@gtrabanco/pi-nan-provider 0.8.0 → 0.10.0

package/AGENTS.md

@@ -51,7 +51,7 @@ maintainer's quota, so they are **permission-gated**:
   gate covers ad-hoc diagnosis only, never `bun test`.
 - **Default to `qwen3.6` — it is unlimited.**
 - **For massive/bulk probes prefer a model the maintainer uses less with a large
-  token budget, e.g. `mimo-v2.5`** (1M context).
+  token budget, e.g. `mimo-v2.6-flash`** (1M context, 1.0B monthly quota).
 - **When the model under investigation is the point** (e.g. reproducing a
   model-specific 400), use it, but minimize tokens: smallest viable prompt,
   lowest `max_tokens`, stop at the first decisive response.
@@ -77,7 +77,7 @@ Every PR that changes code MUST bump `package.json` version in the same PR; CI p
 
 ## Verified API facts (do not re-derive from stale docs)
 
-- **Extension-side pi-ai imports + streaming-API instance binding (v0.6.10; verified on pi-ai 0.83.0–0.84.4 and pi 0.87.0):**
+- **Extension-side pi-ai imports + streaming-API instance binding (v0.6.10; verified on pi-ai 0.83.0–0.87.1 and pi 0.87.1):**
   statically import ONLY the bare `@earendil-works/pi-ai` root from `src/`. pi's
   extension loader maps that specifier to the compat entrypoint on the bundled
   CLI, Node-mode jiti aliases and compiled-binary virtualModules, and compat
@@ -107,7 +107,7 @@ Every PR that changes code MUST bump `package.json` version in the same PR; CI p
   `openAICompletionsApi`; `createProvider` and `envApiKeyAuth(name, envVars)` are
   on the root. `envApiKeyAuth` implements exactly: stored credential key wins →
   first set env var → unconfigured; `login()` prompts with `{ type: "secret" }`.
-- pi awaits extension factories (`await factory(api)`) on 0.83.0 and 0.84.4
+- pi awaits extension factories (`await factory(api)`) on 0.83.0 through 0.87.1
   alike, so the extension entrypoint may be async (v0.5.0: streaming-API
   resolution needs it).
 - pi-ai 0.83.0 runtime surface verified identical for this package's needs:
@@ -116,6 +116,26 @@ Every PR that changes code MUST bump `package.json` version in the same PR; CI p
   `fetchModels(context)`, `filterModels(models, credential)`, `api`) and
   `RefreshModelsContext.credential` match 0.84.4; `registerProvider` has both
   the full-`Provider` and `(name, config)` overloads in 0.83's ExtensionAPI.
+  (pi-ai 0.86 changed provider stream entry points to a branded `TranscriptContext`
+  — see next bullet — but this package's runtime is untouched.)
+- **pi-ai 0.86.0 `TranscriptContext` migration (verified 2026-09-29):** provider
+  stream entry points (`Provider.stream`, `ProviderStreams.stream/streamSimple`,
+  `StreamFunction`) now take a branded `TranscriptContext = { messages: Message[] }`
+  instead of the public `Context = { systemPrompt?: string; messages; tools? }`.
+  `normalizeContext(context: Context): TranscriptContext` (exported from the pi-ai
+  root) folds prompt + tools into a leading system message
+  `{ role: "system", content: <prompt>, toolsAdded: <tools>, timestamp: 0 }`.
+  `Context` itself still exists and is what the public entry points accept, so raw
+  `Context` literals only fail where a *provider-level* stream is called directly
+  (the 6 test call sites). Tests now build contexts with `normalizeContext(...)`.
+  This package's `src/` files never hand-build a provider context, so no `src/`
+  code changed: `wrapApiForStrictSanitization` forwards `context` untouched, and
+  `withContextOverflowClassification` only *reads* it for the estimate, which still
+  counts prompt + tools because they ride inside `messages[0]`.
+- pi 0.87 rejects extension tools that declare no parameter schema at registration;
+  all this package's MCP tools declare TypeBox `parameters`, so they register fine.
+  pi 0.87 also changed `pi.on()` to return an unsubscribe function (unused by
+  this package).
 - `pi.registerProvider(provider)` accepts a complete pi-ai `Provider`; pi's Models
   runtime then drives `fetchModels` refreshes (network refresh at interactive
   startup and periodically, cache-only at registration) and persists the overlay.
@@ -132,20 +152,37 @@ Every PR that changes code MUST bump `package.json` version in the same PR; CI p
   override (maintainer-confirmed 2026-09-05) was withdrawn 2026-09-07 — the
   updated NaN docs still say 262K "the model's native window" and models.dev
   agrees at 262,144.
-- NaN's official chat model list (https://nan.builders/openapi.json `model`
-  param description + https://nan.builders/docs/models, checked 2026-09-07):
-  community `deepseek-v4-flash`, `mimo-v2.5`, `qwen3.8-flash`, `glm5.3-flash`,
-  `qwen3.6`, `gemma4` (all text+image vision) + premium-tier `glm5.3`
+- **Which models exist**: https://nan.builders/docs/models is the source of
+  truth (maintainer instruction, reaffirmed 2026-09-29), cross-checked against
+  the `model` param description in https://nan.builders/openapi.json; models.dev
+  (provider `nan`) supplies the numeric limits for the ids it documents, and
+  every divergence or exclusion is recorded with provenance.
+  Official chat models (checked 2026-09-29): community `deepseek-v4-flash`,
+  `mimo-v2.6-flash`, `qwen3.8-flash`, `glm5.3-flash`, `qwen3.6`, `gemma4`
+  (all text+image vision) + premium-tier `glm5.3`
