Rewrite the gateway around health, retries, slicing and a Windows service

Scanner
- manifest lookup is now depth-bounded and prunes numeric zoom directories, so
  a scan no longer walks the whole tile payload
- rescans only report a version as updated when something actually changed
- overlapping runs are refused instead of interleaving their bookkeeping

Hot path
- token authorisation loads only that token grants and throttles the
  last_used_at write instead of touching it on every tile
- SQLite runs in WAL with a busy timeout and a real connection pool
- the catalog lookup used by /tiles no longer loads every basemap

Security
- the admin surface requires ADMIN_TOKEN (bearer) or ADMIN_USER/ADMIN_PASSWORD
  (basic), and the service refuses to bind off-host without credentials
- CORS is an explicit allow-list; newly minted tokens never reach a redirect URL
- client tokens are redacted from the access log

Operations
- resource health inspection flags a moved or deleted tile root before a 404
- pushes retry with backoff and can be re-queued by hand; the schedule lives in
  the database so a restart does not lose it
- access log plus /metrics counters

Image slicing
- tile_jobs drive the GDAL bundled with QGIS via scripts/gdal2tiles-qgis.bat
- layer_sources remembers what a layer is made of: submit one source to append
  a flight, or all of them to rebuild the layer as a VRT mosaic with no tile
  seams; the console exposes both, including a one-click rebuild
- slicing is available to integrations through a narrow slice token scope
  (submit, poll, idempotent by code, completion callback)

Console
- rebuilt around a fixed rail and single-view navigation with health and
  outstanding work leading, instead of one long scrolling page

Windows service
- native install/start/stop/status with crash recovery, auto-start and a
  rotating log file, so no NSSM wrapper is needed
- start-all.bat and stop-all.bat are removed: they killed the process by port
  with taskkill, which fought the service restart policy

