diff --git a/packages/pi-memory/package.json b/packages/pi-memory/package.json
index a9f8af2..47aa6b7 100644
--- a/packages/pi-memory/package.json
+++ b/packages/pi-memory/package.json
@@ -44,8 +44,8 @@
     "pack:check": "pnpm pack --pack-destination ../../.pack"
   },
   "devDependencies": {
-    "@earendil-works/pi-ai": "^0.80.0",
-    "@earendil-works/pi-coding-agent": "^0.80.0",
+    "@earendil-works/pi-ai": "^0.80.9",
+    "@earendil-works/pi-coding-agent": "^0.80.9",
     "@types/node": "^25.5.0",
     "markdownlint-cli2": "^0.18.1",
     "oxfmt": "^0.42.0",
diff --git a/packages/pi-web-search/package.json b/packages/pi-web-search/package.json
index 3ec0fcb..dc849f4 100644
--- a/packages/pi-web-search/package.json
+++ b/packages/pi-web-search/package.json
@@ -48,8 +48,8 @@
     "pack:check": "pnpm pack --pack-destination ../../.pack"
   },
   "devDependencies": {
-    "@earendil-works/pi-ai": "^0.80.0",
-    "@earendil-works/pi-coding-agent": "^0.80.0",
+    "@earendil-works/pi-ai": "^0.80.9",
+    "@earendil-works/pi-coding-agent": "^0.80.9",
     "@types/node": "^25.5.0",
     "oxfmt": "^0.42.0",
     "oxlint": "^1.57.0",
diff --git a/packages/skill-pi/CHANGELOG.md b/packages/skill-pi/CHANGELOG.md
index 20ca783..1865640 100644
--- a/packages/skill-pi/CHANGELOG.md
+++ b/packages/skill-pi/CHANGELOG.md
@@ -1,5 +1,38 @@
 # @counterposition/skill-pi
 
+## 0.80.9
+
+### Minor Changes
+
+- Sync the Pi skill with Pi 0.80.9, covering changes across 0.80.4–0.80.9.
+  - SDK (breaking in Pi 0.80.8): rewrite `references/sdk.md` around `ModelRuntime`, which
+    replaces the removed `AuthStorage`/`ModelRegistry` SDK surface and the
+    `authStorage`/`modelRegistry` options on `createAgentSession()`. Document
+    `ModelRuntime.create()` (custom paths, injected pi-ai `CredentialStore`),
+    auth resolution priority, `getAuth()`, `checkAuth()`, `readStoredCredential()`,
+    the `resolveCliModel`/`resolveModelScopeWithDiagnostics` helpers, named
+    `InlineExtension` factories, and the `agent_settled` session/RPC event with
+    `willRetry` on `agent_end`.
+  - Extensions: document dynamic tool loading (Pi 0.80.7) — additive
+    `pi.setActiveTools()` during execution, native deferred loading on Anthropic
+    and OpenAI Responses models, Kimi `deferredToolsMode` (Pi 0.80.9), compat
+    flags, and cache guidance. Add the `agent_settled` and
+    `before_provider_headers` hooks, `pi.registerEntryRenderer()` for TUI-only
+    custom entries, provider `refreshModels(context)` discovery, the async
+    `ModelRegistry.refresh()`, and `sessionManager.buildContextEntries()`.
+  - Providers: xAI subscription login and Radius gateway (Pi 0.80.8), Bedrock
+    `/login` API key (Pi 0.80.7), `/login <provider>` autocomplete, live model
+    catalog refresh via `/model`, `pi update --models`, and `models-store.json`.
+  - models.json: replace the removed `compat.sendSessionIdHeader` with
+    `compat.sessionAffinityFormat` (breaking in Pi 0.80.7), add request-wide
+    input pricing `cost.tiers` (Pi 0.80.6), `max` in `thinkingLevelMap` with
+    hole semantics, and expanded `modelOverrides` (extension-registered models,
+    `thinkingLevelMap`).
+  - Settings: the `max` thinking level (Pi 0.80.6) across settings and CLI,
+    `showCacheMissNotices` (Pi 0.80.4), and `~` expansion for `shellPath`.
+  - Packages: `pi update --models`, `pi config -l` with Tab scope switching
+    (Pi 0.80.4), and `autoload: false` project-entry delta semantics.
+
 ## 0.80.3
 
 ### Minor Changes
diff --git a/packages/skill-pi/package.json b/packages/skill-pi/package.json
index c3faa4f..17f9382 100644
--- a/packages/skill-pi/package.json
+++ b/packages/skill-pi/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@counterposition/skill-pi",
-  "version": "0.80.3",
+  "version": "0.80.9",
   "description": "Pi coding agent reference skill — extensions, settings, providers, SDK/RPC, packages, and .pi/ config",
   "keywords": [
     "ai-skill",
diff --git a/packages/skill-pi/skills/pi/references/extensions.md b/packages/skill-pi/skills/pi/references/extensions.md
index 43f462c..065dab2 100644
--- a/packages/skill-pi/skills/pi/references/extensions.md
+++ b/packages/skill-pi/skills/pi/references/extensions.md
@@ -90,13 +90,15 @@ Useful agent events:
 - `input` — carries `event.streamingBehavior` (`"steer" | "followUp" | undefined`) so handlers can distinguish idle prompts, mid-stream steers, and queued follow-ups; return `{ action: "transform" | "handled" | "continue" }`
 - `before_agent_start` — receives `event.systemPromptOptions` (a `BuildSystemPromptOptions`) so handlers can inspect the structured inputs feeding the system prompt
 - `agent_start`
-- `agent_end`
+- `agent_end` — one low-level run; Pi may still auto-retry, auto-compact and retry, or continue with queued follow-ups
+- `agent_settled` (Pi 0.80.4) — fired when no retry/compaction/follow-up remains; use for status integrations that need to know Pi will not continue automatically (`ctx.isIdle()` is true here unless another extension started a new run)
 - `turn_start`
 - `turn_end`
 - `message_start`
 - `message_update`
 - `message_end` — return a replacement message to override usage/cost or rewrite the finalized assistant message
 - `context`
+- `before_provider_headers` (Pi 0.80.4) — mutate `event.headers` in place after outgoing HTTP headers are assembled: set a key to a string to add/override, `null` to delete. Runs once per provider request; retries reuse the same headers
 - `before_provider_request`
 - `after_provider_response` — inspect the provider HTTP status and headers before stream consumption
 - `model_select`
@@ -121,8 +123,8 @@ Tool results may include `terminate: true` to end the current tool batch without
 - `ctx.ui` for interactive UI hooks
 - `ctx.mode` — `"tui" | "rpc" | "json" | "print"`; gate terminal-only features on `ctx.mode === "tui"`
 - `ctx.cwd`
-- `ctx.sessionManager` (read-only)
-- `ctx.modelRegistry` / `ctx.model`
+- `ctx.sessionManager` (read-only; `buildContextEntries()` returns active-branch entries with compaction applied, Pi 0.80.4)
+- `ctx.modelRegistry` / `ctx.model` — `ctx.modelRegistry` is the synchronous extension-facing facade; its `refresh()` became `Promise<void>` in Pi 0.80.8 (await it before synchronous registry reads)
 - `ctx.hasUI` — `true` in TUI and RPC modes
 - `ctx.signal` — the active agent abort signal (or `undefined` when idle); pass it to `fetch`/model calls for abort-aware nested work
 - `ctx.isIdle()` / `ctx.hasPendingMessages()`
@@ -171,6 +173,19 @@ Important rules:
 4. Use the file-mutation queue for write/edit style tools.
 5. Put reconstructable state in `details`; it persists in session history.
 
