feat: Implement autonomous repository management and self-healing systems by NITISH-R-G · Pull Request #111 · NITISH-R-G/Intelli-Credit-V2

NITISH-R-G · 2026-07-11T17:55:17Z

This PR fulfills the requirement to transform the repository into an advanced, autonomous, self-improving, and contributor-friendly system utilizing free GitHub capabilities.

Changes Included:

AGENTS.md: Created to define repository interactions for automation tools and AI assistants.
package.json: Added execution scripts (ai:triage, ai:improve, ai:pr-review, etc.) targeting local and continuous intelligence functions.
Core Automation Scripts (scripts/automation/):
- ai-triage.ts: Auto-labels newly opened issues by querying Gemini.
- ai-improve.ts: Continuous self-healing script applying linting and formatting.
- ai-pr-review.ts: Retrieves GitHub diffs and queries Gemini for insightful code reviews, storing the output to a markdown file for GitHub Actions to post.
- analyze-repo.ts: Maps and evaluates the directory structure.
- generate-diagrams.ts: Dynamically generates mermaid-based architecture diagrams based on repo analysis.
- generate-knowledge-graph.ts: Parses import statements to build an automated relationship map.
GitHub Action Workflows (.github/workflows/):
- ai-issue-triager.yml: Fires on issue creation.
- ai-pr-reviewer.yml: Fires on PR updates, posts AI code review as a comment securely.
- continuous-improvement.yml: Runs on schedule to push a self-healing PR if code style drifts.
- autonomous-documentation.yml: Triggers on push to main, auto-updating repo docs and diagrams.

Security considerations were carefully addressed by safely referencing environment variables in actions and favoring execFileSync in NodeJS scripts.

PR created automatically by Jules for task 9411547778336918527 started by @NITISH-R-G

- Added `AGENTS.md` to define guidelines for AI assistants and automation. - Updated `package.json` with scripts for `fix`, `ai:triage`, `ai:improve`, `ai:pr-review`, `analyze:repo`, `generate:diagrams`, and `generate:knowledge-graph`. - Implemented core automation scripts in `scripts/automation/` using `@google/genai` to automatically manage issues, perform code reviews, generate system architectures, and create knowledge graphs. - Created GitHub Action workflows (`ai-pr-reviewer.yml`, `ai-issue-triager.yml`, `continuous-improvement.yml`, `autonomous-documentation.yml`) to integrate automation seamlessly into the CI/CD pipeline. - Adhered to security practices: avoided `execSync` for shell execution, restricted `console.log` usage, and passed GitHub variables as environment values in CI. Co-authored-by: NITISH-R-G <225521762+NITISH-R-G@users.noreply.github.com>

google-labs-jules · 2026-07-11T17:55:19Z

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

For security, I will only act on instructions from the user who triggered this task.

vercel · 2026-07-11T17:55:21Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
intelli-credit-v2	Ready	Preview, Comment	Jul 11, 2026 6:42pm

sourcery-ai

Sorry @NITISH-R-G, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

greptile-apps

Your trial has ended. Reactivate Greptile to resume code reviews.

github-actions · 2026-07-11T17:55:38Z

AI PR Reviewer: No GEMINI_API_KEY found. Skipping review.

coderabbitai · 2026-07-11T17:55:41Z

Warning

Review limit reached

@NITISH-R-G, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 13 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 3a279961-be5c-452e-9dfd-5ed1bdf374d8

📥 Commits

Reviewing files that changed from the base of the PR and between 1f3ea7a and 30979c5.

📒 Files selected for processing (6)

.github/workflows/ai-pr-reviewer.yml
scripts/automation/ai-pr-review.ts
scripts/automation/ai-triage.ts
scripts/automation/analyze-repo.ts
scripts/automation/generate-diagrams.ts
scripts/automation/generate-knowledge-graph.ts

📝 Walkthrough

Walkthrough

Adds GitHub Actions for AI issue triage, pull request reviews, documentation generation, and continuous improvement, with supporting scripts, repository guidance, changelog updates, and formatting-only maintenance.

Changes

Issue and pull request automation

Layer / File(s)	Summary
Issue and pull request automation `.github/workflows/ai-issue-triager.yml`, `.github/workflows/ai-pr-reviewer.yml`, `scripts/automation/ai-triage.ts`, `scripts/automation/ai-pr-review.ts`, `package.json`	Adds Gemini-based issue labeling and pull request review workflows, including diff generation, comment output, and GitHub integration.

Repository documentation generation

Layer / File(s)	Summary
Repository documentation generation `.github/workflows/autonomous-documentation.yml`, `scripts/automation/analyze-repo.ts`, `scripts/automation/generate-diagrams.ts`, `scripts/automation/generate-knowledge-graph.ts`	Generates repository analysis, architecture diagrams, and knowledge-graph documentation, then commits changes under `docs/`.

