pi-neuralwatt releases

Minor Changes f5a2e13: Remove the built-in sub-bar integration. The subBarIntegration feature (live quota usage in the status bar) is no longer part of the package; it ships as a standalone one-off pi extension distributed as a GitHub gist (https://gist.github.com/aliou/9939544f…

Minor Changes 53c4e26: Add provider.apiBaseUrl config. It sets the base URL for the extension's catalog and quota requests and is the fallback for models that carry no baseUrl of their own — models.json overrides, custom providers, and proxy routing all take precedence. Defaults…

Patch Changes 03eda9d: Sync the offline fallback model table with the live API: add mimo-v2.6-pro, the nw-large/nw-flash/nw-small tracking aliases (with flex variants), and deepseek-v4.1-flash-speed.

Patch Changes 4bcbe4c: Fix reasoning replay on the openai-completions surface: prior-turn chain-of-thought is replayed in the reasoning field (the field K3 streams), but the served chat templates only render reasoning_content, so the model never saw its earlier thinking on any t…

Patch Changes 2dcc7ce: Model sync: add DeepSeek V4.1 Flash (+ flex) with its full reasoning ladder, raise DeepSeek V4 Flash's max output tokens to 393216, and snapshot effort_aliases for every reasoning family so the anthropic-messages thinking map resolves unsupported levels of…

Minor Changes e7b6b5d: Add a provider.api setting (/neuralwatt:settings → API, default openai-completions) that serves the catalog on Neuralwatt's Anthropic-compatible POST /v1/messages endpoint (vLLM-backed) — native tool use and thinking streams with the same model ids. Applie…

Patch Changes 45373d6: Take flex model pricing from the API's already-discounted values instead of applying a local 0.65 multiplier at catalog build time. 48b331e: Sync the offline fallback model table with the live Neuralwatt API: remove GLM-5.2 and its variants (gone upstream)…

Patch Changes 51f9dbf: fix: exclude embeddings model from catalog and harden resolveMaxTokens d15f9c8: Make the model-store cache scaffold-aware. A fresh entry persisted without a key only carries the public scope, so logged-in users never saw preview, grant-gated, or private mo…

Minor Changes b3caf85: Build the model catalog from the live /v1/models response instead of local visibility buckets. Model refresh now fetches anonymously when no API key is configured, builds the catalog with overrides for Flex pricing, Kimi K3 context, Qwen chat-template comp…

Minor Changes 36ece2d: Register the Neuralwatt provider as a complete pi-ai Provider via pi.registerProvider(provider) instead of the name-plus-config form, with auth resolution that falls back to an anonymous credential so the model catalog refreshes without an API key.

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…