+## Dynamic Tool Loading
+
+Pi 0.80.7 lets an extension register many tools while keeping only a small initial set active, then add more during execution — cache-friendly on models with native deferred loading. Lifecycle:
+
+1. Register every tool with `pi.registerTool()` (all appear in `pi.getAllTools()`).
+2. Keep a loader tool (e.g. `search_tools`) active; leave searchable tools inactive — e.g. on `session_start`, `pi.setActiveTools()` to the filtered set.
+3. During loader execution, call `pi.setActiveTools([...pi.getActiveTools(), ...matches])`. The change must be purely additive; unknown names are ignored.
+4. Pi records the added tools on that tool result and exposes their definitions before the next model response.
+
+Native deferred loading preserves the cached prompt prefix on Anthropic Sonnet/Opus/Fable ≥ 4.5 (not Haiku) and OpenAI `gpt-5.4`+; Kimi K3 works via `compat.deferredToolsMode: "kimi"` (Pi 0.80.9). For verified custom models/proxies, enable `compat.supportsToolReferences: true` (`anthropic-messages`) or `compat.supportsToolSearch: true` (`openai-responses`/`openai-codex-responses`). All other models fall back to sending the full active tool list on the next request — activation still works, but may invalidate the provider's cached prefix. Non-additive changes (removals/replacements) always use the fallback.
+
+Cache tips: keep the loader active for the whole session; add rather than replace. Activating a tool that has `promptSnippet`/`promptGuidelines` rebuilds the system prompt and can invalidate the prefix even with native support — lazily loaded tools should rely on their `description` alone.
+
 ## UI Methods
 
 Check `ctx.hasUI` first. Non-interactive modes may not support UI.
@@ -240,6 +255,15 @@ Store extension state with custom session entries:
 pi.appendEntry("my-extension-state", { key: "value" });
 ```
 
+Custom entries never participate in LLM context. Since Pi 0.80.4 they can also render in the interactive transcript via `pi.registerEntryRenderer(customType, renderer)` — the TUI-only counterpart to `pi.registerMessageRenderer()` (whose custom messages DO enter LLM context via `pi.sendMessage()`):
+
+```typescript
+pi.registerEntryRenderer("status-card", (entry, { expanded }, theme) => {
+  return new Text(theme.fg("accent", JSON.stringify(entry.data)));
+});
+pi.appendEntry("status-card", { title: "Indexed files", count: 17 });
+```
+
 Use lifecycle hooks to restore it:
 
 ```typescript
@@ -280,12 +304,16 @@ pi.registerProvider("anthropic", { baseUrl: "https://proxy.example.com" });
 pi.unregisterProvider("my-provider");
 ```
 
+Dynamic providers can implement `refreshModels(context)` (Pi 0.80.8) for model discovery: Pi calls it during catalog refresh (`/model`, `pi update --models`) and publishes the returned list; its models replace extension-provided `models`. Persist results through the scoped `context.store` only when they should survive restarts — live servers like llama.cpp can ignore it.
+
 If you need auth for a specific model request, use:
 
 ```typescript
 const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
 ```
 
+(Still supported for extensions in Pi 0.80.8+; SDK code should use `ModelRuntime.getAuth()` — see `references/sdk.md`.)
+
 Pass `shouldStopAfterTurn` via the SDK to exit the agent loop gracefully after a completed turn. See `references/sdk.md` and `references/providers.md` for the full provider/model schema.
 
 ## Handy Patterns
diff --git a/packages/skill-pi/skills/pi/references/packages.md b/packages/skill-pi/skills/pi/references/packages.md
index 1c4d640..9e2abbd 100644
--- a/packages/skill-pi/skills/pi/references/packages.md
+++ b/packages/skill-pi/skills/pi/references/packages.md
@@ -19,9 +19,11 @@ pi list
 pi update                 # update pi only (changed in Pi 0.79.7)
 pi update --all           # update pi + packages, reconcile pinned git refs
 pi update --extensions    # update packages only
+pi update --models        # refresh model catalogs only (Pi 0.80.8)
 pi update --self          # update pi only
 pi update <source>        # update one package
-pi config
+pi config                 # starts in global settings; Tab switches scope
+pi config -l              # start in project overrides (.pi/settings.json)
 ```
 
 By default, `install` and `remove` write to user settings (`~/.pi/agent/settings.json`). Use `-l` to write to project settings (`.pi/settings.json`) instead. `pi update` installs the exact version returned by the update check.
@@ -129,6 +131,6 @@ Rules:
 
 ## Scope and Deduplication
 
-- Project settings override global settings for the same package identity
+- Project settings override global settings for the same package identity — unless the project entry has `autoload: false`, in which case it is applied as a delta over the global entry (Pi 0.80.4)
 - Identity is package name for npm, repo URL for git, and resolved absolute path for local sources
-- `pi config` can enable or disable package resources after installation
+- `pi config` can enable or disable package resources after installation; since Pi 0.80.4 it manages global vs project-local scopes (Tab to switch, `pi config -l` to start in project mode with inherited global resources dimmed)
diff --git a/packages/skill-pi/skills/pi/references/providers.md b/packages/skill-pi/skills/pi/references/providers.md
index bb75638..f6f5970 100644
--- a/packages/skill-pi/skills/pi/references/providers.md
+++ b/packages/skill-pi/skills/pi/references/providers.md
@@ -9,8 +9,12 @@ Use `/login` in interactive mode, then select a provider. The `/login` selector
 - Anthropic Claude Pro / Max — third-party usage draws from extra usage and is billed per token (suppress the warning via `warnings.anthropicExtraUsage`)
 - OpenAI ChatGPT Plus / Pro (Codex) — `/login` defaults to browser auth but can use a device-code flow for headless environments
 - GitHub Copilot
+- xAI (Grok/X subscription, Pi 0.80.8) — `/login xai` then **Use a subscription** (device-code OAuth); `XAI_API_KEY` remains available via **Use an API key**
+- Radius (Pi 0.80.8) — a dynamic `pi-messages` gateway; `/login radius` stores OAuth tokens, and custom Radius gateways can be declared in `models.json` with `"oauth": "radius"` plus a gateway `baseUrl`
 
-Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Google Gemini CLI and Google Antigravity providers.
+`/login <provider>` with autocomplete works since Pi 0.80.4, and login methods are provider-owned since 0.80.8 (registered pi-ai providers expose their own auth options and status in `/login`). Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Google Gemini CLI and Google Antigravity providers.
+
+Since Pi 0.80.8, built-in catalogs are complemented by dynamic ones: `/model` refreshes configured providers in the background, `pi update --models` forces an immediate refresh, and refreshed catalogs are cached in `~/.pi/agent/models-store.json` for offline use.
 
 ## API Key Providers
 
@@ -35,6 +39,8 @@ Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Goog
 | ZAI Coding Plan (China) | `ZAI_CODING_CN_API_KEY` | `zai-coding-cn` |
 | OpenCode Zen | `OPENCODE_API_KEY` | `opencode` |
 | OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
+| Amazon Bedrock | `AWS_BEARER_TOKEN_BEDROCK` | `amazon-bedrock` |
+| Radius | `RADIUS_API_KEY` | `radius` |
 | Hugging Face | `HF_TOKEN` | `huggingface` |
 | Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
 | Together AI | `TOGETHER_API_KEY` | `together` |
@@ -99,7 +105,7 @@ export AZURE_OPENAI_DEPLOYMENT_NAME_MAP=gpt-4o=my-gpt4o
 
 ### Amazon Bedrock
 
-Pi supports standard AWS auth flows:
+`/login amazon-bedrock` stores a Bedrock API key (Pi 0.80.7). Ambient AWS credential flows also work — these keep using SigV4 authentication:
 
 - `AWS_PROFILE`
 - `AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY`
@@ -182,10 +188,14 @@ Common `api` values:
 
