feat: 更新后端平台模块、Compute引擎、前端组件及构建产物

- 更新 backend 平台 API、platform_store、compute_gateway sync
- 更新 compute agent/engine/adapter 及 API
- 更新 Docker 部署配置(app/compute)
- 新增 frontend/src/utils/ 工具模块
- 新增 scripts/ops_diagnostics.py 运维诊断脚本
- 新增 docs/2026-07-23-development-summary.md 开发总结
- 重构 frontend/dist 构建产物(新 hash)
- 更新前端多个视图组件及 API 模块

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
wuyongtao
2026-07-23 19:32:42 +08:00
parent f04dc479bb
commit b28cfbc6fa
193 changed files with 2647 additions and 424 deletions

View File

@@ -36,6 +36,45 @@ CREATE TABLE IF NOT EXISTS trained_models (
merged_path TEXT
);
CREATE TABLE IF NOT EXISTS model_lineage (
id TEXT PRIMARY KEY,
child_resource_type TEXT NOT NULL,
child_resource_id TEXT NOT NULL,
parent_resource_type TEXT NOT NULL,
parent_resource_id TEXT NOT NULL,
relation_type TEXT NOT NULL,
compute_job_id TEXT,
payload TEXT NOT NULL,
create_time TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS model_artifacts (
id TEXT PRIMARY KEY,
model_id TEXT NOT NULL,
model_kind TEXT NOT NULL,
artifact_type TEXT NOT NULL,
path TEXT NOT NULL,
size_bytes BIGINT NOT NULL DEFAULT 0,
checksum_sha256 TEXT,
metadata TEXT NOT NULL,
compute_job_id TEXT,
create_time TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS model_export_jobs (
id TEXT PRIMARY KEY,
trained_model_id TEXT,
compute_job_id TEXT NOT NULL,
node_id TEXT,
export_type TEXT NOT NULL,
quantization_bit INTEGER NOT NULL DEFAULT 0,
status TEXT NOT NULL,
output_dir TEXT,
payload TEXT NOT NULL,
create_time TEXT NOT NULL,
completed_at TEXT
);
CREATE TABLE IF NOT EXISTS datasets (
id TEXT PRIMARY KEY,
name TEXT NOT NULL UNIQUE,
@@ -111,6 +150,62 @@ CREATE TABLE IF NOT EXISTS fine_tune_tasks (
compute_job_id TEXT
);
CREATE TABLE IF NOT EXISTS fine_tune_metrics (
id TEXT PRIMARY KEY,
task_id TEXT NOT NULL REFERENCES fine_tune_tasks(id) ON DELETE CASCADE,
step INTEGER NOT NULL,
epoch DOUBLE PRECISION,
loss DOUBLE PRECISION,
grad_norm DOUBLE PRECISION,
learning_rate DOUBLE PRECISION,
raw TEXT NOT NULL,
create_time TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS fine_tune_checkpoints (
id TEXT PRIMARY KEY,
task_id TEXT NOT NULL REFERENCES fine_tune_tasks(id) ON DELETE CASCADE,
step INTEGER NOT NULL,
name TEXT NOT NULL,
path TEXT NOT NULL,
size_bytes BIGINT NOT NULL DEFAULT 0,
create_time TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS compute_jobs (
id TEXT PRIMARY KEY,
task_id TEXT REFERENCES fine_tune_tasks(id) ON DELETE SET NULL,
node_id TEXT REFERENCES compute_nodes(id) ON DELETE SET NULL,
engine TEXT NOT NULL,
status TEXT NOT NULL,
command TEXT NOT NULL,
output_dir TEXT,
log_file TEXT,
payload TEXT NOT NULL,
create_time TEXT NOT NULL,
update_time TEXT NOT NULL,
completed_at TEXT
);
CREATE TABLE IF NOT EXISTS gpu_allocations (
id TEXT PRIMARY KEY,
