@code-yeongyu/senpi 2026.9.3 → 2026.9.4-3

package/docs/extensions.md

@@ -650,6 +650,24 @@ pi.on("agent_settled", async (_event, ctx) => {
 });
 ```
 
+#### ui_prompt_start / ui_prompt_end
+
+Notification-only lifecycle events for blocking user-facing extension UI prompts. They fire around `ctx.ui.select()`, `ctx.ui.confirm()`, `ctx.ui.input()`, `ctx.ui.editor()`, and `ctx.ui.custom()` so host/status integrations can report "waiting for user" instead of just "running".
+
+Nested or overlapping prompts are coalesced into one outer waiting span. Handlers are invoked best-effort and are not awaited before showing or closing the prompt.
+
+```typescript
+pi.on("ui_prompt_start", async (event, ctx) => {
+  // event.reason === "ui_prompt"
+  // event.kind: "select" | "confirm" | "input" | "editor" | "custom"
+  // event.title: prompt title when available
+});
+
+pi.on("ui_prompt_end", async (event, ctx) => {
+  // Pi is no longer waiting on that UI prompt span.
+});
+```
+
 #### turn_start / turn_end
 
 Fired for each turn (one LLM response + tool calls).
@@ -1920,7 +1938,7 @@ Typical `sourceInfo.source` values:
 
 ### pi.setModel(model)
 
-Set the current model. Returns `false` if no API key is available for the model. See [models.md](models.md) for configuring custom models.
+Set the model for the current session. The change is recorded in session history and restored when that session is resumed, but it does not change the configured `defaultProvider` or `defaultModel` used by new sessions. Returns `false` if authentication is not configured for the model's provider. See [models.md](models.md) for configuring custom models.
 
 ```typescript
 const model = ctx.modelRegistry.find("anthropic", "claude-sonnet-4-5");
@@ -1934,7 +1952,9 @@ if (model) {
 