   (~753B MoE, text-only input, 1M context, 400M tokens/rolling 4h window).
   glm5.3 is now documented by models.dev too (1M context / 131,072 max output,
   checked 2026-09-13) but stays out of the static catalog via
   `LIVE_ONLY_MODEL_IDS` (premium tier) so a non-premium key never sees a
   model it cannot call when the live `/models` fetch is unavailable; premium
   keys still receive it live with conservative placeholder limits.
-  `glm5.2` was removed by the provider (2026-09-05); models.dev may still list
-  it — the generator excludes it via `PROVIDER_REMOVED_MODEL_IDS`. Non-chat
-  endpoints: qwen3-embedding, rerank, kokoro (TTS), whisper (STT),
-  flux-2-klein (images) — MCP-bridge territory, not chat catalog models.
+  Removed by the provider: `glm5.2` (2026-09-05) and `mimo-v2.5` (checked
+  2026-09-29 — zero mentions in the docs and in openapi.json, and models.dev
+  dropped it too; superseded by `mimo-v2.6-flash`). models.dev may re-list a
+  removed id, so the generator excludes them via `PROVIDER_REMOVED_MODEL_IDS`,
+  and the four community ids the docs require (`qwen3.6`, `gemma4`,
+  `deepseek-v4-flash`, `mimo-v2.6-flash`) are `REQUIRED_MODEL_IDS` — if one
+  never reaches the catalog (from models.dev or from a manual-only entry),
+  generation exits non-zero instead of inventing data.
+  `mimo-v2.6-flash` entered through `MANUAL_ONLY_MODEL_IDS` while models.dev
+  lacked it; models.dev started listing it on 2026-09-29, and the generator
+  then skips the manual entry (attaching its note to the models.dev-derived
+  entry) so the id is never emitted twice.
+  Non-chat endpoints: qwen3-embedding, rerank, kokoro (TTS), whisper (STT),
+  flux-2-klein and qwen-image-2.1 (images) — MCP-bridge territory, not chat
+  catalog models; `qwen-image-2.1` also sits on models.dev with
+  `limit.output: 0`, so generation excludes it via `NON_CHAT_MODEL_IDS`
+  instead of flagging it "needs manual verification" forever.
 - NaN can close an SSE stream **before** `finish_reason`. The catalog sets
   `supportsFinishReason: true` so pi-ai raises the retryable
   `Stream ended without finish_reason` (pi-ai's `RETRYABLE_PROVIDER_ERROR_PATTERN`
@@ -178,19 +215,29 @@ Every PR that changes code MUST bump `package.json` version in the same PR; CI p
   `test/context-overflow-classifier.test.ts`; issue #3.
 - Relative imports inside this package use `.ts` extensions (pi's official
   extension examples do the same; pi transpiles extension sources).
-- pi intentionally has NO built-in MCP client (docs/usage.md). MCP integration
-  happens by bridging servers into pi custom tools via `pi.registerTool()`:
+- pi 0.87 breaking changes NOT used by this package: `ContextEditEntry` added to
+  the `SessionEntry` union, expanded `TurnEndEvent`, removed `shouldStopAfterTurn`,
+  `SessionManager` canonical for provider context. The package touches none of them.
+- Since 0.10.0, this package uses native MCP via `pi.registerMcpServer()`.
+  Both servers are session-scoped, visible in `/mcp` with source "extension".
+  Server names and tool IDs:
+  - `nan-search` → tools: `mcp__nan-search__web_search`
+    (official remote, HTTP, `Authorization: Bearer <key>` header)
+  - `nan-media` → tools: `mcp__nan-media__generate_image/edit_image/text_to_speech/list_voices/speech_to_text`
+    (community stdio, `npx -y nan-mcp-server@1.1.2`, 120s timeout)
+  - `exposure: "direct"` on both — tools are declared to the model.
+  - User `mcp.json` entries with the same name take precedence.
+  - `/nan-mcp enable/disable` calls `pi.registerMcpServer()` / `pi.unregisterMcpServer()` directly.
+  - Missing `NAN_API_KEY` at load: web-search server NOT registered (console.warn).
+  NaN integration facts remain:
   - NaN's official remote MCP server: `https://api.nan.builders/mcp` (host
     root, NOT /v1; JSON-RPC 2.0 over streamable HTTP, stateless; same `sk-`
     key, shared rate limit/quota). Spec: https://nan.builders/openapi.json
-    (tag "MCP"). Currently exposes `web_search` (same args as POST /v1/search);
-    "growing registry" — use tools/list to discover.
+    (tag "MCP"). Currently exposes `web_search`.
   - Community `nan-mcp-server` (https://github.com/luciferfran/nan-mcp-server):
-    stdio MCP server, spawned per tool call (lazy), opt-in NAN_MEDIA_MCP=1,
-    version-pinned via NAN_MEDIA_MCP_VERSION (default 1.0.8) or a full command
-    override via NAN_MEDIA_MCP_COMMAND. Tools: generate_image, edit_image,
-    text_to_speech, list_voices, speech_to_text, embed, rerank, list_models
-    (we bridge the audio/image/transcription scope). An automated check
-    (scripts/check-nan-mcp-server.ts + .github/workflows/check-nan-mcp-server-update.yml)
-    compares the npm registry against the pin weekly and files a `dependencies` issue
-    with a breaking/safe verdict from the live server tool surface (unpkg).
+    stdio MCP server, version-pinned via NAN_MEDIA_MCP_VERSION (default 1.1.2)
+    or full command override via NAN_MEDIA_MCP_COMMAND. Tools: generate_image,
+    edit_image, text_to_speech, list_voices, speech_to_text.
+  - Automated check (scripts/check-nan-mcp-server.ts) compares the npm registry
+    against the pin weekly and files a `dependencies` issue when a newer release
+    exists, with a breaking/safe verdict from the live server tool surface.

