Merge pull request #1897 from qodo-ai/tr/pr_diagram

feat: enable PR diagram by default and improve mermaid diagram genera…

README.md

@@ -65,6 +65,11 @@ Zero-setup hosted solution with advanced features and priority support
 
 ## News and Updates
 
+## Jun 21, 2025
+
+v0.30 was [released](https://github.com/qodo-ai/pr-agent/releases)
+
+
 ## Jun 3, 2025
 
 Qodo Merge now offers a simplified free tier 💎.

docs/docs/ai_search/index.md

@@ -202,7 +202,23 @@ h1 {
 
 <script>
 window.addEventListener('load', function() {
-    function displayResults(responseText) {
+    function extractText(responseText) {
+        try {
+            console.log('responseText: ', responseText);
+            const results = JSON.parse(responseText);
+            const msg = results.message;
+
+            if (!msg || msg.trim() === '') {
+                return "No results found";
+            }
+            return msg;
+        } catch (error) {
+            console.error('Error parsing results:', error);
+            throw new Error("Failed parsing response message");
+        }
+    }
+
+    function displayResults(msg) {
         const resultsContainer = document.getElementById('results');
         const spinner = document.getElementById('spinner');
         const searchContainer = document.querySelector('.search-container');
@@ -214,8 +230,6 @@ window.addEventListener('load', function() {
         searchContainer.scrollIntoView({ behavior: 'smooth', block: 'start' });
 
         try {
-            const results = JSON.parse(responseText);
-
             marked.setOptions({
                 breaks: true,
                 gfm: true,
@@ -223,7 +237,7 @@ window.addEventListener('load', function() {
                 sanitize: false
             });
 
-            const htmlContent = marked.parse(results.message);
+            const htmlContent = marked.parse(msg);
 
             resultsContainer.className = 'markdown-content';
             resultsContainer.innerHTML = htmlContent;
@@ -242,7 +256,7 @@ window.addEventListener('load', function() {
             }, 100);
         } catch (error) {
             console.error('Error parsing results:', error);
-            resultsContainer.innerHTML = '<div class="error-message">Error processing results</div>';
+            resultsContainer.innerHTML = '<div class="error-message">Cannot process results</div>';
         }
     }
 
@@ -275,24 +289,25 @@ window.addEventListener('load', function() {
                 body: JSON.stringify(data)
             };
 
-            // const API_ENDPOINT = 'http://0.0.0.0:3000/api/v1/docs_help';
+            //const API_ENDPOINT = 'http://0.0.0.0:3000/api/v1/docs_help';
             const API_ENDPOINT = 'https://help.merge.qodo.ai/api/v1/docs_help';
 
             const response = await fetch(API_ENDPOINT, options);
+            const responseText = await response.text();
+            const msg = extractText(responseText);
 
             if (!response.ok) {
-                throw new Error(`HTTP error! status: ${response.status}`);
+                throw new Error(`An error (${response.status}) occurred during search: "${msg}"`);
             }
-
-            const responseText = await response.text();
-            displayResults(responseText);
+ 
+            displayResults(msg);
         } catch (error) {
             spinner.style.display = 'none';
-            resultsContainer.innerHTML = `
-                <div class="error-message">
-                    An error occurred while searching. Please try again later.
-                </div>
-            `;
+            const errorDiv = document.createElement('div');
+            errorDiv.className = 'error-message';
+            errorDiv.textContent = `${error}`;
+            resultsContainer.value = "";
+            resultsContainer.appendChild(errorDiv);
         }
     }
 

docs/docs/overview/pr_agent_pro.md

@@ -3,7 +3,8 @@
 [Qodo Merge](https://www.codium.ai/pricing/){:target="_blank"} is a hosted version of the open-source [PR-Agent](https://github.com/Codium-ai/pr-agent){:target="_blank"}. 
 It is designed for companies and teams that require additional features and capabilities.
 