 ### Model & Compatibility Knobs
 
-- `thinkingLevelMap` (Pi 0.72) replaces `compat.reasoningEffortMap`. Map pi levels (`off`/`minimal`/`low`/`medium`/`high`/`xhigh`) to provider values; use `null` to hide a level.
+- `thinkingLevelMap` (Pi 0.72) replaces `compat.reasoningEffortMap`. Map pi levels (`off`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`) to provider values; use `null` to hide a level. Maps may contain holes (Pi 0.80.6) — e.g. expose `high` and `max` without `xhigh`. When a key is omitted, standard levels through `high` use the provider default mapping, but the extended `xhigh`/`max` levels are unsupported.
+- `cost` supports request-wide input pricing tiers (Pi 0.80.6): a `tiers` array where each tier supplies a complete alternate rate set and applies to the whole request when total input usage (`input + cacheRead + cacheWrite`) exceeds `inputTokensAbove`; the highest matching threshold wins. Also usable in `modelOverrides` and extension-registered providers.
+- `modelOverrides` applies to built-in and (since Pi 0.80.4) extension-registered provider models; per-model fields: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
 - `openRouterRouting` is forwarded as-is in the OpenRouter `provider` field (fallbacks, ZDR, ignore lists, throughput/latency).
 - `compat.thinkingFormat` supports OpenAI-compatible reasoning variants: `openrouter` sends `reasoning: { effort }`, `together` sends `reasoning: { enabled }` plus `reasoning_effort` when supported, `qwen-chat-template` targets local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`, and `chat-template` (Pi 0.79.9) sends configurable `chat_template_kwargs` via `compat.chatTemplateKwargs` — e.g. `{ "thinking": { "$var": "thinking.enabled" } }` for DeepSeek models behind vLLM/Hugging Face chat templates (`"$var"` accepts `"thinking.enabled"` or `"thinking.effort"`).
-- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat`, `supportsReasoningEffort`, `supportsLongCacheRetention`, `supportsEagerToolInputStreaming`, `sendSessionIdHeader`, `sendSessionAffinityHeaders`). See [Pi `docs/models.md`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md) when a proxy rejects pi's defaults.
+- **Breaking (Pi 0.80.7):** `compat.sendSessionIdHeader` was removed. Session affinity is now controlled by `compat.sessionAffinityFormat` (`"openai"` sends `session_id`/`x-client-request-id`, `"openai-nosession"` omits the underscore-containing `session_id` header, `"openrouter"` sends `x-session-id`; default auto-detected). Replace `sendSessionIdHeader: false` with `sessionAffinityFormat: "openai-nosession"`. `sendSessionAffinityHeaders` still gates the behavior for `openai-completions`.
+- `compat.deferredToolsMode: "kimi"` (Pi 0.80.9) enables Kimi's deferred tool serialization; `compat.supportsToolReferences` / `compat.supportsToolSearch` enable native dynamic tool loading on verified custom endpoints (see `references/extensions.md`).
+- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat`, `supportsReasoningEffort`, `supportsLongCacheRetention`, `supportsEagerToolInputStreaming`, `supportsStrictMode`). See [Pi `docs/models.md`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md) when a proxy rejects pi's defaults.
 
 ### Context Overflow Recovery
 
@@ -219,7 +229,7 @@ pi.registerProvider("anthropic", { baseUrl: "https://proxy.example.com" });
 
 ## SDK / Extension Auth Lookup
 
-If extension or SDK code needs auth for a specific model request, use `getApiKeyAndHeaders(model)` rather than the removed `getApiKey(model)`:
+If extension code needs auth for a specific model request, use `getApiKeyAndHeaders(model)` rather than the removed `getApiKey(model)`:
 
 ```typescript
 const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
@@ -228,4 +238,4 @@ if (!auth.ok) throw new Error(auth.error);
 const { apiKey, headers } = auth;
 ```
 
-This matters for providers whose headers or auth values resolve dynamically on every request.
+This matters for providers whose headers or auth values resolve dynamically on every request. In SDK code, use `ModelRuntime.getAuth(providerOrModel)` instead (Pi 0.80.8) — passing a model also resolves built-in, `models.json`, and extension model headers; see `references/sdk.md`.
diff --git a/packages/skill-pi/skills/pi/references/sdk.md b/packages/skill-pi/skills/pi/references/sdk.md
index d8834f2..9479c7c 100644
--- a/packages/skill-pi/skills/pi/references/sdk.md
+++ b/packages/skill-pi/skills/pi/references/sdk.md
@@ -12,19 +12,16 @@ npm install @earendil-works/pi-coding-agent
 
 ```typescript
 import {
-  AuthStorage,
   createAgentSession,
-  ModelRegistry,
+  ModelRuntime,
   SessionManager,
 } from "@earendil-works/pi-coding-agent";
 
-const authStorage = AuthStorage.create();
-const modelRegistry = ModelRegistry.create(authStorage);
+const modelRuntime = await ModelRuntime.create();
 
 const { session } = await createAgentSession({
   sessionManager: SessionManager.inMemory(),
-  authStorage,
-  modelRegistry,
+  modelRuntime,
 });
 
 session.subscribe((event) => {
@@ -38,17 +35,16 @@ await session.prompt("What files are in the current directory?");
 
 Run with `npx tsx my-script.ts`.
 
-**Important:** `ModelRegistry` no longer has a public constructor. Use `ModelRegistry.create(authStorage, modelsJsonPath?)` for file-backed registries or `ModelRegistry.inMemory(authStorage)` for built-in models only.
+**Breaking (Pi 0.80.8):** `ModelRuntime` replaced the old `AuthStorage`/`ModelRegistry` pair as the SDK model/auth facade. `CreateAgentSessionOptions.authStorage` and `modelRegistry` are gone — pass the async `modelRuntime` instead. `AuthStorage` is no longer exported; use `ModelRuntime` (or a custom pi-ai `CredentialStore`), or `readStoredCredential()` for one-off reads of `auth.json`. `ModelRegistry` still exists only as the synchronous extension-facing compatibility facade, and its `refresh()` is now `Promise<void>`.
 
 ## Key Imports
 