package/README.es.md

@@ -1,11 +1,11 @@
 # @gtrabanco/pi-nan-provider
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.8.0-blue)](https://github.com/gtrabanco/pi-nan-provider/releases)
+[![Version](https://img.shields.io/badge/version-0.10.0-blue)](https://github.com/gtrabanco/pi-nan-provider/releases)
 
-[NaN Builders](https://nan.builders) model provider + MCP bridges para [pi](https://github.com/earendil-works/pi). 
+[NaN Builders](https://nan.builders) model provider + MCP nativo para [pi](https://github.com/earendil-works/pi). 
 
-Registra el proveedor `nan` vía `pi.registerProvider()` usando la API OpenAI-compatible de NaN (`https://api.nan.builders/v1`), y conecta las herramientas MCP de NaN en pi con `pi.registerTool()`.
+Registra el proveedor `nan` vía `pi.registerProvider()` usando la API OpenAI-compatible de NaN (`https://api.nan.builders/v1`), y registra servidores MCP nativos con `pi.registerMcpServer()`.
 
 ---
 
@@ -97,11 +97,11 @@ Puedes sobrescribir el `compat` de cualquier modelo en `~/.pi/agent/models.json`
 
 Consigue una clave en la [plataforma NaN](https://cloud.nan.builders/r/7GK06FX8) (ajustes de usuario → API Keys; enlace de referidos).
 
-## 🔌 Puentes MCP
+## 🔌 MCP nativo
 
-Dado que [pi no incluye un cliente MCP integrado](https://github.com/earendil-works/pi/blob/main/docs/usage.md), este paquete conecta los servidores MCP como **herramientas nativas de pi**.
+Dado que [pi 0.99.0 incluye un cliente MCP integrado](https://github.com/earendil-works/pi/blob/main/docs/usage.md), este paquete migra sus puentes a MCP nativo (requiere `pi >=0.99` — cambio rotundo).
 
-Ambos puentes están **activados y son perezosos (lazy) por defecto**. Usa `/nan-mcp` para gestionarlos.
+Ambos puentes están **activados por defecto** (por sesión, visibles en `/mcp`). Usa `/nan-mcp` para gestionarlos.
 
 ### 🛠️ Comando de Gestión: `/nan-mcp`
 
@@ -116,21 +116,21 @@ Ambos puentes están **activados y son perezosos (lazy) por defecto**. Usa `/nan
 ### 1. Servidor MCP oficial de NaN
 *Puente oficial para herramientas remotas vía [https://api.nan.builders/mcp](https://nan.builders/docs/api).*
 
-- **`nan_web_search(query, ...)`**: Realiza búsquedas web a través del gateway de NaN.
+- **`mcp__nan-search__web_search(query, ...)`**: Realiza búsquedas web a través del gateway de NaN.
 
