Add GitHub PR to Launchpad MP comment mirroring tool

DEVELOPMENT.md

@@ -58,4 +58,46 @@ and the server
 spaghettihubserver
 ```
 
+## Environment Variables
+
+The following environment variables are used by the application:
+
+- `GITHUB_TOKEN` (or `--gh_token` for worker): GitHub personal access token with repo permissions for API access
+
+## Using the Mirror PR Comments Tool
+
+The mirror PR comments tool allows you to mirror all open comments from a GitHub Pull Request to a Launchpad Merge Proposal.
+
+### API Endpoint
+
+`POST /v1/tools/mirror-pr-comments`
+
+**Request Body:**
+```json
+{
+  "github_pr_url": "https://github.com/owner/repo/pull/123",
+  "launchpad_mp_url": "https://code.launchpad.net/~owner/project/+merge/456",
+  "include_outdated": false,
+  "include_review_states": false
+}
+```
+
+**Response:**
+```json
+{
+  "workflow_id": "mirror-pr-comments-<hash>",
+  "status": "started"
+}
+```
+
+**Options:**
+- `include_outdated` (bool): Include outdated review comments (default: false)
+- `include_review_states` (bool): Include review approval/rejection states as comments (default: false)
+
+The tool will:
+1. Fetch all issue comments and review comments from the GitHub PR
+2. Deduplicate against already mirrored comments (idempotent)
+3. Post new comments to the Launchpad MP
+4. Record sync metadata in the database
+
 Please note that some configurations are hardcoded. Contributions to make the code generic are more than welcome

alembic/versions/d4f9a1b2c3e5_add_mirrored_comment_table.py

@@ -0,0 +1,53 @@
+"""add mirrored_comment table
+
+Revision ID: d4f9a1b2c3e5
+Revises: cea232fe4aef
+Create Date: 2025-11-06 07:56:20.000000
+
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from sqlalchemy.schema import CreateSequence, Sequence
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = 'd4f9a1b2c3e5'
+down_revision: Union[str, None] = 'cea232fe4aef'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.execute(CreateSequence(Sequence('mirrored_comment_id_seq')))
+
+    op.create_table(
+        "mirrored_comment",
+        sa.Column("id", sa.Integer, server_default=sa.text(
+            "nextval('mirrored_comment_id_seq')"), primary_key=True),
+        sa.Column("fingerprint", sa.String(64), nullable=False),
+        sa.Column("github_comment_id", sa.String(64), nullable=False),
+        sa.Column("github_source", sa.String(32), nullable=False),
+        sa.Column("mp_identifier", sa.String(256), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("posted_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("status", sa.String(32), nullable=False),
+        sa.Column("error_message", sa.Text, nullable=True),
+    )
+
+    op.create_unique_constraint(
+        "uq_mirrored_comment_fingerprint",
+        "mirrored_comment",
+        ["fingerprint"]
+    )
+
+    op.create_index(
+        "ix_mirrored_comment_mp_identifier",
+        "mirrored_comment",
+        ["mp_identifier"]
+    )
+
+
+def downgrade() -> None:
+    pass

spaghettihub/common/db/mirrored_comments.py

@@ -0,0 +1,84 @@
+from typing import List, Optional
+
+from sqlalchemy import insert, select
+from sqlalchemy.sql.functions import count
+
+from spaghettihub.common.db.repository import BaseRepository
+from spaghettihub.common.db.sequences import MirroredCommentSequence
+from spaghettihub.common.db.tables import MirroredCommentTable
+from spaghettihub.common.models.base import ListResult
+from spaghettihub.common.models.mirrored_comments import MirroredComment
+
+
+class MirroredCommentsRepository(BaseRepository[MirroredComment]):
+    async def get_next_id(self) -> int:
+        stmt = select(MirroredCommentSequence.next_value())
+        return (
+            await self.connection_provider.get_current_connection().execute(stmt)
+        ).scalar()
+
+    async def create(self, entity: MirroredComment) -> MirroredComment:
+        stmt = (
+            insert(MirroredCommentTable)
+            .returning(
+                MirroredCommentTable.c.id,
+                MirroredCommentTable.c.fingerprint,
+                MirroredCommentTable.c.github_comment_id,
+                MirroredCommentTable.c.github_source,
+                MirroredCommentTable.c.mp_identifier,
+                MirroredCommentTable.c.created_at,
+                MirroredCommentTable.c.posted_at,
+                MirroredCommentTable.c.status,
+                MirroredCommentTable.c.error_message,
+            )
+            .values(
+                id=entity.id,
