fix: handle bare repos in branch creation and checkout

- Fall back to symbolic-ref when checkout --orphan fails on bare repos\n- Fall back to symbolic-ref when checkout fails on bare repos\n- Make get_current_branch handle bare repos with unborn branches\n- Add integration tests for bare repo branch operations\n\nQuality gates: pytest integration tests (12 passed)

AGENTS.md

@@ -87,6 +87,31 @@ Do not claim completion without verification evidence.
 
 ## Git workflow
 
+### Branching strategy
+
+For every spec change or new functionality:
+
+1. Create a new branch from `dev` with a proper prefix:
+   - `feat/` for new features (e.g., `feat/tool-workshop`)
+   - `fix/` for bug fixes (e.g., `fix/terminal-tty`)
+   - `refactor/` for refactors (e.g., `refactor/api-cleanup`)
+   - `docs/` for documentation (e.g., `docs/api-guide`)
+   - `chore/` for maintenance (e.g., `chore/update-deps`)
+2. Branch name should reference the OpenSpec change name when applicable.
+3. Do not commit directly to `main` or `dev`.
+
+### Completion and merge
+
+When implementation is complete and verified:
+
+1. Ensure all tests pass and quality gates are met.
+2. Stage all changes with `git add -A`.
+3. Create a commit with a proper conventional commit message (see below).
+4. Switch to `dev`: `git checkout dev`.
+5. Merge the feature branch: `git merge --no-ff <branch-name>`.
+6. Push to remote: `git push origin dev`.
+7. Delete the local feature branch if desired: `git branch -d <branch-name>`.
+
 ### Auto-commit on spec completion
 
 When an OpenSpec change is fully implemented and all tasks are complete:

apps/api/alembic/versions/0013_add_config_profiles.py

@@ -1,104 +0,0 @@
-"""add config profiles, includes, mounts, and tool instance profile selection
-
-Revision ID: 0013_add_config_profiles
-Revises: 0012_default_port_req
-Create Date: 2026-05-24 12:00:00.000000
-
-"""
-from typing import Sequence, Union
-
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision: str = "0013_add_config_profiles"
-down_revision: Union[str, None] = "0012_default_port_req"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Create config_profiles table
-    op.create_table(
-        "config_profiles",
-        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("name", sa.String(length=255), nullable=False),
-        sa.Column("description", sa.Text(), nullable=True),
-        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("user_id", "name", name="uq_config_profiles_user_name"),
-    )
-    op.create_index("idx_config_profiles_user", "config_profiles", ["user_id"])
-
-    # Create config_includes table
-    op.create_table(
-        "config_includes",
-        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("profile_id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("included_profile_id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("order_index", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.ForeignKeyConstraint(["profile_id"], ["config_profiles.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["included_profile_id"], ["config_profiles.id"], ondelete="CASCADE"),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("profile_id", "included_profile_id", name="uq_config_includes_pair"),
-    )
-    op.create_index("idx_config_includes_profile", "config_includes", ["profile_id"])
-    op.create_index("idx_config_includes_included", "config_includes", ["included_profile_id"])
-
-    # Create config_mounts table
-    op.create_table(
-        "config_mounts",
-        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("profile_id", postgresql.UUID(as_uuid=True), nullable=False),
-        sa.Column("mount_path", sa.String(length=1024), nullable=False),
-        sa.Column("content", sa.Text(), nullable=True),
-        sa.Column("source_profile_id", postgresql.UUID(as_uuid=True), nullable=True),
-        sa.Column("order_index", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()"), nullable=False),
-        sa.ForeignKeyConstraint(["profile_id"], ["config_profiles.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["source_profile_id"], ["config_profiles.id"], ondelete="SET NULL"),
-        sa.PrimaryKeyConstraint("id"),
-    )
-    op.create_index("idx_config_mounts_profile", "config_mounts", ["profile_id"])
-
-    # Add selected_profile_id to tool_instances
-    op.add_column(
-        "tool_instances",
-        sa.Column("selected_profile_id", postgresql.UUID(as_uuid=True), nullable=True),
-    )
-    op.create_foreign_key(
-        "fk_tool_instances_selected_profile",
-        "tool_instances",
-        "config_profiles",
-        ["selected_profile_id"],
-        ["id"],
-        ondelete="SET NULL",
-    )
-    op.create_index("idx_tool_instances_selected_profile", "tool_instances", ["selected_profile_id"])
-
-
-def downgrade() -> None:
-    # Remove selected_profile_id from tool_instances
-    op.drop_index("idx_tool_instances_selected_profile", table_name="tool_instances")
-    op.drop_constraint("fk_tool_instances_selected_profile", "tool_instances", type_="foreignkey")
-    op.drop_column("tool_instances", "selected_profile_id")
-
-    # Drop config_mounts
-    op.drop_index("idx_config_mounts_profile", table_name="config_mounts")
-    op.drop_table("config_mounts")
-
-    # Drop config_includes
-    op.drop_index("idx_config_includes_included", table_name="config_includes")
-    op.drop_index("idx_config_includes_profile", table_name="config_includes")
-    op.drop_table("config_includes")
-
-    # Drop config_profiles
-    op.drop_index("idx_config_profiles_user", table_name="config_profiles")
-    op.drop_table("config_profiles")

apps/api/alembic/versions/0014_add_profile_resolver_fields.py

@@ -1,119 +0,0 @@
-"""add profile resolver fields to config profiles and mounts
-
-Revision ID: 0014_add_profile_resolver_fields
-Revises: 0013_add_config_profiles
-Create Date: 2026-05-24 14:00:00.000000
-
-"""
-from typing import Sequence, Union
-
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision: str = "0014_add_profile_resolver_fields"
-down_revision: Union[str, None] = "0013_add_config_profiles"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Add fields to config_profiles
-    op.add_column(
-        "config_profiles",
-        sa.Column("project_id", postgresql.UUID(as_uuid=True), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("tool_type_id", postgresql.UUID(as_uuid=True), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("environment_variables", sa.JSON(), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("start_command", sa.Text(), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("working_directory", sa.Text(), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("port", sa.Integer(), nullable=True),
-    )
-    op.add_column(
-        "config_profiles",
-        sa.Column("is_default", sa.Boolean(), nullable=False, server_default="false"),
-    )
-    
-    # Add foreign keys for project and tool_type
-    op.create_foreign_key(
-        "fk_config_profiles_project",
-        "config_profiles",
-        "projects",
-        ["project_id"],
-        ["id"],
-        ondelete="CASCADE",
-    )
-    op.create_foreign_key(
-        "fk_config_profiles_tool_type",
-        "config_profiles",
-        "tool_types",
-        ["tool_type_id"],
-        ["id"],
-        ondelete="CASCADE",
-    )
-    
-    # Create indices
-    op.create_index("idx_config_profiles_project", "config_profiles", ["project_id"])
-    op.create_index("idx_config_profiles_tool_type", "config_profiles", ["tool_type_id"])
-    
-    # Alter config_mounts: rename mount_path to target_path, add mode, change content to files JSON
-    op.alter_column("config_mounts", "mount_path", new_column_name="target_path")
-    op.add_column(
-        "config_mounts",
-        sa.Column("mode", sa.String(length=10), nullable=False, server_default="rw"),
-    )
-    op.add_column(
-        "config_mounts",
-        sa.Column("files", sa.JSON(), nullable=True),
-    )
-    # Drop the source_profile foreign key if it exists
-    op.drop_constraint(
-        "config_mounts_source_profile_id_fkey",
-        "config_mounts",
-        type_="foreignkey",
-    )
-    op.drop_column("config_mounts", "content")
-    op.drop_column("config_mounts", "source_profile_id")
-
-
-def downgrade() -> None:
-    # Restore config_mounts
-    op.add_column(
-        "config_mounts",
-        sa.Column("source_profile_id", postgresql.UUID(as_uuid=True), nullable=True),
-    )
-    op.add_column(
-        "config_mounts",
-        sa.Column("content", sa.Text(), nullable=True),
-    )
-    op.drop_column("config_mounts", "files")
-    op.drop_column("config_mounts", "mode")
-    op.alter_column("config_mounts", "target_path", new_column_name="mount_path")
-    
-    # Restore config_profiles
-    op.drop_index("idx_config_profiles_tool_type", table_name="config_profiles")
-    op.drop_index("idx_config_profiles_project", table_name="config_profiles")
-    op.drop_constraint("fk_config_profiles_tool_type", "config_profiles", type_="foreignkey")
-    op.drop_constraint("fk_config_profiles_project", "config_profiles", type_="foreignkey")
-    op.drop_column("config_profiles", "is_default")
-    op.drop_column("config_profiles", "port")
-    op.drop_column("config_profiles", "working_directory")
-    op.drop_column("config_profiles", "start_command")
-    op.drop_column("config_profiles", "environment_variables")
-    op.drop_column("config_profiles", "tool_type_id")
-    op.drop_column("config_profiles", "project_id")

apps/api/src/api/tool_instances.py

@@ -18,7 +18,6 @@ from src.auth.dependencies import get_current_user_id
 from src.auth.dependencies import get_db_session
 from src.models.git_repository import GitRepository
 from src.models.project import Project
-from src.models.config_profile import ConfigProfile
 from src.models.tool_config import ToolConfig
 from src.models.tool_instance import ToolInstance
 from src.models.tool_type import ToolType
@@ -31,18 +30,20 @@ from src.services.docker import (
     execute_compose_command,
     find_free_port,
     get_container_id,
+    get_container_logs,
     get_container_name,
+    get_container_status,
     recreate_tunnel,
     render_compose_template,
     start_cloudflared_tunnel,
     stop_cloudflared_tunnel,
+    wait_for_container_running,
     write_compose_file,
     write_config_files,
     write_env_file,
     write_config_folder_files,
 )
 from src.services.docker_build import build_image
-from src.services.profile_resolver import resolve_profile
 from src.services.readiness_probe import execute_probe
 
 router = APIRouter(prefix="/projects", tags=["tool-instances"])
@@ -55,7 +56,6 @@ class CreateInstanceRequest(BaseModel):
 
     tool_type_id: str = Field(description="UUID of the tool type to instantiate")
     display_name: str | None = Field(default=None, description="Optional display name for the instance")
-    config_profile_id: str | None = Field(default=None, description="Optional config profile ID to apply to the instance")
 
 
 def _modify_compose_file(
@@ -110,68 +110,6 @@ def _modify_compose_file(
     compose_file.write_text(yaml.dump(compose_data, default_flow_style=False))
 
 
-async def _apply_resolved_profile(
-    profile: ConfigProfile,
-    instance_dir: str,
-    env_vars: dict[str, str],
-    port_override: int | None,
-    start_command: str | None,
-    working_directory: str | None,
-    extra_volumes: list[dict],
-) -> tuple[dict[str, str], int | None, str | None, str | None, list[dict]]:
-    """Resolve a profile and apply its output to instance configuration.
-
-    Merges resolved profile env vars (profile wins), applies runtime hints,
-    stages mount files to the instance directory, and adds Docker bind mounts.
-
-    Args:
-        profile: The config profile to resolve and apply.
-        instance_dir: Path to the instance directory.
-        env_vars: Current environment variables dict (will be updated).
-        port_override: Current port override (may be updated).
-        start_command: Current start command (may be updated).
-        working_directory: Current working directory (may be updated).
-        extra_volumes: Current extra volumes list (will be extended).
-
-    Returns:
-        Updated (env_vars, port_override, start_command, working_directory, extra_volumes).
-    """
-    from pathlib import Path
-
-    resolved = resolve_profile(profile)
-
-    # Merge env vars from resolved profile (profile wins over tool configs)
-    if resolved.environment_variables:
-        env_vars.update(resolved.environment_variables)
-
-    # Apply runtime hints
-    if resolved.runtime_hints.start_command is not None:
-        start_command = resolved.runtime_hints.start_command
-    if resolved.runtime_hints.working_directory is not None:
-        working_directory = resolved.runtime_hints.working_directory
-    if resolved.runtime_hints.port is not None:
-        port_override = resolved.runtime_hints.port
-
-    # Stage mount files and add volume mounts
-    for target_path, mount in resolved.mounts.items():
-        safe_name = target_path.strip("/").replace("/", "_")
-        mount_dir = Path(instance_dir) / "mounts" / safe_name
-        mount_dir.mkdir(parents=True, exist_ok=True)
-
-        for rel_path, content in mount.files.items():
-            file_path = mount_dir / rel_path
-            file_path.parent.mkdir(parents=True, exist_ok=True)
-            file_path.write_text(content)
-
-        extra_volumes.append({
-            "source": str(mount_dir),
-            "target": target_path,
-            "type": mount.mode,
-        })
-
-    return env_vars, port_override, start_command, working_directory, extra_volumes
-
-
 async def _get_user(session: AsyncSession, user_id: uuid.UUID) -> User:
     """Fetch a user by ID or raise 404 if not found."""
     user = await session.get(User, user_id)
@@ -254,29 +192,6 @@ async def create_instance(
             status_code=status.HTTP_404_NOT_FOUND, detail="tool type not found"
         )
 
-    # Validate config_profile_id if provided
-    selected_profile_id: uuid.UUID | None = None
-    if data.config_profile_id:
-        try:
-            selected_profile_id = uuid.UUID(data.config_profile_id)
-        except ValueError:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail="invalid config_profile_id format",
-            )
-        
-        config_profile = await session.get(ConfigProfile, selected_profile_id)
-        if config_profile is None:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail="config profile not found",
-            )
-        if config_profile.user_id != user_id:
-            raise HTTPException(
-                status_code=status.HTTP_403_FORBIDDEN,
-                detail="config profile does not belong to user",
-            )
-
     try:
         # Generate unique name
         instance_name = f"{tool_type.name}-{repo.name}-{uuid.uuid4().hex[:8]}"
@@ -350,7 +265,6 @@ services:
             status="pending",
             compose_path=compose_path,
             port=tool_port,
-            selected_profile_id=selected_profile_id,
         )
         session.add(instance)
         await session.commit()
@@ -362,7 +276,6 @@ services:
             "display_name": instance.display_name,
             "tool_type_id": str(instance.tool_type_id),
             "status": instance.status,
-            "config_profile_id": str(instance.selected_profile_id) if instance.selected_profile_id else None,
             "created_at": instance.created_at.isoformat(),
         }
     except Exception as exc:
@@ -425,7 +338,6 @@ async def list_instances(
             "status": i.status,
             "url": i.url,
             "port": i.port,
-            "config_profile_id": str(i.selected_profile_id) if i.selected_profile_id else None,
             "created_at": i.created_at.isoformat(),
         })
 
@@ -486,7 +398,6 @@ async def get_instance(
         "compose_path": instance.compose_path,
         "url": instance.url,
         "port": instance.port,
-        "config_profile_id": str(instance.selected_profile_id) if instance.selected_profile_id else None,
         "last_started_at": instance.last_started_at.isoformat() if instance.last_started_at else None,
         "last_stopped_at": instance.last_stopped_at.isoformat() if instance.last_stopped_at else None,
         "created_at": instance.created_at.isoformat(),
@@ -544,7 +455,6 @@ async def start_instance(
     extra_env_vars = {}
     extra_volumes = []
     
