- Rename the original health monitor to endpoint health monitor
- Add tab navigation for endpoint, model, and provider health views
- Add model health monitor cards with availability, latency, first-byte latency, and 60-point history
- Add admin-only provider health monitor with collapsible active-provider sections
- Show per-provider model health cards after expanding a provider
- Add backend model health and provider health monitor payload builders
- Add admin endpoint for provider health monitoring
- Add provider-scoped usage breakdown filtering for per-provider model statistics
- Add frontend API types and request helpers for model/provider health data
- Add demo mock data for model and provider health monitoring
- Fix model health timeline time-unit handling so request history segments render correctly
Verification:
- cargo fmt
- npm run type-check
- npm run build
- cargo test -p aether-gateway health_models
- cargo test -p aether-gateway health_providers
- cargo test -p aether-gateway gateway_exposes_frontdoor_manifest_without_proxying_upstream
- extract provider reasoning effort from request body metadata
- extract priority service tier and expose it as service_tier
- show reasoning level and fast badges after model names
- include badges in active request updates and usage list payloads
- add targeted backend and frontend coverage
The stale-pending cleanup task previously hardcoded status_code=504 and a
generic timeout message for every usage row it finalized. When a request
had already been observed as failing — e.g. upstream Connection reset by
peer, watchdog 504, or an authenticated 4xx — the cleanup overwrote that
context with a misleading "服务器超时" outcome and 504 status, hiding the
real cause from the dashboards and customer.
Pull the most recent failed/cancelled candidate per stale request_id and,
if present, finalize the usage row with the candidate's status_code
(defaulting to 502 when none was recorded) and error_message. Requests
that have no terminal candidate (truly stuck pending/streaming) keep the
existing 504 + timeout-message behavior, since they really are timeouts
from the cleanup's perspective. Applied to all three SQL backends with
parameterized UPDATE statements.
The Postgres failed-candidate lookup orders by
COALESCE(finished_at, started_at, created_at) DESC, matching the MySQL
and SQLite ORDER BY clauses so the three backends pick the same
"most recent terminal candidate" under every NULL combination of timing
columns.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The "upstream_is_stream" JSON key flows from the AI execution report
context producer (aether-ai-serving::report_context) through several
consumers — usage runtime metadata copy/move, gateway watchdog, sync
execution decision, observability handlers, and the per-driver usage
repositories. Each site spelled the key as a bare string literal, so a
producer-side rename would silently degrade every consumer to its
fallback (typically assuming streaming) with no compile-time signal.
Introduce a single pub const UPSTREAM_IS_STREAM_KEY in
aether-ai-formats (the lowest crate every consumer already depends on),
re-export from the crate root, and route producer + all map-style
consumers through it. The change is purely a string-literal → constant
swap; behaviour is identical.
Sites left as literals (intentional):
- `json!({"upstream_is_stream": ...})` macro keys, which must be string
literals at the macro layer; these are also API-response payload
field names (an external contract that should not silently track
internal report-context renames).
- SQL column accessors (`try_get::<...>("upstream_is_stream")`), which
refer to the database schema column, not the JSON key.
- Test fixtures and assertions, which validate the on-the-wire contract
and should keep verifying the actual string.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AAEE86