Continuous improvement automation

Layer / File(s)	Summary
Continuous improvement automation `.github/workflows/continuous-improvement.yml`, `scripts/automation/ai-improve.ts`, `AGENTS.md`	Runs automated fixes on a schedule or manually, then creates a branch and pull request when changes are detected.

Repository documentation and formatting

Layer / File(s)	Summary
Repository guidance and release documentation `AGENTS.md`, `CHANGELOG.md`, `CONTRIBUTING.md`	Documents automation practices, records removed automation in the changelog, and reformats issue-label guidance.
Formatting-only maintenance `api/...`, `src/...`, `vercel.json`	Reformats existing code, tests, configuration, and expressions without changing behavior.

Estimated code review effort: 3 (Moderate) | ~25 minutes

Sequence Diagram(s)

sequenceDiagram
  participant GitHubActions
  participant aiTriage
  participant Gemini
  participant GitHubCLI
  GitHubActions->>aiTriage: issue event and credentials
  aiTriage->>Gemini: issue details
  Gemini-->>aiTriage: suggested labels
  aiTriage->>GitHubCLI: apply labels

sequenceDiagram
  participant DocumentationWorkflow
  participant AutomationScripts
  participant Gemini
  participant Docs
  DocumentationWorkflow->>AutomationScripts: run generation commands
  AutomationScripts->>Gemini: repository analysis data
  Gemini-->>AutomationScripts: generated Markdown and Mermaid
  AutomationScripts->>Docs: write generated artifacts
  DocumentationWorkflow->>Docs: commit and push changes

Poem

I’m a rabbit with scripts in my paws,
Sorting issues and reviewing applause.
Gemini hums, docs bloom bright,
Workflows hop through the night.
New branches spring where changes grow!

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately summarizes the PR’s main addition: autonomous repository management and self-healing automation.
Description check	✅ Passed	The description is clearly related to the changeset and matches the added automation scripts, workflows, and AGENTS guidelines.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch feature/repo-automation-9411547778336918527

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands.}

coderabbitai

Actionable comments posted: 15

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

CHANGELOG.md (1)
16-22: 📐 Maintainability & Code Quality | 🟠 Major | ⚡ Quick win

CHANGELOG "Removed" entry contradicts this PR's additions.

The new "### Removed" bullet states that "All AI-dependent and autonomous-commit automation (AI doc agent, self-healing auto-fix, ... autonomous repo analysis, dashboard generator) ... has been removed" and that "the repo is now maintainable without any LLM API keys." However, this PR adds exactly those systems — ai-improve.ts (self-healing auto-fix), continuous-improvement.yml (autonomous commits), ai-triage.ts, ai-pr-review.ts, analyze-repo.ts, generate-diagrams.ts, and generate-knowledge-graph.ts. Update or remove this entry to reflect the actual changes.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@CHANGELOG.md` around lines 16 - 22, Update the “### Removed” section in
CHANGELOG.md to remove or rewrite the bullet claiming that AI-dependent and
autonomous-commit automation was removed. Ensure the entry accurately reflects
the additions of ai-improve.ts, continuous-improvement.yml, ai-triage.ts,
ai-pr-review.ts, analyze-repo.ts, generate-diagrams.ts, and
generate-knowledge-graph.ts, and do not claim the repository is free of LLM API
key requirements.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In @.github/workflows/ai-issue-triager.yml:
- Around line 14-15: Update the “Checkout Repository” step using
actions/checkout@v4 to disable credential persistence, while leaving the
existing checkout behavior unchanged. Configure the checkout action’s
persist-credentials option to false.

In @.github/workflows/ai-pr-reviewer.yml:
- Around line 3-9: Add a workflow-level concurrency group to the pull request
reviewer workflow, keyed by the PR or branch and configured to cancel
in-progress runs so superseded synchronize events stop consuming resources. Also
update the checkout step to use persist-credentials: false.

In @.github/workflows/autonomous-documentation.yml:
- Around line 15-19: Pin both actions in the workflow to immutable commit SHA
hashes instead of version tags. Update the Checkout Repository step to set
persist-credentials to false, then configure Git credentials explicitly only in
the later push step, preserving the existing checkout and push behavior.
- Around line 3-6: Add a concurrency block to the workflow triggered by the push
event, using a shared group for main-branch runs and canceling or otherwise
preventing overlapping runs so documentation generation and git push execute
serially without non-fast-forward conflicts.
- Around line 8-9: Move the contents: write permission from workflow scope into
the document job, leaving other jobs with their default permissions. Add a
concise comment at the job-level permission explaining it is required for the
commit/push step.
- Around line 42-52: Update the “Commit and Push Documentation Changes” workflow
step to run npm run fix, npm test, npm run format, and npm run lint before
staging, committing, and pushing documentation changes. Keep the existing commit
conditional and push behavior unchanged.

