WeKnora deployment source with the reviewed wiki identity, summary and recovery fixes
Anydoc / anydoc parser engine (push) Canceled after 0s
App / Format, vet, test, and build (push) Canceled after 0s
CLI / test (macos-latest / go 1.26) (push) Canceled after 0s
CLI / test (ubuntu-latest / go 1.26) (push) Canceled after 0s
CLI / test (windows-latest / go 1.26) (push) Canceled after 0s
Build and Push Docker Image / build-ui (push) Canceled after 0s
Build and Push Docker Image / build-docreader (push) Canceled after 0s
Build and Push Docker Image / build-sandbox (push) Canceled after 0s
Build and Push Docker Image / build-app (amd64, linux/amd64, ubuntu-latest) (push) Canceled after 0s
Build and Push Docker Image / build-app (arm64, linux/arm64, ubuntu-24.04-arm) (push) Canceled after 0s
DocReader / Python tests and Go client tests (push) Canceled after 0s
Build & Publish (dsh-weknora) / Typecheck, test, pack (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (pinned) (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (latest, advisory) (push) Canceled after 0s
Frontend / Test, type-check, and build (push) Canceled after 0s
Go Lint Cache / warm lint cache (.) (push) Canceled after 0s
Go Lint Cache / warm lint cache (cli) (push) Canceled after 0s
Go Lint Cache / warm lint cache (client) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.10) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.11) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.12) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.13) (push) Canceled after 0s
Build and Push Docker Image / merge (push) Canceled after 0s
Build & Publish (dsh-weknora) / Publish to npm (push) Canceled after 0s
Build & Publish (mcp-server) / Build sdist + wheel (push) Canceled after 0s
Build & Publish (mcp-server) / Publish to PyPI (push) Canceled after 0s

This commit is contained in:
yawan
2026-09-22 16:19:06 +08:00
commit f7fc992f57
3929 changed files with 1006607 additions and 0 deletions
+230
View File
@@ -0,0 +1,230 @@
DROP TABLE IF EXISTS tenants;
DROP TABLE IF EXISTS models;
DROP TABLE IF EXISTS knowledge_bases;
DROP TABLE IF EXISTS knowledges;
DROP TABLE IF EXISTS sessions;
DROP TABLE IF EXISTS messages;
DROP TABLE IF EXISTS chunks;
CREATE TABLE tenants (
id BIGINT AUTO_INCREMENT PRIMARY KEY,
name VARCHAR(255) NOT NULL,
description TEXT,
retriever_engines JSON NOT NULL,
status VARCHAR(50) DEFAULT 'active',
business VARCHAR(255) NOT NULL,
storage_quota BIGINT NOT NULL DEFAULT 10737418240,
storage_used BIGINT NOT NULL DEFAULT 0,
agent_config JSON DEFAULT NULL COMMENT 'Tenant-level agent configuration in JSON format',
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 AUTO_INCREMENT=10000;
CREATE TABLE models (
id VARCHAR(64) PRIMARY KEY,
tenant_id INT NOT NULL,
name VARCHAR(255) NOT NULL,
display_name VARCHAR(255) NOT NULL DEFAULT '',
type VARCHAR(50) NOT NULL,
source VARCHAR(50) NOT NULL,
description TEXT,
parameters JSON NOT NULL,
is_default BOOLEAN NOT NULL DEFAULT FALSE,
status VARCHAR(50) NOT NULL DEFAULT 'active',
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_models_tenant_source_type ON models(tenant_id, source, type);
CREATE TABLE knowledge_bases (
id VARCHAR(36) PRIMARY KEY,
name VARCHAR(255) NOT NULL,
description TEXT,
