exist in the default configuration, and no Python code accesses
these settings. A comprehensive search of the codebase found no references to 'review_agent.enabled'
or 'review_agent.publish_output', confirming these settings are not used by any component.

.pr_agent.toml[18-20]
pr_agent/settings/configuration.toml[1-396]

Agent Prompt

## Issue Description
The configuration file includes a [review_agent] section with settings that are not referenced or used anywhere in the codebase. This creates confusion about what these settings control and may lead users to believe they can configure behavior that doesn't actually exist.

## Issue Context
Configuration sections in PR-Agent should correspond to actual functionality in the codebase. The settings system uses Dynaconf to load configuration, and sections should be documented and implemented. Currently, no code reads review_agent.enabled or review_agent.publish_output.

## Fix Focus Areas
- .pr_agent.toml[18-20] - Remove the [review_agent] section entirely, or add explanatory comments if this is for future use

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---