feat(repos): multi-machine path support via host_paths

Adds a JSONB column `host_paths` to managed_repos mapping hostname → absolute local path. Fixes the consistency-checker failure when the same repo lives at different paths on different machines (e.g. /home/worsch/marki-docx on the workstation vs /home/tegwick/marki-docx on custodiancore). Changes: - Migration g4b5c6d7e8f9: adds host_paths JSONB (default {}) - Model: host_paths Mapped[dict] column - Schemas: host_paths in RepoRead; new RepoPathRegister schema - Router: POST /repos/{slug}/paths/ — merges one host entry - consistency_check.py: resolve_repo_path() prefers host_paths [hostname] over local_path; --repo-path CLI override added - MCP: update_repo_path(slug, path, host?) tool - Makefile: register-path target; REPO_PATH passthrough on check-consistency and fix-consistency targets - TOOLS.md: documents update_repo_path Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-16 16:30:55 +01:00
parent d66f23026d
commit 82552b8d59
8 changed files with 133 additions and 11 deletions
--- a/22
+++ b/22
@@ -1,4 +1,4 @@
-.PHONY: install install-cli db db-tools migrate seed api dashboard check start clean register-project validate-adr add-domain rename-domain add-repo list-repos cleanup-stale tunnel tunnel-daemon tunnel-loop tunnel-status tunnel-stop install-hooks install-hooks-all gitea-inventory
+.PHONY: install install-cli db db-tools migrate seed api dashboard check start clean register-project validate-adr add-domain rename-domain add-repo list-repos register-path cleanup-stale tunnel tunnel-daemon tunnel-loop tunnel-status tunnel-stop install-hooks install-hooks-all gitea-inventory

 COMPOSE = docker compose -f infra/docker-compose.yml --env-file .env

@@ -135,6 +135,14 @@ rename-domain:
 	  -H "Content-Type: application/json" \
 	  -d "{\"new_slug\": \"$(NEW_SLUG)\", \"new_name\": \"$(NEW_NAME)\"}" | python3 -m json.tool

+## Register this machine's local path for a repo: make register-path REPO=marki-docx PATH=/home/tegwick/marki-docx
+register-path:
+	@test -n "$(REPO)" || (echo "ERROR: REPO is required. Usage: make register-path REPO=<slug> PATH=<path>"; exit 1)
+	@test -n "$(PATH)" || (echo "ERROR: PATH is required. Usage: make register-path REPO=<slug> PATH=<path>"; exit 1)
+	curl -sf -X POST "http://127.0.0.1:8000/repos/$(REPO)/paths/" \
+	  -H "Content-Type: application/json" \
+	  -d "{\"host\": \"$$(hostname)\", \"path\": \"$(PATH)\"}" | python3 -m json.tool
+
 ## List repos for a domain: make list-repos DOMAIN=railiance
 list-repos:
 	@test -n "$(DOMAIN)" || (echo "ERROR: DOMAIN is required."; exit 1)
@@ -166,15 +174,19 @@ validate-adr:
 	@test -n "$(REPO)" || (echo "ERROR: REPO is required. Usage: make validate-adr REPO=<path> [DOMAIN=<slug>]"; exit 1)
 	uv run python scripts/validate_repo_adr.py "$(REPO)" $(if $(DOMAIN),--domain "$(DOMAIN)",)

-## Check a single repo for ADR-001 consistency: make check-consistency REPO=the-custodian
+## Check a single repo for ADR-001 consistency: make check-consistency REPO=the-custodian [REPO_PATH=/override]
 check-consistency:
 	@test -n "$(REPO)" || (echo "ERROR: REPO is required. Usage: make check-consistency REPO=<slug>"; exit 1)
-	uv run python scripts/consistency_check.py --repo "$(REPO)" $(if $(API_BASE),--api-base "$(API_BASE)",)
+	uv run python scripts/consistency_check.py --repo "$(REPO)" \
+	  $(if $(API_BASE),--api-base "$(API_BASE)",) \
+	  $(if $(REPO_PATH),--repo-path "$(REPO_PATH)",)

-## Check and auto-fix a single repo: make fix-consistency REPO=the-custodian
+## Check and auto-fix a single repo: make fix-consistency REPO=the-custodian [REPO_PATH=/override]
 fix-consistency:
 	@test -n "$(REPO)" || (echo "ERROR: REPO is required. Usage: make fix-consistency REPO=<slug>"; exit 1)
-	uv run python scripts/consistency_check.py --repo "$(REPO)" --fix $(if $(API_BASE),--api-base "$(API_BASE)",)
+	uv run python scripts/consistency_check.py --repo "$(REPO)" --fix \
+	  $(if $(API_BASE),--api-base "$(API_BASE)",) \
+	  $(if $(REPO_PATH),--repo-path "$(REPO_PATH)",)