 ```typescript
 import {
-  AuthStorage,
   createAgentSession,
   DefaultResourceLoader,
   defineTool,
-  ModelRegistry,
+  ModelRuntime,
   SessionManager,
 } from "@earendil-works/pi-coding-agent";
 import { getBuiltinModel } from "@earendil-works/pi-ai/providers/all";
@@ -60,16 +56,14 @@ import { getBuiltinModel } from "@earendil-works/pi-ai/providers/all";
 
 ```typescript
 const cwd = "/path/to/project";
-const authStorage = AuthStorage.create();
-const modelRegistry = ModelRegistry.create(authStorage);
+const modelRuntime = await ModelRuntime.create();
 
 const { session } = await createAgentSession({
   cwd,
   agentDir: "~/.pi/agent",
-  authStorage,
-  modelRegistry,
+  modelRuntime,
   model: getBuiltinModel("anthropic", "claude-opus-4-8"),
-  thinkingLevel: "medium",
+  thinkingLevel: "medium",  // off | minimal | low | medium | high | xhigh | max
   scopedModels: [
     { model: getBuiltinModel("anthropic", "claude-opus-4-8"), thinkingLevel: "high" },
   ],
@@ -90,6 +84,50 @@ Notes:
 - `DefaultResourceLoader` loads extensions, skills, prompt templates, themes, and context files. Replace it to drive resource discovery from custom sources (and it must implement `loadProjectContextFiles()` if you want `AGENTS.md`/`CLAUDE.md` discovery; that helper is also exported standalone).
 - Pass `shouldStopAfterTurn(state) => boolean` (Pi 0.72.0) to exit the agent loop gracefully after a completed turn.
 
+## Models & Auth (`ModelRuntime`)
+
+`ModelRuntime` (Pi 0.80.8) implements the pi-ai `Models` interface and owns credential storage. Auth resolution priority: runtime overrides (`setRuntimeApiKey`, not persisted) → stored credentials in `auth.json` → environment variables → fallback resolver for `models.json` keys.
+
+```typescript
+import { InMemoryCredentialStore } from "@earendil-works/pi-ai";
+import { ModelRuntime } from "@earendil-works/pi-coding-agent";
+
+// Default: ~/.pi/agent/auth.json and ~/.pi/agent/models.json
+const modelRuntime = await ModelRuntime.create();
+
+// Model lookup (use pi-ai Models methods directly; the old
+// getAll()/find()/getSnapshot() projections were removed)
+const model = modelRuntime.getModel("my-provider", "my-model");
+const available = await modelRuntime.getAvailable();  // only models with valid auth
+
+// Provider-owned auth methods and current status
+for (const provider of modelRuntime.getProviders()) {
+  const status = await modelRuntime.checkAuth(provider.id);
+}
+
+modelRuntime.setRuntimeApiKey("anthropic", "sk-my-temp-key");
+
+// Custom locations, or inject any pi-ai CredentialStore
+const custom = await ModelRuntime.create({ authPath: "/my/auth.json", modelsPath: "/my/models.json" });
+const inMemory = await ModelRuntime.create({ credentials: new InMemoryCredentialStore() });
+```
+
+`ModelRuntime.getAuth(providerOrModel)` assembles final request auth (replacing `ModelRegistry.getApiKeyAndHeaders()` on the SDK side); passing a model also resolves built-in, `models.json`, and extension model headers. Dynamic provider catalogs refresh via async `ModelRuntime.refresh()` and are cached in `~/.pi/agent/models-store.json`.
+
+To match CLI model parsing, use the exported resolver helpers (Pi 0.80.4):
+
+```typescript
+import { resolveCliModel, resolveModelScopeWithDiagnostics } from "@earendil-works/pi-coding-agent";
+
+const cliModel = resolveCliModel({ cliModel: "anthropic/claude-opus-4-8:high", modelRuntime });
+const { scopedModels, diagnostics } = await resolveModelScopeWithDiagnostics(
+  ["anthropic/*:high", "gpt-5"],
+  modelRuntime,
+);
+```
+
+`resolveCliModel()` resolves against all registered models (so `--api-key`-style first-time setup works before stored auth exists); `resolveModelScopeWithDiagnostics()` matches `--models`/`enabledModels` semantics and returns warnings instead of printing.
+
 ## Prompting & Queueing
 
 ```typescript
@@ -193,7 +231,8 @@ session.subscribe((event) => {
     case "tool_execution_update":
     case "tool_execution_end":
     case "agent_start":
-    case "agent_end":
+    case "agent_end":      // one low-level run; may be followed by retry/compaction/queued follow-ups
+    case "agent_settled":  // fully settled — no automatic continuation left (Pi 0.80.4)
     case "turn_start":
     case "turn_end":
     case "queue_update":
@@ -212,6 +251,7 @@ session.subscribe((event) => {
 
 `pi --mode rpc` speaks newline-delimited JSON over stdio. Additions since Pi 0.79:
 
+- `agent_settled` event (Pi 0.80.4) fires when a run is fully settled — no automatic retry, compaction retry, or queued continuation remains; `agent_end` now carries `willRetry`. `set_thinking_level` accepts `"max"` where the model supports it.
 - `get_entries` / `get_tree` (Pi 0.80.3) read session entries and tree snapshots over RPC.
 - `@earendil-works/pi-coding-agent/rpc-entry` (Pi 0.80.3) launches Pi directly in RPC mode from an importing process.
 - RPC extension UI request/response types are exported from the public API (Pi 0.79.0).
@@ -227,6 +267,20 @@ session.subscribe((event) => {
 - Add custom skills or prompt templates without touching disk
 - Share an event bus between the host app and loaded extensions
 
+To name an inline factory in the startup Extensions list (instead of `<inline:1>`), wrap it in an `InlineExtension` (Pi 0.80.4):
+
+```typescript
+import type { InlineExtension } from "@earendil-works/pi-coding-agent";
+
+const myProvider: InlineExtension = {
+  name: "my-provider",
+  factory: (pi) => { /* ... */ },
+};
+const loader = new DefaultResourceLoader({ extensionFactories: [myProvider] });
+```
+
+Bare factory functions are still accepted.
+
 ## Standalone Custom Tools
 
 Use `defineTool()` when you want a reusable custom tool definition outside `pi.registerTool(...)`:
diff --git a/packages/skill-pi/skills/pi/references/settings.md b/packages/skill-pi/skills/pi/references/settings.md
index b57900e..f220b0d 100644
--- a/packages/skill-pi/skills/pi/references/settings.md
+++ b/packages/skill-pi/skills/pi/references/settings.md
@@ -17,6 +17,7 @@ Edit JSON directly or use `/settings` for common interactive options.
   "defaultModel": "claude-sonnet-4-20250514",
   "defaultThinkingLevel": "medium",
   "hideThinkingBlock": false,
+  "showCacheMissNotices": false,
   "thinkingBudgets": {
     "minimal": 1024,
     "low": 4096,
@@ -26,8 +27,9 @@ Edit JSON directly or use `/settings` for common interactive options.
 }
 ```
 
-- Thinking levels: `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`
+- Thinking levels: `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` — `max` (Pi 0.80.6) is an opt-in level above `xhigh`, exposed only when the selected model supports it (some models, e.g. GPT-5.6, expose both). Custom themes can define `thinkingMax`; existing themes fall back to `thinkingXhigh`.
 - `hideThinkingBlock` hides visible thinking output in the UI
+- `showCacheMissNotices` (Pi 0.80.4) shows transcript notices for significant prompt-cache misses
 
 ## UI & Display
 
@@ -125,6 +127,7 @@ Notes:
 }
 ```
 
+- `shellPath` supports a leading `~` for the home directory (Pi 0.80.6).
 - `npmCommand` is argv-style and is used for npm lookup/install operations, including git-package installs. User-scoped npm packages install under `~/.pi/agent/npm/`; project-scoped npm packages install under `.pi/npm/`.
 - `terminal.showTerminalProgress` (default `false` since Pi 0.70.0) toggles OSC 9;4 progress reporting in supporting terminals (iTerm2, WezTerm, Windows Terminal, Kitty).
 - `terminal.imageWidthCells` (Pi 0.68.1) caps inline tool-output image width in terminal cells.
@@ -236,7 +239,7 @@ pi [options] [@files...] [messages...]
 --provider <name>                e.g. anthropic, openai, google
 --model <pattern>                supports provider/id and optional :<thinking>
 --api-key <key>
---thinking off|minimal|low|medium|high|xhigh
+--thinking off|minimal|low|medium|high|xhigh|max
 --models <patterns>              Ctrl+P cycling allowlist
 --list-models [search]
 
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 0701ba4..e44185b 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -33,11 +33,11 @@ importers:
   packages/pi-memory:
     devDependencies:
       '@earendil-works/pi-ai':
-        specifier: ^0.80.0
-        version: 0.80.3(ws@8.20.0)(zod@4.3.6)
+        specifier: ^0.80.9
+        version: 0.80.9(ws@8.20.0)(zod@4.3.6)
       '@earendil-works/pi-coding-agent':
-        specifier: ^0.80.0
-        version: 0.80.3(ws@8.20.0)(zod@4.3.6)
+        specifier: ^0.80.9
+        version: 0.80.9(ws@8.20.0)(zod@4.3.6)
       '@types/node':
         specifier: ^25.5.0
         version: 25.5.0
@@ -63,11 +63,11 @@ importers:
   packages/pi-web-search:
     devDependencies:
       '@earendil-works/pi-ai':
-        specifier: ^0.80.0
-        version: 0.80.3(ws@8.20.0)(zod@4.3.6)
+        specifier: ^0.80.9
+        version: 0.80.9(ws@8.20.0)(zod@4.3.6)
       '@earendil-works/pi-coding-agent':
-        specifier: ^0.80.0
-        version: 0.80.3(ws@8.20.0)(zod@4.3.6)
+        specifier: ^0.80.9
+        version: 0.80.9(ws@8.20.0)(zod@4.3.6)
       '@types/node':
         specifier: ^25.5.0
         version: 25.5.0
@@ -260,22 +260,22 @@ packages:
   '@changesets/write@0.4.0':
     resolution: {integrity: sha512-CdTLvIOPiCNuH71pyDu3rA+Q0n65cmAbXnwWH84rKGiFumFzkmHNT8KHTMEchcxN+Kl8I54xGUhJ7l3E7X396Q==}
 
