@counterposition/skill-pi 0.87.1 → 1.0.0

package/skills/pi/references/extensions.md

@@ -103,6 +103,7 @@ Useful agent events:
 - `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
+- `provider_stream_event` (Pi 0.99.0) — notification-only view of each parsed provider stream event before Pi normalizes it (`provider`, `api`, `model`, `data`). Treat `data` as read-only; handlers are awaited in stream order, so keep them fast. Not persisted
 - `model_select`
 - `thinking_level_select` — observe interactive thinking-level changes
 - `ui_prompt_start` / `ui_prompt_end` (Pi 0.84.4) — distinguish active agent work from time spent waiting on blocking `ctx.ui` prompts (`kind`: `select`/`confirm`/`input`/`editor`/`custom`)
@@ -121,6 +122,8 @@ Useful tool events:
 - `tool_result`
 - `tool_execution_end`
 
+Calls another tool makes through `ctx.executeTool()` (codemode scripts, orchestrating tools) fire the same tool events, so permission gates see them; see [Nested Calls and Permissions](codemode.md#nested-calls-and-permissions).
+
 Since Pi 0.86.0, tool-call `arguments` and result `details` must be JSON-compatible values (no `Date`, `Map`, class instances, `undefined` array slots); use `details: undefined` when there is nothing structured to keep. Tools registered without a parameter schema are rejected at registration.
 
 Tool results may include `terminate: true` to end the current tool batch without an automatic follow-up LLM turn — useful for tools that produce a structured final answer (see `examples/extensions/structured-output.ts` in the Pi repo). Since Pi 0.84.1, blocked `tool_call` results may also return `terminate: true`; the agent stops early only when every finalized result in the batch is terminating. Tools that make nested LLM calls can return their combined `Usage` as `usage` on the tool result — Pi persists it and includes it in footer, `/session`, and RPC session totals (Pi 0.81.0), and `tool_result` handlers may inspect or replace that value.
@@ -137,6 +140,7 @@ Tool results may include `terminate: true` to end the current tool batch without
 - `ctx.sessionManager` (read-only; `buildContextEntries()` returns active-branch entries with compaction applied, Pi 0.80.4)
 - `ctx.modelRegistry` / `ctx.model` / `ctx.thinkingLevel` / `ctx.scopedModels` (Pi 0.83.0) — `ctx.modelRegistry` is the synchronous extension-facing facade; its `refresh()` became `Promise<void>` in Pi 0.80.8 (await it before synchronous registry reads). Since Pi 0.84.x it also exposes `getProvider(id)` (effective pi-ai provider) and `getProviderAuth(id)` (API key, headers, base URL, provider-scoped env — no loaded model required). `ctx.scopedModels` is the read-only session model scope resolved from `--models`/`enabledModels` (`{ model, thinkingLevel? }[]`, empty when unscoped); prefer it over enumerating `getAvailable()` for model pickers
 - `ctx.modelRegistry.stream()` / `streamSimple()` / `complete()` (Pi 0.86.0) — nested model calls through configured providers with request-time auth; prefer `streamSimple()` for provider-neutral calls, pass `ctx.signal`, and report the combined `usage` on the tool result
+- `ctx.modelRegistry.findOfType(type, provider, id)`, `getModelsOfType()`, `getAvailableOfType()`, and `classify(model, { state, questions }, { signal })` (Pi 0.99.0), plus `generateImages(model, { input }, options?)` (Pi 1.0.0) — classifier and image models live beside chat models; neither call rejects, so check `result.stopReason`, and report the returned `usage` on the tool result (see `references/providers.md`)
 - `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()`
@@ -146,6 +150,8 @@ Tool results may include `terminate: true` to end the current tool batch without
 - `ctx.getSystemPrompt()`
 - `ctx.isProjectTrusted()` — the effective project trust decision, including temporary `--approve`/`--no-approve` decisions
 
+Tool `execute()` receives `ExtensionToolContext`, which adds `ctx.tools` (the tools this call can reach) and `ctx.executeTool(name, args, { signal?, onUpdate? })` (Pi 0.99.0). `executeTool()` runs validation and the `tool_call`/`tool_result` hooks like a model call and never rejects: unknown tools, validation errors, blocks, and thrown errors come back as `{ isError: true }`, including after an abort. The signal defaults to the calling tool's. Nested usage is added to the calling tool's result, so report only the tool's own `usage`.
+
 Use `CONFIG_DIR_NAME` (exported from `@earendil-works/pi-coding-agent`) instead of hardcoding `.pi` when building project config paths, e.g. `join(ctx.cwd, CONFIG_DIR_NAME, "my-extension.json")`.
 
 Command handlers receive `ExtensionCommandContext`, which extends the above with session-control methods that would deadlock from event handlers: `ctx.getSystemPromptOptions()` (inspect the base system-prompt inputs), `ctx.waitForIdle()`, `ctx.newSession()`, `ctx.fork()`, `ctx.switchSession()`, `ctx.navigateTree()`, and `ctx.reload()`.
@@ -181,12 +187,27 @@ Important rules:
 
 1. Truncate large output.
 2. Respect `signal.aborted`.
-3. Throw on failure instead of returning fake success.
-4. Use the file-mutation queue for write/edit style tools.
+3. Throw on failure instead of returning fake success, or return `isError: true` when the failure still carries data. A returned object without `isError` counts as success.
+4. Use the file-mutation queue (`withFileMutationQueue()`) for write/edit style tools.
 5. Put reconstructable state in `details`; it persists in session history.
 