 ## Check all registered repos for ADR-001 consistency
 check-consistency-all:
--- a/api/models/managed_repo.py
+++ b/api/models/managed_repo.py
@@ -2,7 +2,7 @@ import uuid
 from datetime import datetime

 from sqlalchemy import DateTime, ForeignKey, String, Text
-from sqlalchemy.dialects.postgresql import UUID
+from sqlalchemy.dialects.postgresql import JSONB, UUID
 from sqlalchemy.orm import Mapped, mapped_column, relationship

 from api.models.base import Base, TimestampMixin, new_uuid
@@ -20,6 +20,7 @@ class ManagedRepo(Base, TimestampMixin):
    slug: Mapped[str] = mapped_column(String(100), unique=True, nullable=False, index=True)
    name: Mapped[str] = mapped_column(String(200), nullable=False)
    local_path: Mapped[str | None] = mapped_column(Text, nullable=True)
+    host_paths: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict, server_default="{}")
    remote_url: Mapped[str | None] = mapped_column(Text, nullable=True)
    description: Mapped[str | None] = mapped_column(Text, nullable=True)
    status: Mapped[str] = mapped_column(String(20), nullable=False, default="active")
--- a/api/routers/repos.py
+++ b/api/routers/repos.py
@@ -15,6 +15,7 @@ from api.schemas.managed_repo import (
    DispatchWorkstream,
    RepoCreate,
    RepoDispatch,
+    RepoPathRegister,
    RepoRead,
    RepoUpdate,
 )
@@ -89,6 +90,26 @@ async def update_repo(
    return repo


+@router.post("/{slug}/paths/", response_model=RepoRead)
+async def register_host_path(
+    slug: str,
+    body: RepoPathRegister,
+    session: AsyncSession = Depends(get_session),
+) -> ManagedRepo:
+    """Register or update the local path for a specific host.
+
+    Merges {"host": path} into host_paths without overwriting other entries.
+    Use this when a repo lives at a different absolute path on different machines.
+    """
+    repo = await _get_repo_by_slug(slug, session)
+    updated = dict(repo.host_paths or {})
+    updated[body.host] = body.path
+    repo.host_paths = updated
+    await session.commit()
+    await session.refresh(repo)
+    return repo
+
+
@router.patch("/{slug}/archive", response_model=RepoRead)
 async def archive_repo(
    slug: str,
--- a/api/schemas/managed_repo.py
+++ b/api/schemas/managed_repo.py
@@ -24,6 +24,12 @@ class RepoUpdate(BaseModel):
    last_state_synced_at: datetime | None = None


+class RepoPathRegister(BaseModel):
+    """Register a machine-local path for a repo on a specific host."""
+    host: str
+    path: str
+
+
 class RepoRead(BaseModel):
    model_config = ConfigDict(from_attributes=True)
    id: uuid.UUID
@@ -32,6 +38,7 @@ class RepoRead(BaseModel):
    slug: str
    name: str
    local_path: str | None = None
+    host_paths: dict = {}
    remote_url: str | None = None
    description: str | None = None
    status: str
--- a/mcp_server/TOOLS.md
+++ b/mcp_server/TOOLS.md
@@ -104,6 +104,7 @@ Domains are now first-class DB entities. Use `list_domains()` to discover availa
 | `archive_domain(slug)` | `slug` | Soft-delete; fails if active topics exist. |
 | `list_domain_repos(domain_slug)` | `domain_slug` | List repos registered under a domain. |
 | `register_repo(domain_slug, name, ...)` | `slug?`; `local_path?`; `remote_url?` | Register a git repo under a domain. |
+| `update_repo_path(repo_slug, path, host?)` | `repo_slug`: e.g. `"marki-docx"`; `path`: absolute local path; `host`: defaults to current hostname | Register this machine's local path for a repo. Use when the same repo lives at different paths on different machines (e.g. `/home/worsch/…` vs `/home/tegwick/…`). The consistency checker prefers this over `local_path`. |

 ---

--- a/mcp_server/server.py
+++ b/mcp_server/server.py
@@ -971,6 +971,27 @@ def register_repo(
    return json.dumps(repo, indent=2)