-  '@earendil-works/pi-agent-core@0.80.3':
-    resolution: {integrity: sha512-3qw0/GeRQBU/nlGjDe5Yb7ePKTmoxefx2YxyKMFAviFUMXpFexBG/hS7mBtwFahFvzrrTPPoRT6sFIDjwoDWPQ==}
+  '@earendil-works/pi-agent-core@0.80.9':
+    resolution: {integrity: sha512-tObjeOLiw1kYUciBi9R+rRyc4QGK+1akbLLQHvzsn2JrrV2btUdDncJ7jMIR5TKvOYKzKxAwQSl/5k7h3Tjrrg==}
     engines: {node: '>=22.19.0'}
 
-  '@earendil-works/pi-ai@0.80.3':
-    resolution: {integrity: sha512-jPZLMeGL5kkMSEAwAklfXTMHqZvfhsJtCCpKGIr5Duk7mc0n4skjB1dugk7y0z3z8ZHIUCmPAWHdyDqgUz5vdA==}
+  '@earendil-works/pi-ai@0.80.9':
+    resolution: {integrity: sha512-kHsH5nO4FU7mbKnskK0BVPVuWzNb2DrZtiN1fb6LamP+6BMI8xEZiAOw2fqs4VudvlMQgOLjtbgErv+kNJRPIg==}
     engines: {node: '>=22.19.0'}
     hasBin: true
 
-  '@earendil-works/pi-coding-agent@0.80.3':
-    resolution: {integrity: sha512-TIggw9gCXpA+Ph7OjdTA7ka2NPwTVuPmy39KDSyUzaKq8VvHfMGR7vtRz4JB7Um/RMRblmzhu4p9tUCk6MTgGA==}
+  '@earendil-works/pi-coding-agent@0.80.9':
+    resolution: {integrity: sha512-Clgx2Bg5NbMcCpGxusSDQwE+GC0g/d6sCBluE9aypPgSgtJ6n8VmZIIT6auXObMskpRgkr+XZ77wG5hf+cSDtg==}
     engines: {node: '>=22.19.0'}
     hasBin: true
 
-  '@earendil-works/pi-tui@0.80.3':
-    resolution: {integrity: sha512-2BJI6qwRQfnM0Q7seL1+SbacU/jRRjBnN7Hu3n9BjAn7/s5FaBNnvdD1qBQYRsFTHfjqMaDsjYqanPyqwXj99w==}
+  '@earendil-works/pi-tui@0.80.9':
+    resolution: {integrity: sha512-unPTW8hRgIHEGjV8mJJ2jqm+fzgnRubes6V2FPk9ay1W9ZLofcpYQ3NDfrODXSci+oKbBpX9JyYUMfQV6jCA/A==}
     engines: {node: '>=22.19.0'}
 
   '@emnapi/core@1.9.1':
@@ -2270,9 +2270,9 @@ snapshots:
       human-id: 4.1.3
       prettier: 2.8.8
 
-  '@earendil-works/pi-agent-core@0.80.3(ws@8.20.0)(zod@4.3.6)':
+  '@earendil-works/pi-agent-core@0.80.9(ws@8.20.0)(zod@4.3.6)':
     dependencies:
-      '@earendil-works/pi-ai': 0.80.3(ws@8.20.0)(zod@4.3.6)
+      '@earendil-works/pi-ai': 0.80.9(ws@8.20.0)(zod@4.3.6)
       ignore: 7.0.5
       typebox: 1.1.38
       yaml: 2.9.0
@@ -2284,7 +2284,7 @@ snapshots:
       - ws
       - zod
 
-  '@earendil-works/pi-ai@0.80.3(ws@8.20.0)(zod@4.3.6)':
+  '@earendil-works/pi-ai@0.80.9(ws@8.20.0)(zod@4.3.6)':
     dependencies:
       '@anthropic-ai/sdk': 0.91.1(zod@4.3.6)
       '@aws-sdk/client-bedrock-runtime': 3.1048.0
@@ -2305,11 +2305,11 @@ snapshots:
       - ws
       - zod
 
-  '@earendil-works/pi-coding-agent@0.80.3(ws@8.20.0)(zod@4.3.6)':
+  '@earendil-works/pi-coding-agent@0.80.9(ws@8.20.0)(zod@4.3.6)':
     dependencies:
-      '@earendil-works/pi-agent-core': 0.80.3(ws@8.20.0)(zod@4.3.6)
-      '@earendil-works/pi-ai': 0.80.3(ws@8.20.0)(zod@4.3.6)
-      '@earendil-works/pi-tui': 0.80.3
+      '@earendil-works/pi-agent-core': 0.80.9(ws@8.20.0)(zod@4.3.6)
+      '@earendil-works/pi-ai': 0.80.9(ws@8.20.0)(zod@4.3.6)
+      '@earendil-works/pi-tui': 0.80.9
       '@silvia-odwyer/photon-node': 0.3.4
       chalk: 5.6.2
       cross-spawn: 7.0.6
@@ -2335,7 +2335,7 @@ snapshots:
       - ws
       - zod
 
-  '@earendil-works/pi-tui@0.80.3':
+  '@earendil-works/pi-tui@0.80.9':
     dependencies:
       get-east-asian-width: 1.6.0
       marked: 18.0.5
diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml
index 924b55f..4976c8d 100644
--- a/pnpm-workspace.yaml
+++ b/pnpm-workspace.yaml
@@ -1,2 +1,5 @@
 packages:
   - packages/*
+# Keep pnpm's release quarantine, but track same-day Pi releases.
+minimumReleaseAgeExclude:
+  - '@earendil-works/*'
diff --git a/skills/pi/references/extensions.md b/skills/pi/references/extensions.md
index 43f462c..065dab2 100644
--- a/skills/pi/references/extensions.md
+++ b/skills/pi/references/extensions.md
@@ -90,13 +90,15 @@ Useful agent events:
 - `input` — carries `event.streamingBehavior` (`"steer" | "followUp" | undefined`) so handlers can distinguish idle prompts, mid-stream steers, and queued follow-ups; return `{ action: "transform" | "handled" | "continue" }`
 - `before_agent_start` — receives `event.systemPromptOptions` (a `BuildSystemPromptOptions`) so handlers can inspect the structured inputs feeding the system prompt
 - `agent_start`
-- `agent_end`
+- `agent_end` — one low-level run; Pi may still auto-retry, auto-compact and retry, or continue with queued follow-ups
+- `agent_settled` (Pi 0.80.4) — fired when no retry/compaction/follow-up remains; use for status integrations that need to know Pi will not continue automatically (`ctx.isIdle()` is true here unless another extension started a new run)
 - `turn_start`
 - `turn_end`
 - `message_start`
 - `message_update`
 - `message_end` — return a replacement message to override usage/cost or rewrite the finalized assistant message
 - `context`
+- `before_provider_headers` (Pi 0.80.4) — mutate `event.headers` in place after outgoing HTTP headers are assembled: set a key to a string to add/override, `null` to delete. Runs once per provider request; retries reuse the same headers
 - `before_provider_request`
 - `after_provider_response` — inspect the provider HTTP status and headers before stream consumption
 - `model_select`
@@ -121,8 +123,8 @@ Tool results may include `terminate: true` to end the current tool batch without
 - `ctx.ui` for interactive UI hooks
 - `ctx.mode` — `"tui" | "rpc" | "json" | "print"`; gate terminal-only features on `ctx.mode === "tui"`
 - `ctx.cwd`
-- `ctx.sessionManager` (read-only)
-- `ctx.modelRegistry` / `ctx.model`
+- `ctx.sessionManager` (read-only; `buildContextEntries()` returns active-branch entries with compaction applied, Pi 0.80.4)
+- `ctx.modelRegistry` / `ctx.model` — `ctx.modelRegistry` is the synchronous extension-facing facade; its `refresh()` became `Promise<void>` in Pi 0.80.8 (await it before synchronous registry reads)
 - `ctx.hasUI` — `true` in TUI and RPC modes
 - `ctx.signal` — the active agent abort signal (or `undefined` when idle); pass it to `fetch`/model calls for abort-aware nested work
 - `ctx.isIdle()` / `ctx.hasPendingMessages()`
@@ -171,6 +173,19 @@ Important rules:
 4. Use the file-mutation queue for write/edit style tools.
 5. Put reconstructable state in `details`; it persists in session history.
 
