3a5c3bcde3
When a subsequent revision of a proof is uploaded, the analysis now takes place in context of the previous version's results. The system identifies: - Resolved issues: fixed in the new revision - Outstanding issues: still present from previous version - New issues: introduced in the new revision Key changes: - Add resolvedIssues, outstandingIssues, newIssues fields to SubReview - Add PreviousReviewContext model for passing previous review data - Update all specialist agents to accept previous_review context - Extend GeminiService with include_revision_fields parameter - Add get_latest_version_review() repository method - Update LeadAgent to synthesize cross-version context in summary - Fetch previous analysis in WebSocket handler for revisions First version analysis continues to work exactly as before with revision fields set to null. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
33 lines
1.1 KiB
Python
Executable file
33 lines
1.1 KiB
Python
Executable file
from abc import ABC, abstractmethod
|
|
from typing import List, Optional, Tuple
|
|
|
|
from app.models.schemas import PreviousReviewContext, SubReview
|
|
|
|
|
|
class BaseAgent(ABC):
|
|
"""Abstract base class for all review agents."""
|
|
|
|
name: str = "Base Agent"
|
|
|
|
@abstractmethod
|
|
async def analyze(
|
|
self,
|
|
images: List[Tuple[bytes, str]],
|
|
previous_review: Optional[PreviousReviewContext] = None,
|
|
) -> SubReview:
|
|
"""
|
|
Analyze the proof and return a SubReview.
|
|
|
|
Args:
|
|
images: List of (file_data, mime_type) tuples representing the proof.
|
|
For single images/videos, this will contain one tuple.
|
|
For multi-page PDFs, this will contain one tuple per page.
|
|
previous_review: Optional context from the previous version's review
|
|
for revision-aware analysis.
|
|
|
|
Returns:
|
|
SubReview containing ragStatus, feedback, and issues.
|
|
When previous_review is provided, also includes resolvedIssues,
|
|
outstandingIssues, and newIssues.
|
|
"""
|
|
pass
|