 ### 2. Servidor MCP de Media (Comunidad)
 *Conecta [`nan-mcp-server`](https://github.com/luciferfran/nan-mcp-server) mediante un cliente stdio local mínimo.*
 
-- **Carga Perezosa (Lazy)**: El proceso del servidor se lanza **solo** cuando se invoca una herramienta y se cierra inmediatamente después.
+- **Por sesión**: El servidor se conecta al registrarse (eager). Aparece en `/mcp` con fuente "extension".
 - **Configuración**: Los archivos se guardan en `~/nan-mcp-output/`.
 
 | Herramienta | Propósito |
 | :--- | :--- |
-| `nan_generate_image` | Generación de imágenes (flux-2-klein) |
-| `nan_edit_image` | Edición imagen→imagen (flux-2-klein) |
-| `nan_text_to_speech` | Síntesis de audio (kokoro) |
-| `nan_list_voices` | Listar voces disponibles |
-| `nan_speech_to_text` | Transcripción de audio (whisper) |
+| `mcp__nan-media__generate_image` | Generación de imágenes (flux-2-klein) |
+| `mcp__nan-media__edit_image` | Edición imagen→imagen (flux-2-klein) |
+| `mcp__nan-media__text_to_speech` | Síntesis de audio (kokoro) |
+| `mcp__nan-media__list_voices` | Listar voces disponibles |
+| `mcp__nan-media__speech_to_text` | Transcripción de audio (whisper) |
 
 #### 🔧 Configuración del Puente de Media
 
@@ -260,10 +260,15 @@ Catálogo base (verificado contra [docs de NaN](https://nan.builders/docs/models
 | `qwen3.6` | 262,144 | 65,536 | texto, imagen | ✅ |
 | `gemma4` | 262,144 | 32,768 | texto, imagen | ✅ |
 | `deepseek-v4-flash` | 1,000,000 | 384,000 | texto, imagen | ✅ |
-| `mimo-v2.5` | 1,048,576 | 131,072 | texto, imagen | ✅ |
+| `mimo-v2.6-flash` | 1,048,576 | 131,072 | texto, imagen | ✅ |
 | `glm5.3-flash` | 1,000,000 | 131,072 | texto, imagen | ✅ |
 | `qwen3.8-flash` | 262,144 | 131,072 | texto, imagen | ✅ |
 
+> [!NOTE]  
+> `mimo-v2.6-flash` está servido por NaN y desde el 2026-09-29 aparece también en models.dev (proveedor `nan`); la entrada manual que lo sostenía se conserva como fallback y su nota de procedencia sigue unida a la entrada generada.
+>
+> `mimo-v2.5` fue eliminado por NaN: ya no aparece ni en [los docs de NaN](https://nan.builders/docs/models) ni en la [lista de modelos del OpenAPI](https://nan.builders/openapi.json) (comprobado 2026-09-29), así que sale del catálogo — lo sustituye `mimo-v2.6-flash` (mismos límites 1,048,576 / 131,072 y cuota mensual de 1.0B). El consumo histórico de `mimo-v2.5` en `/nan-usage` sigue apareciendo en la sección de modelos no documentados.
+
 ---
 
 ## 🚀 Desarrollo

package/README.md

@@ -1,11 +1,11 @@
 # @gtrabanco/pi-nan-provider
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.8.0-blue)](https://github.com/gtrabanco/pi-nan-provider/releases)
+[![Version](https://img.shields.io/badge/version-0.10.0-blue)](https://github.com/gtrabanco/pi-nan-provider/releases)
 
-[NaN Builders](https://nan.builders) model provider + MCP bridges for [pi](https://github.com/earendil-works/pi). 
+[NaN Builders](https://nan.builders) model provider + native MCP servers for [pi](https://github.com/earendil-works/pi). 
 
-Registers the `nan` provider via `pi.registerProvider()` using NaN's OpenAI-compatible API (`https://api.nan.builders/v1`), and bridges NaN's MCP tools into pi with `pi.registerTool()`.
+Registers the `nan` provider via `pi.registerProvider()` using NaN's OpenAI-compatible API (`https://api.nan.builders/v1`), and registers MCP servers via pi's native `pi.registerMcpServer()`.
 
 ---
 
@@ -97,11 +97,11 @@ You can override any model's `compat` per-model in `~/.pi/agent/models.json` (pi
 
 Get a key from the [NaN platform](https://cloud.nan.builders/r/7GK06FX8) (user settings → API Keys; referral link).
 
-## 🔌 MCP Bridges
+## 🔌 Native MCP Servers
 
-Since [pi does not include a built-in MCP client](https://github.com/earendil-works/pi/blob/main/docs/usage.md), this package bridges MCP servers as **native pi tools**.
+Since [pi 0.99.0 ships a built-in MCP client](https://github.com/earendil-works/pi/blob/main/docs/usage.md), this package migrates its bridges to native MCP (requires `pi >=0.99` — breaking).
 
-Both bridges are **enabled and lazy by default**. Use `/nan-mcp` to manage them.
+Both bridges are **enabled by default** (session-scoped, visible in `/mcp`). Use `/nan-mcp` to manage them.
 
 ### 🛠️ Management Command: `/nan-mcp`
 
@@ -114,23 +114,23 @@ Both bridges are **enabled and lazy by default**. Use `/nan-mcp` to manage them.
 ---
 
 ### 1. Official NaN MCP Server
-*Official bridge for remote tools via [https://api.nan.builders/mcp](https://nan.builders/docs/api).*
+*Official remote MCP server registered natively via `pi.registerMcpServer()`.*
 
-- **`nan_web_search(query, ...)`**: Performs web searches through NaN's gateway.
+- **`mcp__nan-search__web_search(query, ...)`**: Performs web searches through NaN's gateway.
 