+## Tool Exposure & Structured Results
+
+Pi 0.99.0 added fields for tools that other tools, codemode scripts, and permission extensions consume ([docs](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/extensions.md#tool-exposure), [types](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/src/core/extensions/types.ts)):
+
+- `outputSchema` (TypeBox) plus `structuredContent` on every result: the model still reads `content`; codemode scripts receive `structuredContent` instead of text. Without `outputSchema`, scripts get the text. `structuredContent` must be JSON-compatible. A `tool_result` handler that replaces `content` must also return `structuredContent`, or it is dropped.
+- `isError: true` on a returned result: the model sees an error, while `details` and `structuredContent` are kept for the UI and scripts.
+- `exposure`: `direct` (default), `model-only`, `codemode`, `deferred`, or `hidden`. `direct` and `model-only` tools activate on registration; the others do not (`defaultActive: false` also keeps a `direct` tool inactive until `--tools`/`defaultTools`/`setActiveTools()` names it). Tools cannot be unregistered: re-register with `exposure: "hidden"` to withdraw one. The table of what each value declares and allows is in `references/codemode.md`.
+- `namespace: { name, description?, instructions? }` groups related tools, as MCP servers do. Codemode lists a namespace under one heading with its short `description`. `instructions` (Pi 0.99.2) holds longer usage guidance that is not listed; scripts read it with `describeNamespace(name)`.
+- `annotations`: `readOnlyHint`, `destructiveHint`, `idempotentHint`, `openWorldHint`, with MCP meanings. Missing hints mean "not read-only, may be destructive, open world". They are unverified; mark writes neither read-only nor casually idempotent.
+- `prepareLoadout(loadout)`: for tools that orchestrate others. Runs whenever the active tools change with `declared`, `callable`, and `registered` tools, and returns replacement `descriptions` and `hiddenDeclarations` (active tools left out of requests but still callable). The built-in `codemode` uses only this, `exposure`, and `ctx.executeTool()`.
+
+`pi.getAllTools()` reports each tool's `exposure`, `namespace`, and `annotations`. `pi.setActiveTools()` ignores unknown and `hidden` names. Compilable examples: `examples/structured-tool.ts` and `examples/nested-tools.ts`.
+
 ## Dynamic Tool Loading
 
+For tools the model should find on demand, prefer `exposure: "deferred"` with the built-in `tool_search` (Pi 0.99.0), or `exposure: "codemode"` for tools scripts call. `tool_search` is inactive by default: enable it with `"defaultTools": ["+tool_search"]` or `--tools`, or let a connected MCP server with `deferred` exposure turn it on. Without it, the model can reach `deferred` tools only through codemode. The manual loader pattern below still works.
+
 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()`).
@@ -206,7 +227,7 @@ Cache tips: keep the loader active for the whole session; add rather than replac
 - `{ type: "grammar", variants: { openai_lark?: string, openai_regex?: string } }` — OpenAI Lark/regex grammar encodings
 - Set `false` to explicitly disable for that tool
 
-Model capability metadata gates what is actually sent: `compat.supportsStrictTools` / Anthropic built-ins enable strict JSON-schema tools, and `compat.supportsOpenAIGrammarTools` marks endpoints that accept Lark/regex grammar tools (enabled in generated metadata for GPT-5+ across OpenAI, Codex, Azure, GitHub Copilot, opencode, Cloudflare AI Gateway). Unsupported combinations fall back to normal function tools rather than failing. Since Pi 0.86.0, strict-prefer JSON-schema sampling is on by default for the built-in `read`, `bash`, `powershell`, `edit`, and `write` tools (no `PI_EXPERIMENTAL` needed); re-register a definition with `constrainedSampling: false` to opt out.
+Model capability metadata gates what is actually sent: `compat.supportsStrictTools` / Anthropic built-ins enable strict JSON-schema tools, and `compat.supportsOpenAIGrammarTools` marks endpoints that accept Lark/regex grammar tools (enabled in generated metadata for GPT-5+ across OpenAI, Codex, Azure, GitHub Copilot, opencode, Cloudflare AI Gateway). With `strict: "prefer"`, unsupported combinations fall back to normal function tools; with `strict: "require"`, the request fails when the model has no strict tools or the schema uses keywords strict mode rejects. Since Pi 0.99.2 Anthropic strict tools also reject keywords such as `minimum`/`maximum`, so such `prefer` tools are sent non-strict. Since Pi 0.86.0, strict-prefer JSON-schema sampling is on by default for the built-in `read`, `bash`, `powershell`, `edit`, and `write` tools (no `PI_EXPERIMENTAL` needed); re-register a definition with `constrainedSampling: false` to opt out.
 