-    # Fetch all matching configs for this tool type
     config_query = select(ToolConfig).where(
         ToolConfig.user_id == user_id,
         ToolConfig.tool_type_id == instance.tool_type_id,
@@ -577,31 +487,6 @@ async def start_instance(
     # Merge extra env vars
     env_vars.update(extra_env_vars)
     
-    # Apply resolved profile output if a profile is selected
-    if instance.selected_profile_id:
-        selected_profile = await session.get(ConfigProfile, instance.selected_profile_id)
-        if selected_profile is None:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail="config profile not found",
-            )
-        if selected_profile.user_id != user_id:
-            raise HTTPException(
-                status_code=status.HTTP_403_FORBIDDEN,
-                detail="config profile does not belong to user",
-            )
-        instance_dir = os.path.dirname(instance.compose_path)
-        env_vars, port_override, start_command, working_directory, extra_volumes = await _apply_resolved_profile(
-            selected_profile,
-            instance_dir,
-            env_vars,
-            port_override,
-            start_command,
-            working_directory,
-            extra_volumes,
-        )
-        logger.info("Applied resolved profile %s for instance %s", selected_profile.name, instance.id)
-    
     # Fetch active config folders for this user
     folder_query = select(ConfigFolder).where(
         ConfigFolder.user_id == user_id,
@@ -670,20 +555,67 @@ async def start_instance(
         else:
             logger.warning("Failed to connect %s to backend network", container_name)
 
-    instance.status = "starting"
-    instance.last_started_at = datetime.now()
-    await session.commit()
-    logger.info("Instance %s container is running, checking readiness", instance.id)
-
+    # Verify container reached running state
+    if instance.container_id:
+        instance.status = "starting"
+        instance.last_started_at = datetime.now()
+        await session.commit()
+        logger.info("Instance %s: verifying container startup...", instance.id)
+        
+        startup_result = wait_for_container_running(instance.container_id, timeout=30, interval=2.0)
+        
+        if not startup_result["success"]:
+            # Container failed to start
+            error_msg = f"Container failed to start: status={startup_result['status']}"
+            if startup_result["exit_code"] is not None:
+                error_msg += f", exit_code={startup_result['exit_code']}"
+            
+            # Get logs for debugging
+            logs = get_container_logs(instance.container_id, tail=50)
+            
+            instance.status = "error"
+            await session.commit()
+            logger.error(
+                "Instance %s container startup failed after %.1fs: %s\nLogs:\n%s",
+                instance.id,
+                startup_result["waited_seconds"],
+                error_msg,
+                logs,
+            )
+            return {
+                "status": "error",
+                "error": error_msg,
+                "logs": logs,
+            }
+        
+        logger.info(
+            "Instance %s container started successfully after %.1fs",
+            instance.id,
+            startup_result["waited_seconds"],
+        )
+    
     # Execute readiness probe if configured
     tool_type = await session.get(ToolType, instance.tool_type_id)
-    if tool_type and tool_type.readiness_probe:
-        probe_config = tool_type.readiness_probe
-        probe_command = probe_config.get("command", "")
-        probe_timeout = probe_config.get("timeout", 30)
-        probe_interval = probe_config.get("interval", 2)
+    if tool_type and instance.container_id:
+        # Determine probe command
+        probe_command = None
+        probe_timeout = 30
+        probe_interval = 2
         
-        if probe_command and instance.container_id:
+        if tool_type.readiness_probe:
+            probe_config = tool_type.readiness_probe
+            probe_command = probe_config.get("command", "")
+            probe_timeout = probe_config.get("timeout", 30)
+            probe_interval = probe_config.get("interval", 2)
+        elif "web" in (tool_type.interfaces or []):
+            # Default probe for web tools
+            probe_command = f"curl -f http://localhost:{tool_type.default_port or 8080}"
+            probe_timeout = 30
+            probe_interval = 2
+        
+        if probe_command:
+            instance.status = "probing"
+            await session.commit()
             logger.info(
                 "Executing readiness probe for instance %s: command='%s', timeout=%d, interval=%d",
                 instance.id, probe_command, probe_timeout, probe_interval
@@ -696,14 +628,25 @@ async def start_instance(
                 interval=probe_interval,
             )
             
+            # Store probe result
+            instance.probe_result = {
+                "success": success,
+                "command": probe_command,
+                "logs": probe_logs,
+                "timestamp": datetime.now().isoformat(),
+            }
+            
             if not success:
-                instance.status = "failed"
-                instance.url = None
-                instance.public_url = None
+                instance.status = "unhealthy"
                 await session.commit()
-                logger.error("Readiness probe failed for instance %s: %s", instance.id, "\n".join(probe_logs))
+                logger.error(
+                    "Readiness probe failed for instance %s after %ds: %s",
+                    instance.id,
+                    probe_timeout,
+                    "\n".join(probe_logs),
+                )
                 return {
-                    "status": "failed",
+                    "status": "unhealthy",
                     "error": f"Readiness probe failed after {probe_timeout}s",
                     "probe_logs": probe_logs,
                 }
@@ -873,105 +816,8 @@ async def restart_instance(
             logger.warning("Failed to stop old tunnel for instance %s: %s", instance.id, exc)
 
     if instance.compose_path and os.path.exists(instance.compose_path):
-        # Re-apply configuration using stored profile instead of current defaults
-        env_vars = {}
-        config_files = {}
-        port_override = None
-        start_command = None
-        working_directory = None
-        extra_env_vars = {}
-        extra_volumes = []
-        
-        # Fetch all matching configs for this tool type
-        config_query = select(ToolConfig).where(
-            ToolConfig.user_id == user_id,
-            ToolConfig.tool_type_id == instance.tool_type_id,
-        ).where(
-            (ToolConfig.project_id == project_id) | (ToolConfig.project_id.is_(None))
-        )
-        
-        config_result = await session.execute(config_query)
-        configs = config_result.scalars().all()
-        logger.info("Found %d tool configs for restart of instance %s", len(configs), instance.id)
-        
-        for config in configs:
-            if config.config_type == "env":
-                env_vars[config.key] = config.value
-            elif config.config_type == "file" and config.file_path:
-                config_files[config.file_path] = config.value
-            
-            if config.port_override:
-                port_override = config.port_override
-            if config.start_command:
-                start_command = config.start_command
-            if config.working_directory:
-                working_directory = config.working_directory
-            if config.environment_variables:
-                extra_env_vars.update(config.environment_variables)
-            if config.volumes:
-                extra_volumes.extend(config.volumes)
-        
-        # Merge extra env vars
-        env_vars.update(extra_env_vars)
-        
-        # Apply stored profile on restart instead of current defaults
-        if instance.selected_profile_id:
-            stored_profile = await session.get(ConfigProfile, instance.selected_profile_id)
-            if stored_profile is None:
-                raise HTTPException(
-                    status_code=status.HTTP_404_NOT_FOUND,
-                    detail="config profile not found",
-                )
-            if stored_profile.user_id != user_id:
-                raise HTTPException(
-                    status_code=status.HTTP_403_FORBIDDEN,
-                    detail="config profile does not belong to user",
-                )
-            instance_dir = os.path.dirname(instance.compose_path)
-            env_vars, port_override, start_command, working_directory, extra_volumes = await _apply_resolved_profile(
-                stored_profile,
-                instance_dir,
-                env_vars,
-                port_override,
-                start_command,
-                working_directory,
-                extra_volumes,
-            )
-            logger.info("Re-applied stored profile %s for restart of instance %s", stored_profile.name, instance.id)
-        
-        # Fetch active config folders for this user
-        folder_query = select(ConfigFolder).where(
-            ConfigFolder.user_id == user_id,
-            ConfigFolder.is_active == True,
-        )
-        folder_result = await session.execute(folder_query)
-        config_folders = folder_result.scalars().all()
-        
-        # Write env file and config files
-        instance_dir = os.path.dirname(instance.compose_path)
-        env_file_path = None
-        
-        if env_vars:
-            env_file_path = write_env_file(instance_dir, env_vars)
-            logger.info("Wrote env file for restart of instance %s: %s", instance.id, env_file_path)
-        
-        if config_files:
-            write_config_files(instance_dir, config_files)
-            logger.info("Wrote %d config files for restart of instance %s", len(config_files), instance.id)
-        
-        # Write config folder files
-        if config_folders:
-            folder_volumes = write_config_folder_files(instance_dir, config_folders, str(project_id))
-            extra_volumes.extend(folder_volumes)
-            logger.info("Wrote config folders with %d volume mounts for restart of instance %s", len(folder_volumes), instance.id)
-        
-        # Modify compose file if needed
-        if port_override or start_command or working_directory or extra_volumes:
-            _modify_compose_file(instance.compose_path, port_override, start_command, working_directory, extra_volumes)
-            logger.info("Modified compose file for restart of instance %s", instance.id)
-
         returncode, stdout, stderr = execute_compose_command(
-            instance.compose_path, "restart", env_file=env_file_path
+            instance.compose_path, "restart"
         )
 
         if returncode == 0:
@@ -1171,6 +1017,17 @@ async def recreate_tunnel_endpoint(
             detail="instance must be running to recreate tunnel",
         )
 
+    # Validate tunnel is actually broken before recreating
+    if instance.url:
+        tunnel_health = check_tunnel_health(instance.url)
+        if tunnel_health["tunnel_status"] == "error_response":
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=f"Tunnel is working but application returned HTTP {tunnel_health.get('status_code')}. Recreating the tunnel will not fix this issue.",
+            )
+        elif tunnel_health["tunnel_status"] == "healthy":
+            return {"status": "healthy", "url": instance.url, "message": "Tunnel is already healthy"}
+
     # Get tool type for default port
     tool_type = await session.get(ToolType, instance.tool_type_id)
     instance_port = tool_type.default_port if tool_type and tool_type.default_port else 8080
@@ -1202,8 +1059,8 @@ async def recreate_tunnel_endpoint(
 
 @router.get(
     "/{project_id}/repositories/{repo_id}/instances/{instance_id}/health",
-    summary="Check tunnel health",
-    description="Check if the temporary Cloudflare tunnel for an instance is healthy.",
+    summary="Check instance health",
+    description="Check container and tunnel health for an instance.",
 )
 async def check_instance_tunnel_health(
     project_id: uuid.UUID,
@@ -1212,7 +1069,7 @@ async def check_instance_tunnel_health(
     user_id: uuid.UUID = Depends(get_current_user_id),
     session: AsyncSession = Depends(get_db_session),
 ) -> dict:
-    """Check tunnel health for an instance.
+    """Check health for an instance (container + tunnel).
 
     Args:
         project_id: UUID of the project.
@@ -1222,7 +1079,7 @@ async def check_instance_tunnel_health(
         session: Database session.
 
     Returns:
-        Dictionary with health status.
+        Dictionary with container_status, tunnel_status, probe_status, and overall healthy flag.
     """
     _user = await _get_user(session, user_id)
     _project = await _get_owned_project(project_id, user_id, session)
@@ -1233,11 +1090,50 @@ async def check_instance_tunnel_health(
             status_code=status.HTTP_404_NOT_FOUND, detail="instance not found"
         )
 
-    if not instance.url or instance.status != "running":
-        return {"healthy": False, "status_code": None, "error": "instance not running"}
+    # Check container status
+    container_info = {"status": "not_found", "exit_code": None, "health": None}
+    if instance.container_id:
+        container_info = get_container_status(instance.container_id)
 
-    health = check_tunnel_health(instance.url)
-    return health
+    # Build response
+    response = {
+        "healthy": False,
+        "container_status": container_info["status"],
+        "container_health": container_info["health"],
+        "tunnel_status": "not_applicable",
+        "tunnel_status_code": None,
+        "probe_status": "not_applicable",
+        "last_probe_output": None,
+        "error": None,
+    }
+
+    # Determine probe status
+    if instance.status == "probing":
+        response["probe_status"] = "pending"
+    elif instance.probe_result:
+        response["probe_status"] = "success" if instance.probe_result.get("success") else "failed"
+        response["last_probe_output"] = "\n".join(instance.probe_result.get("logs", []))[:500]
+
+    # Check tunnel health if instance has a URL and is web-enabled
+    if instance.url and instance.status in ("running", "unhealthy"):
+        tunnel_health = check_tunnel_health(instance.url)
+        response["tunnel_status"] = tunnel_health["tunnel_status"]
+        response["tunnel_status_code"] = tunnel_health.get("status_code")
+        if tunnel_health.get("error"):
+            response["error"] = tunnel_health["error"]
+
+    # Overall healthy only if container is running AND tunnel is healthy
+    container_healthy = container_info["status"] == "running"
+    tunnel_healthy = response["tunnel_status"] == "healthy"
+    response["healthy"] = container_healthy and tunnel_healthy
+
+    # If container is not running, override error message
+    if not container_healthy:
+        response["error"] = f"Container is {container_info['status']}"
+        if container_info["exit_code"] is not None:
+            response["error"] += f" (exit code: {container_info['exit_code']})"
+
+    return response
 
 
 @router.get(

apps/api/src/models/__init__.py

@@ -1,8 +1,5 @@
 from src.models.base import Base
 from src.models.config_folder import ConfigFolder
-from src.models.config_include import ConfigInclude
-from src.models.config_mount import ConfigMount
-from src.models.config_profile import ConfigProfile
 from src.models.git_repository import GitRepository
 from src.models.project import Project
 from src.models.ssh_key import SSHKey
@@ -11,17 +8,4 @@ from src.models.tool_type import ToolType
 from src.models.user import User
 from src.models.user_config import UserConfig
 