 ### 2. Community Media MCP Server
 *Bridges [`nan-mcp-server`](https://github.com/luciferfran/nan-mcp-server) via a minimal local stdio client.*
 
-- **Lazy Loading**: The server process is spawned **only** when a tool is invoked and terminated immediately after.
+- **Session-scoped**: The server connects at registration time (eager). Appears in `/mcp` with source "extension".
 - **Config**: Files land in `~/nan-mcp-output/`.
 
 | Tool | Purpose |
 | :--- | :--- |
-| `nan_generate_image` | Image generation (flux-2-klein) |
-| `nan_edit_image` | Image-to-image editing (flux-2-klein) |
-| `nan_text_to_speech` | Audio synthesis (kokoro) |
-| `nan_list_voices` | List available voices |
-| `nan_speech_to_text` | Audio transcription (whisper) |
+| `mcp__nan-media__generate_image` | Image generation (flux-2-klein) |
+| `mcp__nan-media__edit_image` | Image-to-image editing (flux-2-klein) |
+| `mcp__nan-media__text_to_speech` | Audio synthesis (kokoro) |
+| `mcp__nan-media__list_voices` | List available voices |
+| `mcp__nan-media__speech_to_text` | Audio transcription (whisper) |
 
 #### 🔧 Media Bridge Configuration
 
@@ -260,13 +260,14 @@ Baseline catalog (verified against [NaN docs](https://nan.builders/docs/models)
 | `qwen3.6` | 262,144 | 65,536 | text, image | ✅ |
 | `gemma4` | 262,144 | 32,768 | text, image | ✅ |
 | `deepseek-v4-flash` | 1,000,000 | 384,000 | text, image | ✅ |
-| `mimo-v2.5` | 1,048,576 | 131,072 | text, image | ✅ |
 | `mimo-v2.6-flash` | 1,048,576 | 131,072 | text, image | ✅ |
 | `glm5.3-flash` | 1,000,000 | 131,072 | text, image | ✅ |
 | `qwen3.8-flash` | 262,144 | 131,072 | text, image | ✅ |
 
 > [!NOTE]  
-> `mimo-v2.6-flash` is served by NaN but not yet listed on models.dev provider `nan`; it enters the catalog through a manual-only entry with the same limits as `mimo-v2.5`. The model will be auto-detected from models.dev once added there.
+> `mimo-v2.6-flash` is served by NaN and has been listed by models.dev provider `nan` since 2026-09-29. Before that it entered the catalog through a manual-only entry; that entry is kept as a fallback (re-emitted automatically if models.dev drops the model again) and its provenance note stays attached to the generated entry.
+>
+> `mimo-v2.5` was removed by NaN: it no longer appears in the [NaN docs](https://nan.builders/docs/models) nor in the [OpenAPI model list](https://nan.builders/openapi.json) (checked 2026-09-29), so it is out of the catalog — `mimo-v2.6-flash` replaces it (same 1,048,576 / 131,072 limits, 1.0B monthly quota). Historical `/nan-usage` consumption for `mimo-v2.5` still shows under the undocumented-models section.
 
 ---
 
@@ -278,7 +279,7 @@ NaN's `reasoning_effort` parameter controls how much the model thinks before ans
 | :--- | :--- | :--- |
 | `glm5.3`, `glm5.3-flash` | `low` · `medium` · `high` · `max` | Fully controllable — higher values let the model reason longer |
 | `qwen3.6`, `gemma4` | `none` · `minimal` · `low` · `medium` · `high` · `max` | `none`/`minimal` skip reasoning entirely; others cap at 2K / 8K / 16K / 32K tokens |
-| `deepseek-v4-flash`, `qwen3.8-flash`, `mimo-v2.5`, `mimo-v2.6-flash` | *(accepted but not adjustable)* | The parameter is accepted and never rejected, but the model manages its own reasoning depth — it is never an error to send a value these models don't adjust |
+| `deepseek-v4-flash`, `qwen3.8-flash`, `mimo-v2.6-flash` | *(accepted but not adjustable)* | The parameter is accepted and never rejected, but the model manages its own reasoning depth — it is never an error to send a value these models don't adjust |
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@gtrabanco/pi-nan-provider",
-	"version": "0.8.0",
+	"version": "0.10.0",
 	"description": "NaN Builders (api.nan.builders) model provider for pi - OpenAI-compatible registration with a models.dev-generated fallback, tier-aware live catalog, and MCP bridges (official web search + optional community media server)",
 	"keywords": [
 		"pi",
@@ -42,12 +42,12 @@
 		"check-pi-sdk-versions": "node scripts/check-pi-sdk-versions.mjs --report"
 	},
 	"peerDependencies": {
-		"@earendil-works/pi-ai": ">=0.83.0 <1",
-		"@earendil-works/pi-coding-agent": ">=0.83.0 <1"
+		"@earendil-works/pi-ai": ">=0.99.0 <1",
+		"@earendil-works/pi-coding-agent": ">=0.99.0 <1"
 	},
 	"devDependencies": {
-		"@earendil-works/pi-ai": "0.84.4",
-		"@earendil-works/pi-coding-agent": "0.84.4",
+		"@earendil-works/pi-ai": "0.99.1",
+		"@earendil-works/pi-coding-agent": "0.99.1",
 		"@types/bun": "1.4",
 		"typescript": "7"
 	},