 ### pi.getThinkingLevel() / pi.setThinkingLevel(level)
 
-Get or set the thinking level. Level is clamped to model capabilities (non-reasoning models always use "off"). Changes emit `thinking_level_select`.
+Get the current thinking level. Level is clamped to model capabilities (non-reasoning models always use "off"). Changes emit `thinking_level_select`.
+
+`pi.setThinkingLevel()` changes the thinking level for the current session. The change is recorded in session history and restored when that session is resumed, but it does not change the configured default used by new sessions.
 
 ```typescript
 const current = pi.getThinkingLevel();  // "off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max"

package/docs/keybindings.md

@@ -158,7 +158,7 @@ This routing remains configurable through the ordinary action bindings. For exam
 | Keybinding id | Default | Description |
 |--------|---------|-------------|
 | `app.tools.expand` | `ctrl+o` | Collapse or expand tool output |
-| `app.message.copy` | `ctrl+x` | Copy the last assistant message, or the selected message in `/tree` |
+| `app.message.copy` | `ctrl+x` | Copy the selected message in `/tree`; otherwise copy the last assistant message, or the active fullscreen text selection when `fullscreenCopyOnSelect` is disabled |
 | `app.message.followUp` | `alt+enter` | Queue follow-up message |
 | `app.message.dequeue` | `alt+up` | Restore queued messages to editor |
 

package/docs/models.md

@@ -497,6 +497,8 @@ By default senpi sends per-tool `eager_input_streaming: true`. If a proxy or Ant
 
 Some Anthropic models require adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`) instead of the legacy budget-based thinking payload. Built-in models set this automatically. For custom providers or aliases that route to those models, set `forceAdaptiveThinking` to `true`.
 
+Claude models with per-turn effort support use `supportsMidConvoEffort`. Pi then persists each response's provider effort, reconstructs effort-only system messages on later requests, and sends thinking binding controls with `prefix_mismatch_behavior: "drop_block"` to avoid stale signed-thinking prefixes causing persistent 400 responses. Set this only for the exact supported Claude model on a faithful Anthropic Messages transport; do not enable it for APIs that merely imitate the Messages shape.
+
 Some Anthropic-compatible providers emit thinking blocks with empty signatures and still expect them on replay. Set `allowEmptySignature` to `true` only for those providers; real Anthropic rejects empty thinking signatures.
 
 Built-in Anthropic models enable `supportsStrictTools` in their model metadata. Custom Anthropic-compatible models must set it to `true` when their endpoint accepts strict JSON-schema tool definitions.
@@ -533,6 +535,7 @@ Built-in Anthropic models enable `supportsStrictTools` in their model metadata.
 | `sendSessionAffinityHeaders` | Whether to send `x-session-affinity` from the session id when caching is enabled. Default: auto-detected for known providers. |
 | `supportsCacheControlOnTools` | Whether the provider accepts Anthropic-style `cache_control` markers on tool definitions. Default: `true`. |
 | `forceAdaptiveThinking` | Whether to send adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`) for this model. Built-in adaptive models set this automatically. Default: `false`. |
+| `supportsMidConvoEffort` | Whether the exact Claude model transport supports per-turn effort system messages and thinking binding controls. Pi persists native effort levels and always sends `drop_block` when enabled. Default: `false`. |
 | `allowEmptySignature` | Whether to replay empty thinking signatures as `signature: ""` instead of converting thinking to text. Default: `false`. |
 | `supportsStrictTools` | Whether the provider accepts strict JSON-schema tool definitions. Default: `false`; built-in Anthropic models enable it in generated metadata. |
 

package/docs/quickstart.md

@@ -130,7 +130,7 @@ The command output is sent to the model. Use `!!command` to run a command withou
 
 ### Switch models
 
-Use `/model` or Ctrl+L to choose a model. Use Shift+Tab to cycle thinking level. Use Ctrl+P / Shift+Ctrl+P to cycle through favorite models.
+Use `/model` or Ctrl+L to choose a model for the current session. Press Ctrl+S in the model picker to save the highlighted model as the startup default. Use `/thinking` to choose a thinking level for the current session, or Ctrl+S in that picker to save the startup default thinking level. Use Shift+Tab to cycle thinking level. Use Ctrl+P / Shift+Ctrl+P to cycle through favorite models.
 
 ### Continue later
 

package/docs/rpc.md

@@ -39,6 +39,33 @@ Rebranded distributions read the equivalent variable under their configured envi
 `extension_events` opts the client into generic extension-owned event records; clients that omit it
 retain the previous wire stream unchanged.
 
+#### media_placeholders
+
+A client that advertises `media_placeholders` in `set_client_info` tells the host it does not want
+inline media bytes on the wire. For that connection the host replaces every image block inside a
+tool result (`ToolResultMessage.content` and `tool_execution_end.result.content`, including the
+entries carried by `get_entries`, `get_messages`, `get_tree`, `open_session` state and attach-time
+snapshot replay) with an `image_ref` placeholder:
+
+```json
+{
+  "type": "image_ref",
+  "mimeType": "image/png",
+  "byteLength": 553000,
+  "ref": {"toolCallId": "call_abc123", "contentIndex": 1}
+}
+```
+
+`byteLength` is the decoded size of the omitted payload. The original block is fetched on demand with
+[`get_media`](#get_media) using the `ref`. User-authored images (`prompt`/`steer`/`follow_up`
+`images`) are never replaced.
+
+A connection that does not advertise the capability receives byte-identical output to before. The
+capability is advertised by the host in `get_protocol_info.capabilities` in both classic and
+multi-session mode, but the transform itself is applied only by the multi-session host: classic
+single-connection stdio mode never rewrites its output, so a stdio client always receives inline
+media even if it names the capability. `get_media` is answered in both modes.
+
 ## Multi-session mode (D1 wire protocol)
 
 Multi-session mode lets one `senpi --mode rpc` process serve several independent conversations concurrently over the same stdio JSONL stream. Classic single-session mode is byte-identical to today; the only additive classic-mode behavior is that `get_protocol_info` is answered.
@@ -199,6 +226,7 @@ In the response `error` field, machine-matchable:
 - `invalid_path` (relative `sessionPath`/`cwd`)
 - `too_many_sessions` (`open_session` while `SENPI_RPC_MAX_SESSIONS` sessions are already opening/open; attaching to a live session never fails this way)
 - `open_failed: <detail>`
+- `media_not_found` (`get_media` for an unknown `toolCallId`, or a `contentIndex` that does not point at an image block)
 
 ### Tagging
 
@@ -333,7 +361,7 @@ See [set_follow_up_mode](#set_follow_up_mode) for controlling how follow-up mess
 
 #### abort
 
-Abort the current agent operation.
+Abort the current operation and wait for the session to become idle before responding.
 
 ```json
 {"type": "abort"}
@@ -449,6 +477,51 @@ Response:
 
 Messages are `AgentMessage` objects (see [Message Types](#message-types)).
 