 ## Display Transformers
 
@@ -311,6 +332,14 @@ pi.on("session_start", async (_event, ctx) => {
 });
 ```
 
+## MCP Servers
+
+`pi.registerMcpServer(name, config)` adds a server for the current session with the `mcp.json` entry shape; `pi.unregisterMcpServer(name)` closes it. Registrations are not saved, and an `mcp.json` server with the same name wins. Extensions that implement their own MCP client read `pi.getMcpServers()` on `session_start` and handle `mcp_servers_change`. See `references/mcp.md`.
+
+## Virtual Models
+
+`pi.registerVirtualModel({ provider, id, name, thinkingLevels?, route(request, ctx) })` (experimental, Pi 0.99.0) adds a selectable model that picks a physical model and thinking level for every request. See `references/providers.md#virtual-models`.
+
 ## Provider Integration
 
 Extensions can register or override providers:
@@ -341,6 +370,8 @@ 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`. Since Pi 0.84.0 the context is read-snapshot + generation-checked publication: read `context.stored` (the persisted provider snapshot) instead of `context.store`, and persist through `context.publish({ update?, persist? })` — `persist` omitted leaves storage unchanged, a `ModelsStoreEntry` writes it, `persist: null` deletes it. Config-form callbacks that only return models remain unchanged.
 
+A config-form `models` list replaces the provider's models across chat, image, and classifier operations (Pi 0.99.0). Omitted `type` means `"chat"`; image and classifier entries need an explicit `type` plus implementations keyed by `api` through `images`/`classifiers` (see `references/providers.md`).
+
 Since Pi 0.81.0, extensions can also register a complete pi-ai `Provider` via `pi.registerProvider(createProvider({...}))` — native auth (`login`/`resolve`), `getModels`, `refreshModels`, `filterModels`, and custom streaming. The registered provider becomes the composition base; `models.json` overrides still apply above it. Prefer this when you need real authentication or stream behavior rather than just a model list. The legacy config form (`name`, `baseUrl`, `apiKey`, `models`, `oauth`, `streamSimple`) remains supported. OAuth `refreshToken(credentials, signal)` callbacks must accept and honor the abort signal since Pi 0.84.0.
 
 If you need auth for a specific model request, use:
@@ -355,7 +386,9 @@ Custom `streamSimple` implementations receive a normalized `TranscriptContext` s
 
 ## Handy Patterns
 
-- Permission gates via `tool_call`
+- Permission gates via `tool_call` (they also see nested calls from codemode; see `references/codemode.md`)
+- Data tools for codemode via `outputSchema` + `structuredContent`
+- Orchestrating tools via `ctx.executeTool()` with `exposure: "model-only"`
 - Prompt injection via `before_agent_start` (`systemPromptOptions.sections`)
 - Model-context pruning via `context`, or durable omission via `context_edit` entries from `turn_end`/`agent_before_settle`
 - Branch or compaction customization via `session_before_tree` / `session_before_compact`

package/skills/pi/references/mcp.md

@@ -0,0 +1,137 @@
+# MCP Servers
+
+Pi connects to MCP servers through a built-in extension. There is no package to install. Checked against Pi v1.0.0: [mcp.md](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/mcp.md), [cli.md#mcp-commands](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/cli.md#mcp-commands), [extensions.md#mcp-servers](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/extensions.md#mcp-servers).
+
+## Configure
+
+| File | Scope |
+|------|-------|
+| `~/.pi/agent/mcp.json` | Global. Put personal servers and servers with credentials here |
+| `.pi/mcp.json` | Project. Read only after the project is trusted, because stdio servers run commands |
+
+A project entry replaces a global entry with the same name. The format is the usual `mcpServers` object, so Claude Desktop, Claude Code, and Cursor entries copy over unchanged:
+
+```json
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
+    },
+    "docs": {
+      "url": "https://example.com/mcp",
+      "headers": { "Authorization": "Bearer ${DOCS_TOKEN}" },
+      "description": "Search and read the product documentation",
+      "exposure": "direct"
+    }
+  }
+}
+```
+
+- stdio: `command` (one executable, not a shell string), `args`, `env`, `cwd`. Relative `cwd` resolves against the session directory; a leading `~/` works in `command`, args, and `cwd`.
+- HTTP: `url`, `headers`, `oauth`. Only streamable HTTP; `"type": "sse"` is rejected (try the server's `/mcp` endpoint instead of `/sse`).
+- `type` is optional (`stdio`, `http`, or `streamable-http`); `command` implies stdio and `url` implies HTTP.
+- `env` and `headers` values accept `${NAME}` and `!command`. A command must produce the whole value: `"Authorization": "!echo Bearer $(gh auth token)"`.
+- `timeout` is seconds per request (default 60); progress notifications reset it. `enabled: false` keeps the entry without connecting.
+- `description` (Pi 0.99.2): one sentence on what the server offers. It lists the server in the system prompt's `mcp_servers` section, ranks its tools in tool search, and is returned by codemode's `describeNamespace()`. Without it, Pi uses the first line of the server instructions once connected.
+- Server names use letters, digits, `_`, `-`. Tools are named `mcp__<server>__<tool>`, with every character other than letters, digits, and `_` replaced by `_` (Pi 0.99.2: `mcp__my-server__x` is now `mcp__my_server__x`; update permission rules that name the old spelling). Tools of one server whose names then collide all get a hash suffix. Server names that differ only in `-` and `_` count as the same server; a second one is rejected.
+- Invalid entries are skipped and reported; other servers still connect.
+