+## Dynamic Tool Loading
+
+Pi 0.80.7 lets an extension register many tools while keeping only a small initial set active, then add more during execution — cache-friendly on models with native deferred loading. Lifecycle:
+
+1. Register every tool with `pi.registerTool()` (all appear in `pi.getAllTools()`).
+2. Keep a loader tool (e.g. `search_tools`) active; leave searchable tools inactive — e.g. on `session_start`, `pi.setActiveTools()` to the filtered set.
+3. During loader execution, call `pi.setActiveTools([...pi.getActiveTools(), ...matches])`. The change must be purely additive; unknown names are ignored.
+4. Pi records the added tools on that tool result and exposes their definitions before the next model response.
+
+Native deferred loading preserves the cached prompt prefix on Anthropic Sonnet/Opus/Fable ≥ 4.5 (not Haiku) and OpenAI `gpt-5.4`+; Kimi K3 works via `compat.deferredToolsMode: "kimi"` (Pi 0.80.9). For verified custom models/proxies, enable `compat.supportsToolReferences: true` (`anthropic-messages`) or `compat.supportsToolSearch: true` (`openai-responses`/`openai-codex-responses`). All other models fall back to sending the full active tool list on the next request — activation still works, but may invalidate the provider's cached prefix. Non-additive changes (removals/replacements) always use the fallback.
+
+Cache tips: keep the loader active for the whole session; add rather than replace. Activating a tool that has `promptSnippet`/`promptGuidelines` rebuilds the system prompt and can invalidate the prefix even with native support — lazily loaded tools should rely on their `description` alone.
+
 ## UI Methods
 
 Check `ctx.hasUI` first. Non-interactive modes may not support UI.
@@ -240,6 +255,15 @@ Store extension state with custom session entries:
 pi.appendEntry("my-extension-state", { key: "value" });
 ```
 
+Custom entries never participate in LLM context. Since Pi 0.80.4 they can also render in the interactive transcript via `pi.registerEntryRenderer(customType, renderer)` — the TUI-only counterpart to `pi.registerMessageRenderer()` (whose custom messages DO enter LLM context via `pi.sendMessage()`):
+
+```typescript
+pi.registerEntryRenderer("status-card", (entry, { expanded }, theme) => {
+  return new Text(theme.fg("accent", JSON.stringify(entry.data)));
+});
+pi.appendEntry("status-card", { title: "Indexed files", count: 17 });
+```
+
 Use lifecycle hooks to restore it:
 
 ```typescript
@@ -280,12 +304,16 @@ pi.registerProvider("anthropic", { baseUrl: "https://proxy.example.com" });
 pi.unregisterProvider("my-provider");
 ```
 
+Dynamic providers can implement `refreshModels(context)` (Pi 0.80.8) for model discovery: Pi calls it during catalog refresh (`/model`, `pi update --models`) and publishes the returned list; its models replace extension-provided `models`. Persist results through the scoped `context.store` only when they should survive restarts — live servers like llama.cpp can ignore it.
+
 If you need auth for a specific model request, use:
 
 ```typescript
 const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
 ```
 
+(Still supported for extensions in Pi 0.80.8+; SDK code should use `ModelRuntime.getAuth()` — see `references/sdk.md`.)
+
 Pass `shouldStopAfterTurn` via the SDK to exit the agent loop gracefully after a completed turn. See `references/sdk.md` and `references/providers.md` for the full provider/model schema.
 
 ## Handy Patterns
diff --git a/skills/pi/references/packages.md b/skills/pi/references/packages.md
index 1c4d640..9e2abbd 100644
--- a/skills/pi/references/packages.md
+++ b/skills/pi/references/packages.md
@@ -19,9 +19,11 @@ pi list
 pi update                 # update pi only (changed in Pi 0.79.7)
 pi update --all           # update pi + packages, reconcile pinned git refs
 pi update --extensions    # update packages only
+pi update --models        # refresh model catalogs only (Pi 0.80.8)
 pi update --self          # update pi only
 pi update <source>        # update one package
-pi config
+pi config                 # starts in global settings; Tab switches scope
+pi config -l              # start in project overrides (.pi/settings.json)
 ```
 
 By default, `install` and `remove` write to user settings (`~/.pi/agent/settings.json`). Use `-l` to write to project settings (`.pi/settings.json`) instead. `pi update` installs the exact version returned by the update check.
@@ -129,6 +131,6 @@ Rules:
 
 ## Scope and Deduplication
 
-- Project settings override global settings for the same package identity
+- Project settings override global settings for the same package identity — unless the project entry has `autoload: false`, in which case it is applied as a delta over the global entry (Pi 0.80.4)
 - Identity is package name for npm, repo URL for git, and resolved absolute path for local sources
-- `pi config` can enable or disable package resources after installation
+- `pi config` can enable or disable package resources after installation; since Pi 0.80.4 it manages global vs project-local scopes (Tab to switch, `pi config -l` to start in project mode with inherited global resources dimmed)
diff --git a/skills/pi/references/providers.md b/skills/pi/references/providers.md
index bb75638..f6f5970 100644
--- a/skills/pi/references/providers.md
+++ b/skills/pi/references/providers.md
@@ -9,8 +9,12 @@ Use `/login` in interactive mode, then select a provider. The `/login` selector
 - Anthropic Claude Pro / Max — third-party usage draws from extra usage and is billed per token (suppress the warning via `warnings.anthropicExtraUsage`)
 - OpenAI ChatGPT Plus / Pro (Codex) — `/login` defaults to browser auth but can use a device-code flow for headless environments
 - GitHub Copilot
+- xAI (Grok/X subscription, Pi 0.80.8) — `/login xai` then **Use a subscription** (device-code OAuth); `XAI_API_KEY` remains available via **Use an API key**
+- Radius (Pi 0.80.8) — a dynamic `pi-messages` gateway; `/login radius` stores OAuth tokens, and custom Radius gateways can be declared in `models.json` with `"oauth": "radius"` plus a gateway `baseUrl`
 
-Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Google Gemini CLI and Google Antigravity providers.
+`/login <provider>` with autocomplete works since Pi 0.80.4, and login methods are provider-owned since 0.80.8 (registered pi-ai providers expose their own auth options and status in `/login`). Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Google Gemini CLI and Google Antigravity providers.
+
+Since Pi 0.80.8, built-in catalogs are complemented by dynamic ones: `/model` refreshes configured providers in the background, `pi update --models` forces an immediate refresh, and refreshed catalogs are cached in `~/.pi/agent/models-store.json` for offline use.
 
