pi-neuralwatt releases

Minor Changes d58a55f: Derive reasoning levels from the endpoint's supported_efforts. thinkingLevelMap is now built by identity from each model's metadata.reasoning.supported_efforts (plus mandatory) via a single buildThinkingLevelMap helper, instead of hand-tuned per-family con…

Minor Changes fbd1b1c: Adopt @aliou/pi-utils-settings 0.19.1 versioned migrations. Bumps the dependency and adds semver version strings to all config migrations, leaving their content-based shouldRun gates intact. Switches schema generation to pi-settings-schema. 32ba87a: Add an…

Minor Changes 4d10d48: Add a separate alias model ID setting for active creator-scoped Neuralwatt model IDs.

Minor Changes ad515e8: Update to Pi 0.80.8 provider authentication and refreshable model catalogs. Cache the complete Neuralwatt catalog through Pi's model store and preserve stale hidden models when refresh fails.

Minor Changes e5e562a: Migrate Neuralwatt settings to nested per-feature configuration. Old flat config is migrated automatically, and a backup file is written next to the migrated config. Feature behavior is unchanged.

Minor Changes 9384557: Handle Neuralwatt stream rate limits before the OpenAI SDK drops response headers. Show layer-specific 429 messages, keep Pi auto-retry detection working, and parse SSE quota comments for live quota updates. Patch Changes 57e5ac2: Sync model list with live…

Minor Changes 64a0791: Add a setting for showing legacy Neuralwatt model IDs. Legacy IDs now default to disabled, and existing config files are migrated with a notice pointing users to /neuralwatt:settings. Patch Changes 2d60a83: Add Kimi K2.7 Code model

Minor Changes 3c467b3: Remove live model sync from provider endpoint. Models are now purely hardcoded in src/extensions/provider/models.ts and validated against the Neuralwatt /v1/models API at test time. Removed: src/lib/fetch-models.ts (live model fetch + mapApiModel) src/util…

Minor Changes 6f4672e: Fetch live models from Neuralwatt API on session start. The extension registers with a hardcoded model cache immediately on startup, then fetches /v1/models on session start and re-registers the provider with live data (including pricing, capabilities, and…