tenant_id INT NOT NULL,
chunking_config JSON NOT NULL,
image_processing_config JSON NOT NULL,
embedding_model_id VARCHAR(64) NOT NULL,
summary_model_id VARCHAR(64) NOT NULL,
rerank_model_id VARCHAR(64) NOT NULL,
cos_config JSON NOT NULL,
vlm_config JSON NOT NULL,
extract_config JSON NULL,
auto_tag_config JSON NULL,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_knowledge_bases_tenant_name ON knowledge_bases(tenant_id, name);
CREATE TABLE knowledges (
id VARCHAR(36) PRIMARY KEY,
tenant_id INT NOT NULL,
knowledge_base_id VARCHAR(36) NOT NULL,
type VARCHAR(50) NOT NULL,
title VARCHAR(255) NOT NULL,
description TEXT,
source VARCHAR(2048) NOT NULL,
parse_status VARCHAR(50) NOT NULL DEFAULT 'unprocessed',
enable_status VARCHAR(50) NOT NULL DEFAULT 'enabled',
embedding_model_id VARCHAR(64),
file_name VARCHAR(255),
file_type VARCHAR(50),
file_size BIGINT,
file_path TEXT,
file_hash VARCHAR(64),
storage_size BIGINT NOT NULL DEFAULT 0,
metadata JSON,
custom_metadata JSON NOT NULL,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL,
processed_at TIMESTAMP,
error_message TEXT
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_knowledges_tenant_id ON knowledges(tenant_id, knowledge_base_id);
CREATE TABLE sessions (
id VARCHAR(36) PRIMARY KEY,
tenant_id INTEGER NOT NULL,
title VARCHAR(255),
description TEXT,
knowledge_base_id VARCHAR(36),
max_rounds INT NOT NULL DEFAULT 5,
enable_rewrite BOOLEAN NOT NULL DEFAULT TRUE,
fallback_strategy VARCHAR(255) NOT NULL DEFAULT 'fixed',
fallback_response VARCHAR(255) NOT NULL DEFAULT '很抱歉,我暂时无法回答这个问题。',
keyword_threshold FLOAT NOT NULL DEFAULT 0.5,
vector_threshold FLOAT NOT NULL DEFAULT 0.5,
rerank_model_id VARCHAR(64),
embedding_top_k INTEGER NOT NULL DEFAULT 10,
rerank_top_k INTEGER NOT NULL DEFAULT 10,
rerank_threshold FLOAT NOT NULL DEFAULT 0.65,
summary_model_id VARCHAR(64),
summary_parameters JSON NOT NULL,
agent_config JSON DEFAULT NULL COMMENT 'Session-level agent configuration in JSON format',
context_config JSON DEFAULT NULL COMMENT 'LLM context management configuration (separate from message storage)',
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_sessions_tenant_id ON sessions(tenant_id);
CREATE TABLE messages (
id VARCHAR(36) PRIMARY KEY,
request_id VARCHAR(36) NOT NULL,
session_id VARCHAR(36) NOT NULL,
role VARCHAR(50) NOT NULL,
content TEXT NOT NULL,
knowledge_references JSON NOT NULL,
agent_steps JSON DEFAULT NULL COMMENT 'Agent execution steps (reasoning process and tool calls)',
is_completed BOOLEAN NOT NULL DEFAULT FALSE,
agent_id VARCHAR(36) NOT NULL DEFAULT '',
agent_tenant_id INTEGER NOT NULL DEFAULT 0,
model_id VARCHAR(64) NOT NULL DEFAULT '',
execution_context JSON NOT NULL,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_messages_session_role ON messages(session_id, role);
CREATE INDEX idx_messages_agent_id ON messages(agent_id);
CREATE TABLE message_suggestion_sets (
id VARCHAR(36) PRIMARY KEY,
tenant_id INTEGER NOT NULL,
session_id VARCHAR(36) NOT NULL,
assistant_message_id VARCHAR(36) NOT NULL,
agent_id VARCHAR(36) NOT NULL DEFAULT '',
agent_tenant_id INTEGER NOT NULL DEFAULT 0,
placement VARCHAR(32) NOT NULL,
config_hash VARCHAR(64) NOT NULL,
locale VARCHAR(16) NOT NULL DEFAULT '',
status VARCHAR(16) NOT NULL,