-Free users receive a monthly quota of 75 PR reviews per git organization, while unlimited usage requires a paid subscription. See [details](https://qodo-merge-docs.qodo.ai/installation/qodo_merge/#cloud-users).
+Free users receive a quota of 75 monthly PR feedbacks per git organization. Unlimited usage requires a paid subscription. See [details](https://qodo-merge-docs.qodo.ai/installation/qodo_merge/#cloud-users).
+
 
 Qodo Merge provides the following benefits:
 

docs/docs/pr_benchmark/index.md

@@ -19,7 +19,7 @@ This approach provides not just a quantitative score but also a detailed analysi
 
 [//]: # ()
 
-## Results
+## PR Benchmark Results
 
 <table>
   <thead>
@@ -67,6 +67,12 @@ This approach provides not just a quantitative score but also a detailed analysi
       <td style="text-align:left;"></td>
       <td style="text-align:center;"><b>39.0</b></td>
     </tr>
+    <tr>
+      <td style="text-align:left;">Codex-mini</td>
+      <td style="text-align:left;">2025-06-20</td>
+      <td style="text-align:left;"><a href="https://platform.openai.com/docs/models/codex-mini-latest">unknown</a></td>
+      <td style="text-align:center;"><b>37.2</b></td>
+    </tr>
     <tr>
       <td style="text-align:left;">Gemini-2.5-flash</td>
       <td style="text-align:left;">2025-04-17</td>
@@ -196,7 +202,7 @@ weaknesses:
 - **Very low recall / shallow coverage:** In a large majority of cases it gives 0-1 suggestions and misses other evident, critical bugs highlighted by peer models, leading to inferior rankings.  
 - **Occasional incorrect or harmful fixes:** A noticeable subset of answers propose changes that break functionality or misunderstand the code (e.g. bad constant, wrong header logic, speculative rollbacks).  
 - **Non-actionable placeholders:** Some “improved_code” sections contain comments or “…” rather than real patches, reducing practical value.  
-- 
+
 ### GPT-4.1
 
 Final score: **26.5**
@@ -214,6 +220,22 @@ weaknesses:
 - **Occasional technical inaccuracies:** A noticeable subset of suggestions are wrong (mis-ordered assertions, harmful Bash `set` change, false dangling-reference claims) or carry metadata errors (mis-labeling files as “python”).  
 - **Repetitive / derivative fixes:** Many outputs duplicate earlier simplistic ideas (e.g., single null-check) without new insight, showing limited reasoning breadth.
 
+### OpenAI codex-mini
+
+final score: **37.2**
+
+strengths:
+
+- **Can spot high-impact defects:** When it “locks on”, codex-mini often identifies the main runtime or security regression (e.g., race-conditions, logic inversions, blocking I/O, resource leaks) and proposes a minimal, direct patch that compiles and respects neighbouring style.
+- **Produces concise, scoped fixes:** Valid answers usually stay within the allowed 3-suggestion limit, reference only the added lines, and contain clear before/after snippets that reviewers can apply verbatim.
+- **Occasional broad coverage:** In a minority of cases the model catches multiple independent issues (logic + tests + docs) and outperforms every baseline answer, showing good contextual understanding of heterogeneous diffs.
+
+weaknesses:
+
+- **Output instability / format errors:** A very large share of responses are unusable—plain refusals, shell commands, or malformed/empty YAML—indicating brittle adherence to the required schema and tanking overall usefulness.
+- **Critical-miss rate:** Even when the format is correct the model frequently overlooks the single most serious bug the diff introduces, instead focusing on stylistic nits or speculative refactors.
+- **Introduces new problems:** Several suggestions add unsupported APIs, undeclared variables, wrong types, or break compilation, hurting trust in the recommendations.
+- **Rule violations:** It often edits lines outside the diff, exceeds the 3-suggestion cap, or labels cosmetic tweaks as “critical”, showing inconsistent guideline compliance.
 
 ## Appendix - models used for generating the benchmark baseline
 

docs/docs/recent_updates/index.md

@@ -7,6 +7,7 @@ This page summarizes recent enhancements to Qodo Merge (last three months).
 It also outlines our development roadmap for the upcoming three months. Please note that the roadmap is subject to change, and features may be adjusted, added, or reprioritized.
 