+Converting other clients: VS Code uses `servers` + `inputs` (move under `mcpServers`, replace `${input:...}` with `${NAME}`); Codex uses TOML `[mcp_servers.<name>]` (same fields as JSON); opencode uses `"type": "local"` with an array `command` (split into `command`/`args`), `environment` for `env`, and `{env:NAME}` for `${NAME}`.
+
+## Set Up From a Shell
+
+These commands work outside a session, so an agent can run them through `bash`:
+
+```bash
+pi mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem .
+pi mcp add docs --url https://example.com/mcp --bearer-token-env-var DOCS_TOKEN --exposure direct --description "Product docs"
+pi mcp add -l tools --env API_KEY='${TOOLS_KEY}' -- uvx tools-mcp   # -l writes .pi/mcp.json
+pi mcp list            # connects to every enabled server; exits 1 while anything is wrong
+pi mcp login sentry    # OAuth: opens the browser and waits for the user to approve
+pi mcp remove docs     # keeps stored OAuth credentials
+pi mcp logout sentry
+```
+
+`pi mcp add` also takes `--oauth-client-id`, `--oauth-client-secret`, `--oauth-callback-port`, and `--oauth-client-name`. It does not connect; verify with `pi mcp list`. A running session picks up added or changed servers after `/reload` or a new session.
+
+In a session, `/mcp` opens the server manager (state, tools, errors, sign in/out, reconnect, exposure, enable/disable). Changes are written back to the `mcp.json` that defines the server. Outside the TUI, `/mcp` prints status and `/mcp login|logout|reconnect <server>` run directly.
+
+Pi connects every enabled server in the background when a session starts (Pi 0.99.2). The first prompt waits up to 10 seconds only for servers with `direct` tools. Other servers are waited for when needed: a codemode script waits for the servers it names (`mcp__<server>`), and `searchTools()`, `ALL_TOOLS`, `tool_search`, and the resource tools wait for all of them. Server log notifications go to `~/.pi/agent/mcp.log`.
+
+### Authentication
+
+- OAuth is used only for HTTP servers whose config has no `Authorization` header. Tokens live in `~/.pi/agent/mcp-auth.json`, stored per server name and URL (Pi 1.0.0), so two names for the same URL sign in with different accounts.
+- `oauth: { clientId?, clientSecret?, callbackPort?, callbackUrl?, scope?, clientName?, authServerMetadataUrl? }`:
+  - `clientId`/`clientSecret` set a pre-registered client for servers without dynamic client registration.
+  - `callbackPort` alone gives `http://127.0.0.1:<port>/callback`; a `callbackUrl` (HTTP on a loopback host) without a port gets `callbackPort` or a free one.
+  - `scope`: space-separated scopes to request when the server does not advertise the ones it needs.
+  - `clientName` (Pi 0.99.2): the name sent at client registration (default `pi`), for servers that only accept known clients, e.g. `"Claude Code"`. Sign out first to register again under a new name.
+  - `authServerMetadataUrl` (Pi 1.0.0): the authorization server metadata document to use instead of discovery, for servers that advertise a wrong authorization server or none. Trusted as configured; HTTPS except on loopback.
+- Pi rejects an authorization response whose `iss` names another authorization server (RFC 9207), and step-up sign-in after `insufficient_scope` keeps the scopes already granted (Pi 1.0.0).
+- `"auth": { "provider": "<provider>" }` (Pi 0.99.2) sends a `/login` provider's current token as the bearer token instead of MCP OAuth, read on every request. Allowed only in the global `mcp.json` and from extensions, and HTTPS except on loopback. After a Radius sign-in, `/login` offers to add the Radius MCP server this way.
+
+## Exposure
+
+`exposure` decides how the model reaches a server's tools:
+
+| Value | Declared to the model | Callable from codemode | Notes |
+|-------|----------------------|------------------------|-------|
+| `codemode` (default) | No | Yes, found with `searchTools()`, `describeNamespace()`, or `ALL_TOOLS`; not listed in the `codemode` description | Pi activates `codemode` when such a server connects |
+| `deferred` | After `tool_search` loads them | Yes | Pi activates `tool_search`; for large servers without codemode |
+| `direct` | Yes, like built-in tools | Yes | |
+| `hidden` | No | No | Registered but unreachable |
+
+`toolExposure` overrides single tools by name or `*` pattern (exact name wins, then first matching pattern):
+
+```json
+{
+  "mcpServers": {
+    "github": {
+      "url": "https://api.githubcopilot.com/mcp/",
+      "exposure": "deferred",
+      "toolExposure": { "search_code": "direct", "get_*": "codemode", "delete_*": "hidden" }
+    }
+  }
+}
+```
+
+`codemode-deferred` is an alias for `codemode` since Pi 0.99.2. Servers with `codemode` or `deferred` tools are listed in an `mcp_servers` system prompt section with how their tools are reached and a one-line summary. Pi updates it when a prompt starts and appends a changed section to the conversation, so neither tool descriptions nor the cached prefix change when servers connect.
+
+Undeclared tools (`codemode`, `deferred`) are reachable through either tool: codemode scripts can call a `deferred` server's tools, and `tool_search` can load a `codemode` server's tools. Set top-level `"autoEnableCodemode": false` in `mcp.json` to stop Pi from activating `codemode`. Pi warns once when neither `codemode` nor `tool_search` is active, because the tools are then unreachable.
+
+## Results
+
+- Text results over 20KB reach the model with the middle cut out; the full text goes to a temp file named in the result.
+- Codemode scripts receive the whole `CallToolResult` (`content`, `structuredContent`, `isError`). A result with `isError` resolves in scripts and is reported to the model as an error for direct calls. `image(result.content[0])` forwards an image block. Server instructions are not part of any tool description; scripts read them with `describeNamespace("mcp__<server>")`.
+- Servers with resources add `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource` (marked read-only).
