Skip to main content
Use this page to decide which capabilities are safe for production defaults and which should stay behind tighter rollout controls.

Feature maturity

AreaScopeStatusNotes
LLM provider layerOpenAI, Azure OpenAI, Gemini, Anthropic, AWS Bedrock, LM Studio, Groq, OllamaStablePrimary generation path for run.
Plan-first + lockfilerun --dry-run, deterministic planning, .hyperlocalise.lock.json checkpointsStableRecommended default for CI and PR review flows.
TMS adaptersCrowdin, LILT AI, Lokalise, Phrase, POEditor, SmartlingExperimentalsync push / sync pull contracts may evolve. Pin CLI versions in CI.
Eval frameworkeval run, eval compare, quality/regression scoringExperimentalReport schema and scoring can change between releases.
CI-ready status labelsready, needs review, missing derived from status CSVExperimentalLabel mapping is stable for current docs, but classification semantics may evolve.
  1. Treat run + lockfile as baseline in default CI checks.
  2. Use sync and eval in controlled pipelines with explicit version pinning.
  3. Gate releases with status-based checks before enabling write-capable sync jobs.

See also