 === "Recent Updates"
+    - **Best Practices Hierarchy**: Introducing support for structured best practices, such as for folders in monorepos or a unified best practice file for a group of repositories.
     - **Simplified Free Tier**: Qodo Merge now offers a simplified free tier with a monthly limit of 75 PR reviews per organization, replacing the previous two-week trial. ([Learn more](https://qodo-merge-docs.qodo.ai/installation/qodo_merge/#cloud-users))
     - **CLI Endpoint**: A new Qodo Merge endpoint that accepts a lists of before/after code changes, executes Qodo Merge commands, and return the results. Currently available for enterprise customers. Contact [Qodo](https://www.qodo.ai/contact/) for more information.
     - **Linear tickets support**: Qodo Merge now supports Linear tickets. ([Learn more](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/#linear-integration))
@@ -17,7 +18,6 @@ It also outlines our development roadmap for the upcoming three months. Please n
 
 
 === "Future Roadmap"
-    - **Best Practices Hierarchy**: Introducing support for structured best practices, such as for folders in monorepos or a unified best practice file for a group of repositories.
     - **Enhanced `review` tool**: Enhancing the `review` tool validate compliance across multiple categories including security, tickets, and custom best practices.
     - **Smarter context retrieval**: Leverage AST and LSP analysis to gather relevant context from across the entire repository.
     - **Enhanced portal experience**: Improved user experience in the Qodo Merge portal with new options and capabilities.

docs/docs/tools/describe.md

@@ -59,17 +59,23 @@ Everything below this marker is treated as previously auto-generated content and
 ### Sequence Diagram Support 
 When the `enable_pr_diagram` option is enabled in your configuration, the `/describe` tool will include a `Mermaid` sequence diagram in the PR description.
 
-This diagram represents interactions between components/functions based on the diff content.
+This diagram represents interactions between components/functions based on the PR content.
 
-### How to enable
+[//]: # (### How to enable\disable)
 
-In your configuration:
+[//]: # ()
+[//]: # (In your configuration:)
 
-```
-toml
-[pr_description]
-enable_pr_diagram = true
-```
+[//]: # ()
+[//]: # (```)
+
+[//]: # (toml)
+
+[//]: # ([pr_description])
+
+[//]: # (enable_pr_diagram = true)
+
+[//]: # (```)
 
 ## Configuration options
 
@@ -126,7 +132,7 @@ enable_pr_diagram = true
       </tr>
       <tr>
         <td><b>enable_pr_diagram</b></td>
-        <td>If set to true, the tool will generate a horizontal Mermaid flowchart summarizing the main pull request changes. This field remains empty if not applicable. Default is false.</td>
+        <td>If set to true, the tool will generate a horizontal Mermaid flowchart summarizing the main pull request changes. This field remains empty if not applicable. Default is true.</td>
       </tr>
     </table>
 