+- Tool calls are never retried (the server may have run them); resource reads retry once on 408/429/5xx.
+
+## Permissions
+
+Every MCP call goes through Pi's tool pipeline, so `tool_call` and `tool_result` handlers (permission gates included) see MCP tools. Calls from codemode scripts are nested calls; see [Nested Calls and Permissions](codemode.md#nested-calls-and-permissions). `pi.getAllTools()` reports the server's `readOnlyHint`, `destructiveHint`, `idempotentHint`, and `openWorldHint` annotations. They are unverified hints; see [Tool Exposure](extensions.md#tool-exposure--structured-results).
+
+## Servers From Extensions
+
+```typescript
+pi.registerMcpServer("jira", { url: "https://mcp.example.com/jira", exposure: "codemode", description: "Jira issues" });
+pi.unregisterMcpServer("jira");
+```
+
+- Same config shape as an `mcpServers` entry. Registrations are not saved: register on every load.
+- Registered during load: connects on `session_start` with the `mcp.json` servers. Registered later: connects right away.
+- An `mcp.json` server with the same name wins. Another extension's name, an invalid name, or an invalid config throws.
+- `pi mcp` shell commands do not load extensions and only see `mcp.json` servers.
+- Alternative MCP extensions read registrations with `pi.getMcpServers()` on `session_start` and handle `mcp_servers_change`.
+
+## Turning It Off or Replacing It
+
+- `"extensions": ["-builtin:mcp"]` in settings, or `pi config` → Built-in, disables the built-in support. `pi mcp` shell commands still work.
+- `--no-extensions` disables built-ins too; `pi -ne -e builtin:mcp` keeps only MCP.
+- An extension that registers the `/mcp` command (for example `pi-mcp-adapter`) replaces the built-in support: `mcp.json` is then not read in sessions.
+
+## SDK
+
+SDK sessions do not load built-in extensions. Add `createMcpExtension()`, plus `createCodemodeExtension()` for `codemode` servers and `createToolSearchExtension()` for `deferred` servers, then call `session.bindExtensions()` so `session_start` connects the servers. See `references/sdk.md`.
+
+The standalone client is published as `@earendil-works/pi-mcp` (stdio and streamable HTTP transports, OAuth, an in-memory testing transport). It has no Pi session dependency.

package/skills/pi/references/packages.md

@@ -94,16 +94,21 @@ If there is no `pi` manifest, Pi auto-discovers:
 
 ## Dependencies
 
+Checked against Pi v1.0.0 [packages.md](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/packages.md#declare-dependencies).
+
 - Normal runtime dependencies belong in `dependencies`
-- Pi core libraries should be peer deps with `"*"` ranges:
+- Pi supplies these to extensions; declare them as peer deps with `"*"` ranges and never bundle them:
   - `@earendil-works/pi-ai`
   - `@earendil-works/pi-agent-core`
   - `@earendil-works/pi-coding-agent`
   - `@earendil-works/pi-tui`
   - `typebox`
-- Pin dev dependencies to a current Pi line (e.g. `^0.84.2`) so typecheck/tests validate against what users run; keep peers `"*"` so installs stay compatible across Pi versions
-- Other Pi packages must be bundled explicitly
-- Git package installs run `npm install --omit=dev` — runtime needs go in `dependencies`, not `devDependencies`
+- Do not list those host-provided packages in `dependencies`. A physical copy can bypass Pi's extension module mapping and create duplicate classes and registries; since Pi 0.99.0 Pi reports an extension warning for this manifest.
+- Pi suppresses automatic peer installation for managed npm packages and for git packages installed with npm (`--omit=dev --legacy-peer-deps`), pnpm (`--prod`, no auto-installed peers), or Bun (`--omit=dev --omit=peer`). Local path packages are not installed or modified; their dependency tree is the author's responsibility.
+- Git package installs omit dev dependencies — runtime needs go in `dependencies`, not `devDependencies`
+- Installed packages load with separate module roots. Do not rely on two packages sharing one dependency instance, or on one package resolving another package's undeclared dependency.
+- Other Pi packages used as dependencies must be included in the published tarball and referenced through their `node_modules` resource paths.
+- Pin dev dependencies to the Pi line you test against (e.g. `^1.0.0`) so typecheck/tests validate against what users run; keep peers `"*"` so installs stay compatible across Pi versions. `"*"` does not prove compatibility: document the minimum supported Pi version and feature-check newer APIs (for example `ctx.executeTool`, `pi.registerMcpServer`) if you support older hosts.
 
 ## Package Filtering
 
@@ -134,4 +139,5 @@ Rules:
 
 - 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; 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)
+- `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). Since Pi 0.99.0 its Built-in section also disables the built-in `mcp`, `llama.cpp`, `codemode`, and `tool-search` extensions, stored as `-builtin:<name>` in `extensions`
+- The `codemode`, `tool-search`, and `mcp` built-ins are replaceable: an extension that registers one of their tools, commands, or flags (for example `/mcp`, `codemode`, or `tool_search`) replaces that built-in, and Pi warns

package/skills/pi/references/patterns.md

@@ -19,6 +19,11 @@ Practical recipes for extending Pi. Each pattern is a self-contained example.
 13. [File Watcher / Trigger](#file-watcher--trigger)
 14. [Input Transform](#input-transform)
 15. [Tool Override](#tool-override)
+16. [Structured Tool](#structured-tool)
+17. [Nested Tool Calls](#nested-tool-calls)
+18. [Classifier Gate](#classifier-gate)
+
+Patterns 16–18 are full files under `examples/` that type-check against Pi 1.0.0 in this skill's package; read them rather than retyping.
 
 ---
 
@@ -43,6 +48,8 @@ export default function (pi: ExtensionAPI) {
 }
 ```
 
