Advanced routing & execution: 5 opt-in features#1
Merged
Conversation
- Predictive SLA routing: rolling p95 latency window per backend (sla.go), rule max_ttft_ms drops over-budget backends (never empties candidates) - Spot-market arbitrage: cost_aware_routing prefers cheapest eligible backend + optional price_feed_url live-cost updater (pricefeed.go) - Semantic/fuzzy prompt cache: embed prompt, return on cosine >= min_similarity (semcache.go, reuses graphify embedder + pgvector); X-Kronaxis-Cache: SEMANTIC - System-2 reflection: X-Kronaxis-Reflect runs a self-review pass (reflect.go) - Adversarial consensus: X-Kronaxis-Consensus fans out + arbiter (consensus.go) All off by default. Tests for SLA window/filter, price-feed parse, EffectiveCost, header parsing (race-clean). Docs: README, CHANGELOG, config.yaml, api-reference.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements 5 of the roadmap's clean-win features, all off by default:
max_ttft_msdrops over-budget backends (never empties candidates).cost_aware_routingprefers cheapest eligible backend; optionalprice_feed_urlkeeps costs live.min_similarity(0.96); reuses graphify embedder + pgvector;X-Kronaxis-Cache: SEMANTIC.X-Kronaxis-Reflect: 1self-review pass.X-Kronaxis-Consensus: 1fan-out + arbiter.Each is additive and opt-in; reuses existing infra (embedder/pgvector, parallel dispatch, Jaccard, latency tracking, cost routing). 213 tests pass, race + vet clean. Docs updated (README, CHANGELOG, config.yaml, api-reference).