package/scripts/check-nan-mcp-server.ts

@@ -42,8 +42,16 @@
 
 import {
 	DEFAULT_NAN_MEDIA_MCP_VERSION,
-	NAN_MEDIA_MCP_SERVER_TOOLS,
-} from "../src/mcp/nan-media.ts";
+} from "../src/mcp/media-server.ts";
+
+/** The audio/image/transcription scope we bridge from the community server. */
+const bridgedtools = [
+	"generate_image",
+	"edit_image",
+	"text_to_speech",
+	"list_voices",
+	"speech_to_text",
+] as const;
 
 /** npm package name of the community stdio MCP server we bridge. */
 export const NAN_MCP_SERVER_PACKAGE = "nan-mcp-server";
@@ -143,7 +151,7 @@ export function assessUpdate(latestTools: string[]): {
 	removedTools: string[];
 	reason: string;
 } {
-	const bridged: readonly string[] = [...NAN_MEDIA_MCP_SERVER_TOOLS];
+	const bridged: readonly string[] = [...bridgedtools];
 	const latest = new Set(latestTools.map((t) => t.trim()));
 
 	const removedTools = bridged.filter((tool) => !latest.has(tool));

package/scripts/generate-models.ts

@@ -8,16 +8,28 @@
  * package. Run before publishing (`bun run generate-models`, wired into
  * `prepublishOnly`).
  *
+ * Sources of truth (maintainer instruction, reaffirmed 2026-09-29):
+ * - https://nan.builders/docs/models decides WHICH models exist — which ids
+ *   belong in the chat catalog, which are premium/live-only, which were
+ *   removed by the provider, which are not chat models at all. Every
+ *   exclusion cites it.
+ * - models.dev (provider "nan") supplies the numeric limits for the ids it
+ *   documents; a divergence from the docs is recorded in MANUAL_OVERRIDES
+ *   with a source note.
+ *
  * Provenance rules (enforced, not decorative):
  * - Every emitted number must come from models.dev or an explicit
  *   MANUAL_OVERRIDES note recording where it was confirmed. Nothing invented.
- * - The founding models (qwen3.6, gemma4, deepseek-v4-flash, mimo-v2.5) MUST
- *   exist on models.dev with complete limits, or this script exits non-zero.
+ * - The official community chat models (qwen3.6, gemma4, deepseek-v4-flash,
+ *   mimo-v2.6-flash) MUST reach the catalog — from models.dev or from a
+ *   MANUAL_ONLY entry — or this script exits non-zero.
  * - Any other models.dev entry missing `limit.context`/`limit.output` is
- *   skipped and flagged "needs manual verification" — never guessed.
+ *   skipped and flagged "needs manual verification" — never guessed. Entries
+ *   that are not chat models are excluded via NON_CHAT_MODEL_IDS instead.
  * - models.dev modalities are intersected with pi's supported input set
- *   ("text" | "image"); e.g. mimo-v2.5's audio input is not representable in
- *   pi's Model type and is dropped from `input` (noted on the entry).
+ *   ("text" | "image"); e.g. mimo-v2.6-flash's audio input is not
+ *   representable in pi's Model type and is dropped from `input` (noted on
+ *   the entry).
  */
 
 import type { GeneratedModelEntry } from "../src/fetch-models.ts";
@@ -39,17 +51,23 @@ const REASONING_EFFORT_VALUES_FROM_DOCS: Record<string, string[]> = {
 	...REASONING_EFFORT_VALUES,
 	// deepseek-v4-flash: any value (no effect) — model decides per request
 	"deepseek-v4-flash": [],
-	// qwen3.8-flash, mimo-v2.5: accepted, depth not adjustable
+	// qwen3.8-flash, mimo-v2.6-flash: accepted, depth not adjustable
 	"qwen3.8-flash": [],
-	"mimo-v2.5": [],
+	"mimo-v2.6-flash": [],
 };
 
 const MODELS_DEV_API_URL = "https://models.dev/api.json";
 const SOURCE_PROVIDER_ID = "nan";
 const FETCH_TIMEOUT_MS = 15_000;
 