+The handler also runs for `bash` calls made by codemode scripts; see [Nested Calls and Permissions](codemode.md#nested-calls-and-permissions).
+
 ## Protected Paths
 
 Block writes to sensitive files:
@@ -313,3 +320,30 @@ pi.on("tool_call", async (event, ctx) => {
   }
 });
 ```
+
+## Structured Tool
+
+`examples/structured-tool.ts` registers a read-only data tool:
+
+- `outputSchema` plus `structuredContent` on every result, so codemode scripts get `{ files, missing }` as an object while the model reads a text summary.
+- `annotations: { readOnlyHint: true, openWorldHint: false }` for permission extensions, and a `namespace` for grouping in the `codemode` description.
+- `isError: true` when no file was found: the model sees an error, scripts still get the data.
+- Only `ENOENT` is treated as "missing"; other errors are rethrown.
+
+## Nested Tool Calls
+
+`examples/nested-tools.ts` registers `read_many`, which reads several files in parallel through `ctx.executeTool("read", ...)`:
+
+- `exposure: "model-only"`: the model can call it, other tools and codemode cannot, so it cannot recurse.
+- Checks `ctx.tools` first: an inactive `direct` tool is not callable.
+- Each nested call runs every `tool_call` gate (see [Nested Calls and Permissions](codemode.md#nested-calls-and-permissions)). `executeTool()` never rejects, and aborted calls come back as `isError`, so the tool calls `signal?.throwIfAborted()` after the batch to report the abort as an abort rather than as failed reads.
+- Streams progress through `onUpdate`.
+
+## Classifier Gate
+
+`examples/classifier-gate.ts` asks a classifier model whether a `bash` command is destructive before it runs:
+
+- Finds Jev with `ctx.modelRegistry.findOfType("classifier", "typesafe", "jev-latest")` and calls `ctx.modelRegistry.classify(..., { signal: ctx.signal })`.
+- `classify()` never rejects: it checks `stopReason` (`"aborted"` blocks, `"error"` falls through to confirmation) and validates the `bool` answer's probability.
+- Fails closed: a missing model, an error, an out-of-range answer, or a probability above the strict `MAX_ALLOWED_PROBABILITY` (0.2; tune it) asks the user, and blocks when `ctx.hasUI` is false.
+- Uses `satisfies ClassifierContext["questions"]` so the question literal keeps its narrow types.

package/skills/pi/references/providers.md

@@ -6,12 +6,13 @@ Pi supports subscription-based providers via OAuth, API-key providers via env va
 
 Use `/login` in interactive mode, then select a provider. The `/login` selector is fuzzy-searchable and shows where each entry's auth comes from (`--api-key`, env var, custom provider) without leaking the secret.
 
-- 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
+- Anthropic Claude Pro / Max — third-party usage draws from extra usage and is billed per token (suppress the warning via `warnings.anthropicExtraUsage`). Since Pi 1.0.0 `/login anthropic` offers browser login (default) or **copy code** login, which shows the authorization code on Anthropic's page for pasting into Pi when the browser runs on another machine
+- OpenAI with a ChatGPT subscription (Pi 0.99.0) — `/login openai` offers **Sign in with ChatGPT**, an OAuth login that uses the subscription with the OpenAI API on the regular `openai` provider. Pi stores a stable `deviceId` for it in global settings. Subscription usage-limit errors are not retried
+- OpenAI Codex (legacy) — the older `openai-codex` provider, renamed in Pi 0.99.0 and superseded by Sign in with ChatGPT. Its `/login` still offers browser auth or a device-code flow; its default model is `gpt-6.1-sol` (Pi 0.99.1). Prefer Sign in with ChatGPT on `openai` for new setups
 - GitHub Copilot
 - OpenRouter (Pi 0.82.0) — `/login openrouter` runs a PKCE flow that mints a user-controlled API key billed from OpenRouter credits; on headless/SSH hosts paste the redirect URL or authorization code into the prompt (Pi 0.83.0). `OPENROUTER_API_KEY` still works via **Use an API key**
 - 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`. Since Pi 0.86.0 a public Radius catalog ships for immediate/offline selection (cached and live gateway catalogs overlay it); custom gateways use their own catalog
+- 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`. Since Pi 0.86.0 a public Radius catalog ships for immediate/offline selection (cached and live gateway catalogs overlay it); custom gateways use their own catalog. Since Pi 1.0.0 `/login` lists **Sign in with Radius** at the top level and, after sign-in, offers to add the Radius MCP server to the global `mcp.json` with `"auth": { "provider": "radius" }`
 - Meta Muse (Pi 0.86.1) — `/login meta` with automatic Model API key refresh; `META_API_KEY` also works
 
 `/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. `pi auth check [provider|model]` (Pi 0.84.1) preflights credential readiness; `pi auth print-api-key` / `pi auth print-bearer-token` (Pi 0.83.0) export resolved credentials to external clients, refreshing OAuth as needed.
@@ -43,6 +44,7 @@ Since Pi 0.80.8, built-in catalogs are complemented by dynamic ones: `/model` re
 | OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
 | Amazon Bedrock | `AWS_BEARER_TOKEN_BEDROCK` | `amazon-bedrock` |
 | Radius | `RADIUS_API_KEY` | `radius` |
+| TypeSafe (classifier models only) | `TYPESAFE_API_KEY` | `typesafe` |
 | Hugging Face | `HF_TOKEN` | `huggingface` |
 | Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
 | Together AI | `TOGETHER_API_KEY` | `together` |
@@ -56,6 +58,8 @@ Since Pi 0.80.8, built-in catalogs are complemented by dynamic ones: `/model` re
 | Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
 | Xiaomi MiMo Token Plan (CN/AMS/SGP) | `XIAOMI_TOKEN_PLAN_{CN,AMS,SGP}_API_KEY` | `xiaomi-token-plan-{cn,ams,sgp}` |
 
+With no Anthropic key or token set, Pi 0.99.2+ uses Anthropic workload identity federation when `ANTHROPIC_FEDERATION_RULE_ID`, `ANTHROPIC_ORGANIZATION_ID`, and `ANTHROPIC_IDENTITY_TOKEN_FILE` are set (plus optional `ANTHROPIC_SERVICE_ACCOUNT_ID` and `ANTHROPIC_WORKSPACE_ID`). The Anthropic SDK exchanges and refreshes the token, re-reading the identity token file, so keep that file fresh for long sessions.
+
 ## Auth File
 
 `~/.pi/agent/auth.json` stores API keys and OAuth tokens with `0600` permissions:
@@ -86,12 +90,14 @@ Entries may include an `env` object (Pi 0.79.5) for provider-scoped environment
 
 ## Credential Resolution Order
 
-1. `--api-key`
+1. `--api-key` (runtime override)
 2. `auth.json`
-3. Environment variables
-4. Custom provider keys from `models.json`
+3. `apiKey` from `models.json`
+4. Environment variables or ambient cloud credentials
+
+Provider extensions can define their own authentication behavior.
 
-## Cloud Providers
+## Provider-Specific Setup
 
 ### Azure OpenAI
 
@@ -151,12 +157,11 @@ Use `models.json` for OpenAI-compatible, Anthropic-compatible, Google-compatible
 