+                fingerprint=entity.fingerprint,
+                github_comment_id=entity.github_comment_id,
+                github_source=entity.github_source,
+                mp_identifier=entity.mp_identifier,
+                created_at=entity.created_at,
+                posted_at=entity.posted_at,
+                status=entity.status,
+                error_message=entity.error_message,
+            )
+        )
+        result = await self.connection_provider.get_current_connection().execute(stmt)
+        row = result.one()
+        return MirroredComment(**row._asdict())
+
+    async def find_by_fingerprint(self, fingerprint: str) -> Optional[MirroredComment]:
+        stmt = select("*").select_from(MirroredCommentTable).where(
+            MirroredCommentTable.c.fingerprint == fingerprint
+        )
+        result = await self.connection_provider.get_current_connection().execute(stmt)
+        row = result.first()
+        if not row:
+            return None
+        return MirroredComment(**row._asdict())
+
+    async def find_by_mp_identifier(self, mp_identifier: str) -> List[MirroredComment]:
+        stmt = select("*").select_from(MirroredCommentTable).where(
+            MirroredCommentTable.c.mp_identifier == mp_identifier
+        )
+        result = await self.connection_provider.get_current_connection().execute(stmt)
+        return [MirroredComment(**row._asdict()) for row in result.all()]
+
+    async def find_by_id(self, id: int) -> Optional[MirroredComment]:
+        stmt = select("*").select_from(MirroredCommentTable).where(
+            MirroredCommentTable.c.id == id
+        )
+        result = await self.connection_provider.get_current_connection().execute(stmt)
+        row = result.first()
+        if not row:
+            return None
+        return MirroredComment(**row._asdict())
+
+    async def list(self, size: int, page: int) -> ListResult[MirroredComment]:
+        pass
+
+    async def update(self, entity: MirroredComment) -> MirroredComment:
+        pass
+
+    async def delete(self, id: int) -> None:
+        pass

spaghettihub/common/db/sequences.py

@@ -9,3 +9,4 @@
     "launchpad_to_github_work_id_seq", start=1)
 UsersSequence = Sequence("user_auth_id_seq", start=1)
 MAASSequence = Sequence("maas_id_seq", start=1)
+MirroredCommentSequence = Sequence("mirrored_comment_id_seq", start=1)

spaghettihub/common/db/tables.py

@@ -4,8 +4,10 @@
 from spaghettihub.common.db.sequences import (BugCommentSequence,
                                               EmbeddingSequence,
                                               LaunchpadToGithubWorkSequence,
+                                              MAASSequence,
                                               MergeProposalsSequence,
-                                              MyTextSequence, UsersSequence, MAASSequence)
+                                              MirroredCommentSequence,
+                                              MyTextSequence, UsersSequence)
 
 METADATA = MetaData()
 
@@ -95,3 +97,17 @@
     Column("username", String(128), nullable=False),
     Column("password", Text, nullable=False)
 )
+
+MirroredCommentTable = Table(
+    "mirrored_comment",
+    METADATA,
+    Column("id", Integer, MirroredCommentSequence, primary_key=True),
+    Column("fingerprint", String(64), nullable=False, unique=True),
+    Column("github_comment_id", String(64), nullable=False),
+    Column("github_source", String(32), nullable=False),
+    Column("mp_identifier", String(256), nullable=False),
+    Column("created_at", DateTime(timezone=True), nullable=False),
+    Column("posted_at", DateTime(timezone=True), nullable=True),
+    Column("status", String(32), nullable=False),
+    Column("error_message", Text, nullable=True),
+)

spaghettihub/common/models/mirrored_comments.py

@@ -0,0 +1,16 @@
+from datetime import datetime
+from typing import Optional
+
+from pydantic import BaseModel
+
+
+class MirroredComment(BaseModel):
+    id: int
+    fingerprint: str
+    github_comment_id: str
+    github_source: str
+    mp_identifier: str
+    created_at: datetime
+    posted_at: Optional[datetime] = None
+    status: str
+    error_message: Optional[str] = None

spaghettihub/common/services/collection.py

@@ -7,6 +7,7 @@
 from spaghettihub.common.db.last_update import LastUpdateRepository
 from spaghettihub.common.db.maas import MAASRepository
 from spaghettihub.common.db.merge_proposals import MergeProposalsRepository
