mirror of
https://github.com/Haidra-Org/AI-Horde.git
synced 2026-11-06 05:17:31 +00:00
tazlin
7c0c1868fd
- The quorum publisher job now polls every 60 s and publishes only when the served snapshot is degraded or older than FLEET_PUBLISH_INTERVAL_SECONDS (publish_fleet_snapshot_if_due), so a newly elected owner or a fleet on a degraded document refreshes within a minute instead of after a full hourly interval - refresh_text_reference drops individual entries without a numeric parameter count with a warning instead of rejecting the whole payload; only an unusable or empty payload retains the previous text reference - Document both behaviors in docs/reference/model_reference.md
Reference
How the running service behaves, down to the classes, caches, and gate orderings involved. These pages are for reading alongside the code.
The concepts they assume (what a worker is, what a job's lifecycle means) are in
haidra-assets/docs.
Documents
| Document | Summary |
|---|---|
| Kudos accounting reference | The mutation and consumption contract: accounting events, projection targets, reservations, the lock order, and the read models. |
| Samplers and schedulers reference | What sampler_name and scheduler select, why deterministic samplers agree once converged, measured steps-to-converge and cost, and the combinations known to fail. |
| Image baseline policy reference | The two authorities a baseline-dependent request is checked against, what each one decides, and what applies to a baseline with no record. |
| Image model reference loader reference | Where the image model reference comes from, how beta (pending) models are merged over it, the environment that configures both, and what the loader exposes. |