 ```json
 {
-  "providers": [
-    {
-      "name": "ollama",
+  "providers": {
+    "ollama": {
       "baseUrl": "http://localhost:11434/v1",
       "api": "openai-completions",
-      "apiKey": "unused",
+      "apiKey": "ollama",
       "models": [
         {
           "id": "llama3.2",
@@ -175,10 +180,12 @@ Use `models.json` for OpenAI-compatible, Anthropic-compatible, Google-compatible
         }
       ]
     }
-  ]
+  }
 }
 ```
 
+`providers` is an object keyed by provider ID, not an array; the optional `name` field is only a display label. A `models` entry adds or replaces a model with the same ID on that provider; use `modelOverrides` to change metadata of an existing built-in or extension model.
+
 `apiKey` is optional (Pi 0.80.0): omit it when auth comes from `/login`, `auth.json`, or CLI `--api-key`. Like `auth.json` keys, `apiKey` and `headers` values support `!command` execution and `$ENV_VAR` interpolation; plain uppercase strings are literals. Keyless local servers (e.g. Ollama) should keep a dummy value so their models appear in `/model`.
 
 Common `api` values:
@@ -206,7 +213,7 @@ Common `api` values:
 - `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`, `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 — and `baseten` (Pi 0.84.0) sends `chat_template_args` via `compat.chatTemplateArgs`.
 - **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, and `compat.supportsStrictTools` / `compat.supportsOpenAIGrammarTools` / per-model `constrainedSampling` gate constrained sampling (see `references/extensions.md`). `compat.supportsFinishReason: false` (Pi 0.84.0) tells pi to infer stop/toolUse for OpenAI-compatible streams that omit `finish_reason`.
-- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat` — now also covering tool-result text content, `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.
+- Advanced `compat` flags exist for proxy quirks (`cacheControlFormat` — now also covering tool-result text content, `supportsReasoningEffort`, `supportsLongCacheRetention`, `supportsEagerToolInputStreaming`, `supportsStrictMode`). See [Pi `docs/models.md`](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/models.md) when a proxy rejects pi's defaults.
 
 ### Context Overflow Recovery
 
@@ -214,12 +221,96 @@ Pi can auto-compact and retry when a provider fails with a recognized context-wi
 
 ### llama.cpp
 
-Pi supports the llama.cpp router server (Pi 0.81.0): configure with `/login llama.cpp`, search/download Hugging Face models and load/unload with live progress via `/llama`, then select loaded models in `/model`. The model catalog persists across restarts (fixed in Pi 0.82.1). See [Pi `docs/llama-cpp.md`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/llama-cpp.md).
+Pi supports the llama.cpp router server (Pi 0.81.0): configure with `/login llama.cpp`, search/download Hugging Face models and load/unload with live progress via `/llama`, then select loaded models in `/model`. The model catalog persists across restarts (fixed in Pi 0.82.1). Every llama.cpp chat model is also listed as a classifier model (see [Classifier Models](#classifier-models)). `"extensions": ["-builtin:llama.cpp"]` removes the provider and `/llama`. See [Pi `docs/llama-cpp.md`](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/llama-cpp.md).
+
+## Model Types
+
+Since Pi 0.99.0 catalogs hold typed models: `type` is `"chat"` (the default when omitted), `"image"`, or `"classifier"`. Chat-facing reads (`getModels()`, `getAvailable()`, `ctx.modelRegistry.getAll()`, `/model`) stay chat-only. `ModelRuntime`, `ctx.modelRegistry`, and pi-ai `Models` all have `getModelsOfType(type, provider?)`, `getModelOfType(type, provider, id)`, and async `getAvailableOfType(type, provider?)`. Only `ModelRuntime` and `Models` have `getAllModels()` and `getAllAvailable()` for every type; `ctx.modelRegistry` adds `findOfType(type, provider, id)` instead. pi-ai exports `isModelType()` and `getModelType()` for mixed lists. One upstream ID may have separate chat and image entries. Sources: [models.md](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/models.md#use-classifier-models), [pi-ai types](https://github.com/earendil-works/pi/blob/v1.0.0/packages/ai/src/types.ts).
+
+### Classifier Models
+
+Classifiers do not chat. They answer typed questions about JSON state with probabilities, and do not appear in `/model`.
+
+| Provider | Model IDs | Auth |
+|----------|-----------|------|
+| `typesafe` | `jev-latest` | `TYPESAFE_API_KEY` |
+| `openrouter` | `typesafe/jev-1.13`, `~typesafe/jev-latest` | `OPENROUTER_API_KEY` or `/login` |
+| `cloudflare-workers-ai` | `typesafe/jev` | `CLOUDFLARE_API_KEY` + `CLOUDFLARE_ACCOUNT_ID` |
+| `vercel-ai-gateway` | `typesafe-ai/jev` | `AI_GATEWAY_API_KEY` |
+| `opencode` | `jev-1.13`, `jev-1.13-free` | `OPENCODE_API_KEY` |
+| llama.cpp router | every loaded chat model ID | `/login llama.cpp` |
+
+```typescript
+const jev = ctx.modelRegistry.findOfType("classifier", "typesafe", "jev-latest");
+if (jev) {
+  const result = await ctx.modelRegistry.classify(
+    jev,
+    {
+      state: { message: "The change works, thanks." },
+      questions: {
+        approved: {
+          type: "bool",
+          instructions: "Does the user approve of the result?",
+          criteria: { true: "Approval", false: "No approval" },
+        },