-/** Models the founding prompt requires in the catalog; absence is fatal. */
-const REQUIRED_MODEL_IDS = ["qwen3.6", "gemma4", "deepseek-v4-flash", "mimo-v2.5"] as const;
+/**
+ * Official community chat models per https://nan.builders/docs/models
+ * (checked 2026-09-29; glm5.3 is premium-tier and deliberately live-only).
+ * Each MUST reach the catalog — from models.dev or from a MANUAL_ONLY entry —
+ * or generation fails. The docs decide this set, not models.dev: models.dev
+ * dropped mimo-v2.5 together with the docs in 2026-09.
+ */
+const REQUIRED_MODEL_IDS = ["qwen3.6", "gemma4", "deepseek-v4-flash", "mimo-v2.6-flash"] as const;
 
 /** pi's Model.input only supports these values. */
 const PI_SUPPORTED_INPUT = new Set(["text", "image"]);
@@ -75,6 +93,20 @@ const MANUAL_NOTES: Record<string, string> = {
 const PROVIDER_REMOVED_MODEL_IDS: Record<string, string> = {
 	"glm5.2":
 		"removed by NaN (2026-09-05); absent from the official chat model list in https://nan.builders/openapi.json and https://nan.builders/docs/models (checked 2026-09-07) while models.dev provider nan still listed it — excluded so regeneration does not resurrect it",
+	"mimo-v2.5":
+		"removed by NaN (checked 2026-09-29): zero mentions in https://nan.builders/docs/models and in the model param description of https://nan.builders/openapi.json, and models.dev provider nan dropped it as well — superseded by mimo-v2.6-flash; excluded so regeneration does not resurrect it",
+};
+
+/**
+ * models.dev entries that are not chat models. They can never join a chat
+ * catalog (their output is an image, and models.dev reports limit.output 0),
+ * so they are excluded with the docs as the reason instead of being flagged
+ * "needs manual verification" forever — that flag would suggest limits worth
+ * confirming for a model this package must not serve as chat.
+ */
+const NON_CHAT_MODEL_IDS: Record<string, string> = {
+	"qwen-image-2.1":
+		"image-generation model (text→image; output modality image) documented in https://nan.builders/docs/models and https://nan.builders/openapi.json (checked 2026-09-29) — not a chat model, out of the static chat catalog (models.dev reports limit.output 0)",
 };
 
 /**
@@ -221,6 +253,10 @@ function convertModel(modelId: string, m: ModelsDevModel): GeneratedModel | { sk
 	if (removedReason) {
 		return { skip: `provider-removed: "${modelId}" excluded from the catalog (${removedReason})` };
 	}
+	const nonChatReason = NON_CHAT_MODEL_IDS[modelId];
+	if (nonChatReason) {
+		return { skip: `non-chat: "${modelId}" excluded from the chat catalog (${nonChatReason})` };
+	}
 	const liveOnlyReason = LIVE_ONLY_MODEL_IDS[modelId];
 	if (liveOnlyReason) {
 		return { skip: `live-only: "${modelId}" kept out of the static catalog (${liveOnlyReason})` };
@@ -301,8 +337,20 @@ async function main(): Promise<void> {
 		}
 	}
 
-	// Add manual-only models (not yet on models.dev).
+	// Add manual-only models (models.dev provider "nan" does not list them).
+	// When models.dev starts listing one, the manual entry is NOT emitted —
+	// otherwise the id would reach the catalog twice — and the reason plus the
+	// original manual provenance are attached to the models.dev-derived entry,
+	// so the manual data never disappears silently.
+	const entryById = new Map(entries.map((entry) => [entry.id, entry]));
 	for (const [modelId, detail] of Object.entries(MANUAL_ONLY_MODEL_IDS)) {
+		const existing = entryById.get(modelId);
+		if (existing) {
+			const note = `manual-only: "${modelId}" skipped: models.dev provider "${SOURCE_PROVIDER_ID}" now lists it, so the manual-only entry is not emitted and the models.dev values are used (${detail})`;
+			existing.notes = [...(existing.notes ?? []), note];
+			console.warn(`generate-models: skipped ${note}`);
+			continue;
+		}
 		const override = MANUAL_OVERRIDES[modelId];
 		if (override) {
 			console.log(`generate-models: manual override for "${modelId}" (${Object.keys(override).filter((k) => k !== "note").join(", ")})`);
@@ -318,8 +366,9 @@ async function main(): Promise<void> {
 	const missingRequired = REQUIRED_MODEL_IDS.filter((id) => !entryIds.has(id));
 	if (missingRequired.length > 0) {
 		fail(
-			`required models missing from models.dev provider "${SOURCE_PROVIDER_ID}": ${missingRequired.join(", ")} — ` +
-				"do NOT invent their data; confirm and add them via MANUAL_OVERRIDES with a source note.",
+			`required models missing from the catalog: ${missingRequired.join(", ")} (official community chat models per ` +
+				"https://nan.builders/docs/models) — do NOT invent their data; confirm them in the docs and add them " +
+				"via MANUAL_OVERRIDES (models.dev lists them) or MANUAL_ONLY_MODEL_IDS (models.dev does not), with a source note.",
 		);
 	}
 