docs/docs/usage-guide/changing_a_model.md

@@ -232,6 +232,14 @@ AWS_SECRET_ACCESS_KEY="..."
 AWS_REGION_NAME="..."
 ```
 
+You can also use the new Meta Llama 4 models available on Amazon Bedrock:
+
+```toml
+[config] # in configuration.toml
+model="bedrock/us.meta.llama4-scout-17b-instruct-v1:0"
+fallback_models=["bedrock/us.meta.llama4-maverick-17b-instruct-v1:0"]
+```
+
 See [litellm](https://docs.litellm.ai/docs/providers/bedrock#usage) documentation for more information about the environment variables required for Amazon Bedrock.
 
 ### DeepSeek

pr_agent/agent/pr_agent.py

@@ -51,7 +51,7 @@ class PRAgent:
     def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
         self.ai_handler = ai_handler  # will be initialized in run_action
 
-    async def handle_request(self, pr_url, request, notify=None) -> bool:
+    async def _handle_request(self, pr_url, request, notify=None) -> bool:
         # First, apply repo specific settings if exists
         apply_repo_settings(pr_url)
 
@@ -117,3 +117,10 @@ class PRAgent:
             else:
                 return False
             return True
+
+    async def handle_request(self, pr_url, request, notify=None) -> bool:
+        try:
+            return await self._handle_request(pr_url, request, notify)
+        except:
+            get_logger().exception("Failed to process the command.")
+            return False

pr_agent/algo/__init__.py

@@ -62,19 +62,23 @@ MAX_TOKENS = {
     'vertex_ai/gemini-2.5-pro-preview-03-25': 1048576,
     'vertex_ai/gemini-2.5-pro-preview-05-06': 1048576,
     'vertex_ai/gemini-2.5-pro-preview-06-05': 1048576,
+    'vertex_ai/gemini-2.5-pro': 1048576,
     'vertex_ai/gemini-1.5-flash': 1048576,
     'vertex_ai/gemini-2.0-flash': 1048576,
     'vertex_ai/gemini-2.5-flash-preview-04-17': 1048576,
     'vertex_ai/gemini-2.5-flash-preview-05-20': 1048576,
+    'vertex_ai/gemini-2.5-flash': 1048576,
     'vertex_ai/gemma2': 8200,
     'gemini/gemini-1.5-pro': 1048576,
     'gemini/gemini-1.5-flash': 1048576,
     'gemini/gemini-2.0-flash': 1048576,
     'gemini/gemini-2.5-flash-preview-04-17': 1048576,
     'gemini/gemini-2.5-flash-preview-05-20': 1048576,
+    'gemini/gemini-2.5-flash': 1048576,
     'gemini/gemini-2.5-pro-preview-03-25': 1048576,
     'gemini/gemini-2.5-pro-preview-05-06': 1048576,
     'gemini/gemini-2.5-pro-preview-06-05': 1048576,
+    'gemini/gemini-2.5-pro': 1048576,
     'codechat-bison': 6144,
     'codechat-bison-32k': 32000,
     'anthropic.claude-instant-v1': 100000,
@@ -109,6 +113,8 @@ MAX_TOKENS = {
     'claude-3-5-sonnet': 100000,
     'groq/meta-llama/llama-4-scout-17b-16e-instruct': 131072,
     'groq/meta-llama/llama-4-maverick-17b-128e-instruct': 131072,
+    'bedrock/us.meta.llama4-scout-17b-instruct-v1:0': 128000,
+    'bedrock/us.meta.llama4-maverick-17b-instruct-v1:0': 128000,
     'groq/llama3-8b-8192': 8192,
     'groq/llama3-70b-8192': 8192,
     'groq/llama-3.1-8b-instant': 8192,

pr_agent/git_providers/azuredevops_provider.py

@@ -22,6 +22,7 @@ try:
     from azure.devops.connection import Connection
     # noinspection PyUnresolvedReferences
     from azure.devops.released.git import (Comment, CommentThread, GitPullRequest, GitVersionDescriptor, GitClient, CommentThreadContext, CommentPosition)
+    from azure.devops.released.work_item_tracking import WorkItemTrackingClient
     # noinspection PyUnresolvedReferences
     from azure.identity import DefaultAzureCredential
     from msrest.authentication import BasicAuthentication
@@ -39,7 +40,7 @@ class AzureDevopsProvider(GitProvider):
                 "Azure DevOps provider is not available. Please install the required dependencies."
             )
 
-        self.azure_devops_client = self._get_azure_devops_client()
+        self.azure_devops_client, self.azure_devops_board_client = self._get_azure_devops_client()
         self.diff_files = None
         self.workspace_slug = None
         self.repo_slug = None
@@ -566,7 +567,7 @@ class AzureDevopsProvider(GitProvider):
         return workspace_slug, repo_slug, pr_number
 
     @staticmethod
-    def _get_azure_devops_client() -> GitClient:
+    def _get_azure_devops_client() -> Tuple[GitClient, WorkItemTrackingClient]:
