mirror of
https://github.com/Haidra-Org/AI-Horde.git
synced 2026-11-06 05:17:31 +00:00
tazlin
7337c844f1
- select_next_unit catalogues the legacy partition as soon as it is attached and takes a unit when its own upper bound is past the window, so the catch-up of pre-swap history starts when retention is enabled instead of one window after the swap time. The partition drop still waits for every sub-range, so the last one, ending at the swap time, holds the detach for a window. - retention_health computes oldest_eligible_age by sub-range for a legacy partition with catalog rows (_eligible_uppers), and by partition bound otherwise. - Tests: the early catalogue and the per-sub-range selection. - Docs: the how-to, reference, explanation and ADR 42 state the per-unit rule.
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 |
|---|---|
| Prompt provenance reference | What each stored prompt value means, who may read the original submission, and why a missing original is never filled in. |
| Moderation operations reference | Moderation evidence, retention and object storage, with API fields for event review, promotion queues and worker suspicion history. |
| Kudos accounting reference | The mutation and consumption contract: accounting events, projection targets, reservations, the lock order, the read models, and event retention. |
| 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. |
| Style contract reference | What an image or text style may declare about the params a request may set and the placeholders its prompt accepts, and how a text request is sized against the prompt it ends up sending. |
| Chat requests reference | Native chat routes, request fields, worker declarations, job payloads, submissions, pricing and progress streams, with implementation and test references. |
| Chat wire examples | Checked JSON examples for native chat requests, OpenAI-compatible responses and worker pop, progress and submit routes. |
| Chat front reference | OpenAI-compatible request and response formats, stream behavior, availability errors and telemetry for the horde.oai service. |
| Outbound requests reference | Which client-supplied URLs the horde requests, the address check every hop passes, and the timeouts, redirect limits and byte caps of image fetches and webhooks. |