+      },
+    },
+    { signal: ctx.signal },
+  );
+  const answer = result.stopReason === "stop" ? result.answers.approved : undefined;
+  if (answer?.type === "bool") console.log(answer.probability);
+}
+```
+
+- Question types: `choice` (`criteria` maps labels to descriptions; answer has `choice`, `probabilities`, `confidence`), `bool` (`criteria: { true, false }`; answer has `probability`), and `score` (`criteria` is an ordered list; answer has `score`, `confidence`). Pi translates `bool` to TypeSafe's wire format.
+- `classify()` never rejects. Failures and aborts return `stopReason: "error"` or `"aborted"` with `errorMessage`. Check `stopReason` and each answer's `type` before use, and validate probabilities yourself if a decision depends on them (for example finite and within `[0, 1]`).
+- `result.usage` carries token counts and catalog cost when the service reports them; TypeSafe's direct `jev-latest` has no catalog price.
+- `jev-latest` moves with the service. Pin a versioned ID such as `openrouter`'s `typesafe/jev-1.13` when thresholds were tuned against one model.
+- Codemode scripts reach classifiers through `models.classify()` (see `references/codemode.md`). The SDK equivalent is `modelRuntime.classify()`. A llama.cpp classifier accepts a per-request `temperature` to soften overconfident label probabilities.
+
+A gate that fails closed on classifier errors is in `examples/classifier-gate.ts`.
+
+### Image Generation
+
+`ModelRuntime.generateImages(model, { input }, options?)` (Pi 0.99.0) generates images with runtime-resolved auth; list image models with `getModelsOfType("image")`. OpenRouter image models such as `google/gemini-2.5-flash-image` appear under the `openrouter` provider with its credential. Like `classify()`, it returns an error result rather than rejecting. Image models do not appear in `/model`: extensions call `ctx.modelRegistry.generateImages()` and codemode scripts call `models.generateImages()` (both Pi 1.0.0). Codemode adds a script's image usage to its result; an extension tool must report the returned `usage` on its own tool result, combined across calls. `input` takes text blocks plus `{ type: "image", data, mimeType }` blocks to edit or use as references; output images are base64 blocks and are not saved to disk.
+
+In pi-ai, image models live in the same catalog as chat models: `builtinModels()` includes them, `models.getModelOfType("image", provider, id)` finds one (type `ImageModel`), `models.generateImages()` runs it, and `createProvider({ models, images })` registers image implementations. The separate `*Images*` API was removed in pi-ai 0.99.0.
+
+## Virtual Models
+
+A virtual model (experimental, Pi 0.99.0) is a selectable entry that routes each request to a physical model. It is for routing by task, cost, or conversation state, not for permission decisions. Source: [virtual-models.md](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/virtual-models.md), [`jev-router.ts`](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/examples/extensions/jev-router.ts).
+
+```typescript
+pi.registerVirtualModel({
+  provider: "router",
+  id: "auto",
+  name: "Auto",
+  thinkingLevels: ["low", "high"],
+  route(request, ctx) {
+    const sticky = request.failed ?? request.previous;
+    if (request.reason !== "user" && sticky) {
+      return { model: sticky.model, thinkingLevel: sticky.thinkingLevel ?? "medium" };
+    }
+    const id = request.thinkingLevel === "high" ? "claude-sonnet-4-5" : "claude-haiku-4-5";
+    const model = ctx.modelRegistry.find("anthropic", id);
+    if (!model) throw new Error(`anthropic/${id} is not in the catalog`);
+    return { model, thinkingLevel: "medium" };
+  },
+});
+```
+
+- `route()` runs before every request with `reason` (`user`, `continuation`, `retry`, `direct`), `previous`, `failed`, `state`, `messages`, and `signal`. Returning `previous` for continuations and `failed` for retries keeps prompt caches and thinking signatures valid.
+- Returned `state` (JSON) is stored on the session branch and comes back as `request.state`; `direct` requests (compaction summaries, `ctx.modelRegistry.streamSimple()`) have none.
+- The route must be a physical model with credentials; throwing or returning a virtual model ends the request with an error.
+- Selection (`ctx.model`, `model_change`) names the virtual model; each assistant message records the physical `provider`/`model`/`thinkingLevel`. The footer shows both; `/session` lists cost per physical model.
+- `pi.unregisterVirtualModel(provider, id)` removes one (`unregisterProvider()` does not). SDK code can call `modelRuntime.registerVirtualModel(definition)`.
 
 ## Custom Providers via Extensions
 
 Use extensions when you need custom streaming, custom headers, OAuth/device-flow logic, or want to override an existing provider's `baseUrl`/`headers`:
 
+A config-form `models` list replaces the provider's models across chat, image, and classifier operations; image and classifier entries need an explicit `type` and implementations keyed by `api` through `images` and `classifiers`. Registering only `baseUrl` or `headers` keeps the built-in models. See [custom-provider.md](https://github.com/earendil-works/pi/blob/v1.0.0/packages/coding-agent/docs/custom-provider.md).
+
 ```typescript
 // Full registration
 pi.registerProvider("my-provider", {