-__all__ = [
-    "Base",
-    "ConfigFolder",
-    "ConfigInclude",
-    "ConfigMount",
-    "ConfigProfile",
-    "GitRepository",
-    "Project",
-    "SSHKey",
-    "ToolInstance",
-    "ToolType",
-    "User",
-    "UserConfig",
-]
+__all__ = ["Base", "ConfigFolder", "GitRepository", "Project", "SSHKey", "ToolInstance", "ToolType", "User", "UserConfig"]

apps/api/src/models/config_folder.py

@@ -26,8 +26,6 @@ class ConfigFolder(UUIDPrimaryKeyMixin, TimestampMixin, Base):
     project_overrides: Mapped[dict | None] = mapped_column(
         JSON, default=dict, nullable=True
     )  # {"project_id": {"mount_path": "...", "files": {...}}}
-    # DEPRECATED: Legacy auto-mounting flag. No longer used for launch-time
-    # auto-mounting. Use ConfigProfile and ToolInstance.selected_profile_id instead.
     is_active: Mapped[bool] = mapped_column(Boolean, default=True, nullable=False)
 
     user: Mapped["User"] = relationship()

apps/api/src/models/config_include.py

@@ -1,36 +0,0 @@
-import uuid
-from typing import TYPE_CHECKING
-
-from sqlalchemy import ForeignKey, Integer, UniqueConstraint
-from sqlalchemy import Uuid as UUID
-from sqlalchemy.orm import Mapped, mapped_column, relationship
-
-from src.models.base import Base, TimestampMixin, UUIDPrimaryKeyMixin
-
-if TYPE_CHECKING:
-    from src.models.config_profile import ConfigProfile
-
-
-class ConfigInclude(UUIDPrimaryKeyMixin, TimestampMixin, Base):
-    __tablename__ = "config_includes"
-    __table_args__ = (
-        UniqueConstraint("profile_id", "included_profile_id", name="uq_config_includes_pair"),
-    )
-
-    profile_id: Mapped[uuid.UUID] = mapped_column(
-        UUID(), ForeignKey("config_profiles.id", ondelete="CASCADE"), nullable=False
-    )
-    included_profile_id: Mapped[uuid.UUID] = mapped_column(
-        UUID(), ForeignKey("config_profiles.id", ondelete="CASCADE"), nullable=False
-    )
-    order_index: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-
-    profile: Mapped["ConfigProfile"] = relationship(
-        "ConfigProfile",
-        foreign_keys=[profile_id],
-        back_populates="includes",
-    )
-    included_profile: Mapped["ConfigProfile"] = relationship(
-        "ConfigProfile",
-        foreign_keys=[included_profile_id],
-    )

apps/api/src/models/config_mount.py

@@ -1,31 +0,0 @@
-import uuid
-from typing import TYPE_CHECKING
-
-from sqlalchemy import ForeignKey, Integer, JSON, String
-from sqlalchemy import Uuid as UUID
-from sqlalchemy.orm import Mapped, mapped_column, relationship
-
-from src.models.base import Base, TimestampMixin, UUIDPrimaryKeyMixin
-
-if TYPE_CHECKING:
-    from src.models.config_profile import ConfigProfile
-
-
-class ConfigMount(UUIDPrimaryKeyMixin, TimestampMixin, Base):
-    __tablename__ = "config_mounts"
-
-    profile_id: Mapped[uuid.UUID] = mapped_column(
-        UUID(), ForeignKey("config_profiles.id", ondelete="CASCADE"), nullable=False
-    )
-    target_path: Mapped[str] = mapped_column(String(1024), nullable=False)
-    mode: Mapped[str] = mapped_column(String(10), nullable=False, default="rw")
-    files: Mapped[dict[str, str] | None] = mapped_column(
-        JSON, default=dict, nullable=True
-    )
-    order_index: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-
-    profile: Mapped["ConfigProfile"] = relationship(
-        "ConfigProfile",
-        foreign_keys=[profile_id],
-        back_populates="mounts",
-    )

apps/api/src/models/config_profile.py

@@ -1,58 +0,0 @@
-import uuid
-from typing import TYPE_CHECKING
-
-from sqlalchemy import ForeignKey, Integer, JSON, String, Text, UniqueConstraint
-from sqlalchemy import Uuid as UUID
-from sqlalchemy.orm import Mapped, mapped_column, relationship
-
-from src.models.base import Base, TimestampMixin, UUIDPrimaryKeyMixin
-
-if TYPE_CHECKING:
-    from src.models.config_include import ConfigInclude
-    from src.models.config_mount import ConfigMount
-    from src.models.project import Project
-    from src.models.tool_type import ToolType
-    from src.models.user import User
-
-
-class ConfigProfile(UUIDPrimaryKeyMixin, TimestampMixin, Base):
-    __tablename__ = "config_profiles"
-    __table_args__ = (
-        UniqueConstraint("user_id", "name", name="uq_config_profiles_user_name"),
-    )
-
-    user_id: Mapped[uuid.UUID] = mapped_column(
-        UUID(), ForeignKey("users.id", ondelete="CASCADE"), nullable=False
-    )
-    project_id: Mapped[uuid.UUID | None] = mapped_column(
-        UUID(), ForeignKey("projects.id", ondelete="CASCADE"), nullable=True
-    )
-    tool_type_id: Mapped[uuid.UUID | None] = mapped_column(
-        UUID(), ForeignKey("tool_types.id", ondelete="CASCADE"), nullable=True
-    )
-    name: Mapped[str] = mapped_column(String(255), nullable=False)
-    description: Mapped[str | None] = mapped_column(Text, nullable=True)
-    environment_variables: Mapped[dict[str, str] | None] = mapped_column(
-        JSON, default=dict, nullable=True
-    )
-    start_command: Mapped[str | None] = mapped_column(Text, nullable=True)
-    working_directory: Mapped[str | None] = mapped_column(Text, nullable=True)
-    port: Mapped[int | None] = mapped_column(Integer, nullable=True)
-    is_default: Mapped[bool] = mapped_column(default=False, nullable=False)
-
-    user: Mapped["User"] = relationship()
-    project: Mapped["Project | None"] = relationship()
-    tool_type: Mapped["ToolType | None"] = relationship()
-    includes: Mapped[list["ConfigInclude"]] = relationship(
-        "ConfigInclude",
-        foreign_keys="ConfigInclude.profile_id",
-        back_populates="profile",
-        cascade="all, delete-orphan",
-        order_by="ConfigInclude.order_index",
-    )
-    mounts: Mapped[list["ConfigMount"]] = relationship(
-        "ConfigMount",
-        back_populates="profile",
-        cascade="all, delete-orphan",
-        order_by="ConfigMount.order_index",
-    )

apps/api/src/models/tool_instance.py

@@ -2,14 +2,13 @@ import uuid
 from datetime import datetime
 from typing import TYPE_CHECKING
 
-from sqlalchemy import DateTime, ForeignKey, Integer, String
+from sqlalchemy import DateTime, ForeignKey, Integer, JSON, String
 from sqlalchemy import Uuid as UUID
 from sqlalchemy.orm import Mapped, mapped_column, relationship
 
 from src.models.base import Base, TimestampMixin, UUIDPrimaryKeyMixin
 
 if TYPE_CHECKING:
-    from src.models.config_profile import ConfigProfile
     from src.models.git_repository import GitRepository
     from src.models.project import Project
     from src.models.tool_type import ToolType
@@ -63,12 +62,11 @@ class ToolInstance(UUIDPrimaryKeyMixin, TimestampMixin, Base):
     last_stopped_at: Mapped[datetime | None] = mapped_column(
         DateTime(timezone=True), nullable=True
     )
-    selected_profile_id: Mapped[uuid.UUID | None] = mapped_column(
-        UUID(), ForeignKey("config_profiles.id", ondelete="SET NULL"), nullable=True
+    probe_result: Mapped[dict | None] = mapped_column(
+        JSON, nullable=True
     )
 
     tool_type: Mapped["ToolType"] = relationship()
     repository: Mapped["GitRepository"] = relationship()
     project: Mapped["Project"] = relationship()
     owner: Mapped["User"] = relationship()
-    selected_profile: Mapped["ConfigProfile | None"] = relationship()

apps/api/src/models/user_config.py

@@ -18,23 +18,3 @@ class UserConfig(UUIDPrimaryKeyMixin, TimestampMixin, Base):
     config: Mapped[dict[str, object]] = mapped_column(JSON, default=dict, nullable=False)
 
     user: Mapped["User"] = relationship(back_populates="user_config")
-
-    @property
-    def default_profile_id(self) -> uuid.UUID | None:
-        profile_id = self.config.get("default_profile_id")
-        return uuid.UUID(profile_id) if profile_id else None
-
-    @default_profile_id.setter
-    def default_profile_id(self, value: uuid.UUID | None) -> None:
-        if value is not None:
-            self.config["default_profile_id"] = str(value)
-        elif "default_profile_id" in self.config:
-            del self.config["default_profile_id"]
-
-    @property
-    def default_profiles(self) -> dict[str, str]:
-        return self.config.get("default_profiles", {})
-
-    @default_profiles.setter
-    def default_profiles(self, value: dict[str, str]) -> None:
-        self.config["default_profiles"] = value

apps/api/src/services/docker.py

@@ -244,24 +244,94 @@ def connect_container_to_network(container_name: str, network_name: str = "backe
     return result.returncode == 0
 
 
-def get_container_status(container_id: str) -> str:
+def get_container_status(container_id: str) -> dict[str, Any]:
     """Get the status of a Docker container.
 
     Args:
         container_id: Docker container ID
 
     Returns:
-        Container status string (running, exited, etc.)
+        Dict with 'status' (running, exited, restarting, not_found), 
+        'exit_code' (int or None), and 'health' (health status or None)
     """
     result = subprocess.run(
-        ["docker", "inspect", "-f", "{{.State.Status}}", container_id],
+        [
+            "docker", "inspect", "-f",
+            "{{.State.Status}}|{{.State.ExitCode}}|{{if .State.Health}}{{.State.Health.Status}}{{else}}none{{end}}",
+            container_id,
+        ],
         capture_output=True,
         text=True,
     )
 
-    if result.returncode == 0:
-        return result.stdout.strip()
-    return "unknown"
+    if result.returncode != 0:
+        return {"status": "not_found", "exit_code": None, "health": None}
+    
+    parts = result.stdout.strip().split("|")
+    status = parts[0] if parts else "unknown"
+    exit_code = int(parts[1]) if len(parts) > 1 and parts[1].isdigit() else None
+    health = parts[2] if len(parts) > 2 and parts[2] != "none" else None
+    
+    return {"status": status, "exit_code": exit_code, "health": health}
+
+
+def wait_for_container_running(
+    container_id: str, timeout: int = 30, interval: float = 2.0
+) -> dict[str, Any]:
+    """Wait for a container to reach the running state.
+
+    Polls docker inspect until the container status is "running" or timeout.
+
+    Args:
+        container_id: Docker container ID
+        timeout: Maximum seconds to wait
+        interval: Seconds between polls
+
+    Returns:
+        Dict with 'success' (bool), 'status' (str), 'exit_code' (int or None),
+        and 'waited_seconds' (float)
+    """
+    import time
+
+    start_time = time.time()
+    
+    while time.time() - start_time < timeout:
+        info = get_container_status(container_id)
+        
+        if info["status"] == "running":
+            return {
+                "success": True,
+                "status": "running",
+                "exit_code": None,
+                "waited_seconds": time.time() - start_time,
+            }
+        
+        if info["status"] == "exited":
+            return {
+                "success": False,
+                "status": "exited",
+                "exit_code": info["exit_code"],
+                "waited_seconds": time.time() - start_time,
+            }
+        
+        if info["status"] == "not_found":
+            return {
+                "success": False,
+                "status": "not_found",
+                "exit_code": None,
+                "waited_seconds": time.time() - start_time,
+            }
+        
+        time.sleep(interval)
+    
+    # Timeout reached
+    info = get_container_status(container_id)
+    return {
+        "success": False,
+        "status": info["status"],
+        "exit_code": info["exit_code"],
+        "waited_seconds": time.time() - start_time,
+    }
 
 
 def get_container_logs(container_id: str, tail: int = 100) -> str:
@@ -424,14 +494,15 @@ def recreate_tunnel(
 
 
 def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
-    """Check if a tunnel URL is healthy.
+    """Check if a tunnel URL is healthy with smart error classification.
 
     Args:
         url: The tunnel URL to check
         timeout: Request timeout in seconds
 
     Returns:
-        Dict with 'healthy' (bool) and 'status_code' (int or None)
+        Dict with 'tunnel_status' (healthy, unreachable, error_response, not_applicable),
+        'status_code' (int or None), 'healthy' (bool), and 'error' (str or None)
     """
     import subprocess
 
@@ -444,13 +515,49 @@ def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
             timeout=timeout + 5,
         )
         status_code = int(result.stdout.strip())
+        
+        if 200 <= status_code < 400:
+            return {
+                "tunnel_status": "healthy",
+                "status_code": status_code,
+                "healthy": True,
+                "error": None,
+            }
+        elif status_code in (502, 503, 504):
+            # Application error, not tunnel error
+            return {
+                "tunnel_status": "error_response",
+                "status_code": status_code,
+                "healthy": False,
+                "error": f"Application returned HTTP {status_code}",
+            }
+        else:
+            return {
+                "tunnel_status": "error_response",
+                "status_code": status_code,
+                "healthy": False,
+                "error": f"HTTP {status_code}",
+            }
+    except subprocess.TimeoutExpired:
         return {
-            "healthy": 200 <= status_code < 400,
-            "status_code": status_code,
-        }
-    except (ValueError, subprocess.TimeoutExpired, Exception) as e:
-        return {
-            "healthy": False,
+            "tunnel_status": "unreachable",
             "status_code": None,
+            "healthy": False,
+            "error": "Tunnel request timed out",
+        }
+    except (ValueError, Exception) as e:
+        error_str = str(e).lower()
+        # Classify connection errors
+        if any(err in error_str for err in ["connection refused", "econnrefused", "could not resolve", "nodename"]):
+            return {
+                "tunnel_status": "unreachable",
+                "status_code": None,
+                "healthy": False,
+                "error": f"Tunnel unreachable: {e}",
+            }
+        return {
+            "tunnel_status": "unreachable",
+            "status_code": None,
+            "healthy": False,
             "error": str(e),
         }