         org = get_settings().azure_devops.get("org", None)
         pat = get_settings().azure_devops.get("pat", None)
 
@@ -588,13 +589,12 @@ class AzureDevopsProvider(GitProvider):
                 get_logger().error(f"No PAT found in settings, and Azure Default Authentication failed, error: {e}")
                 raise
 
-        credentials = BasicAuthentication("", auth_token)
-
         credentials = BasicAuthentication("", auth_token)
         azure_devops_connection = Connection(base_url=org, creds=credentials)
         azure_devops_client = azure_devops_connection.clients.get_git_client()
+        azure_devops_board_client = azure_devops_connection.clients.get_work_item_tracking_client()
 
-        return azure_devops_client
+        return azure_devops_client, azure_devops_board_client
 
     def _get_repo(self):
         if self.repo is None:
@@ -635,4 +635,50 @@ class AzureDevopsProvider(GitProvider):
         last = commits[0]
         url = self.azure_devops_client.normalized_url + "/" + self.workspace_slug + "/_git/" + self.repo_slug + "/commit/" + last.commit_id
         return url
-    
+
+    def get_linked_work_items(self) -> list:
+        """
+        Get linked work items from the PR.
+        """
+        try:
+            work_items = self.azure_devops_client.get_pull_request_work_item_refs(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+            )
+            ids = [work_item.id for work_item in work_items]
+            if not work_items:
+                return []
+            items = self.get_work_items(ids)
+            return items
+        except Exception as e:
+            get_logger().exception(f"Failed to get linked work items, error: {e}")
+            return []
+
+    def get_work_items(self, work_item_ids: list) -> list:
+        """
+        Get work items by their IDs.
+        """
+        try:
+            raw_work_items = self.azure_devops_board_client.get_work_items(
+                project=self.workspace_slug,
+                ids=work_item_ids,
+            )
+            work_items = []
+            for item in raw_work_items:
+                work_items.append(
+                    {
+                        "id": item.id,
+                        "title": item.fields.get("System.Title", ""),
+                        "url": item.url,
+                        "body": item.fields.get("System.Description", ""),
+                        "acceptance_criteria": item.fields.get(
+                            "Microsoft.VSTS.Common.AcceptanceCriteria", ""
+                        ),
+                        "tags": item.fields.get("System.Tags", "").split("; ") if item.fields.get("System.Tags") else [],
+                    }
+                )
+            return work_items
+        except Exception as e:
+            get_logger().exception(f"Failed to get work items, error: {e}")
+            return []

pr_agent/servers/atlassian-connect-qodo-merge.json

@@ -0,0 +1,38 @@
+{
+  "name": "Qodo Merge",
+  "description": "Qodo Merge",
+  "key": "app_key",
+  "vendor": {
+    "name": "Qodo",
+    "url": "https://qodo.ai"
+  },
+  "authentication": {
+    "type": "jwt"
+  },
+  "baseUrl": "base_url",
+  "lifecycle": {
+    "installed": "/installed",
+    "uninstalled": "/uninstalled"
+  },
+  "scopes": [
+    "account",
+    "repository:write",
+    "pullrequest:write",
+    "wiki"
+  ],
+  "contexts": [
+    "account"
+  ],
+  "modules": {
+    "webhooks": [
+      {
+        "event": "*",
+        "url": "/webhook"
+      }
+    ]
+  },
+  "links": {
+    "privacy": "https://qodo.ai/privacy-policy",
+    "terms": "https://qodo.ai/terms"
+  }
+}

pr_agent/settings/configuration.toml

@@ -106,7 +106,7 @@ enable_pr_type=true
 final_update_message = true
 enable_help_text=false
 enable_help_comment=true
-enable_pr_diagram=false # adds a section with a diagram of the PR changes
+enable_pr_diagram=true # adds a section with a diagram of the PR changes
 # describe as comment
 publish_description_as_comment=false
 publish_description_as_comment_persistent=true

pr_agent/settings/pr_description_prompts.toml

@@ -48,7 +48,7 @@ class PRDescription(BaseModel):