 ## API Key Providers
 
@@ -35,6 +39,8 @@ Use `/logout` to clear stored OAuth credentials. Pi 0.71.0 removed built-in Goog
 | ZAI Coding Plan (China) | `ZAI_CODING_CN_API_KEY` | `zai-coding-cn` |
 | OpenCode Zen | `OPENCODE_API_KEY` | `opencode` |
 | OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
+| Amazon Bedrock | `AWS_BEARER_TOKEN_BEDROCK` | `amazon-bedrock` |
+| Radius | `RADIUS_API_KEY` | `radius` |
 | Hugging Face | `HF_TOKEN` | `huggingface` |
 | Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
 | Together AI | `TOGETHER_API_KEY` | `together` |
@@ -99,7 +105,7 @@ export AZURE_OPENAI_DEPLOYMENT_NAME_MAP=gpt-4o=my-gpt4o
 
 ### Amazon Bedrock
 
-Pi supports standard AWS auth flows:
+`/login amazon-bedrock` stores a Bedrock API key (Pi 0.80.7). Ambient AWS credential flows also work — these keep using SigV4 authentication:
 
 - `AWS_PROFILE`
 - `AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY`
@@ -182,10 +188,14 @@ Common `api` values:
 
 ### Model & Compatibility Knobs
 
-- `thinkingLevelMap` (Pi 0.72) replaces `compat.reasoningEffortMap`. Map pi levels (`off`/`minimal`/`low`/`medium`/`high`/`xhigh`) to provider values; use `null` to hide a level.
+- `thinkingLevelMap` (Pi 0.72) replaces `compat.reasoningEffortMap`. Map pi levels (`off`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`) to provider values; use `null` to hide a level. Maps may contain holes (Pi 0.80.6) — e.g. expose `high` and `max` without `xhigh`. When a key is omitted, standard levels through `high` use the provider default mapping, but the extended `xhigh`/`max` levels are unsupported.
+- `cost` supports request-wide input pricing tiers (Pi 0.80.6): a `tiers` array where each tier supplies a complete alternate rate set and applies to the whole request when total input usage (`input + cacheRead + cacheWrite`) exceeds `inputTokensAbove`; the highest matching threshold wins. Also usable in `modelOverrides` and extension-registered providers.
+- `modelOverrides` applies to built-in and (since Pi 0.80.4) extension-registered provider models; per-model fields: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
 - `openRouterRouting` is forwarded as-is in the OpenRouter `provider` field (fallbacks, ZDR, ignore lists, throughput/latency).
 - `compat.thinkingFormat` supports OpenAI-compatible reasoning variants: `openrouter` sends `reasoning: { effort }`, `together` sends `reasoning: { enabled }` plus `reasoning_effort` when supported, `qwen-chat-template` targets local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`, and `chat-template` (Pi 0.79.9) sends configurable `chat_template_kwargs` via `compat.chatTemplateKwargs` — e.g. `{ "thinking": { "$var": "thinking.enabled" } }` for DeepSeek models behind vLLM/Hugging Face chat templates (`"$var"` accepts `"thinking.enabled"` or `"thinking.effort"`).
-- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat`, `supportsReasoningEffort`, `supportsLongCacheRetention`, `supportsEagerToolInputStreaming`, `sendSessionIdHeader`, `sendSessionAffinityHeaders`). See [Pi `docs/models.md`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md) when a proxy rejects pi's defaults.
+- **Breaking (Pi 0.80.7):** `compat.sendSessionIdHeader` was removed. Session affinity is now controlled by `compat.sessionAffinityFormat` (`"openai"` sends `session_id`/`x-client-request-id`, `"openai-nosession"` omits the underscore-containing `session_id` header, `"openrouter"` sends `x-session-id`; default auto-detected). Replace `sendSessionIdHeader: false` with `sessionAffinityFormat: "openai-nosession"`. `sendSessionAffinityHeaders` still gates the behavior for `openai-completions`.
+- `compat.deferredToolsMode: "kimi"` (Pi 0.80.9) enables Kimi's deferred tool serialization; `compat.supportsToolReferences` / `compat.supportsToolSearch` enable native dynamic tool loading on verified custom endpoints (see `references/extensions.md`).
+- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat`, `supportsReasoningEffort`, `supportsLongCacheRetention`, `supportsEagerToolInputStreaming`, `supportsStrictMode`). See [Pi `docs/models.md`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md) when a proxy rejects pi's defaults.
 
 ### Context Overflow Recovery
 
@@ -219,7 +229,7 @@ pi.registerProvider("anthropic", { baseUrl: "https://proxy.example.com" });
 
 ## SDK / Extension Auth Lookup
 
-If extension or SDK code needs auth for a specific model request, use `getApiKeyAndHeaders(model)` rather than the removed `getApiKey(model)`:
+If extension code needs auth for a specific model request, use `getApiKeyAndHeaders(model)` rather than the removed `getApiKey(model)`:
 
 ```typescript
 const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
@@ -228,4 +238,4 @@ if (!auth.ok) throw new Error(auth.error);
 const { apiKey, headers } = auth;
 ```
 
-This matters for providers whose headers or auth values resolve dynamically on every request.
+This matters for providers whose headers or auth values resolve dynamically on every request. In SDK code, use `ModelRuntime.getAuth(providerOrModel)` instead (Pi 0.80.8) — passing a model also resolves built-in, `models.json`, and extension model headers; see `references/sdk.md`.
diff --git a/skills/pi/references/sdk.md b/skills/pi/references/sdk.md
index d8834f2..9479c7c 100644
--- a/skills/pi/references/sdk.md
+++ b/skills/pi/references/sdk.md
@@ -12,19 +12,16 @@ npm install @earendil-works/pi-coding-agent
 
 ```typescript
 import {
-  AuthStorage,
   createAgentSession,
-  ModelRegistry,
+  ModelRuntime,
   SessionManager,
 } from "@earendil-works/pi-coding-agent";
 
-const authStorage = AuthStorage.create();
-const modelRegistry = ModelRegistry.create(authStorage);
+const modelRuntime = await ModelRuntime.create();
 
 const { session } = await createAgentSession({
   sessionManager: SessionManager.inMemory(),
-  authStorage,
-  modelRegistry,
+  modelRuntime,
 });
 
 session.subscribe((event) => {
@@ -38,17 +35,16 @@ await session.prompt("What files are in the current directory?");
 
 Run with `npx tsx my-script.ts`.
 
-**Important:** `ModelRegistry` no longer has a public constructor. Use `ModelRegistry.create(authStorage, modelsJsonPath?)` for file-backed registries or `ModelRegistry.inMemory(authStorage)` for built-in models only.
+**Breaking (Pi 0.80.8):** `ModelRuntime` replaced the old `AuthStorage`/`ModelRegistry` pair as the SDK model/auth facade. `CreateAgentSessionOptions.authStorage` and `modelRegistry` are gone — pass the async `modelRuntime` instead. `AuthStorage` is no longer exported; use `ModelRuntime` (or a custom pi-ai `CredentialStore`), or `readStoredCredential()` for one-off reads of `auth.json`. `ModelRegistry` still exists only as the synchronous extension-facing compatibility facade, and its `refresh()` is now `Promise<void>`.
 
 ## Key Imports
 