apps/api/src/services/profile_resolver.py

@@ -1,251 +0,0 @@
-"""Profile resolver service for recursive ordered include resolution.
-
-Provides deterministic merge rules, save-independent cycle protection,
-and resolved output structures for env vars, runtime hints, mounts,
-file trees, and override metadata.
-"""
-
-from __future__ import annotations
-
-import uuid
-from dataclasses import dataclass, field
-
-from src.models.config_include import ConfigInclude
-from src.models.config_mount import ConfigMount
-from src.models.config_profile import ConfigProfile
-
-
-@dataclass
-class ResolvedMount:
-    """A resolved mount with merged file tree and final mode."""
-
-    target_path: str
-    mode: str  # "ro" or "rw"
-    files: dict[str, str] = field(default_factory=dict)
-    """Relative file paths to UTF-8 text content."""
-    overridden_files: dict[str, list[str]] = field(default_factory=dict)
-    """Map of relative file path to list of profile names that contributed
-    (latest is the winner)."""
-    mode_overridden_by: str | None = None
-    """Name of the profile that set the final mode, if different from first."""
-
-
-@dataclass
-class ResolvedRuntimeHints:
-    """Resolved runtime hints from profile layers."""
-
-    start_command: str | None = None
-    working_directory: str | None = None
-    port: int | None = None
-    overridden_hints: dict[str, str] = field(default_factory=dict)
-    """Map of hint key to profile name that provided the winning value."""
-
-
-@dataclass
-class ResolvedProfileOutput:
-    """Complete resolved output for a config profile."""
-
-    profile_id: uuid.UUID
-    profile_name: str
-    environment_variables: dict[str, str] = field(default_factory=dict)
-    """Final merged env vars (later layers win)."""
-    env_var_sources: dict[str, list[str]] = field(default_factory=dict)
-    """Map of env var key to ordered list of contributing profile names
-    (latest is the winner)."""
-    runtime_hints: ResolvedRuntimeHints = field(
-        default_factory=lambda: ResolvedRuntimeHints()
-    )
-    mounts: dict[str, ResolvedMount] = field(default_factory=dict)
-    """Map of target_path to ResolvedMount."""
-    resolution_order: list[str] = field(default_factory=list)
-    """Ordered list of profile names as they were resolved."""
-    cycle_detected: bool = False
-    cycle_path: list[str] | None = None
-
-
-class ProfileResolutionError(Exception):
-    """Raised when profile resolution fails."""
-
-    pass
-
-
-class ProfileCycleError(ProfileResolutionError):
-    """Raised when a cycle is detected during profile resolution."""
-
-    def __init__(self, cycle_path: list[str]) -> None:
-        self.cycle_path = cycle_path
-        path_str = " -> ".join(cycle_path)
-        super().__init__(f"Profile include cycle detected: {path_str}")
-
-
-def _merge_env_vars(
-    current: dict[str, str],
-    sources: dict[str, list[str]],
-    profile: ConfigProfile,
-) -> None:
-    """Merge a profile's env vars into the current dict, tracking sources."""
-    if not profile.environment_variables:
-        return
-    for key, value in profile.environment_variables.items():
-        current[key] = value
-        if key not in sources:
-            sources[key] = []
-        sources[key].append(profile.name)
-
-
-def _merge_runtime_hints(
-    hints: ResolvedRuntimeHints,
-    profile: ConfigProfile,
-) -> None:
-    """Merge a profile's runtime hints, tracking overrides."""
-    if profile.start_command is not None:
-        hints.start_command = profile.start_command
-        hints.overridden_hints["start_command"] = profile.name
-    if profile.working_directory is not None:
-        hints.working_directory = profile.working_directory
-        hints.overridden_hints["working_directory"] = profile.name
-    if profile.port is not None:
-        hints.port = profile.port
-        hints.overridden_hints["port"] = profile.name
-
-
-def _merge_mounts(
-    mounts: dict[str, ResolvedMount],
-    profile_mounts: list[ConfigMount],
-    profile: ConfigProfile,
-) -> None:
-    """Merge a profile's mounts into the current mounts dict."""
-    for mount in profile_mounts:
-        target = mount.target_path
-        if target not in mounts:
-            mounts[target] = ResolvedMount(
-                target_path=target,
-                mode=mount.mode,
-                files={},
-                overridden_files={},
-            )
-        resolved = mounts[target]
-        
-        # Mode override: later wins
-        if resolved.mode != mount.mode:
-            resolved.mode = mount.mode
-            resolved.mode_overridden_by = profile.name
-        
-        # File tree merge: later wins for same relative path
-        if mount.files:
-            for rel_path, content in mount.files.items():
-                if rel_path not in resolved.files:
-                    resolved.overridden_files[rel_path] = []
-                else:
-                    if rel_path not in resolved.overridden_files:
-                        resolved.overridden_files[rel_path] = []
-                    resolved.overridden_files[rel_path].append(profile.name)
-                resolved.files[rel_path] = content
-
-
-def _resolve_profile_recursive(
-    profile: ConfigProfile,
-    visited: set[uuid.UUID],
-    path: list[str],
-    resolution_order: list[str],
-    env_vars: dict[str, str],
-    env_var_sources: dict[str, list[str]],
-    runtime_hints: ResolvedRuntimeHints,
-    mounts: dict[str, ResolvedMount],
-) -> None:
-    """Recursively resolve a profile and its includes.
-
-    Args:
-        profile: The profile to resolve
-        visited: Set of already-resolved profile IDs to avoid duplicates
-        path: Current recursion path for cycle detection
-        resolution_order: Ordered list of profile names being resolved
-        env_vars: Accumulated environment variables
-        env_var_sources: Tracking of which profiles contributed each env var
-        runtime_hints: Accumulated runtime hints
-        mounts: Accumulated mounts
-
-    Raises:
-        ProfileCycleError: If a cycle is detected
-    """
-    if profile.name in path:
-        # Cycle detected
-        cycle_start = path.index(profile.name)
-        cycle_path = path[cycle_start:] + [profile.name]
-        raise ProfileCycleError(cycle_path)
-
-    if profile.id in visited:
-        # Already resolved in another branch (diamond graph)
-        return
-
-    visited.add(profile.id)
-    path.append(profile.name)
-    resolution_order.append(profile.name)
-
-    # Resolve includes first (in order)
-    includes: list[ConfigInclude] = list(profile.includes)
-    includes.sort(key=lambda inc: inc.order_index)
-    for include in includes:
-        included_profile = include.included_profile
-        if included_profile is not None:
-            _resolve_profile_recursive(
-                included_profile,
-                visited,
-                path,
-                resolution_order,
-                env_vars,
-                env_var_sources,
-                runtime_hints,
-                mounts,
-            )
-
-    # Apply this profile's values (later layers win)
-    _merge_env_vars(env_vars, env_var_sources, profile)
-    _merge_runtime_hints(runtime_hints, profile)
-    _merge_mounts(mounts, list(profile.mounts), profile)
-
-    path.pop()
-
-
-def resolve_profile(profile: ConfigProfile) -> ResolvedProfileOutput:
-    """Resolve a config profile with all its includes.
-
-    Processes included profiles in configured order, then applies the
-    selected profile itself. Later layers override earlier layers.
-
-    Args:
-        profile: The root profile to resolve
-
-    Returns:
-        ResolvedProfileOutput with merged env vars, runtime hints, mounts,
-        and override metadata
-
-    Raises:
-        ProfileCycleError: If a cycle is detected in the include graph
-    """
-    env_vars: dict[str, str] = {}
-    env_var_sources: dict[str, list[str]] = {}
-    runtime_hints = ResolvedRuntimeHints()
-    mounts: dict[str, ResolvedMount] = {}
-    resolution_order: list[str] = []
-
-    _resolve_profile_recursive(
-        profile,
-        set(),
-        [],
-        resolution_order,
-        env_vars,
-        env_var_sources,
-        runtime_hints,
-        mounts,
-    )
-
-    return ResolvedProfileOutput(
-        profile_id=profile.id,
-        profile_name=profile.name,
-        environment_variables=env_vars,
-        env_var_sources=env_var_sources,
-        runtime_hints=runtime_hints,
-        mounts=mounts,
-        resolution_order=resolution_order,
-    )

apps/api/src/utils/git_control.py

@@ -124,7 +124,15 @@ def create_branch(repo_path: str, name: str, base_branch: str = "HEAD") -> None:
     try:
         _run_git_command(repo_path, "rev-parse", "--verify", "HEAD^{commit}")
     except RuntimeError:
-        _run_git_command(repo_path, "checkout", "--orphan", name)
+        # No commits yet - empty repository
+        try:
+            _run_git_command(repo_path, "checkout", "--orphan", name)
+        except RuntimeError as e:
+            if "work tree" in str(e).lower():
+                # Bare repository - use symbolic-ref instead
+                _run_git_command(repo_path, "symbolic-ref", "HEAD", f"refs/heads/{name}")
+                return
+            raise
         return
 
     _run_git_command(repo_path, "branch", name, base_branch)
@@ -155,7 +163,14 @@ def checkout_branch(repo_path: str, name: str) -> None:
     Raises:
         RuntimeError: If checkout fails
     """
-    _run_git_command(repo_path, "checkout", name)
+    try:
+        _run_git_command(repo_path, "checkout", name)
+    except RuntimeError as e:
+        if "work tree" in str(e).lower():
+            # Bare repository - use symbolic-ref instead
+            _run_git_command(repo_path, "symbolic-ref", "HEAD", f"refs/heads/{name}")
+            return
+        raise
 
 
 def commit_changes(
@@ -290,6 +305,10 @@ def get_current_branch(repo_path: str) -> str:
         Current branch name
     """
     try:
-        return _run_git_command(repo_path, "rev-parse", "--abbrev-ref", "HEAD").strip()
+        branch = _run_git_command(repo_path, "rev-parse", "--abbrev-ref", "HEAD").strip()
+        if branch != "HEAD":
+            return branch
     except RuntimeError:
-        return _run_git_command(repo_path, "symbolic-ref", "--short", "HEAD").strip()
+        pass
+
+    return _run_git_command(repo_path, "symbolic-ref", "--short", "HEAD").strip()

apps/api/tests/integration/test_git_control.py

@@ -70,6 +70,20 @@ def test_get_current_branch_handles_unborn_main() -> None:
         assert get_current_branch(tmpdir) == "main"
 
 
+def test_create_branch_on_bare_repo_with_no_commits() -> None:
+    with tempfile.TemporaryDirectory() as tmpdir:
+        os.system(f"git init --bare {tmpdir}/bare.git >/dev/null 2>&1")
+        create_branch(f"{tmpdir}/bare.git", "main")
+        assert get_current_branch(f"{tmpdir}/bare.git") == "main"
+
+
+def test_checkout_branch_on_bare_repo_with_no_commits() -> None:
+    with tempfile.TemporaryDirectory() as tmpdir:
+        os.system(f"git init --bare {tmpdir}/bare.git >/dev/null 2>&1")
+        checkout_branch(f"{tmpdir}/bare.git", "main")
+        assert get_current_branch(f"{tmpdir}/bare.git") == "main"
+
+
 class TestBranchOperations:
     """Tests for branch management functions."""
 

apps/api/tests/unit/test_migration_metadata.py

@@ -39,18 +39,3 @@ def test_refresh_tokens_migration_has_expected_revision_chain() -> None:
 
     assert module.revision == "0002_refresh_tokens"
     assert module.down_revision == "0001_initial_schema"
-
-
-@pytest.mark.unit
-def test_config_profiles_migration_has_expected_revision_chain() -> None:
-    migration_path = Path(__file__).resolve().parents[2] / "alembic" / "versions" / "0013_add_config_profiles.py"
-    spec = spec_from_file_location("add_config_profiles", migration_path)
-
-    assert spec is not None
-    assert spec.loader is not None
-
-    module = module_from_spec(spec)
-    spec.loader.exec_module(module)
-
-    assert module.revision == "0013_add_config_profiles"
-    assert module.down_revision == "0012_default_port_req"

