feat: Red Flag DD workflow, unified file_id, and document-file linking

[larryro]

Summary

• Red Flag DD workflow: Add a new red-flag-dd.json workflow example that uses the structured DOCX round-trip pattern (RAG index → extract → batch LLM → apply modifications) for due diligence report generation from VDR documents. Reorganize examples/workflows/ by renaming contract-generation/ to docx-generation/.
• Unified file_id across RAG API: Rename document_id to file_id throughout the RAG service (API, database, platform callers, tests) for consistent naming. Add runtime migration helper and extract shared result parsing into parse_search_results with source filename annotations.
• Link fileMetadata to documents: Add documentId field to fileMetadata schema establishing bidirectional file↔document linking, with schema changes, mutation updates, backfill migration, and OneDrive import propagation.
• Cross-thread human input status: Fix chat sidebar to show "awaiting input" instead of "running" when a workflow is paused for human input on a sub-thread.
• File ID in RAG search results: Include FileID annotation in formatted search output so agents can reference specific files.

Test plan

• New tests for fileMetadata mutations and document upload flows
• Updated document_retrieve_tool tests for file_id naming
• New find_document_by_file_id tests
• Updated RAG service tests (test_rag_service, test_search_service, test_indexing_service) for file_id
• format_search_results tests updated for file_id annotation
• Output validation step tests updated
• Manual: verify Red Flag DD workflow end-to-end
• Manual: verify chat sidebar shows correct status for cross-thread human input

Summary by CodeRabbit

• New Features

  • Introduced "Red Flag DD Report" workflow enabling automated document generation with knowledge base integration and LLM-powered analysis.
  • Enhanced chat status indicators to display when a workflow is paused awaiting user input.

• Improvements

  • Refined document identification and tracking mechanisms across the system.

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[coderabbitai]

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

This PR unifies identifiers across the RAG, Convex platform, and database layers by systematically replacing document_id/document_ids with file_id/file_ids throughout API models, database schemas, service implementations, and client code. It adds file metadata linking to associate uploaded files with created documents via a new fileMetadata schema field and linkDocumentToFile internal mutation. A shared RAG result parsing utility (parseRagResults) is introduced to extract normalized relevance scores and matched content blocks. The chat sidebar logic is updated to detect workflow execution pauses by cross-referencing human input approvals. A new DOCX generation workflow definition (red-flag-dd.json) is added to support templated report generation with RAG-backed content replacement and track changes.

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~45 minutes

Possibly related PRs

• #833: Performs identical document_id → file_id identifier unification across RAG APIs, Convex agent document helpers, and workflow document actions.
• #794: Modifies RAG search tool payload structure and file-ID resolution logic with overlapping changes to file identifier propagation.
• #722: Adds DOCX-generation and contract-comparison workflows with extensive overlapping code-level changes to RAG identifier migration, file metadata, and search schema.

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 44.94% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the three main objectives: introducing a Red Flag DD workflow, unifying the file_id naming across the RAG service, and implementing document-file linking.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch feat/red-flag-dd-workflow

---

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