allow_regenerate BOOLEAN NOT NULL DEFAULT FALSE,
suppression_reason VARCHAR(64) NOT NULL DEFAULT '',
questions JSON NOT NULL,
model_id VARCHAR(64) NOT NULL DEFAULT '',
prompt_tokens INTEGER NOT NULL DEFAULT 0,
completion_tokens INTEGER NOT NULL DEFAULT 0,
latency_ms BIGINT NOT NULL DEFAULT 0,
error_code VARCHAR(64) NOT NULL DEFAULT '',
lease_until TIMESTAMP NULL DEFAULT NULL,
generated_at TIMESTAMP NULL DEFAULT NULL,
created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
UNIQUE KEY idx_message_suggestion_sets_cache_key
(tenant_id, assistant_message_id, placement, config_hash, locale),
KEY idx_message_suggestion_sets_session (tenant_id, session_id, created_at),
KEY idx_message_suggestion_sets_status (status, lease_until)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE TABLE message_suggestion_events (
id BIGINT UNSIGNED AUTO_INCREMENT PRIMARY KEY,
tenant_id INTEGER NOT NULL,
session_id VARCHAR(36) NOT NULL,
suggestion_set_id VARCHAR(36) NOT NULL,
question_id VARCHAR(64) NOT NULL DEFAULT '',
event_type VARCHAR(32) NOT NULL,
actor_id VARCHAR(512) NOT NULL DEFAULT '',
created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
KEY idx_message_suggestion_events_set (suggestion_set_id, created_at),
KEY idx_message_suggestion_events_session (tenant_id, session_id, created_at),
KEY idx_message_suggestion_events_type (event_type, created_at),
CONSTRAINT fk_message_suggestion_events_set
FOREIGN KEY (suggestion_set_id) REFERENCES message_suggestion_sets(id) ON DELETE CASCADE
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE TABLE chunks (
id VARCHAR(36) PRIMARY KEY,
tenant_id INTEGER NOT NULL,
knowledge_base_id VARCHAR(36) NOT NULL,
knowledge_id VARCHAR(36) NOT NULL,
content TEXT NOT NULL,
source_content TEXT NOT NULL,
content_revision INT NOT NULL DEFAULT 0,
index_status VARCHAR(16) NOT NULL DEFAULT 'ready',
last_editor_id VARCHAR(64) NOT NULL DEFAULT '',
context_header TEXT NOT NULL,
chunk_index INTEGER NOT NULL,
is_enabled BOOLEAN NOT NULL DEFAULT TRUE,
start_at INTEGER NOT NULL,
end_at INTEGER NOT NULL,
pre_chunk_id VARCHAR(36),
next_chunk_id VARCHAR(36),
chunk_type VARCHAR(20) NOT NULL DEFAULT 'text',
parent_chunk_id VARCHAR(36),
image_info TEXT,
relation_chunks JSON,
indirect_relation_chunks JSON,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
deleted_at TIMESTAMP NULL DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE INDEX idx_chunks_tenant_knowledge ON chunks(tenant_id, knowledge_id);
CREATE INDEX idx_chunks_parent_id ON chunks(parent_chunk_id);
CREATE INDEX idx_chunks_chunk_type ON chunks(chunk_type);
CREATE TABLE chunk_revisions (
id VARCHAR(36) PRIMARY KEY,
tenant_id BIGINT NOT NULL,
knowledge_base_id VARCHAR(36) NOT NULL,
knowledge_id VARCHAR(36) NOT NULL,
chunk_id VARCHAR(36) NOT NULL,
revision INT NOT NULL,
content TEXT NOT NULL,
is_enabled BOOLEAN NOT NULL DEFAULT TRUE,
editor_id VARCHAR(64) NOT NULL DEFAULT '',
edit_source VARCHAR(16) NOT NULL DEFAULT 'user',
edited_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
UNIQUE KEY idx_chunk_revisions_chunk_revision (chunk_id, revision),
KEY idx_chunk_revisions_tenant_chunk (tenant_id, chunk_id)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
@@ -0,0 +1 @@
DROP TABLE IF EXISTS wiki_ingest_checkpoints;
@@ -0,0 +1,11 @@