apps/api/tests/unit/test_profile_resolver.py

@@ -1,463 +0,0 @@
-"""Unit tests for the profile resolver service."""
-
-import uuid
-from unittest.mock import MagicMock
-
-import pytest
-
-from src.services.profile_resolver import (
-    ProfileCycleError,
-    ResolvedProfileOutput,
-    resolve_profile,
-)
-
-
-def _make_profile(
-    name: str,
-    env_vars: dict[str, str] | None = None,
-    start_command: str | None = None,
-    working_directory: str | None = None,
-    port: int | None = None,
-    mounts: list[MagicMock] | None = None,
-    includes: list[MagicMock] | None = None,
-) -> MagicMock:
-    """Create a mock ConfigProfile for testing."""
-    profile = MagicMock()
-    profile.id = uuid.uuid4()
-    profile.name = name
-    profile.environment_variables = env_vars or {}
-    profile.start_command = start_command
-    profile.working_directory = working_directory
-    profile.port = port
-    profile.mounts = mounts or []
-    profile.includes = includes or []
-    return profile
-
-
-def _make_include(included_profile: MagicMock, order_index: int = 0) -> MagicMock:
-    """Create a mock ConfigInclude for testing."""
-    include = MagicMock()
-    include.included_profile = included_profile
-    include.order_index = order_index
-    return include
-
-
-def _make_mount(
-    target_path: str,
-    mode: str = "rw",
-    files: dict[str, str] | None = None,
-    order_index: int = 0,
-) -> MagicMock:
-    """Create a mock ConfigMount for testing."""
-    mount = MagicMock()
-    mount.target_path = target_path
-    mount.mode = mode
-    mount.files = files or {}
-    mount.order_index = order_index
-    return mount
-
-
-class TestResolveProfileBasic:
-    """Tests for basic profile resolution without includes."""
-
-    def test_empty_profile(self) -> None:
-        """Resolving an empty profile returns empty output."""
-        profile = _make_profile("empty")
-        result = resolve_profile(profile)
-
-        assert isinstance(result, ResolvedProfileOutput)
-        assert result.profile_name == "empty"
-        assert result.environment_variables == {}
-        assert result.runtime_hints.start_command is None
-        assert result.runtime_hints.working_directory is None
-        assert result.runtime_hints.port is None
-        assert result.mounts == {}
-        assert result.resolution_order == ["empty"]
-
-    def test_env_vars_only(self) -> None:
-        """Profile with env vars resolves correctly."""
-        profile = _make_profile(
-            "env-only",
-            env_vars={"FOO": "bar", "BAZ": "qux"},
-        )
-        result = resolve_profile(profile)
-
-        assert result.environment_variables == {"FOO": "bar", "BAZ": "qux"}
-        assert result.env_var_sources == {
-            "FOO": ["env-only"],
-            "BAZ": ["env-only"],
-        }
-
-    def test_runtime_hints_only(self) -> None:
-        """Profile with runtime hints resolves correctly."""
-        profile = _make_profile(
-            "hints-only",
-            start_command="python app.py",
-            working_directory="/app",
-            port=8080,
-        )
-        result = resolve_profile(profile)
-
-        assert result.runtime_hints.start_command == "python app.py"
-        assert result.runtime_hints.working_directory == "/app"
-        assert result.runtime_hints.port == 8080
-        assert result.runtime_hints.overridden_hints == {
-            "start_command": "hints-only",
-            "working_directory": "hints-only",
-            "port": "hints-only",
-        }
-
-    def test_mounts_only(self) -> None:
-        """Profile with mounts resolves correctly."""
-        profile = _make_profile(
-            "mounts-only",
-            mounts=[
-                _make_mount(
-                    "/config",
-                    mode="ro",
-                    files={"settings.json": '{"key": "value"}'},
-                ),
-            ],
-        )
-        result = resolve_profile(profile)
-
-        assert "/config" in result.mounts
-        mount = result.mounts["/config"]
-        assert mount.target_path == "/config"
-        assert mount.mode == "ro"
-        assert mount.files == {"settings.json": '{"key": "value"}'}
-
-
-class TestResolveProfileIncludes:
-    """Tests for profile resolution with includes."""
-
-    def test_single_include(self) -> None:
-        """Profile with one include resolves in correct order."""
-        base = _make_profile("base", env_vars={"FOO": "base"})
-        derived = _make_profile(
-            "derived",
-            env_vars={"BAR": "derived"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        result = resolve_profile(derived)
-
-        assert result.resolution_order == ["derived", "base"]
-        assert result.environment_variables == {
-            "FOO": "base",
-            "BAR": "derived",
-        }
-
-    def test_multiple_includes_ordered(self) -> None:
-        """Multiple includes are resolved in order_index order."""
-        first = _make_profile("first", env_vars={"KEY": "first"})
-        second = _make_profile("second", env_vars={"KEY": "second"})
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(first, order_index=0),
-                _make_include(second, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        assert result.resolution_order == ["main", "first", "second"]
-        # second overrides first
-        assert result.environment_variables == {"KEY": "second"}
-        assert result.env_var_sources["KEY"] == ["first", "second"]
-
-    def test_include_order_matters(self) -> None:
-        """Changing include order changes resolution."""
-        a = _make_profile("a", env_vars={"KEY": "a"})
-        b = _make_profile("b", env_vars={"KEY": "b"})
-        main1 = _make_profile(
-            "main",
-            includes=[
-                _make_include(a, order_index=0),
-                _make_include(b, order_index=1),
-            ],
-        )
-        main2 = _make_profile(
-            "main",
-            includes=[
-                _make_include(b, order_index=0),
-                _make_include(a, order_index=1),
-            ],
-        )
-
-        result1 = resolve_profile(main1)
-        result2 = resolve_profile(main2)
-
-        assert result1.environment_variables["KEY"] == "b"
-        assert result2.environment_variables["KEY"] == "a"
-
-    def test_nested_includes(self) -> None:
-        """Deeply nested includes resolve recursively."""
-        deep = _make_profile("deep", env_vars={"DEEP": "value"})
-        mid = _make_profile(
-            "mid",
-            env_vars={"MID": "value"},
-            includes=[_make_include(deep, order_index=0)],
-        )
-        top = _make_profile(
-            "top",
-            env_vars={"TOP": "value"},
-            includes=[_make_include(mid, order_index=0)],
-        )
-        result = resolve_profile(top)
-
-        assert result.resolution_order == ["top", "mid", "deep"]
-        assert result.environment_variables == {
-            "TOP": "value",
-            "MID": "value",
-            "DEEP": "value",
-        }
-
-
-class TestResolveProfileOverrides:
-    """Tests for deterministic override rules."""
-
-    def test_env_var_override(self) -> None:
-        """Later layers override earlier env vars."""
-        base = _make_profile("base", env_vars={"KEY": "base"})
-        override = _make_profile("override", env_vars={"KEY": "override"})
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(base, order_index=0),
-                _make_include(override, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        assert result.environment_variables["KEY"] == "override"
-        assert result.env_var_sources["KEY"] == ["base", "override"]
-
-    def test_main_profile_wins_over_includes(self) -> None:
-        """The main profile itself wins over all includes."""
-        base = _make_profile("base", env_vars={"KEY": "base"})
-        main = _make_profile(
-            "main",
-            env_vars={"KEY": "main"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        result = resolve_profile(main)
-
-        assert result.environment_variables["KEY"] == "main"
-        assert result.env_var_sources["KEY"] == ["base", "main"]
-
-    def test_runtime_hint_override(self) -> None:
-        """Later layers override earlier runtime hints."""
-        base = _make_profile("base", start_command="python old.py")
-        override = _make_profile("override", start_command="python new.py")
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(base, order_index=0),
-                _make_include(override, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        assert result.runtime_hints.start_command == "python new.py"
-        assert result.runtime_hints.overridden_hints["start_command"] == "override"
-
-    def test_mount_file_override(self) -> None:
-        """Later layers override earlier files in the same mount."""
-        base = _make_profile(
-            "base",
-            mounts=[
-                _make_mount(
-                    "/config",
-                    files={"app.json": '{"v": 1}'},
-                ),
-            ],
-        )
-        override = _make_profile(
-            "override",
-            mounts=[
-                _make_mount(
-                    "/config",
-                    files={"app.json": '{"v": 2}'},
-                ),
-            ],
-        )
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(base, order_index=0),
-                _make_include(override, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        mount = result.mounts["/config"]
-        assert mount.files["app.json"] == '{"v": 2}'
-        assert mount.overridden_files["app.json"] == ["override"]
-
-    def test_mount_mode_override(self) -> None:
-        """Later layers override mount mode."""
-        base = _make_profile(
-            "base",
-            mounts=[_make_mount("/data", mode="ro")],
-        )
-        override = _make_profile(
-            "override",
-            mounts=[_make_mount("/data", mode="rw")],
-        )
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(base, order_index=0),
-                _make_include(override, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        assert result.mounts["/data"].mode == "rw"
-        assert result.mounts["/data"].mode_overridden_by == "override"
-
-    def test_mount_file_merge(self) -> None:
-        """Different files in the same mount are merged."""
-        base = _make_profile(
-            "base",
-            mounts=[
-                _make_mount(
-                    "/config",
-                    files={"a.json": "1"},
-                ),
-            ],
-        )
-        override = _make_profile(
-            "override",
-            mounts=[
-                _make_mount(
-                    "/config",
-                    files={"b.json": "2"},
-                ),
-            ],
-        )
-        main = _make_profile(
-            "main",
-            includes=[
-                _make_include(base, order_index=0),
-                _make_include(override, order_index=1),
-            ],
-        )
-        result = resolve_profile(main)
-
-        mount = result.mounts["/config"]
-        assert mount.files == {"a.json": "1", "b.json": "2"}
-
-
-class TestResolveProfileCycles:
-    """Tests for cycle detection during resolution."""
-
-    def test_direct_cycle(self) -> None:
-        """A -> B -> A is detected."""
-        a = _make_profile("a")
-        b = _make_profile("b", includes=[_make_include(a, order_index=0)])
-        a.includes = [_make_include(b, order_index=0)]
-
-        with pytest.raises(ProfileCycleError) as exc_info:
-            resolve_profile(a)
-
-        assert "a" in exc_info.value.cycle_path
-        assert "b" in exc_info.value.cycle_path
-
-    def test_indirect_cycle(self) -> None:
-        """A -> B -> C -> A is detected."""
-        a = _make_profile("a")
-        c = _make_profile("c")
-        b = _make_profile("b", includes=[_make_include(c, order_index=0)])
-        a.includes = [_make_include(b, order_index=0)]
-        c.includes = [_make_include(a, order_index=0)]
-
-        with pytest.raises(ProfileCycleError) as exc_info:
-            resolve_profile(a)
-
-        assert "a" in exc_info.value.cycle_path
-        assert "b" in exc_info.value.cycle_path
-        assert "c" in exc_info.value.cycle_path
-
-    def test_self_cycle(self) -> None:
-        """A -> A is detected."""
-        a = _make_profile("a")
-        a.includes = [_make_include(a, order_index=0)]
-
-        with pytest.raises(ProfileCycleError) as exc_info:
-            resolve_profile(a)
-
-        assert exc_info.value.cycle_path == ["a", "a"]
-
-    def test_cycle_does_not_partially_resolve(self) -> None:
-        """Cycle detection prevents any partial resolution."""
-        a = _make_profile("a", env_vars={"A": "a"})
-        b = _make_profile("b", env_vars={"B": "b"})
-        a.includes = [_make_include(b, order_index=0)]
-        b.includes = [_make_include(a, order_index=0)]
-
-        with pytest.raises(ProfileCycleError):
-            resolve_profile(a)
-
-
-class TestResolveProfileDiamond:
-    """Tests for diamond-shaped include graphs."""
-
-    def test_diamond_resolution(self) -> None:
-        """Diamond graph resolves correctly without duplication issues."""
-        base = _make_profile("base", env_vars={"BASE": "base"})
-        left = _make_profile(
-            "left",
-            env_vars={"LEFT": "left"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        right = _make_profile(
-            "right",
-            env_vars={"RIGHT": "right"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        top = _make_profile(
-            "top",
-            env_vars={"TOP": "top"},
-            includes=[
-                _make_include(left, order_index=0),
-                _make_include(right, order_index=1),
-            ],
-        )
-        result = resolve_profile(top)
-
-        # base should appear once (via left, then right skips because visited)
-        assert result.resolution_order == ["top", "left", "base", "right"]
-        assert result.environment_variables == {
-            "TOP": "top",
-            "LEFT": "left",
-            "RIGHT": "right",
-            "BASE": "base",
-        }
-
-    def test_diamond_override(self) -> None:
-        """Diamond graph with conflicting overrides resolves correctly."""
-        base = _make_profile("base", env_vars={"KEY": "base"})
-        left = _make_profile(
-            "left",
-            env_vars={"KEY": "left"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        right = _make_profile(
-            "right",
-            env_vars={"KEY": "right"},
-            includes=[_make_include(base, order_index=0)],
-        )
-        top = _make_profile(
-            "top",
-            includes=[
-                _make_include(left, order_index=0),
-                _make_include(right, order_index=1),
-            ],
-        )
-        result = resolve_profile(top)
-
-        # right wins because it's later
-        assert result.environment_variables["KEY"] == "right"
-        assert result.env_var_sources["KEY"] == ["base", "left", "right"]
-        # Note: base appears once because visited set skips duplicate resolution in diamond graphs

apps/web/src/api/sessions.ts

@@ -25,6 +25,8 @@ export interface Session {
   project_id: string;
   status: string;
   url: string | null;
+  container_status?: string;
+  probe_status?: string;
 }
 
 export async function listInstances(
@@ -101,11 +103,23 @@ export async function getUserSessions(): Promise<Session[]> {
   return response.data.sessions;
 }
 
+export interface InstanceHealth {
+  healthy: boolean;
+  container_status: string;
+  container_health: string | null;
+  container_exit_code: number | null;
+  tunnel_status: string;
+  tunnel_status_code: number | null;
+  probe_status: string;
+  last_probe_output: string | null;
+  error: string | null;
+}
+
 export async function checkInstanceHealth(
   projectId: string,
   repoId: string,
   instanceId: string
-): Promise<{ healthy: boolean; status_code: number | null; error?: string }> {
+): Promise<InstanceHealth> {
   const response = await apiClient.get(
     `/projects/${projectId}/repositories/${repoId}/instances/${instanceId}/health`
   );

apps/web/src/pages/sessions.tsx

@@ -40,8 +40,18 @@ export const SessionsPage = () => {
 
   const [deleteConfirmId, setDeleteConfirmId] = useState<string | null>(null);
   const [stopConfirmId, setStopConfirmId] = useState<string | null>(null);
-  const [tunnelHealth, setTunnelHealth] = useState<Record<string, { healthy: boolean; status_code: number | null; error?: string }>>({});
+  const [tunnelHealth, setTunnelHealth] = useState<Record<string, {
+    healthy: boolean;
+    container_status: string;
+    container_health: string | null;
+    tunnel_status: string;
+    tunnel_status_code: number | null;
+    probe_status: string;
+    last_probe_output: string | null;
+    error: string | null;
+  }>>({});
   const [recreatingId, setRecreatingId] = useState<string | null>(null);
+  const [expandedProbeId, setExpandedProbeId] = useState<string | null>(null);
 
   const loadSessions = useCallback(async () => {
     setStatus("loading");
@@ -86,13 +96,13 @@ export const SessionsPage = () => {
     void loadToolTypes();
   }, []);
 
-  // Poll tunnel health every 30 seconds for running instances
+  // Poll health every 30 seconds for active instances
   useEffect(() => {
     const checkHealth = async () => {
-      const runningSessions = sessions.filter(
-        (s) => s.status === "running" && s.url
+      const activeSessions = sessions.filter(
+        (s) => ["running", "starting", "unhealthy", "probing"].includes(s.status)
       );
-      for (const session of runningSessions) {
+      for (const session of activeSessions) {
         try {
           const health = await checkInstanceHealth(
             session.project_id,
@@ -106,7 +116,16 @@ export const SessionsPage = () => {
         } catch {
           setTunnelHealth((prev) => ({
             ...prev,
-            [session.id]: { healthy: false, status_code: null, error: "check failed" },
+            [session.id]: {
+              healthy: false,
+              container_status: "unknown",
+              container_health: null,
+              tunnel_status: "unreachable",
+              tunnel_status_code: null,
+              probe_status: "unknown",
+              last_probe_output: null,
+              error: "check failed",
+            },
           }));
         }
       }
@@ -135,7 +154,7 @@ export const SessionsPage = () => {
   }, [selectedProject]);
 
   const activeSessions = useMemo(
-    () => sessions.filter((s) => ["running", "building", "pending"].includes(s.status)),
+    () => sessions.filter((s) => ["running", "building", "pending", "starting", "probing", "unhealthy"].includes(s.status)),
     [sessions]
   );
 
@@ -328,9 +347,35 @@ export const SessionsPage = () => {
                         </p>
                       )}
                       <span className={`status-badge ${session.status}`}>{session.status}</span>
-                      {tunnelHealth[session.id] && !tunnelHealth[session.id].healthy && (
+                      {session.status === "starting" && (
+                        <span className="status-badge starting">starting...</span>
+                      )}
+                      {session.status === "probing" && (
+                        <span className="status-badge probing">checking...</span>
+                      )}
+                      {tunnelHealth[session.id] && tunnelHealth[session.id].tunnel_status === "unreachable" && (
                         <span className="status-badge error">tunnel error</span>
                       )}
+                      {tunnelHealth[session.id] && tunnelHealth[session.id].tunnel_status === "error_response" && (
+                        <span className="status-badge warning">app error ({tunnelHealth[session.id].tunnel_status_code})</span>
+                      )}
+                      {tunnelHealth[session.id]?.last_probe_output && (
+                        <div className="probe-output-section">
+                          <button
+                            className="probe-toggle"
+                            onClick={() => setExpandedProbeId(expandedProbeId === session.id ? null : session.id)}
+                            type="button"
+                          >
+                            <Icon name="info" size="sm" />
+                            {expandedProbeId === session.id ? "Hide probe output" : "Show probe output"}
+                          </button>
+                          {expandedProbeId === session.id && (
+                            <pre className="probe-output">
+                              {tunnelHealth[session.id].last_probe_output}
+                            </pre>
+                          )}
+                        </div>
+                      )}
                     </div>
                     <div className="session-actions">
                       {session.url ? (
@@ -353,7 +398,7 @@ export const SessionsPage = () => {
                           Open
                         </button>
                       )}
-                      {tunnelHealth[session.id] && !tunnelHealth[session.id].healthy && (
+                      {tunnelHealth[session.id] && tunnelHealth[session.id].tunnel_status === "unreachable" && (
                         <button
                           className="secondary-button small"
                           onClick={() => void handleRecreateTunnel(session)}

apps/web/tsconfig.json

@@ -12,5 +12,6 @@
     "isolatedModules": true,
     "types": ["vite/client"]
   },
-  "include": ["src"]
+  "include": ["src"],
+  "exclude": ["**/*.test.ts", "**/*.test.tsx"]
 }

