chore: harden common storage bootstrap and slim embedded db assets

Unify embedding config, build providers from system settings, and fail
startup when index builds error or time out. Move Surreal assets under
common/db so embeds exclude crate source, and read storage via streams.
This commit is contained in:
Per Stark
2026-05-29 12:26:26 +02:00
parent 93d11b66eb
commit e3bb2935d0
62 changed files with 672 additions and 443 deletions
@@ -0,0 +1,97 @@
-- Enforce SCHEMAFULL on all tables and define missing fields
-- 1. Define missing fields for ingestion_task (formerly job, but now ingestion_task)
DEFINE TABLE OVERWRITE ingestion_task SCHEMAFULL;
-- Core Fields
DEFINE FIELD IF NOT EXISTS id ON ingestion_task TYPE record<ingestion_task>;
DEFINE FIELD IF NOT EXISTS created_at ON ingestion_task TYPE datetime DEFAULT time::now();
DEFINE FIELD IF NOT EXISTS updated_at ON ingestion_task TYPE datetime DEFAULT time::now();
DEFINE FIELD IF NOT EXISTS user_id ON ingestion_task TYPE string;
-- State Machine Fields
DEFINE FIELD IF NOT EXISTS state ON ingestion_task TYPE string ASSERT $value IN ['Pending', 'Reserved', 'Processing', 'Succeeded', 'Failed', 'Cancelled', 'DeadLetter'];
DEFINE FIELD IF NOT EXISTS attempts ON ingestion_task TYPE int DEFAULT 0;
DEFINE FIELD IF NOT EXISTS max_attempts ON ingestion_task TYPE int DEFAULT 3;
DEFINE FIELD IF NOT EXISTS scheduled_at ON ingestion_task TYPE datetime DEFAULT time::now();
DEFINE FIELD IF NOT EXISTS locked_at ON ingestion_task TYPE option<datetime>;
DEFINE FIELD IF NOT EXISTS lease_duration_secs ON ingestion_task TYPE int DEFAULT 300;
DEFINE FIELD IF NOT EXISTS worker_id ON ingestion_task TYPE option<string>;
DEFINE FIELD IF NOT EXISTS error_code ON ingestion_task TYPE option<string>;
DEFINE FIELD IF NOT EXISTS error_message ON ingestion_task TYPE option<string>;
DEFINE FIELD IF NOT EXISTS last_error_at ON ingestion_task TYPE option<datetime>;
DEFINE FIELD IF NOT EXISTS priority ON ingestion_task TYPE int DEFAULT 0;
-- Content Payload (IngestionPayload Enum)
DEFINE FIELD IF NOT EXISTS content ON ingestion_task TYPE object;
DEFINE FIELD IF NOT EXISTS content.Url ON ingestion_task TYPE option<object>;
DEFINE FIELD IF NOT EXISTS content.Text ON ingestion_task TYPE option<object>;
DEFINE FIELD IF NOT EXISTS content.File ON ingestion_task TYPE option<object>;
-- Content: Url Variant
DEFINE FIELD IF NOT EXISTS content.Url.url ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Url.context ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Url.category ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Url.user_id ON ingestion_task TYPE string;
-- Content: Text Variant
DEFINE FIELD IF NOT EXISTS content.Text.text ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Text.context ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Text.category ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.Text.user_id ON ingestion_task TYPE string;
-- Content: File Variant
DEFINE FIELD IF NOT EXISTS content.File.context ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.category ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.user_id ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info ON ingestion_task TYPE object;
-- Content: File.file_info (FileInfo Struct)
DEFINE FIELD IF NOT EXISTS content.File.file_info.id ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info.created_at ON ingestion_task TYPE datetime;
DEFINE FIELD IF NOT EXISTS content.File.file_info.updated_at ON ingestion_task TYPE datetime;
DEFINE FIELD IF NOT EXISTS content.File.file_info.sha256 ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info.path ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info.file_name ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info.mime_type ON ingestion_task TYPE string;
DEFINE FIELD IF NOT EXISTS content.File.file_info.user_id ON ingestion_task TYPE string;
-- 2. Enforce SCHEMAFULL on all other tables
DEFINE TABLE OVERWRITE analytics SCHEMAFULL;
DEFINE TABLE OVERWRITE conversation SCHEMAFULL;
DEFINE TABLE OVERWRITE file SCHEMAFULL;
DEFINE TABLE OVERWRITE knowledge_entity SCHEMAFULL;
DEFINE TABLE OVERWRITE message SCHEMAFULL;
DEFINE TABLE OVERWRITE relates_to SCHEMAFULL TYPE RELATION;
DEFINE FIELD IF NOT EXISTS in ON relates_to TYPE record<knowledge_entity>;
DEFINE FIELD IF NOT EXISTS out ON relates_to TYPE record<knowledge_entity>;
DEFINE FIELD IF NOT EXISTS metadata ON relates_to TYPE object;
DEFINE FIELD IF NOT EXISTS metadata.user_id ON relates_to TYPE string;
DEFINE FIELD IF NOT EXISTS metadata.source_id ON relates_to TYPE string;
DEFINE FIELD IF NOT EXISTS metadata.relationship_type ON relates_to TYPE string;
DEFINE TABLE OVERWRITE scratchpad SCHEMAFULL;
DEFINE TABLE OVERWRITE system_settings SCHEMAFULL;
DEFINE TABLE OVERWRITE text_chunk SCHEMAFULL;
-- text_content must have fields defined before enforcing SCHEMAFULL
DEFINE TABLE OVERWRITE text_content SCHEMAFULL;
DEFINE FIELD IF NOT EXISTS created_at ON text_content TYPE datetime;
DEFINE FIELD IF NOT EXISTS updated_at ON text_content TYPE datetime;
DEFINE FIELD IF NOT EXISTS text ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info ON text_content TYPE option<object>;
DEFINE FIELD IF NOT EXISTS url_info ON text_content TYPE option<object>;
DEFINE FIELD IF NOT EXISTS url_info.url ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS url_info.title ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS url_info.image_id ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS context ON text_content TYPE option<string>;
DEFINE FIELD IF NOT EXISTS category ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS user_id ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.id ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.created_at ON text_content TYPE datetime;
DEFINE FIELD IF NOT EXISTS file_info.updated_at ON text_content TYPE datetime;
DEFINE FIELD IF NOT EXISTS file_info.sha256 ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.path ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.file_name ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.mime_type ON text_content TYPE string;
DEFINE FIELD IF NOT EXISTS file_info.user_id ON text_content TYPE string;
DEFINE TABLE OVERWRITE user SCHEMAFULL;