In @.github/workflows/continuous-improvement.yml:
- Around line 16-17: Pin the third-party actions in the workflow to immutable
commit SHA references: update both actions/checkout and actions/setup-node while
preserving their existing v4 behavior, optionally retaining the version in an
inline comment for readability.
- Around line 28-52: Insert an npm test step between “Run Continuous Improvement
Script” and “Check for changes” in the workflow, so tests complete successfully
before any automated changes are committed or pushed. Keep the existing change
detection and pull-request flow unchanged.
- Around line 3-6: Add a concurrency configuration to the workflow alongside the
existing schedule and workflow_dispatch triggers, using a stable group
identifier for this workflow and disabling cancellation of an already-running
job. Ensure overlapping scheduled and manually triggered runs share the same
concurrency group.

In `@scripts/automation/ai-improve.ts`:
- Around line 17-19: Update the catch block in the continuous improvement flow
to preserve the error log and terminate with a non-zero exit status when any fix
step fails. Ensure failures from commands such as lint:fix or format propagate
to the workflow so partial changes are not committed.

In `@scripts/automation/ai-triage.ts`:
- Around line 48-61: Validate suggestedLabels against a centralized
allowed-label set before logging or invoking gh, retaining only labels in the
canonical vocabulary and skipping the command when none remain. Define or reuse
the allowed set in the automation code and keep it synchronized with the
canonical labels documented in CONTRIBUTING.md; preserve trimming and comma
parsing.

In `@scripts/automation/analyze-repo.ts`:
- Around line 63-68: Update the error handling in main so repository-analysis
failures are propagated after logging, causing the process to exit nonzero and
preventing downstream workflows from treating stale or missing analysis output
as successful. Ensure the catch path in main does not return normally; preserve
the existing error context in the console output.

In `@scripts/automation/generate-diagrams.ts`:
- Around line 48-53: Update the error handling in the diagram-generation flow’s
catch block to propagate failure after logging the error, ensuring the process
exits nonzero and workflow steps cannot succeed when generation fails. Keep the
existing error context and apply the change to the surrounding main() execution
path.
- Around line 33-36: Add a client-side timeout to the generateContent call in
the diagram generation flow by configuring the request’s supported HTTP timeout
or abort signal. Ensure the Gemini request cannot hang indefinitely while
preserving the existing model and prompt parameters.

In `@scripts/automation/generate-knowledge-graph.ts`:
- Around line 10-16: Update the import extraction logic around importRegex and
its matching loop to include side-effect imports, dynamic import(...) calls, and
CommonJS require(...) dependencies, while retaining import/export ... from
support. Replace the backtracking-prone .*?from pattern with a bounded or
parser-based approach, and ensure each captured module path is added to imports
without duplicate or malformed matches.

---

Outside diff comments:
In `@CHANGELOG.md`:
- Around line 16-22: Update the “### Removed” section in CHANGELOG.md to remove
or rewrite the bullet claiming that AI-dependent and autonomous-commit
automation was removed. Ensure the entry accurately reflects the additions of
ai-improve.ts, continuous-improvement.yml, ai-triage.ts, ai-pr-review.ts,
analyze-repo.ts, generate-diagrams.ts, and generate-knowledge-graph.ts, and do
not claim the repository is free of LLM API key requirements.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 33ecaa65-448a-4a07-8deb-ff37c8294c80

📥 Commits

Reviewing files that changed from the base of the PR and between 95846c3 and 1f3ea7a.

⛔ Files ignored due to path filters (1)

package-lock.json is excluded by !**/package-lock.json

📒 Files selected for processing (22)

.github/workflows/ai-issue-triager.yml
.github/workflows/ai-pr-reviewer.yml
.github/workflows/autonomous-documentation.yml
.github/workflows/continuous-improvement.yml
AGENTS.md
CHANGELOG.md
CONTRIBUTING.md
api/_lib/__tests__/analyze-core.test.ts
api/_lib/limits.ts
api/_lib/mcp-tools.ts
api/analyze.ts
package.json
scripts/automation/ai-improve.ts
scripts/automation/ai-pr-review.ts
scripts/automation/ai-triage.ts
scripts/automation/analyze-repo.ts
scripts/automation/generate-diagrams.ts
scripts/automation/generate-knowledge-graph.ts
src/App.tsx
src/services/__tests__/analysisService.test.ts
src/services/analysisService.ts
vercel.json

💤 Files with no reviewable changes (2)

src/App.tsx
src/services/analysisService.ts

📜 Review details

⏰ Context from checks skipped due to timeout. (5)

GitHub Check: CodeQL
GitHub Check: CodeRabbit
GitHub Check: build-and-test (20.x)
GitHub Check: build-and-test (22.x)
GitHub Check: Analyze (javascript-typescript)

🧰 Additional context used

📓 Path-based instructions (5)

**/*