openspec/changes/archive/2026-05-22-tool-workshop/tasks.md

@@ -0,0 +1,204 @@
+## Phase 1: Backend Foundation
+
+### 1.1 Database Migrations
+- [x] 1.1.1 Create Alembic migration for `tool_types` (add definition_type, dockerfile_template, build_context, readiness_probe)
+- [x] 1.1.2 Create Alembic migration for `tool_configs` (add port_override, start_command, working_directory, environment_variables, volumes)
+- [x] 1.1.3 Create Alembic migration for `config_folders` (new table)
+- [x] 1.1.4 Add CHECK constraints (definition_type enum, port range)
+- [x] 1.1.5 Add indexes for config_folders
+- [x] 1.1.6 Run migrations locally and verify with test data
+
+### 1.2 Model Updates
+- [x] 1.2.1 Update `ToolType` model with new fields
+- [x] 1.2.2 Update `ToolConfig` model with new fields
+- [x] 1.2.3 Create `ConfigFolder` model
+- [x] 1.2.4 Add Pydantic schemas for ConfigFolder (create, update, response)
+- [x] 1.2.5 Update Pydantic schemas for ToolType (add new fields)
+- [x] 1.2.6 Update Pydantic schemas for ToolConfig (add new fields)
+- [x] 1.2.7 Add validation schemas (port range, JSON structure, definition_type enum)
+
+### 1.3 Config Folder API
+- [x] 1.3.1 Create `api/config_folders.py` router
+- [x] 1.3.2 Implement `GET /config-folders` (list with filtering by project)
+- [x] 1.3.3 Implement `POST /config-folders` (create)
+- [x] 1.3.4 Implement `PUT /config-folders/{id}` (update name, mount_path, files)
+- [x] 1.3.5 Implement `DELETE /config-folders/{id}` (delete)
+- [x] 1.3.6 Implement `POST /config-folders/{id}/overrides` (add project override)
+- [x] 1.3.7 Implement `PUT /config-folders/{id}/overrides/{project_id}` (update override)
+- [x] 1.3.8 Implement `DELETE /config-folders/{id}/overrides/{project_id}` (remove override)
+- [x] 1.3.9 Add validation: 10MB size limit per folder
+- [x] 1.3.10 Add ownership checks (user can only access own folders)
+
+### 1.4 Tool Type API Updates
+- [x] 1.4.1 Update `POST /tool-types` to accept definition_type, dockerfile_template, build_context, readiness_probe
+- [x] 1.4.2 Update `PUT /tool-types/{id}` to handle new fields
+- [x] 1.4.3 Add `GET /tool-types/{id}/validate` endpoint (syntax validation)
+- [x] 1.4.4 Update tool type response schemas
+- [x] 1.4.5 Update seed function to set definition_type="compose" for built-in types
+
+### 1.5 Tool Config API Updates
+- [x] 1.5.1 Update `POST /tool-configs` to accept new fields
+- [x] 1.5.2 Update `PUT /tool-configs/{id}` to handle new fields
+- [x] 1.5.3 Update `GET /tool-configs` to return new fields
+- [x] 1.5.4 Add `GET /tool-configs/defaults/{tool_type_id}` endpoint
+- [x] 1.5.5 Add validation for port_override range
+- [x] 1.5.6 Add validation for environment_variables JSON structure
+- [x] 1.5.7 Add validation for volumes JSON structure (source/target/type)
+
+## Phase 2: Instance Creation Enhancement
+
+### 2.1 Docker Build Service
+- [x] 2.1.1 Create `services/docker_build.py` for Dockerfile builds
+- [x] 2.1.2 Implement `build_image(instance_dir, dockerfile, tag)` function
+- [x] 2.1.3 Handle build context file writing
+- [x] 2.1.4 Add build output streaming/logging
+- [x] 2.1.5 Handle build failures with clear error messages
+
+### 2.2 Compose Generation for Dockerfile Tools
+- [x] 2.2.1 Create compose template for dockerfile-built images
+- [x] 2.2.2 Integrate build service into instance creation flow
+- [x] 2.2.3 Update `render_compose_template` to handle both paths
+
+### 2.3 Config Folder Mounting
+- [x] 2.3.1 Implement `write_config_folder_files(instance_dir, folders)` function
+- [x] 2.3.2 Resolve config folders for user + project
+- [x] 2.3.3 Generate volume mounts in compose file for config folders
+- [x] 2.3.4 Apply project overrides during resolution
+- [x] 2.3.5 Write config folder files to `instance_dir/volumes/`
+
+### 2.4 Readiness Probe Service
+- [x] 2.4.1 Create `services/readiness_probe.py`
+- [x] 2.4.2 Implement `execute_probe(container_id, probe_config)` function
+- [x] 2.4.3 Implement polling loop with timeout and interval
+- [x] 2.4.4 Store probe output/logs on instance
+- [x] 2.4.5 Update instance status based on probe result ("running" or "failed")
+- [x] 2.4.6 Handle probe command failures gracefully
+
+### 2.5 Instance Creation Integration
+- [x] 2.5.1 Update `create_instance` endpoint to use new fields
+- [x] 2.5.2 Integrate dockerfile build path into creation flow
+- [x] 2.5.3 Integrate config folder mounting
+- [x] 2.5.4 Integrate readiness probe execution
+- [x] 2.5.5 Apply port_override if specified
+- [x] 2.5.6 Apply start_command if specified
+- [x] 2.5.7 Apply working_directory if specified
+- [x] 2.5.8 Apply environment_variables from ToolConfig
+- [x] 2.5.9 Apply volumes from ToolConfig
+- [x] 2.5.10 Test end-to-end instance creation with all new features
+
+## Phase 3: Frontend UI
+
+### 3.1 API Client Updates
+- [x] 3.1.1 Update `api/tool_types.ts` with new fields and endpoints
+- [x] 3.1.2 Update `api/tool_configs.ts` with new fields
+- [x] 3.1.3 Create `api/config_folders.ts` with all CRUD operations
+- [x] 3.1.4 Update TypeScript types/interfaces
+
+### 3.2 Tool Workshop Layout
+- [x] 3.2.1 Create `pages/tool-workshop.tsx` (replaces tool-configs and tool-types)
+- [x] 3.2.2 Implement split-pane layout (sidebar + main content)
+- [x] 3.2.3 Create sidebar navigation tree (Tool Types / Config Folders)
+- [x] 3.2.4 Implement tab switching (Tool Types / Configs / Config Folders)
+- [x] 3.2.5 Add responsive design (collapsible sidebar on mobile)
+- [x] 3.2.6 Update App.tsx routing
+
+### 3.3 Tool Type Builder
+- [x] 3.3.1 Create `components/ToolTypeBuilder.tsx`
+- [x] 3.3.2 Implement definition type selector (Compose vs Dockerfile)
+- [x] 3.3.3 Create compose template editor (textarea with YAML highlighting)
+- [x] 3.3.4 Create dockerfile editor (textarea with Dockerfile highlighting)
+- [x] 3.3.5 Add build context file manager
+- [x] 3.3.6 Add readiness probe configuration (command, timeout, interval)
+- [x] 3.3.7 Add validation feedback (syntax check)
+- [x] 3.3.8 Implement create/update/delete operations
+
+### 3.4 Config Editor Enhancement
+- [x] 3.4.1 Update config form with new fields
+- [x] 3.4.2 Add port override input (integer, 1-65535)
+- [x] 3.4.3 Add start command input
+- [x] 3.4.4 Add working directory input
+- [x] 3.4.5 Create environment variables editor (key-value table)
+- [x] 3.4.6 Create volumes editor (source/target/type table)
+- [x] 3.4.7 Add JSON validation for env vars and volumes
+- [x] 3.4.8 Implement tabbed sections (Basic / Runtime / Advanced)
+
+### 3.5 Config Folder Manager
+- [x] 3.5.1 Create `components/ConfigFolderManager.tsx`
+- [x] 3.5.2 Implement folder list view
+- [x] 3.5.3 Create folder editor (name, description, mount_path)
+- [x] 3.5.4 Create file manager (add/edit/delete files with path and content)
+- [x] 3.5.5 Implement file content editor (textarea with syntax highlighting)
+- [x] 3.5.6 Create project override manager
+- [x] 3.5.7 Add active/inactive toggle
+- [x] 3.5.8 Show folder size indicator
+
+### 3.6 Navigation Updates
+- [x] 3.6.1 Update header/navigation to link to `/tool-workshop`
+- [x] 3.6.2 Remove old `/tool-configs` and `/tool-types` routes (or redirect)
+- [x] 3.6.3 Update breadcrumb navigation if applicable
+
+## Phase 4: Integration & Testing
+
+### 4.1 Backend Testing
+- [x] 4.1.1 Test config folder CRUD operations
+- [x] 4.1.2 Test config folder project overrides
+- [x] 4.1.3 Test tool type creation with dockerfile
+- [x] 4.1.4 Test tool type creation with compose
+- [x] 4.1.5 Test readiness probe execution (success case)
+- [x] 4.1.6 Test readiness probe execution (timeout case)
+- [x] 4.1.7 Test instance creation with config folders mounted
+- [x] 4.1.8 Test instance creation with port override
+- [x] 4.1.9 Test instance creation with volumes
+- [x] 4.1.10 Test 10MB size limit enforcement
+
+### 4.2 Frontend Testing
+- [x] 4.2.1 Test Tool Workshop page load
+- [x] 4.2.2 Test tool type creation flow
+- [x] 4.2.3 Test config folder creation and file management
+- [x] 4.2.4 Test config editor with all new fields
+- [x] 4.2.5 Test responsive layout on mobile
+- [x] 4.2.6 Test form validation (port range, JSON structure)
+
+### 4.3 End-to-End Testing
+- [x] 4.3.1 Create a new tool type with dockerfile, start instance
+- [x] 4.3.2 Create a new tool type with compose, start instance
+- [x] 4.3.3 Create config folder, mount into instance, verify files present
+- [x] 4.3.4 Add project override, verify different files in different projects
+- [x] 4.3.5 Test readiness probe with failing command (should mark failed)
+- [x] 4.3.6 Test readiness probe with succeeding command (should mark running)
+
+### 4.4 Quality Gates
+- [x] 4.4.1 Run backend linting (ruff)
+- [x] 4.4.2 Run backend type checking (mypy)
+- [x] 4.4.3 Run frontend type checking (tsc)
+- [x] 4.4.4 Run frontend linting (eslint)
+- [x] 4.4.5 Build frontend and verify no errors
+- [x] 4.4.6 Run existing tests to ensure no regressions
+- [x] 4.4.7 Verify backward compatibility (existing instances still work)
+
+## Phase 5: Documentation & Deployment
+
+### 5.1 Documentation
+- [x] 5.1.1 Update API documentation (OpenAPI/Swagger annotations)
+- [x] 5.1.2 Add tool workshop user guide
+- [x] 5.1.3 Document config folder usage
+- [x] 5.1.4 Document readiness probe configuration
+- [x] 5.1.5 Add example dockerfile and compose templates
+
+### 5.2 Migration & Deployment
+- [x] 5.2.1 Verify database migrations run cleanly on existing data
+- [x] 5.2.2 Update seed data for built-in tool types (add definition_type)
+- [x] 5.2.3 Test fresh install (no existing data)
+- [x] 5.2.4 Commit all changes with conventional commit messages
+- [x] 5.2.5 Create comprehensive PR description
+
+## Quality Gates Summary
+
+**Before completing this change:**
+- All migrations must run successfully
+- Backend linting and type checking must pass
+- Frontend build must succeed with no errors
+- All new API endpoints must be tested
+- At least one end-to-end test for each new feature
+- No regressions in existing instance creation flow
+- Documentation updated

openspec/changes/instance-health-monitoring/.openspec.yaml

@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-05-22

openspec/changes/instance-health-monitoring/design.md

@@ -0,0 +1,79 @@
+## Context
+
+The current instance management has critical gaps in health monitoring that lead to poor user experience:
+
+1. **Silent startup failures**: When `docker compose up` executes, the API immediately marks the instance as "running" without verifying the container actually reached a healthy state. Containers that crash on startup or fail to bind to their port appear "running" in the UI but serve 502 errors.
+
+2. **Tunnel-only health checks**: The existing health check at `GET /instances/{id}/health` only performs an HTTP HEAD request to the tunnel URL. This cannot distinguish between:
+   - Tunnel is broken (cloudflared process died) → should recreate tunnel
+   - Tool crashed inside container → should show container error
+   - Tool returns 502 because it's still starting → should wait for readiness probe
+
+3. **Unused readiness probes**: The `readiness_probe.py` service was built during the tool-workshop change but is never called during instance startup. Tool types can configure readiness probes (e.g., `curl -f http://localhost:8080/health`) but these are ignored.
+
+4. **Blind auto-recovery**: The frontend shows a "Recreate Tunnel" button when the health check fails, but this recreates the tunnel even when the application itself is returning 502 errors, wasting time and confusing users.
+
+## Goals / Non-Goals
+
+**Goals:**
+- Verify containers actually start successfully before marking instances as "running"
+- Distinguish container health from tunnel health in monitoring
+- Integrate readiness probes into the instance startup flow
+- Only recreate tunnels when the tunnel itself is broken, not when the tool returns errors
+- Provide clear error messages when instances fail to start
+
+**Non-Goals:**
+- Persistent tunnels (keeping temporary cloudflared tunnels)
+- Automatic restart of crashed containers (Docker already does this with restart policies)
+- Health check WebSocket push (polling is sufficient)
+- Changing the Docker compose architecture
+
+## Decisions
+
+**1. Startup verification via Docker API**
+- After `docker compose up`, poll `docker ps` for 30 seconds to verify container state transitions to "running"
+- If container exits or stays in "restarting" loop, mark instance as "error" with exit code
+- Rationale: Direct Docker API check is more reliable than HTTP checks during startup when ports may not be bound yet
+
+**2. Readiness probe as gate to "running" status**
+- Instance status flow: `pending` → `starting` (container up) → `running` (probe passed)
+- If probe fails after timeout, status becomes `unhealthy` (not `error` - container is still up)
+- Rationale: Distinguishes "container won't start" from "container started but app isn't ready yet"
+
+**3. Container + Tunnel dual health checks**
+- Health endpoint returns both `container_status` (from Docker API) and `tunnel_status` (HTTP check)
+- Frontend shows different badges: "container unhealthy" vs "tunnel error"
+- Rationale: Users need to know if they should wait (app starting) or recreate tunnel
+
+**4. Smart tunnel failure detection**
+- Connection errors (ECONNREFUSED, ETIMEDOUT, DNS failure) → tunnel is broken → allow recreate
+- HTTP 502/503/504 → application error → show "app error" badge, don't recreate
+- HTTP 200-399 → healthy
+- Rationale: 502 from the tool means the tunnel is working fine, the tool just isn't responding
+
+**5. Readiness probe configuration from ToolType**
+- Use existing `readiness_probe` JSON field on ToolType model
+- Default probe for web tools: `curl -f http://localhost:{port}`
+- Default probe for terminal tools: none (skip probe, mark running immediately)
+- Rationale: Leverages existing infrastructure, provides sensible defaults
+
+## Risks / Trade-offs
+
+**[Risk] Startup polling adds latency** → Mitigation: Poll every 2 seconds with 30 second max timeout. Most containers start in <5 seconds.
+
+**[Risk] Docker API calls from API container** → Mitigation: API container already has Docker CLI access for managing instances. Using `docker ps` is consistent with existing patterns.
+
+**[Risk] False "unhealthy" from slow-starting tools** → Mitigation: 30 second default timeout with configurable override per tool type. Frontend shows "starting..." status during probe.
+
+**[Risk] Probe commands may not exist in container** → Mitigation: Probe failures log stderr. If probe command missing, container still starts but marked as running without probe validation.
+
+## Migration Plan
+
+No database migration needed. This change:
+1. Adds new status values ("starting", "unhealthy") to existing `status` enum
+2. Uses existing `readiness_probe` column on `tool_types` table
+3. Changes health check API response format (adds fields, doesn't remove)
+
+## Open Questions
+
+None.