+@mcp.tool()
+def update_repo_path(repo_slug: str, path: str, host: str | None = None) -> str:
+    """Register or update the local filesystem path for a repo on a specific host.
+
+    Use this when a repo lives at a different absolute path on different machines
+    (e.g. /home/worsch/marki-docx on the workstation vs /home/tegwick/marki-docx
+    on custodiancore). The consistency checker will prefer the host-specific path
+    over the legacy local_path field.
+
+    Args:
+        repo_slug: Managed-repo slug (e.g. 'marki-docx')
+        path: Absolute local path on the target machine (e.g. '/home/tegwick/marki-docx')
+        host: Hostname to register the path for. Defaults to the current machine's hostname.
+    """
+    import socket as _socket
+    if not host:
+        host = _socket.gethostname()
+    repo = _post(f"/repos/{repo_slug}/paths", {"host": host, "path": path})
+    return json.dumps(repo, indent=2)
+
+
 # ---------------------------------------------------------------------------
 # ADR-001 compliance validation
 # ---------------------------------------------------------------------------
--- a/migrations/versions/g4b5c6d7e8f9_add_host_paths_to_repos.py
+++ b/migrations/versions/g4b5c6d7e8f9_add_host_paths_to_repos.py
@@ -0,0 +1,38 @@
+"""add host_paths to managed_repos
+
+Revision ID: g4b5c6d7e8f9
+Revises: f3a4b5c6d7e8
+Create Date: 2026-03-16
+
+Adds a JSONB column `host_paths` to managed_repos mapping hostname → absolute
+local path. This allows the same repo to be registered at different paths on
+different machines (e.g. /home/worsch/marki-docx on the workstation and
+/home/tegwick/marki-docx on custodiancore). The consistency checker and any
+other path-resolving code prefers host_paths[current_hostname] over local_path.
+"""
+from __future__ import annotations
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+revision = "g4b5c6d7e8f9"
+down_revision = "f3a4b5c6d7e8"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "managed_repos",
+        sa.Column(
+            "host_paths",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False,
+            server_default="{}",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("managed_repos", "host_paths")
--- a/scripts/consistency_check.py
+++ b/scripts/consistency_check.py
@@ -33,6 +33,7 @@ from __future__ import annotations
 import argparse
 import json
 import re
+import socket
 import sys
 from dataclasses import dataclass, field
 from pathlib import Path
@@ -294,7 +295,22 @@ def _api_post(api_base: str, path: str, body: dict) -> Any:
 # Core check engine
 # ---------------------------------------------------------------------------

-def check_repo(api_base: str, repo_slug: str) -> ConsistencyReport:
+def resolve_repo_path(repo: dict, override: str | None = None) -> str:
+    """Resolve the local filesystem path for a repo on the current machine.
+
+    Priority:
+    1. Explicit --repo-path CLI override
+    2. host_paths[current_hostname] — per-machine path registered via POST /repos/{slug}/paths/
+    3. local_path — legacy single-path field (backward compat)
+    """
+    if override:
+        return override
+    hostname = socket.gethostname()
+    host_paths = repo.get("host_paths") or {}
+    return host_paths.get(hostname) or repo.get("local_path") or ""
+
+
+def check_repo(api_base: str, repo_slug: str, repo_path_override: str | None = None) -> ConsistencyReport:
    """Run all consistency checks for a registered repo."""
    repo = _api_get(api_base, f"/repos/{repo_slug}")
    if repo is None:
@@ -307,7 +323,7 @@ def check_repo(api_base: str, repo_slug: str) -> ConsistencyReport:
        return report

    repo_id: str = repo["id"]
-    repo_path: str = repo.get("local_path") or ""
+    repo_path: str = resolve_repo_path(repo, repo_path_override)
    report = ConsistencyReport(repo_slug=repo_slug, repo_path=repo_path)

    if not repo_path:
@@ -607,9 +623,9 @@ def _check_orphan_db(
 # Fix engine
 # ---------------------------------------------------------------------------

-def fix_repo(api_base: str, repo_slug: str) -> ConsistencyReport:
+def fix_repo(api_base: str, repo_slug: str, repo_path_override: str | None = None) -> ConsistencyReport:
    """Run checks then apply all auto-fixable issues. Returns updated report."""
-    report = check_repo(api_base, repo_slug)
+    report = check_repo(api_base, repo_slug, repo_path_override)
    fixable = [i for i in report.issues if i.fixable]

    for issue in fixable:
@@ -866,6 +882,9 @@ def main() -> None:
                       help="Run checks against all registered repos with local_path")
    parser.add_argument("--fix", action="store_true",
                        help="Apply auto-fixable issues (status drift, repo mismatch, etc.)")
+    parser.add_argument("--repo-path", metavar="PATH", default=None,
+                        help="Override the local repo path (useful when the DB has a different "
+                             "machine's path). Takes priority over host_paths and local_path.")
    parser.add_argument("--api-base", default="http://127.0.0.1:8000",
                        help="State Hub API base URL")
    parser.add_argument("--json", action="store_true", dest="as_json",
@@ -887,7 +906,9 @@ def main() -> None:
        repo_slugs = [args.repo]

    runner = fix_repo if args.fix else check_repo
-    reports = [runner(args.api_base, slug) for slug in repo_slugs]
+    # --repo-path only applies to single-repo runs; silently ignored with --all
+    path_override = args.repo_path if not args.all else None
+    reports = [runner(args.api_base, slug, path_override) for slug in repo_slugs]

    if args.as_json:
        output = (