@@ -333,6 +382,9 @@ async function main(): Promise<void> {
 			...Object.entries(PROVIDER_REMOVED_MODEL_IDS).map(
 				([id, reason]) => `provider-removed: "${id}" excluded from the catalog (${reason})`,
 			),
+			...Object.entries(NON_CHAT_MODEL_IDS).map(
+				([id, reason]) => `non-chat: "${id}" excluded from the chat catalog (${reason})`,
+			),
 			...Object.entries(LIVE_ONLY_MODEL_IDS).map(
 				([id, reason]) => `live-only: "${id}" kept out of the static catalog (${reason})`,
 			),

package/scripts/manual-overrides.ts

@@ -43,7 +43,7 @@ export interface ManualModelOverride {
 
 /**
  * Reasoning effort values sourced from the NaN docs (https://nan.builders/docs/models
- * #controlling-reasoning, checked 2026-09-25).
+ * #controlling-reasoning, checked 2026-09-29).
  *
  * models.dev has NO `reasoning_effort_values` field — only `reasoning_options`
  * (which is [{type:"toggle"}] or []), so this mapping must be hand-maintained
@@ -55,7 +55,10 @@ export interface ManualModelOverride {
  * - glm5.3, glm5.3-flash: fully controllable (low/medium/high/max)
  * - qwen3.6, gemma4: none/minimal skip reasoning, others cap depth
  * - deepseek-v4-flash: any value accepted but model decides per-request
- * - qwen3.8-flash, mimo-v2.5, mimo-v2.6-flash: accepted, depth not adjustable
+ * - qwen3.8-flash, mimo-v2.6-flash: accepted, depth not adjustable
+ *
+ * (mimo-v2.5, which used to share that last row, was removed by NaN — absent
+ * from the docs and from openapi.json, checked 2026-09-29.)
  *
  * A model with reasoning_effort_values=[] means the parameter is accepted but
  * the model manages its own reasoning depth — it is never an error.
@@ -68,13 +71,22 @@ export const REASONING_EFFORT_VALUES: Record<string, string[]> = {
 };
 
 /**
- * Models that NaN serves but models.dev provider nan hasn't listed yet.
- * Mirrors the generator's MANUAL_ONLY_MODEL_IDS — kept in sync so the
- * generator and the tests share the same source.
+ * Provenance for the manual-only mimo-v2.6-flash entry, shared by
+ * MANUAL_ONLY_MODEL_IDS (generator) and MANUAL_ONLY_MODELS (tests) so both
+ * sides assert the exact same string.
+ */
+const MANUAL_ONLY_NOTE =
+	"omnimodal model (text, image, audio input) served by NaN; limits and modalities from https://nan.builders/docs/models#mimo-v2-6-flash (checked 2026-09-25, quotas re-checked 2026-09-29): 1,048,576 context / 131,072 max output / 1.0B monthly quota per member. Reasoning: accepted, depth not adjustable (docs table, checked 2026-09-29). Tool calling: yes. Streaming: yes. Input modalities (pi-representable): text, image (audio not representable in pi's Model type). Fallback entry: emitted only while models.dev provider nan does not list the model — models.dev started listing it on 2026-09-29, so the generator then keeps the models.dev values and attaches this note to that entry instead of emitting a second one.";
+
+/**
+ * Models NaN serves that models.dev provider nan may not list. Mirrors the
+ * generator's MANUAL_ONLY_MODEL_IDS — kept in sync so the generator and the
+ * tests share the same source. An entry stops being emitted as soon as
+ * models.dev lists the model; the note above then rides on the models.dev
+ * entry, so the manual data never vanishes silently.
  */
 export const MANUAL_ONLY_MODEL_IDS: Record<string, string> = {
-	"mimo-v2.6-flash":
-		"omnimodal model (text, image, audio input) served by NaN, not yet listed on models.dev provider nan (checked 2026-09-25); included so the live /models refresh does not hand it UNKNOWN_MODEL_LIMITS. Same limits as mimo-v2.5: 1,048,576 / 131,072 / 1.0B monthly quota per member. Reasoning: accepted, depth not adjustable. Tool calling: yes. Streaming: yes. Input modalities (pi-representable): text, image (audio not representable in pi's Model type).",
+	"mimo-v2.6-flash": MANUAL_ONLY_NOTE,
 };
 
 /**
@@ -89,7 +101,7 @@ export const MANUAL_ONLY_MODELS: Record<string, ManualModelOverride> = {
 		reasoningEffortValues: [],
 		contextWindow: 1_048_576,
 		maxTokens: 131_072,
-		note: "omnimodal model (text, image, audio input) served by NaN, not yet listed on models.dev provider nan (checked 2026-09-25); included so the live /models refresh does not hand it UNKNOWN_MODEL_LIMITS. Same limits as mimo-v2.5: 1,048,576 / 131,072 / 1.0B monthly quota per member. Reasoning: accepted, depth not adjustable. Tool calling: yes. Streaming: yes. Input modalities (pi-representable): text, image (audio not representable in pi's Model type).",
+		note: MANUAL_ONLY_NOTE,
 	},
 };