task_id TEXT REFERENCES fine_tune_tasks(id) ON DELETE CASCADE,
compute_job_id TEXT,
node_id TEXT REFERENCES compute_nodes(id) ON DELETE CASCADE,
gpu_index INTEGER NOT NULL,
status TEXT NOT NULL,
create_time TEXT NOT NULL,
released_at TEXT
);
CREATE TABLE IF NOT EXISTS scheduler_locks (
lock_key TEXT PRIMARY KEY,
owner TEXT NOT NULL,
expires_at TEXT NOT NULL,
create_time TEXT NOT NULL,
update_time TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS resource_replicas (
id TEXT PRIMARY KEY,
node_id TEXT NOT NULL REFERENCES compute_nodes(id) ON DELETE CASCADE,
@@ -119,6 +214,10 @@ CREATE TABLE IF NOT EXISTS resource_replicas (
local_path TEXT NOT NULL,
status TEXT NOT NULL,
sync_status TEXT NOT NULL,
checksum_sha256 TEXT,
byte_size BIGINT NOT NULL DEFAULT 0,
last_checked_at TEXT,
last_error TEXT,
create_time TEXT NOT NULL
);
@@ -160,6 +259,20 @@ CREATE TABLE IF NOT EXISTS compare_tasks (
CREATE INDEX IF NOT EXISTS idx_fine_tune_status ON fine_tune_tasks(status);
CREATE INDEX IF NOT EXISTS idx_fine_tune_compute_job ON fine_tune_tasks(compute_job_id);
CREATE INDEX IF NOT EXISTS idx_fine_tune_compute_node_status ON fine_tune_tasks(compute_node_id, status);
CREATE INDEX IF NOT EXISTS idx_model_lineage_child ON model_lineage(child_resource_type, child_resource_id);
CREATE INDEX IF NOT EXISTS idx_model_lineage_parent ON model_lineage(parent_resource_type, parent_resource_id);
CREATE INDEX IF NOT EXISTS idx_model_artifacts_model ON model_artifacts(model_kind, model_id, artifact_type);
CREATE INDEX IF NOT EXISTS idx_model_export_jobs_model ON model_export_jobs(trained_model_id, create_time DESC);
CREATE INDEX IF NOT EXISTS idx_model_export_jobs_compute ON model_export_jobs(compute_job_id);
CREATE INDEX IF NOT EXISTS idx_fine_tune_metrics_task_step ON fine_tune_metrics(task_id, step);
CREATE UNIQUE INDEX IF NOT EXISTS uq_fine_tune_metrics_task_step_epoch ON fine_tune_metrics(task_id, step, epoch);
CREATE INDEX IF NOT EXISTS idx_fine_tune_checkpoints_task_step ON fine_tune_checkpoints(task_id, step);
CREATE UNIQUE INDEX IF NOT EXISTS uq_fine_tune_checkpoints_task_path ON fine_tune_checkpoints(task_id, path);
CREATE INDEX IF NOT EXISTS idx_compute_jobs_task ON compute_jobs(task_id);
CREATE INDEX IF NOT EXISTS idx_compute_jobs_node_status ON compute_jobs(node_id, status);
CREATE INDEX IF NOT EXISTS idx_gpu_allocations_node_status ON gpu_allocations(node_id, status);
CREATE UNIQUE INDEX IF NOT EXISTS uq_gpu_allocations_active ON gpu_allocations(node_id, gpu_index) WHERE status IN ('allocated','running');
CREATE INDEX IF NOT EXISTS idx_scheduler_locks_expires ON scheduler_locks(expires_at);
CREATE INDEX IF NOT EXISTS idx_dataset_files_dataset ON dataset_files(dataset_id);
CREATE INDEX IF NOT EXISTS idx_gpus_node ON gpus(node_id);
CREATE UNIQUE INDEX IF NOT EXISTS uq_gpus_node_index ON gpus(node_id, gpu_index);