Verified with 49 tests and live runs against real tile data and real GDAL.
This commit is contained in:
2026-10-16 10:35:30 +08:00
parent 8faf25b436
commit 73ad03fa59
49 changed files with 8668 additions and 1817 deletions
+71 -37
View File
@@ -13,20 +13,21 @@ type SystemInfo struct {
SQLitePath string `json:"sqlite_path"`
ScanRoot string `json:"scan_root"`
VectorScanRoot string `json:"vector_scan_root"`
TileJobCommand string `json:"tile_job_command,omitempty"`
StartedAt time.Time `json:"started_at"`
}
type Basemap struct {
ID string `json:"id"`
Code string `json:"code"`
Name string `json:"name"`
Type string `json:"type"`
Status string `json:"status"`
Description string `json:"description,omitempty"`
Default *BasemapVersion `json:"default_version,omitempty"`
Versions []BasemapVersion `json:"versions,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
ID string `json:"id"`
Code string `json:"code"`
Name string `json:"name"`
Type string `json:"type"`
Status string `json:"status"`
Description string `json:"description,omitempty"`
Default *BasemapVersion `json:"default_version,omitempty"`
Versions []BasemapVersion `json:"versions,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
type BasemapVersion struct {
@@ -89,26 +90,27 @@ type TargetSystem struct {
}
type ServiceToken struct {
ID string `json:"id"`
Name string `json:"name"`
TokenPrefix string `json:"token_prefix"`
Status string `json:"status"`
ExpiresAt *time.Time `json:"expires_at,omitempty"`
LastUsedAt *time.Time `json:"last_used_at,omitempty"`
CreatedAt time.Time `json:"created_at"`
Grants []TokenGrant `json:"grants,omitempty"`
ID string `json:"id"`
Name string `json:"name"`
TokenPrefix string `json:"token_prefix"`
Scopes []string `json:"scopes"`
Status string `json:"status"`
ExpiresAt *time.Time `json:"expires_at,omitempty"`
LastUsedAt *time.Time `json:"last_used_at,omitempty"`
CreatedAt time.Time `json:"created_at"`
Grants []TokenGrant `json:"grants,omitempty"`
VectorGrants []VectorTokenGrant `json:"vector_grants,omitempty"`
}
type TokenGrant struct {
ID string `json:"id"`
TokenID string `json:"token_id"`
BasemapID string `json:"basemap_id"`
BasemapCode string `json:"basemap_code"`
BasemapVersionID *string `json:"basemap_version_id,omitempty"`
BasemapVersion *string `json:"basemap_version,omitempty"`
Permission string `json:"permission"`
CreatedAt time.Time `json:"created_at"`
ID string `json:"id"`
TokenID string `json:"token_id"`
BasemapID string `json:"basemap_id"`
BasemapCode string `json:"basemap_code"`
BasemapVersionID *string `json:"basemap_version_id,omitempty"`
BasemapVersion *string `json:"basemap_version,omitempty"`
Permission string `json:"permission"`
CreatedAt time.Time `json:"created_at"`
}
type PushRecord struct {
@@ -123,6 +125,8 @@ type PushRecord struct {
ResponseStatus *int `json:"response_status,omitempty"`
ResponseBody string `json:"response_body,omitempty"`
ErrorMessage string `json:"error_message,omitempty"`
AttemptCount int `json:"attempt_count"`
NextAttemptAt *time.Time `json:"next_attempt_at,omitempty"`
PushedAt time.Time `json:"pushed_at"`
FinishedAt *time.Time `json:"finished_at,omitempty"`
}
@@ -164,6 +168,8 @@ type VectorPushRecord struct {
ResponseStatus *int `json:"response_status,omitempty"`
ResponseBody string `json:"response_body,omitempty"`
ErrorMessage string `json:"error_message,omitempty"`
AttemptCount int `json:"attempt_count"`
NextAttemptAt *time.Time `json:"next_attempt_at,omitempty"`
PushedAt time.Time `json:"pushed_at"`
FinishedAt *time.Time `json:"finished_at,omitempty"`
}
@@ -205,14 +211,17 @@ type CreateTokenInput struct {
Name string
BasemapCodes []string
VectorCodes []string
Scopes []string
ExpiresAt *time.Time
}
type TokenAuth struct {
Token ServiceToken
// permission -> basemap_code -> version scope
Permissions map[string]map[string]VersionScope
Permissions map[string]map[string]VersionScope
VectorPermissions map[string]map[string]struct{}
// Scopes are coarse capabilities beyond resource grants, e.g. "slice".
Scopes map[string]struct{}
}
type VersionScope struct {
@@ -220,16 +229,41 @@ type VersionScope struct {
Versions map[string]struct{}
}
// ResourceHealth is the availability verdict recorded by the health inspector.
// It is kept separate from Status: Status is a catalog fact, Health is whether
// the bytes are still on disk right now.
type ResourceHealth struct {
Health string `json:"health"`
Detail string `json:"detail,omitempty"`
CheckedAt time.Time `json:"checked_at"`
}
// LayerInventory is one layer and the imagery it is built from, ordered for
// deterministic rendering in the console.
type LayerInventory struct {
TargetCode string `json:"target_code"`
Sources []LayerSource `json:"sources"`
// ZoomMin/ZoomMax/TileFormat mirror the layer's current basemap version so
// a rebuild can reuse the range it is already published at.
ZoomMin int `json:"zoom_min"`
ZoomMax int `json:"zoom_max"`
TileFormat string `json:"tile_format"`
}
type DashboardData struct {
SystemInfo SystemInfo
Basemaps []Basemap
VectorAssets []VectorAsset
ScanSources []ScanSource
ScanRuns []ScanRun
TargetSystems []TargetSystem
Tokens []ServiceToken
PushRecords []PushRecord
SystemInfo SystemInfo
Basemaps []Basemap
VectorAssets []VectorAsset
ScanSources []ScanSource
ScanRuns []ScanRun
TargetSystems []TargetSystem
Tokens []ServiceToken
PushRecords []PushRecord
VectorPushRecords []VectorPushRecord
Flash string
CreatedToken string
Flash string
CreatedToken string
VersionHealth map[string]ResourceHealth
VectorHealth map[string]ResourceHealth
TileJobs []TileJob
Layers []LayerInventory
}