     description: str = Field(description="summarize the PR changes in up to four bullet points, each up to 8 words. For large PRs, add sub-bullets if needed. Order bullets by importance, with each bullet highlighting a key change group.")
     title: str = Field(description="a concise and descriptive title that captures the PR's main theme")
 {%- if enable_pr_diagram %}
-    changes_diagram: str = Field(description="a horizontal diagram that represents the main PR changes, in the format of a valid mermaid LR flowchart. The diagram should be concise and easy to read. Leave empty if no diagram is relevant. To create robust Mermaid diagrams, follow this two-step process: (1) Declare the nodes: nodeID["node description"]. (2) Then define the links: nodeID1 -- "link text" --> nodeID2 ")
+    changes_diagram: str = Field(description="a horizontal diagram that represents the main PR changes, in the format of a valid mermaid LR flowchart. The diagram should be concise and easy to read. Leave empty if no diagram is relevant. To create robust Mermaid diagrams, follow this two-step process: (1) Declare the nodes: nodeID["node description"]. (2) Then define the links: nodeID1 -- "link text" --> nodeID2. Node description must always be surrounded with quotation marks.")
 {%- endif %}
 {%- if enable_semantic_files_types %}
     pr_files: List[FileDescription] = Field(max_items=20, description="a list of all the files that were changed in the PR, and summary of their changes. Each file must be analyzed regardless of change size.")

pr_agent/settings/pr_reviewer_prompts.toml

@@ -196,6 +196,13 @@ Ticket Description:
 {{ ticket.body }}
 #####
 {%- endif %}
+
+{%- if ticket.requirements %}
+Ticket Requirements:
+#####
+{{ ticket.requirements }}
+#####
+{%- endif %}
 =====
 {% endfor %}
 {%- endif %}

pr_agent/tools/pr_description.py

@@ -59,6 +59,7 @@ class PRDescription:
 
         # Initialize the variables dictionary
         self.COLLAPSIBLE_FILE_LIST_THRESHOLD = get_settings().pr_description.get("collapsible_file_list_threshold", 8)
+        enable_pr_diagram = get_settings().pr_description.get("enable_pr_diagram", False) and self.git_provider.is_supported("gfm_markdown") # github and gitlab support gfm_markdown
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
@@ -73,7 +74,7 @@ class PRDescription:
             "related_tickets": "",
             "include_file_summary_changes": len(self.git_provider.get_diff_files()) <= self.COLLAPSIBLE_FILE_LIST_THRESHOLD,
             "duplicate_prompt_examples": get_settings().config.get("duplicate_prompt_examples", False),
-            "enable_pr_diagram": get_settings().pr_description.get("enable_pr_diagram", False),
+            "enable_pr_diagram": enable_pr_diagram,
         }
 
         self.user_description = self.git_provider.get_user_description()

pr_agent/tools/ticket_pr_compliance_check.py

@@ -3,6 +3,7 @@ import traceback
 
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import GithubProvider
+from pr_agent.git_providers import AzureDevopsProvider
 from pr_agent.log import get_logger
 
 # Compile the regex pattern once, outside the function
@@ -131,6 +132,32 @@ async def extract_tickets(git_provider):
 
                 return tickets_content
 
+        elif isinstance(git_provider, AzureDevopsProvider):
+            tickets_info = git_provider.get_linked_work_items()
+            tickets_content = []
+            for ticket in tickets_info:
+                try:
+                    ticket_body_str = ticket.get("body", "")
+                    if len(ticket_body_str) > MAX_TICKET_CHARACTERS:
+                        ticket_body_str = ticket_body_str[:MAX_TICKET_CHARACTERS] + "..."
+
+                    tickets_content.append(
+                        {
+                            "ticket_id": ticket.get("id"),
+                            "ticket_url": ticket.get("url"),
+                            "title": ticket.get("title"),
+                            "body": ticket_body_str,
+                            "requirements": ticket.get("acceptance_criteria", ""),
+                            "labels": ", ".join(ticket.get("labels", [])),
+                        }
+                    )
+                except Exception as e:
+                    get_logger().error(
+                        f"Error processing Azure DevOps ticket: {e}",