CREATE TABLE IF NOT EXISTS wiki_ingest_checkpoints (
tenant_id BIGINT UNSIGNED NOT NULL,
knowledge_base_id VARCHAR(36) NOT NULL,
knowledge_id VARCHAR(36) NOT NULL,
fingerprint VARCHAR(64) NOT NULL,
stage VARCHAR(32) NOT NULL,
item_key VARCHAR(64) NOT NULL,
payload LONGTEXT NOT NULL,
updated_at DATETIME(3) NOT NULL DEFAULT CURRENT_TIMESTAMP(3),
PRIMARY KEY (tenant_id, knowledge_base_id, knowledge_id, fingerprint, stage, item_key)
);
@@ -0,0 +1 @@
DROP TABLE IF EXISTS wiki_recovery_budgets;
@@ -0,0 +1,26 @@
CREATE TABLE IF NOT EXISTS wiki_recovery_budgets (
tenant_id BIGINT NOT NULL,
dead_letter_id BIGINT NOT NULL,
attempt_number INTEGER NOT NULL,
pending_op_id BIGINT NOT NULL,
knowledge_base_id VARCHAR(36) NOT NULL,
knowledge_id VARCHAR(36) NOT NULL,
model_id VARCHAR(36) NOT NULL,
embedding_model_id VARCHAR(36) NOT NULL DEFAULT '',
source_fingerprint VARCHAR(64) NOT NULL,
model_fingerprint VARCHAR(64) NOT NULL,
reviewed_release VARCHAR(255) NOT NULL,
reviewed_api_image VARCHAR(255) NOT NULL,
max_provider_requests BIGINT NOT NULL CHECK (max_provider_requests > 0),
reserved_provider_requests BIGINT NOT NULL DEFAULT 0 CHECK (reserved_provider_requests >= 0 AND reserved_provider_requests <= max_provider_requests),
deadline_at DATETIME(6) NOT NULL,
status VARCHAR(32) NOT NULL DEFAULT 'active',
stop_reason VARCHAR(128) NOT NULL DEFAULT '',
last_phase VARCHAR(64) NOT NULL DEFAULT '',
paused_payload TEXT NOT NULL,
verified_progress TEXT NOT NULL,
created_at DATETIME(6) NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at DATETIME(6) NOT NULL DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY (tenant_id, dead_letter_id, attempt_number, pending_op_id),
UNIQUE (tenant_id, pending_op_id)
);
@@ -0,0 +1,12 @@
SET @access_role_permission_version_sql = (
SELECT IF(COUNT(*) > 0,
'ALTER TABLE workbench_access_roles DROP COLUMN permission_version',
'SELECT 1')
FROM information_schema.COLUMNS
WHERE TABLE_SCHEMA = DATABASE()
AND TABLE_NAME = 'workbench_access_roles'
AND COLUMN_NAME = 'permission_version'
);
PREPARE access_role_permission_version_stmt FROM @access_role_permission_version_sql;
EXECUTE access_role_permission_version_stmt;
DEALLOCATE PREPARE access_role_permission_version_stmt;
@@ -0,0 +1,25 @@
-- The MySQL baseline predates the access-role table.
CREATE TABLE IF NOT EXISTS workbench_access_roles (
id VARCHAR(36) PRIMARY KEY,
tenant_id BIGINT NOT NULL,
name VARCHAR(100) NOT NULL,
description TEXT NOT NULL,
permissions JSON NOT NULL,
version INTEGER NOT NULL DEFAULT 1,
created_at DATETIME(6) NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at DATETIME(6) NOT NULL DEFAULT CURRENT_TIMESTAMP,
UNIQUE (tenant_id, name)
);
-- Preserve existing granular roles when applying after an emergency patch.
SET @access_role_permission_version_sql = (
SELECT IF(COUNT(*) = 0,
'ALTER TABLE workbench_access_roles ADD COLUMN permission_version INTEGER NOT NULL DEFAULT 0',
'SELECT 1')
FROM information_schema.COLUMNS
WHERE TABLE_SCHEMA = DATABASE()
AND TABLE_NAME = 'workbench_access_roles'
AND COLUMN_NAME = 'permission_version'
);
PREPARE access_role_permission_version_stmt FROM @access_role_permission_version_sql;
EXECUTE access_role_permission_version_stmt;
DEALLOCATE PREPARE access_role_permission_version_stmt;