+#### get_media
+
+Fetch one media block that was omitted for a [`media_placeholders`](#media_placeholders) client. The
+parameters are exactly the placeholder's `ref`.
+
+```json
+{"type": "get_media", "toolCallId": "call_abc123", "contentIndex": 1}
+```
+
+Response:
+```json
+{
+  "type": "response",
+  "command": "get_media",
+  "success": true,
+  "data": {
+    "toolCallId": "call_abc123",
+    "contentIndex": 1,
+    "content": {"type": "image", "data": "<base64>", "mimeType": "image/png"}
+  }
+}
+```
+
+`content` is the original `ImageContent` block, byte-for-byte. `contentIndex` indexes the tool
+result's `content` array. The host looks the tool call up in the durable session entries first (so a
+block stays fetchable after the live message window moved on), then in the current messages for a
+result that has not been persisted yet.
+
+When the tool call is unknown, the index is out of range, or the index points at a non-image block,
+the response fails with `error` and `errorCode` both set to `media_not_found`:
+
+```json
+{
+  "type": "response",
+  "command": "get_media",
+  "success": false,
+  "error": "media_not_found",
+  "errorCode": "media_not_found"
+}
+```
+
+The command is answered in classic and multi-session mode alike; in multi-session mode it takes the
+usual `sessionId` envelope. It is answerable regardless of whether the connection advertised
+`media_placeholders`.
+
 ### Model
 