+                        artifact={"traceback": traceback.format_exc()},
+                    )
+            return tickets_content
+
     except Exception as e:
         get_logger().error(f"Error extracting tickets error= {e}",
                            artifact={"traceback": traceback.format_exc()})

pyproject.toml

@@ -1,10 +1,10 @@
 [build-system]
-requires = ["setuptools>=61.0"]
+requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "pr-agent"
-version = "0.2.7"
+version = "0.3.0"
 
 authors = [{ name = "QodoAI", email = "tal.r@qodo.ai" }]
 
@@ -16,7 +16,7 @@ description = "QodoAI PR-Agent aims to help efficiently review and handle pull r
 readme = "README.md"
 requires-python = ">=3.12"
 keywords = ["AI", "Agents", "Pull Request", "Automation", "Code Review"]
-license = "Apache-2.0"
+license = { file = "LICENSE" }
 
 classifiers = [
   "Intended Audience :: Developers",
@@ -34,7 +34,6 @@ dependencies = { file = ["requirements.txt"] }
 
 [tool.setuptools]
 include-package-data = true
-license-files = ["LICENSE"]
 
 [tool.setuptools.packages.find]
 where = ["."]

tests/unittest/test_add_docs_trigger.py

@@ -0,0 +1,92 @@
+import pytest
+from pr_agent.servers.github_app import handle_new_pr_opened
+from pr_agent.tools.pr_add_docs import PRAddDocs
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings
+from pr_agent.identity_providers.identity_provider import Eligibility
+from pr_agent.identity_providers import get_identity_provider
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "action,draft,state,should_run",
+    [
+        ("opened", False, "open", True),
+        ("edited", False, "open", False),
+        ("opened", True, "open", False),
+        ("opened", False, "closed", False),
+    ],
+)
+async def test_add_docs_trigger(monkeypatch, action, draft, state, should_run):
+    # Mock settings to enable the "/add_docs" auto-command on PR opened
+    settings = get_settings()
+    settings.github_app.pr_commands = ["/add_docs"]
+    settings.github_app.handle_pr_actions = ["opened"]
+
+    # Define a FakeGitProvider for both apply_repo_settings and PRAddDocs
+    class FakeGitProvider:
+        def __init__(self, pr_url, *args, **kwargs):
+            self.pr = type("pr", (), {"title": "Test PR"})()
+            self.get_pr_branch = lambda: "test-branch"
+            self.get_pr_description = lambda: "desc"
+            self.get_languages = lambda: ["Python"]
+            self.get_files = lambda: []
+            self.get_commit_messages = lambda: "msg"
+            self.publish_comment = lambda *args, **kwargs: None
+            self.remove_initial_comment = lambda: None
+            self.publish_code_suggestions = lambda suggestions: True
+            self.diff_files = []
+            self.get_repo_settings = lambda: {}
+
+    # Patch Git provider lookups
+    monkeypatch.setattr(
+        "pr_agent.git_providers.utils.get_git_provider_with_context",
+        lambda pr_url: FakeGitProvider(pr_url),
+    )
+    monkeypatch.setattr(
+        "pr_agent.tools.pr_add_docs.get_git_provider",
+        lambda: FakeGitProvider,
+    )
+
+    # Ensure identity provider always eligible
+    monkeypatch.setattr(
+        get_identity_provider().__class__,
+        "verify_eligibility",
+        lambda *args, **kwargs: Eligibility.ELIGIBLE,
+    )
+
+    # Spy on PRAddDocs.run()
+    ran = {"flag": False}
+
+    async def fake_run(self):
+        ran["flag"] = True
+
+    monkeypatch.setattr(PRAddDocs, "run", fake_run)
+
+    # Build minimal PR payload
+    body = {
+        "action": action,
+        "pull_request": {
+            "url": "https://example.com/fake/pr",
+            "state": state,
+            "draft": draft,
+        },
+    }
+    log_context = {}
+
+    # Invoke the PR-open handler
+    agent = PRAgent()
+    await handle_new_pr_opened(
+        body=body,
+        event="pull_request",
+        sender="tester",
+        sender_id="123",
+        action=action,
+        log_context=log_context,
+        agent=agent,
+    )
+
+    assert ran["flag"] is should_run, (
+        f"Expected run() to be {'called' if should_run else 'skipped'}"
+        f" for action={action!r}, draft={draft}, state={state!r}"
+    )