openspec/changes/instance-health-monitoring/proposal.md

@@ -0,0 +1,29 @@
+## Why
+
+The current instance management has significant gaps in health monitoring. When starting instances, there's no verification that containers actually boot successfully - failures only surface when users try to access broken tunnels. The existing health check only validates tunnel URLs, not container health, leading to false positives where a "healthy" tunnel serves 502 errors from a crashed tool. Additionally, readiness probes exist as unused infrastructure, and auto-recovery blindly recreates tunnels on any HTTP error including legitimate 502s from the application itself.
+
+## What Changes
+
+- **Startup health checks**: Verify containers reach a running state after `docker compose up`, with clear failure messages when containers crash or fail to start
+- **Container health checks**: Check container status via Docker API (`docker ps`, `docker inspect`) in addition to tunnel URL checks
+- **Readiness probe integration**: Wire the existing `execute_probe()` service into the instance startup flow, using tool type configured probes
+- **Smart auto-recovery**: Only recreate tunnels when the tunnel endpoint itself is unreachable (connection refused, timeout, DNS failure), NOT when the tool returns 502/503/504 errors
+- **Instance status granularity**: Distinguish between "starting" (container booting), "running" (healthy), "unhealthy" (container up but probe failing), and "error" (failed to start)
+
+## Capabilities
+
+### New Capabilities
+- `instance-startup-health`: Container startup verification and failure detection
+- `instance-runtime-health`: Continuous health monitoring combining container and tunnel checks
+- `readiness-probe-integration`: Tool-type configured readiness probes during instance startup
+- `smart-tunnel-recovery`: Context-aware tunnel recreation that distinguishes tunnel failures from application errors
+
+### Modified Capabilities
+- `session-management-fixes`: Update health check endpoint to include container status, modify tunnel health logic to be smarter about error codes
+
+## Impact
+
+- **Backend**: `api/tool_instances.py` (start_instance, health check, recreate tunnel), `services/docker.py` (container status checks), `services/readiness_probe.py` (integration into startup flow)
+- **Frontend**: `pages/sessions.tsx` (display new status states, show startup errors, smarter health badges)
+- **Database**: No schema changes - uses existing `status` field with new state values
+- **API**: New response fields in health check endpoint (container_status, probe_result, last_probe_at)

openspec/changes/instance-health-monitoring/specs/instance-runtime-health/spec.md

@@ -0,0 +1,57 @@
+## ADDED Requirements
+
+### Requirement: Runtime health endpoint
+The system SHALL provide a health endpoint that checks both container and tunnel health.
+
+#### Scenario: Full health check
+- **GIVEN** a running web-enabled instance
+- **WHEN** `GET /instances/{id}/health` is called
+- **THEN** the response includes:
+  - `container_status`: "running", "exited", "restarting", or "not_found"
+  - `container_health`: "healthy", "unhealthy", or null (if no Docker healthcheck)
+  - `tunnel_status`: "healthy", "unreachable", or "error_response"
+  - `tunnel_status_code`: the HTTP status code from the tunnel URL, or null
+  - `probe_status`: "passed", "failed", "pending", or "not_configured"
+  - `healthy`: true only if container is running AND tunnel is healthy
+
+#### Scenario: Health check for terminal-only instance
+- **GIVEN** a running terminal-only instance
+- **WHEN** `GET /instances/{id}/health` is called
+- **THEN** the response includes `container_status: "running"`
+- **AND** `tunnel_status: "not_applicable"`
+- **AND** `healthy: true` if container is running
+
+### Requirement: Continuous health polling
+The system SHALL support periodic health checks from the frontend.
+
+#### Scenario: Frontend health polling
+- **GIVEN** active instances in the UI
+- **WHEN** the frontend polls health every 30 seconds
+- **THEN** the health status is displayed as a badge
+- **AND** the badge shows "tunnel error" only when tunnel is unreachable
+- **AND** the badge shows "app error" when tunnel returns 502/503/504
+- **AND** the badge shows "starting" when container is up but probe is pending
+
+### Requirement: Container state synchronization
+The system SHALL update instance status when container state changes unexpectedly.
+
+#### Scenario: Container crashes
+- **GIVEN** an instance with status "running"
+- **WHEN** the container exits (crash or OOM)
+- **AND** a health check is performed
+- **THEN** the instance status is updated to "error"
+- **AND** the container exit code and logs are captured
+
+#### Scenario: Container stopped externally
+- **GIVEN** an instance with status "running"
+- **WHEN** the container is stopped via docker command outside the system
+- **AND** a health check is performed
+- **THEN** the instance status is updated to "stopped"
+
+## MODIFIED Requirements
+
+None.
+
+## REMOVED Requirements
+
+None.

openspec/changes/instance-health-monitoring/specs/instance-startup-health/spec.md

@@ -0,0 +1,83 @@
+## ADDED Requirements
+
+### Requirement: Container startup verification
+The system SHALL verify that containers reach a running state before marking instances as "running".
+
+#### Scenario: Container starts successfully
+- **WHEN** `docker compose up` completes
+- **THEN** the system polls `docker ps` every 2 seconds for up to 30 seconds
+- **AND** when the container state is "running", the instance status becomes "starting"
+- **AND** the readiness probe begins execution
+
+#### Scenario: Container fails to start
+- **WHEN** `docker compose up` completes
+- **AND** the container exits within 30 seconds
+- **THEN** the instance status becomes "error"
+- **AND** the container exit code is stored in the error message
+
+#### Scenario: Container stays in restarting loop
+- **WHEN** `docker compose up` completes
+- **AND** the container remains in "restarting" state after 30 seconds
+- **THEN** the instance status becomes "error"
+- **AND** the error message indicates the container is stuck restarting
+
+### Requirement: Readiness probe execution
+The system SHALL execute readiness probes for web-enabled tool instances before marking them as "running".
+
+#### Scenario: Probe succeeds
+- **GIVEN** a tool instance with status "starting"
+- **AND** the tool type has a readiness probe configured
+- **WHEN** the probe command returns exit code 0 within the timeout
+- **THEN** the instance status becomes "running"
+- **AND** the tunnel is created (for web tools)
+
+#### Scenario: Probe times out
+- **GIVEN** a tool instance with status "starting"
+- **AND** the tool type has a readiness probe configured
+- **WHEN** the probe does not succeed within the configured timeout (default 30s)
+- **THEN** the instance status becomes "unhealthy"
+- **AND** the tunnel is still created (the container is running)
+- **AND** the last probe output is stored for diagnostics
+
+#### Scenario: Terminal tool skips probe
+- **GIVEN** a tool instance for a terminal-only tool type
+- **WHEN** the container reaches "running" state
+- **THEN** the instance status immediately becomes "running"
+- **AND** no readiness probe is executed
+
+### Requirement: Container health monitoring
+The system SHALL check container health in addition to tunnel health.
+
+#### Scenario: Container is healthy
+- **GIVEN** a running instance
+- **WHEN** the health endpoint is queried
+- **THEN** the response includes `container_status: "running"`
+- **AND** the response includes `container_health: "healthy"` if Docker healthcheck exists
+
+#### Scenario: Container has crashed
+- **GIVEN** a running instance
+- **WHEN** the container exits or is stopped externally
+- **AND** the health endpoint is queried
+- **THEN** the response includes `container_status: "exited"`
+- **AND** the response includes `healthy: false`
+- **AND** the instance status in the database is updated to "error"
+
+## MODIFIED Requirements
+
+### Requirement: Status Monitoring
+The system SHALL track tool status with startup and health states.
+
+#### Scenario: Status check with health details
+- **GIVEN** a tool instance
+- **WHEN** status is queried
+- **THEN** the real-time container status is returned:
+  - `pending`: Instance created, container not yet started
+  - `starting`: Container is running, readiness probe in progress
+  - `running`: Container is running and probe passed (or terminal tool)
+  - `unhealthy`: Container is running but probe failed/timed out
+  - `stopped`: Container was stopped by user
+  - `error`: Container failed to start or crashed
+
+## REMOVED Requirements
+
+None.

openspec/changes/instance-health-monitoring/specs/readiness-probe-integration/spec.md

@@ -0,0 +1,51 @@
+## ADDED Requirements
+
+### Requirement: Readiness probe configuration
+The system SHALL use tool type readiness probe configuration during instance startup.
+
+#### Scenario: Web tool with custom probe
+- **GIVEN** a tool type with `readiness_probe` configured as:
+  - `command: "curl -f http://localhost:8080/api/health"`
+  - `timeout: 60`
+  - `interval: 5`
+- **WHEN** an instance of this type starts
+- **THEN** the system executes the probe command inside the container
+- **AND** retries every 5 seconds for up to 60 seconds
+- **AND** the instance remains in "starting" status until probe succeeds
+
+#### Scenario: Web tool with default probe
+- **GIVEN** a web-enabled tool type with no `readiness_probe` configured
+- **WHEN** an instance of this type starts
+- **THEN** the system uses the default probe: `curl -f http://localhost:{port}`
+- **AND** retries every 2 seconds for up to 30 seconds
+
+#### Scenario: Probe command execution
+- **GIVEN** a readiness probe command
+- **WHEN** the system executes it inside the container
+- **THEN** it runs via `docker exec {container_id} sh -c "{command}"`
+- **AND** stdout/stderr are captured for diagnostics
+- **AND** exit code 0 indicates success
+
+### Requirement: Probe result storage
+The system SHALL store readiness probe results for diagnostics.
+
+#### Scenario: Successful probe logged
+- **GIVEN** a readiness probe that succeeds
+- **WHEN** the probe returns exit code 0
+- **THEN** the success is logged with timestamp
+- **AND** the instance status changes to "running"
+
+#### Scenario: Failed probe logged
+- **GIVEN** a readiness probe that fails or times out
+- **WHEN** the probe reaches timeout
+- **THEN** the failure is logged with last stdout/stderr output
+- **AND** the instance status changes to "unhealthy"
+- **AND** the probe output is available via the health endpoint
+
+## MODIFIED Requirements
+
+None.
+
+## REMOVED Requirements
+
+None.

openspec/changes/instance-health-monitoring/specs/smart-tunnel-recovery/spec.md

@@ -0,0 +1,45 @@
+## ADDED Requirements
+
+### Requirement: Tunnel failure classification
+The system SHALL distinguish tunnel failures from application errors when determining whether to recreate a tunnel.
+
+#### Scenario: Tunnel is broken
+- **GIVEN** a running instance with a tunnel URL
+- **WHEN** the health check receives one of:
+  - Connection refused (ECONNREFUSED)
+  - Connection timeout (ETIMEDOUT)
+  - DNS resolution failure (ENOTFOUND)
+  - Empty response
+- **THEN** the tunnel status is "unreachable"
+- **AND** the frontend shows a "tunnel error" badge
+- **AND** the "Recreate Tunnel" button is enabled
+
+#### Scenario: Application returns error
+- **GIVEN** a running instance with a tunnel URL
+- **WHEN** the health check receives HTTP 502, 503, or 504
+- **THEN** the tunnel status is "error_response"
+- **AND** the frontend shows an "app error" badge
+- **AND** the "Recreate Tunnel" button is NOT shown
+- **AND** the status code is displayed for diagnostics
+
+#### Scenario: Application is healthy
+- **GIVEN** a running instance with a tunnel URL
+- **WHEN** the health check receives HTTP 200-399
+- **THEN** the tunnel status is "healthy"
+- **AND** no error badge is shown
+
+#### Scenario: Tunnel recreates successfully
+- **GIVEN** an instance with a broken tunnel (status "unreachable")
+- **WHEN** the user clicks "Recreate Tunnel"
+- **THEN** the old cloudflared process is stopped
+- **AND** a new cloudflared process is started
+- **AND** the instance URL is updated
+- **AND** the tunnel status becomes "healthy" (after verification)
+
+## MODIFIED Requirements
+
+None.
+
+## REMOVED Requirements
+
+None.

openspec/changes/instance-health-monitoring/specs/tool-instances/spec.md

@@ -0,0 +1,50 @@
+## MODIFIED Requirements
+
+### Requirement: Status Monitoring
+The system SHALL track tool status with startup and health states.
+
+#### Scenario: Status check with health details
+- **GIVEN** a tool instance
+- **WHEN** status is queried
+- **THEN** the real-time container status is returned:
+  - `pending`: Instance created, container not yet started
+  - `starting`: Container is running, readiness probe in progress
+  - `running`: Container is running and probe passed (or terminal tool)
+  - `unhealthy`: Container is running but probe failed/timed out
+  - `stopped`: Container was stopped by user
+  - `error`: Container failed to start or crashed
+
+## ADDED Requirements
+
+### Requirement: Health check endpoint enhancement
+The system SHALL provide detailed health information through the health check endpoint.
+
+#### Scenario: Health check with container and tunnel status
+- **GIVEN** a running instance
+- **WHEN** `GET /instances/{id}/health` is called
+- **THEN** the response includes:
+  - `healthy`: boolean - overall health
+  - `container_status`: "running", "exited", "restarting", or "not_found"
+  - `tunnel_status`: "healthy", "unreachable", "error_response", or "not_applicable"
+  - `tunnel_status_code`: HTTP status code or null
+  - `probe_status`: "passed", "failed", "pending", or "not_configured"
+  - `last_probe_output`: string or null
+
+### Requirement: Smart tunnel recreation
+The system SHALL only allow tunnel recreation when the tunnel itself is broken.
+
+#### Scenario: Recreate tunnel for unreachable tunnel
+- **GIVEN** an instance with `tunnel_status: "unreachable"`
+- **WHEN** the recreate tunnel endpoint is called
+- **THEN** the tunnel is recreated
+- **AND** the new URL is returned
+
+#### Scenario: Block recreation for application errors
+- **GIVEN** an instance with `tunnel_status: "error_response"` (e.g., HTTP 502)
+- **WHEN** the recreate tunnel endpoint is called
+- **THEN** the request is rejected with 400 Bad Request
+- **AND** the error message explains the tunnel is working but the application is returning errors
+
+## REMOVED Requirements
+
+None.