 ```typescript
 import {
-  AuthStorage,
   createAgentSession,
   DefaultResourceLoader,
   defineTool,
-  ModelRegistry,
+  ModelRuntime,
   SessionManager,
 } from "@earendil-works/pi-coding-agent";
 import { getBuiltinModel } from "@earendil-works/pi-ai/providers/all";
@@ -60,16 +56,14 @@ import { getBuiltinModel } from "@earendil-works/pi-ai/providers/all";
 
 ```typescript
 const cwd = "/path/to/project";
-const authStorage = AuthStorage.create();
-const modelRegistry = ModelRegistry.create(authStorage);
+const modelRuntime = await ModelRuntime.create();
 
 const { session } = await createAgentSession({
   cwd,
   agentDir: "~/.pi/agent",
-  authStorage,
-  modelRegistry,
+  modelRuntime,
   model: getBuiltinModel("anthropic", "claude-opus-4-8"),
-  thinkingLevel: "medium",
+  thinkingLevel: "medium",  // off | minimal | low | medium | high | xhigh | max
   scopedModels: [
     { model: getBuiltinModel("anthropic", "claude-opus-4-8"), thinkingLevel: "high" },
   ],
@@ -90,6 +84,50 @@ Notes:
 - `DefaultResourceLoader` loads extensions, skills, prompt templates, themes, and context files. Replace it to drive resource discovery from custom sources (and it must implement `loadProjectContextFiles()` if you want `AGENTS.md`/`CLAUDE.md` discovery; that helper is also exported standalone).
 - Pass `shouldStopAfterTurn(state) => boolean` (Pi 0.72.0) to exit the agent loop gracefully after a completed turn.
 
+## Models & Auth (`ModelRuntime`)
+
+`ModelRuntime` (Pi 0.80.8) implements the pi-ai `Models` interface and owns credential storage. Auth resolution priority: runtime overrides (`setRuntimeApiKey`, not persisted) → stored credentials in `auth.json` → environment variables → fallback resolver for `models.json` keys.
+
+```typescript
+import { InMemoryCredentialStore } from "@earendil-works/pi-ai";
+import { ModelRuntime } from "@earendil-works/pi-coding-agent";
+
+// Default: ~/.pi/agent/auth.json and ~/.pi/agent/models.json
+const modelRuntime = await ModelRuntime.create();
+
+// Model lookup (use pi-ai Models methods directly; the old
+// getAll()/find()/getSnapshot() projections were removed)
+const model = modelRuntime.getModel("my-provider", "my-model");
+const available = await modelRuntime.getAvailable();  // only models with valid auth
+
+// Provider-owned auth methods and current status
+for (const provider of modelRuntime.getProviders()) {
+  const status = await modelRuntime.checkAuth(provider.id);
+}
+
+modelRuntime.setRuntimeApiKey("anthropic", "sk-my-temp-key");
+
+// Custom locations, or inject any pi-ai CredentialStore
+const custom = await ModelRuntime.create({ authPath: "/my/auth.json", modelsPath: "/my/models.json" });
+const inMemory = await ModelRuntime.create({ credentials: new InMemoryCredentialStore() });
+```
+
+`ModelRuntime.getAuth(providerOrModel)` assembles final request auth (replacing `ModelRegistry.getApiKeyAndHeaders()` on the SDK side); passing a model also resolves built-in, `models.json`, and extension model headers. Dynamic provider catalogs refresh via async `ModelRuntime.refresh()` and are cached in `~/.pi/agent/models-store.json`.
+
+To match CLI model parsing, use the exported resolver helpers (Pi 0.80.4):
+
+```typescript
+import { resolveCliModel, resolveModelScopeWithDiagnostics } from "@earendil-works/pi-coding-agent";
+
+const cliModel = resolveCliModel({ cliModel: "anthropic/claude-opus-4-8:high", modelRuntime });
+const { scopedModels, diagnostics } = await resolveModelScopeWithDiagnostics(
+  ["anthropic/*:high", "gpt-5"],
+  modelRuntime,
+);
+```
+
+`resolveCliModel()` resolves against all registered models (so `--api-key`-style first-time setup works before stored auth exists); `resolveModelScopeWithDiagnostics()` matches `--models`/`enabledModels` semantics and returns warnings instead of printing.
+
 ## Prompting & Queueing
 
 ```typescript
@@ -193,7 +231,8 @@ session.subscribe((event) => {
     case "tool_execution_update":
     case "tool_execution_end":
     case "agent_start":
-    case "agent_end":
+    case "agent_end":      // one low-level run; may be followed by retry/compaction/queued follow-ups
+    case "agent_settled":  // fully settled — no automatic continuation left (Pi 0.80.4)
     case "turn_start":
     case "turn_end":
     case "queue_update":
@@ -212,6 +251,7 @@ session.subscribe((event) => {
 
 `pi --mode rpc` speaks newline-delimited JSON over stdio. Additions since Pi 0.79:
 
+- `agent_settled` event (Pi 0.80.4) fires when a run is fully settled — no automatic retry, compaction retry, or queued continuation remains; `agent_end` now carries `willRetry`. `set_thinking_level` accepts `"max"` where the model supports it.
 - `get_entries` / `get_tree` (Pi 0.80.3) read session entries and tree snapshots over RPC.
 - `@earendil-works/pi-coding-agent/rpc-entry` (Pi 0.80.3) launches Pi directly in RPC mode from an importing process.
 - RPC extension UI request/response types are exported from the public API (Pi 0.79.0).
@@ -227,6 +267,20 @@ session.subscribe((event) => {
 - Add custom skills or prompt templates without touching disk
 - Share an event bus between the host app and loaded extensions
 
+To name an inline factory in the startup Extensions list (instead of `<inline:1>`), wrap it in an `InlineExtension` (Pi 0.80.4):
+
+```typescript
+import type { InlineExtension } from "@earendil-works/pi-coding-agent";
+
+const myProvider: InlineExtension = {
+  name: "my-provider",
+  factory: (pi) => { /* ... */ },
+};
+const loader = new DefaultResourceLoader({ extensionFactories: [myProvider] });
+```
+
+Bare factory functions are still accepted.
+
 ## Standalone Custom Tools
 
 Use `defineTool()` when you want a reusable custom tool definition outside `pi.registerTool(...)`:
diff --git a/skills/pi/references/settings.md b/skills/pi/references/settings.md
index b57900e..f220b0d 100644
--- a/skills/pi/references/settings.md
+++ b/skills/pi/references/settings.md
@@ -17,6 +17,7 @@ Edit JSON directly or use `/settings` for common interactive options.
   "defaultModel": "claude-sonnet-4-20250514",
   "defaultThinkingLevel": "medium",
   "hideThinkingBlock": false,
+  "showCacheMissNotices": false,
   "thinkingBudgets": {
     "minimal": 1024,
     "low": 4096,
@@ -26,8 +27,9 @@ Edit JSON directly or use `/settings` for common interactive options.
 }
 ```
 
-- Thinking levels: `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`
+- Thinking levels: `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` — `max` (Pi 0.80.6) is an opt-in level above `xhigh`, exposed only when the selected model supports it (some models, e.g. GPT-5.6, expose both). Custom themes can define `thinkingMax`; existing themes fall back to `thinkingXhigh`.
 - `hideThinkingBlock` hides visible thinking output in the UI
+- `showCacheMissNotices` (Pi 0.80.4) shows transcript notices for significant prompt-cache misses
 
 ## UI & Display
 
@@ -125,6 +127,7 @@ Notes:
 }
 ```
 
+- `shellPath` supports a leading `~` for the home directory (Pi 0.80.6).
 - `npmCommand` is argv-style and is used for npm lookup/install operations, including git-package installs. User-scoped npm packages install under `~/.pi/agent/npm/`; project-scoped npm packages install under `.pi/npm/`.
 - `terminal.showTerminalProgress` (default `false` since Pi 0.70.0) toggles OSC 9;4 progress reporting in supporting terminals (iTerm2, WezTerm, Windows Terminal, Kitty).
 - `terminal.imageWidthCells` (Pi 0.68.1) caps inline tool-output image width in terminal cells.
@@ -236,7 +239,7 @@ pi [options] [@files...] [messages...]
 --provider <name>                e.g. anthropic, openai, google
 --model <pattern>                supports provider/id and optional :<thinking>
 --api-key <key>
---thinking off|minimal|low|medium|high|xhigh
+--thinking off|minimal|low|medium|high|xhigh|max
 --models <patterns>              Ctrl+P cycling allowlist
 --list-models [search]