 #### set_model
@@ -1709,6 +1782,37 @@ Emitted when an extension throws an error.
 }
 ```
 
+## OAuth login
+
+Logins are fire-command-then-subscribe: the command answers as soon as the flow has started, and the URL plus the terminal result arrive as events.
+
+- `login_start` `{provider}`: responds immediately with `success: true` (flow started). A second `login_start` for the same provider aborts the earlier attempt.
+- `auth_login_url` `{provider, url}`: the URL (or device-code verification URL) the user must open.
+- `auth_login_end` `{provider, success, error?}`: exactly one per login; `error` is a non-secret message.
+- `login_cancel` `{provider}`: aborts the in-flight login; the client then sees `auth_login_end` with `success: false`.
+
+Some providers need input mid-flow (a pasted authorization code, a text or secret value, a choice between accounts). Those prompts reuse the extension UI dialog channel described in the next section:
+
+- `text`, `secret`, and `manual_code` prompts arrive as an `extension_ui_request` with `method: "input"`. `title` is the provider's prompt message and `placeholder` is present when the provider supplied one.
+- `select` prompts arrive with `method: "select"`; `options` holds the option labels.
+
+Answer with `extension_ui_response` `{id, value}`. For `select`, `value` is the chosen label and is mapped back to the option id in-process. Sending `{id, cancelled: true}` cancels the login, and `auth_login_end` reports `success: false` with `error: "Login cancelled"`.
+
+A client that never answers loses nothing. The browser/callback completion path still finishes the login, and the pending request is released when the login ends or is cancelled, so an open dialog never blocks completion. Secrets don't cross the wire in either direction: only the prompt message, placeholder, and labels are emitted, and the answer is consumed in-process and never echoed.
+
+Example exchange (Anthropic, user pastes the code instead of finishing in the browser):
+
+```jsonl
+{"id": "login-1", "type": "login_start", "provider": "anthropic"}
+{"id": "login-1", "type": "response", "command": "login_start", "success": true}
+{"type": "auth_login_url", "provider": "anthropic", "url": "https://claude.ai/oauth/authorize?..."}
+{"type": "extension_ui_request", "id": "uuid-7", "method": "input", "title": "Complete login in your browser, or paste the authorization code / redirect URL here:", "placeholder": "http://localhost:53692/callback"}
+{"type": "extension_ui_response", "id": "uuid-7", "value": "<pasted code>"}
+{"type": "auth_login_end", "provider": "anthropic", "success": true}
+```
+
+If the user completes the flow in the browser instead, the same `extension_ui_request` is emitted, no response is needed, and `auth_login_end` arrives on its own.
+
 ## Extension UI Protocol
 
 Extensions can request user interaction via `ctx.ui.select()`, `ctx.ui.confirm()`, etc. In RPC mode, these are translated into a request/response sub-protocol on top of the base command/event flow.

package/docs/settings.md

@@ -7,7 +7,7 @@ Senpi uses JSON settings files with project settings overriding global settings.
 | `~/.senpi/agent/settings.json` | Global (all projects) |
 | `.senpi/settings.json` | Project (current directory) |
 
-Edit directly or use `/settings` for common options.
+Edit directly or use `/settings` for common options. To save startup model defaults interactively, use `/model` and press Ctrl+S on the desired model. To save the startup thinking level, use `/thinking` and press Ctrl+S.
 
 ## Project Trust
 
@@ -81,15 +81,15 @@ Permission rules are a confirmation policy, not a sandbox. Senpi, extensions, pa
 
 | Setting | Type | Default | Description |
 |---------|------|---------|-------------|
-| `defaultProvider` | string | - | Default provider (e.g., `"anthropic"`, `"openai"`) |
-| `defaultModel` | string | - | Default model ID |
-| `defaultThinkingLevel` | string | - | `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` |
+| `defaultProvider` | string | - | Startup provider (e.g., `"anthropic"`, `"openai"`; saved with Ctrl+S in `/model`, or edited manually) |
+| `defaultModel` | string | - | Startup model ID (saved with Ctrl+S in `/model`, or edited manually) |
+| `defaultThinkingLevel` | string | - | Startup thinking level (saved with Ctrl+S in `/thinking`, or edited manually): `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` |
 | `modelThinkingLevels` | object | - | Per-model reasoning effort memory (`"provider/id": "level"`) |
 | `modelLastOnThinkingLevels` | object | - | Per-model last non-off reasoning level, used by `/reasoning on` to restore the previous effort |
 | `modelServiceTiers` | object | - | Per-model service tier memory (`"provider/id": "auto" \| "priority"`) |
-| `promptPreset` | string | `"auto"` | Force a system prompt preset: `"auto"`, `"kimi-k2-6"`, `"kimi-k2-7"`, `"kimi-k3"`, `"glm-5.2"`, `"glm-5.3"`, `"grok-4.5"`, `"grok-4.6"`, `"claude-fable-5"`, `"claude-fable-5-1"`, `"claude-opus-5"`, `"claude-opus-4-5"`, `"claude-opus-4-6"`, `"claude-opus-4-7"`, `"claude-opus-4-8"`, `"deepseek-v4-flash"`, `"deepseek-v4-flash-0731"`, `"deepseek-v4-pro"`, `"gpt-5"`, `"gpt-5.2"`, `"gpt-5.3-codex"`, `"gpt-5.4"`, `"gpt-5.5"`, or `"gpt-5.6"` |
+| `promptPreset` | string | `"auto"` | Force a system prompt preset: `"auto"`, `"kimi-k2-6"`, `"kimi-k2-7"`, `"kimi-k3"`, `"glm-5.2"`, `"glm-5.3"`, `"grok-4.5"`, `"grok-4.6"`, `"claude-fable-5"`, `"claude-fable-5-1"`, `"claude-opus-5"`, `"claude-opus-4-5"`, `"claude-opus-4-6"`, `"claude-opus-4-7"`, `"claude-opus-4-8"`, `"deepseek-v4-flash"`, `"deepseek-v4-flash-0731"`, `"deepseek-v4-pro"`, `"gpt-5"`, `"gpt-5.2"`, `"gpt-5.3-codex"`, `"gpt-5.4"`, `"gpt-5.5"`, `"gpt-5.6"`, or `"gpt-6-astra"` |
 | `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output |
-| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses and compaction or branch-summary usage |
+| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses, compaction or branch-summary usage, and provider recovery diagnostics such as dropped Anthropic thinking blocks |
 | `thinkingBudgets` | object | - | Custom token budgets per thinking level. Anthropic, Google, and Bedrock use these natively. OpenAI-compatible models use them when `compat.thinkingTokenBudgetField` (or `supportsThinkingTokenBudget`) is set. |
 
 #### promptPreset
@@ -141,6 +141,7 @@ When this value is anything other than `"auto"`, it overrides any model-level `p
 | `tuiMode` | string | `"regular"` | Interactive TUI mode: `"regular"` or experimental `"fullscreen"`. Changes from `/settings` apply immediately; `--tui-mode` overrides this setting at startup |
 | `fullscreenExitOutput` | string | `"transcript"` | Fullscreen exit output: `"transcript"` prints the final transcript and resume hint, while `"resume-hint"` restores the previous screen and prints only the resume hint. Has no effect in regular TUI mode |
 | `fullscreenScrollbar` | string | `"auto"` | Fullscreen transcript scrollbar: `"auto"` shows it temporarily while scrolling, `"always"` reserves the rightmost column and keeps it visible, and `"hidden"` hides it. Has no effect in regular TUI mode |
+| `fullscreenCopyOnSelect` | boolean | `true` | Automatically copy selected text in fullscreen mode. When disabled, selections stay highlighted and `Ctrl+X` copies the active selection |
 
 For VS Code, include `--wait` so senpi resumes after the editor exits:
 
@@ -346,6 +347,9 @@ Both ambient-auth providers are explicit opt-in: a vendor CLI being logged in on
 | `terminal.showImages` | boolean | `true` | Show images in terminal (if supported) |
 | `terminal.imageWidthCells` | number | `60` | Preferred inline image width in terminal cells |
 | `terminal.clearOnShrink` | boolean | `false` | Clear empty rows when content shrinks (can cause flicker) |
+| `terminal.hyperlinks` | boolean or `"auto"` | `"auto"` | Override OSC 8 hyperlink support (advanced, JSON-only) |
+| `terminal.images` | string or boolean | `"auto"` | Override image protocol support with `"kitty"`, `"iterm2"`, `false`, or `"auto"` (advanced, JSON-only) |
+| `terminal.trueColor` | boolean or `"auto"` | `"auto"` | Override truecolor support (advanced, JSON-only) |
 | `images.autoResize` | boolean | `true` | Resize images to 2000x2000 max. Applies to `@file` attachments, `read`, and images returned by tools |
 | `images.blockImages` | boolean | `false` | Block all images from being sent to LLM |
 
@@ -399,8 +403,6 @@ Windows paths in JSON must use forward slashes or escaped backslashes:
 | Setting | Type | Default | Description |
 |---------|------|---------|-------------|
 | `defaultTools` | string[] | - | Built-in tools enabled initially. When omitted, Pi uses its standard defaults |
-| `experimental.bashEvalOnly` | boolean | `false` | Route `bash` and `powershell` through eval cells only; the tools leave the model's direct tool list |
-| `experimental.workflowEvalOnly` | boolean | `false` | Route the workflow (dag) tool through eval cells only; the tool leaves the model direct tool list |
 
 `defaultTools` selects the built-in tools enabled at startup. Extension and SDK custom tools remain enabled. Available built-ins are `read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, and `ls`:
 
@@ -420,37 +422,17 @@ On Windows, select `powershell` instead of `bash`, or include both:
 
 An empty array starts with no built-in tools while preserving extension and SDK custom tools. `--tools` replaces this behavior with a strict allowlist for all tools, `--no-tools` disables all tools, and `--no-builtin-tools` disables the built-in defaults. `--exclude-tools` filters the resulting list. A project `defaultTools` array replaces the global array.
 
-With `experimental.bashEvalOnly` enabled, the `bash` and `powershell` tools disappear from the model's direct tool list and run only inside eval cells:
+#### Eval-only tools
 
-```json
-{
-  "experimental": {
-    "bashEvalOnly": true
-  }
-}
-```
+Whenever the `eval` tool is available (codemode loaded), `bash`, `powershell`, `workflow` and `monitor` leave the model's direct tool list and run only inside eval cells:
 