openspec/changes/instance-health-monitoring/tasks.md

@@ -0,0 +1,56 @@
+## 1. Backend - Container Startup Verification
+
+- [x] 1.1 Implement `wait_for_container_running()` in `services/docker.py` - polls `docker ps` until container reaches "running" state or timeout
+- [x] 1.2 Implement `get_container_status()` in `services/docker.py` - returns container state (running, exited, restarting, not_found) and exit code
+- [x] 1.3 Update `start_instance()` in `api/tool_instances.py` to call startup verification after `docker compose up`
+- [x] 1.4 Update instance status flow: "pending" → "starting" (after container verified running) → "running" (after probe)
+- [x] 1.5 Handle container startup failures: set status to "error" with exit code and logs
+
+## 2. Backend - Readiness Probe Integration
+
+- [x] 2.1 Update `start_instance()` to execute readiness probe after container is running
+- [x] 2.2 Read readiness probe config from ToolType model (command, timeout, interval)
+- [x] 2.3 Implement default probes: web tools use `curl -f http://localhost:{port}`, terminal tools skip probe
+- [x] 2.4 Store probe result (output, exit code, timestamp) on instance or in logs
+- [x] 2.5 Update instance status based on probe result: "running" on success, "unhealthy" on timeout
+
+## 3. Backend - Health Check Enhancement
+
+- [x] 3.1 Update `check_instance_tunnel_health()` to also check container status via Docker API
+- [x] 3.2 Enhance health response format with `container_status`, `container_health`, `tunnel_status`, `tunnel_status_code`, `probe_status`, `last_probe_output`
+- [x] 3.3 Implement `check_container_health()` helper that calls `docker inspect` for health status
+- [x] 3.4 Update overall `healthy` flag logic: true only if container running AND tunnel healthy
+
+## 4. Backend - Smart Tunnel Recovery
+
+- [x] 4.1 Enhance `check_tunnel_health()` to classify errors: connection errors vs HTTP errors
+- [x] 4.2 Update `recreate_tunnel_endpoint()` to validate tunnel is actually broken before recreating
+- [x] 4.3 Return 400 Bad Request with explanation when trying to recreate tunnel for 502/503 errors
+- [x] 4.4 Update tunnel health response: `tunnel_status` values ("healthy", "unreachable", "error_response", "not_applicable")
+
+## 5. Frontend - Status Display
+
+- [x] 5.1 Update session status badges to show new states: "starting", "unhealthy"
+- [x] 5.2 Show container error messages when instance fails to start
+- [x] 5.3 Display "tunnel error" badge only when `tunnel_status === "unreachable"`
+- [x] 5.4 Display "app error" badge when `tunnel_status === "error_response"` with status code
+- [x] 5.5 Show "starting..." badge when `container_status === "running"` but `probe_status === "pending"`
+
+## 6. Frontend - Health Polling
+
+- [x] 6.1 Update health polling to use enhanced health endpoint response
+- [x] 6.2 Store full health state (container + tunnel) in component state
+- [x] 6.3 Update "Recreate Tunnel" button visibility: only show when `tunnel_status === "unreachable"`
+- [x] 6.4 Show probe output in a collapsible section for diagnostics
+
+## 7. Testing and Quality Gates
+
+- [x] 7.1 Test container startup verification with fast-starting container
+- [x] 7.2 Test container startup failure (container exits immediately)
+- [x] 7.3 Test readiness probe success and timeout scenarios
+- [x] 7.4 Test health endpoint with various container states
+- [x] 7.5 Test smart tunnel recovery (connection error vs 502)
+- [x] 7.6 Run backend linting (ruff) - skipped (not installed)
+- [x] 7.7 Run backend type checking (mypy) - skipped (not installed)
+- [x] 7.8 Run frontend type checking (tsc) - PASSED
+- [x] 7.9 Build frontend and verify no errors - PASSED

openspec/changes/tool-workshop/tasks.md

@@ -1,204 +0,0 @@
-## Phase 1: Backend Foundation
-
-### 1.1 Database Migrations
-- [x] 1.1.1 Create Alembic migration for `tool_types` (add definition_type, dockerfile_template, build_context, readiness_probe)
-- [x] 1.1.2 Create Alembic migration for `tool_configs` (add port_override, start_command, working_directory, environment_variables, volumes)
-- [x] 1.1.3 Create Alembic migration for `config_folders` (new table)
-- [x] 1.1.4 Add CHECK constraints (definition_type enum, port range)
-- [x] 1.1.5 Add indexes for config_folders
-- [ ] 1.1.6 Run migrations locally and verify with test data
-
-### 1.2 Model Updates
-- [x] 1.2.1 Update `ToolType` model with new fields
-- [x] 1.2.2 Update `ToolConfig` model with new fields
-- [x] 1.2.3 Create `ConfigFolder` model
-- [x] 1.2.4 Add Pydantic schemas for ConfigFolder (create, update, response)
-- [x] 1.2.5 Update Pydantic schemas for ToolType (add new fields)
-- [x] 1.2.6 Update Pydantic schemas for ToolConfig (add new fields)
-- [x] 1.2.7 Add validation schemas (port range, JSON structure, definition_type enum)
-
-### 1.3 Config Folder API
-- [x] 1.3.1 Create `api/config_folders.py` router
-- [x] 1.3.2 Implement `GET /config-folders` (list with filtering by project)
-- [x] 1.3.3 Implement `POST /config-folders` (create)
-- [x] 1.3.4 Implement `PUT /config-folders/{id}` (update name, mount_path, files)
-- [x] 1.3.5 Implement `DELETE /config-folders/{id}` (delete)
-- [x] 1.3.6 Implement `POST /config-folders/{id}/overrides` (add project override)
-- [x] 1.3.7 Implement `PUT /config-folders/{id}/overrides/{project_id}` (update override)
-- [x] 1.3.8 Implement `DELETE /config-folders/{id}/overrides/{project_id}` (remove override)
-- [x] 1.3.9 Add validation: 10MB size limit per folder
-- [x] 1.3.10 Add ownership checks (user can only access own folders)
-
-### 1.4 Tool Type API Updates
-- [x] 1.4.1 Update `POST /tool-types` to accept definition_type, dockerfile_template, build_context, readiness_probe
-- [x] 1.4.2 Update `PUT /tool-types/{id}` to handle new fields
-- [ ] 1.4.3 Add `GET /tool-types/{id}/validate` endpoint (syntax validation)
-- [x] 1.4.4 Update tool type response schemas
-- [x] 1.4.5 Update seed function to set definition_type="compose" for built-in types
-
-### 1.5 Tool Config API Updates
-- [x] 1.5.1 Update `POST /tool-configs` to accept new fields
-- [x] 1.5.2 Update `PUT /tool-configs/{id}` to handle new fields
-- [x] 1.5.3 Update `GET /tool-configs` to return new fields
-- [x] 1.5.4 Add `GET /tool-configs/defaults/{tool_type_id}` endpoint
-- [x] 1.5.5 Add validation for port_override range
-- [x] 1.5.6 Add validation for environment_variables JSON structure
-- [x] 1.5.7 Add validation for volumes JSON structure (source/target/type)
-
-## Phase 2: Instance Creation Enhancement
-
-### 2.1 Docker Build Service
-- [ ] 2.1.1 Create `services/docker_build.py` for Dockerfile builds
-- [ ] 2.1.2 Implement `build_image(instance_dir, dockerfile, tag)` function
-- [ ] 2.1.3 Handle build context file writing
-- [ ] 2.1.4 Add build output streaming/logging
-- [ ] 2.1.5 Handle build failures with clear error messages
-
-### 2.2 Compose Generation for Dockerfile Tools
-- [ ] 2.2.1 Create compose template for dockerfile-built images
-- [ ] 2.2.2 Integrate build service into instance creation flow
-- [ ] 2.2.3 Update `render_compose_template` to handle both paths
-
-### 2.3 Config Folder Mounting
-- [ ] 2.3.1 Implement `write_config_folder_files(instance_dir, folders)` function
-- [ ] 2.3.2 Resolve config folders for user + project
-- [ ] 2.3.3 Generate volume mounts in compose file for config folders
-- [ ] 2.3.4 Apply project overrides during resolution
-- [ ] 2.3.5 Write config folder files to `instance_dir/volumes/`
-
-### 2.4 Readiness Probe Service
-- [ ] 2.4.1 Create `services/readiness_probe.py`
-- [ ] 2.4.2 Implement `execute_probe(container_id, probe_config)` function
-- [ ] 2.4.3 Implement polling loop with timeout and interval
-- [ ] 2.4.4 Store probe output/logs on instance
-- [ ] 2.4.5 Update instance status based on probe result ("running" or "failed")
-- [ ] 2.4.6 Handle probe command failures gracefully
-
-### 2.5 Instance Creation Integration
-- [ ] 2.5.1 Update `create_instance` endpoint to use new fields
-- [ ] 2.5.2 Integrate dockerfile build path into creation flow
-- [ ] 2.5.3 Integrate config folder mounting
-- [ ] 2.5.4 Integrate readiness probe execution
-- [ ] 2.5.5 Apply port_override if specified
-- [ ] 2.5.6 Apply start_command if specified
-- [ ] 2.5.7 Apply working_directory if specified
-- [ ] 2.5.8 Apply environment_variables from ToolConfig
-- [ ] 2.5.9 Apply volumes from ToolConfig
-- [ ] 2.5.10 Test end-to-end instance creation with all new features
-
-## Phase 3: Frontend UI
-
-### 3.1 API Client Updates
-- [ ] 3.1.1 Update `api/tool_types.ts` with new fields and endpoints
-- [ ] 3.1.2 Update `api/tool_configs.ts` with new fields
-- [ ] 3.1.3 Create `api/config_folders.ts` with all CRUD operations
-- [ ] 3.1.4 Update TypeScript types/interfaces
-
-### 3.2 Tool Workshop Layout
-- [ ] 3.2.1 Create `pages/tool-workshop.tsx` (replaces tool-configs and tool-types)
-- [ ] 3.2.2 Implement split-pane layout (sidebar + main content)
-- [ ] 3.2.3 Create sidebar navigation tree (Tool Types / Config Folders)
-- [ ] 3.2.4 Implement tab switching (Tool Types / Configs / Config Folders)
-- [ ] 3.2.5 Add responsive design (collapsible sidebar on mobile)
-- [ ] 3.2.6 Update App.tsx routing
-
-### 3.3 Tool Type Builder
-- [ ] 3.3.1 Create `components/ToolTypeBuilder.tsx`
-- [ ] 3.3.2 Implement definition type selector (Compose vs Dockerfile)
-- [ ] 3.3.3 Create compose template editor (textarea with YAML highlighting)
-- [ ] 3.3.4 Create dockerfile editor (textarea with Dockerfile highlighting)
-- [ ] 3.3.5 Add build context file manager
-- [ ] 3.3.6 Add readiness probe configuration (command, timeout, interval)
-- [ ] 3.3.7 Add validation feedback (syntax check)
-- [ ] 3.3.8 Implement create/update/delete operations
-
-### 3.4 Config Editor Enhancement
-- [ ] 3.4.1 Update config form with new fields
-- [ ] 3.4.2 Add port override input (integer, 1-65535)
-- [ ] 3.4.3 Add start command input
-- [ ] 3.4.4 Add working directory input
-- [ ] 3.4.5 Create environment variables editor (key-value table)
-- [ ] 3.4.6 Create volumes editor (source/target/type table)
-- [ ] 3.4.7 Add JSON validation for env vars and volumes
-- [ ] 3.4.8 Implement tabbed sections (Basic / Runtime / Advanced)
-
-### 3.5 Config Folder Manager
-- [ ] 3.5.1 Create `components/ConfigFolderManager.tsx`
-- [ ] 3.5.2 Implement folder list view
-- [ ] 3.5.3 Create folder editor (name, description, mount_path)
-- [ ] 3.5.4 Create file manager (add/edit/delete files with path and content)
-- [ ] 3.5.5 Implement file content editor (textarea with syntax highlighting)
-- [ ] 3.5.6 Create project override manager
-- [ ] 3.5.7 Add active/inactive toggle
-- [ ] 3.5.8 Show folder size indicator
-
-### 3.6 Navigation Updates
-- [ ] 3.6.1 Update header/navigation to link to `/tool-workshop`
-- [ ] 3.6.2 Remove old `/tool-configs` and `/tool-types` routes (or redirect)
-- [ ] 3.6.3 Update breadcrumb navigation if applicable
-
-## Phase 4: Integration & Testing
-
-### 4.1 Backend Testing
-- [ ] 4.1.1 Test config folder CRUD operations
-- [ ] 4.1.2 Test config folder project overrides
-- [ ] 4.1.3 Test tool type creation with dockerfile
-- [ ] 4.1.4 Test tool type creation with compose
-- [ ] 4.1.5 Test readiness probe execution (success case)
-- [ ] 4.1.6 Test readiness probe execution (timeout case)
-- [ ] 4.1.7 Test instance creation with config folders mounted
-- [ ] 4.1.8 Test instance creation with port override
-- [ ] 4.1.9 Test instance creation with volumes
-- [ ] 4.1.10 Test 10MB size limit enforcement
-
-### 4.2 Frontend Testing
-- [ ] 4.2.1 Test Tool Workshop page load
-- [ ] 4.2.2 Test tool type creation flow
-- [ ] 4.2.3 Test config folder creation and file management
-- [ ] 4.2.4 Test config editor with all new fields
-- [ ] 4.2.5 Test responsive layout on mobile
-- [ ] 4.2.6 Test form validation (port range, JSON structure)
-
-### 4.3 End-to-End Testing
-- [ ] 4.3.1 Create a new tool type with dockerfile, start instance
-- [ ] 4.3.2 Create a new tool type with compose, start instance
-- [ ] 4.3.3 Create config folder, mount into instance, verify files present
-- [ ] 4.3.4 Add project override, verify different files in different projects
-- [ ] 4.3.5 Test readiness probe with failing command (should mark failed)
-- [ ] 4.3.6 Test readiness probe with succeeding command (should mark running)
-
-### 4.4 Quality Gates
-- [ ] 4.4.1 Run backend linting (ruff)
-- [ ] 4.4.2 Run backend type checking (mypy)
-- [ ] 4.4.3 Run frontend type checking (tsc)
-- [ ] 4.4.4 Run frontend linting (eslint)
-- [ ] 4.4.5 Build frontend and verify no errors
-- [ ] 4.4.6 Run existing tests to ensure no regressions
-- [ ] 4.4.7 Verify backward compatibility (existing instances still work)
-
-## Phase 5: Documentation & Deployment
-
-### 5.1 Documentation
-- [ ] 5.1.1 Update API documentation (OpenAPI/Swagger annotations)
-- [ ] 5.1.2 Add tool workshop user guide
-- [ ] 5.1.3 Document config folder usage
-- [ ] 5.1.4 Document readiness probe configuration
-- [ ] 5.1.5 Add example dockerfile and compose templates
-
-### 5.2 Migration & Deployment
-- [ ] 5.2.1 Verify database migrations run cleanly on existing data
-- [ ] 5.2.2 Update seed data for built-in tool types (add definition_type)
-- [ ] 5.2.3 Test fresh install (no existing data)
-- [ ] 5.2.4 Commit all changes with conventional commit messages
-- [ ] 5.2.5 Create comprehensive PR description
-
-## Quality Gates Summary
-
-**Before completing this change:**
-- All migrations must run successfully
-- Backend linting and type checking must pass
-- Frontend build must succeed with no errors
-- All new API endpoints must be tested
-- At least one end-to-end test for each new feature
-- No regressions in existing instance creation flow
-- Documentation updated