+from spaghettihub.common.db.mirrored_comments import MirroredCommentsRepository
 from spaghettihub.common.db.texts import TextsRepository
 from spaghettihub.common.db.users import UsersRepository
 from spaghettihub.common.services.bugs import BugsService
@@ -15,6 +16,7 @@
 from spaghettihub.common.services.github import LaunchpadToGithubWorkService
 from spaghettihub.common.services.last_update import LastUpdateService
 from spaghettihub.common.services.merge_proposals import MergeProposalsService
+from spaghettihub.common.services.mirror_comments import MirrorCommentsService
 from spaghettihub.common.services.runner import GithubWorkflowRunnerService
 from spaghettihub.common.services.texts import TextsService
 from spaghettihub.common.services.users import UsersService
@@ -29,6 +31,8 @@ class ServiceCollection:
     launchpad_to_github_work_service: LaunchpadToGithubWorkService
     users_service: UsersService
     github_workflow_runner_service: GithubWorkflowRunnerService
+    mirror_comments_service: MirrorCommentsService
+    mirrored_comments_repository: MirroredCommentsRepository
 
     @classmethod
     def produce(cls, connection_provider: ConnectionProvider, embeddings_cache: EmbeddingsCache | None = None,
@@ -75,7 +79,8 @@ def produce(cls, connection_provider: ConnectionProvider, embeddings_cache: Embe
         )
         services.github_workflow_runner_service = GithubWorkflowRunnerService(
             connection_provider=connection_provider,
-            maas_repository=MAASRepository(connection_provider=connection_provider),
+            maas_repository=MAASRepository(
+                connection_provider=connection_provider),
             webhook_secret=webhook_secret,
             temporal_client=temporal_client
         )
@@ -85,4 +90,12 @@ def produce(cls, connection_provider: ConnectionProvider, embeddings_cache: Embe
                 connection_provider=connection_provider
             )
         )
+        services.mirrored_comments_repository = MirroredCommentsRepository(
+            connection_provider=connection_provider
+        )
+        services.mirror_comments_service = MirrorCommentsService(
+            connection_provider=connection_provider,
+            mirrored_comments_repository=services.mirrored_comments_repository,
+            temporal_client=temporal_client
+        )
         return services

spaghettihub/common/services/mirror_comments.py

@@ -0,0 +1,54 @@
+import hashlib
+from typing import Optional
+
+from temporalio.client import Client
+
+from spaghettihub.common.db.base import ConnectionProvider
+from spaghettihub.common.db.mirrored_comments import MirroredCommentsRepository
+from spaghettihub.common.services.base import Service
+from spaghettihub.common.workflows.constants import TASK_QUEUE_NAME
+from spaghettihub.common.workflows.mirror_pr_comments.params import (
+    MirrorCommentsResult, MirrorPullRequestCommentsParams)
+
+
+class MirrorCommentsService(Service):
+
+    def __init__(
+            self,
+            connection_provider: ConnectionProvider,
+            mirrored_comments_repository: MirroredCommentsRepository,
+            temporal_client: Optional[Client] = None
+    ):
+        super().__init__(connection_provider)
+        self.mirrored_comments_repository = mirrored_comments_repository
+        self.temporal_client = temporal_client
+
+    async def start_mirror(
+        self,
+        github_pr_url: str,
+        launchpad_mp_url: str,
+        include_outdated: bool = False,
+        include_review_states: bool = False,
+    ) -> str:
+        """Start a workflow to mirror PR comments to Launchpad MP."""
+        # Generate unique workflow ID
+        workflow_id_content = f"{github_pr_url}:{launchpad_mp_url}"
+        workflow_hash = hashlib.sha256(
+            workflow_id_content.encode()).hexdigest()[:16]
+        workflow_id = f"mirror-pr-comments-{workflow_hash}"
+
+        params = MirrorPullRequestCommentsParams(
+            github_pr_url=github_pr_url,
+            launchpad_mp_url=launchpad_mp_url,
+            include_outdated=include_outdated,
+            include_review_states=include_review_states,
+        )
+
+        await self.temporal_client.start_workflow(
+            "mirror-pr-comments-workflow",
+            params,
+            id=workflow_id,
+            task_queue=TASK_QUEUE_NAME,
+        )
+
+        return workflow_id

spaghettihub/common/workflows/mirror_pr_comments/__init__.py

@@ -0,0 +1 @@
+# Mirror PR Comments Workflow