 ```js
 const { output } = await tool.bash({ command: "ls -la" });
-```
-
-Hooks and permission checks apply unchanged to shell commands run this way. If the model hallucinates a direct `bash` or `powershell` call anyway, the call returns a hint redirecting it to an eval cell. When the `eval` tool is unavailable (codemode not loaded), the policy auto-disables and both tools stay on the direct tool list, so shell access is never lost.
-
-With `experimental.workflowEvalOnly` enabled, the `workflow` (dag) tool disappears from the model's direct tool list and runs only inside eval cells:
-
-```json
-{
-  "experimental": {
-    "workflowEvalOnly": true
-  }
-}
-```
-
-```js
 const snapshot = await tool.workflow({ action: "snapshot", run_id });
+await tool.monitor({ description: "build", command: "bun run build", filter: "^done" });
 ```
 
-Hooks and permission checks apply unchanged to workflow operations run this way. When the `eval` tool is unavailable (codemode not loaded), the policy auto-disables and the workflow tool stays on the direct tool list, so workflow access is never lost.
+This is the default and has no setting. Hooks and permission checks apply unchanged to calls made this way, and the prompt surfaces that document these tools render the `tool.<name>(` form to match. If the model attempts a direct call anyway, the call returns a hint naming the eval form. When the `eval` tool is unavailable (codemode not loaded, or a child agent whose allowlist omits it), the policy stays inert and all four tools remain directly callable, so shell, workflow and monitor access is never lost.
 
 ### Sessions
 
@@ -597,6 +579,9 @@ See [packages.md](packages.md) for package management details.
   "defaultProvider": "anthropic",
   "defaultModel": "claude-sonnet-4-20250514",
   "defaultThinkingLevel": "medium",
+  "modelThinkingLevels": {
+    "anthropic/claude-sonnet-4-20250514": "high"
+  },
   "theme": "dark",
   "compaction": {
     "enabled": true,

package/docs/terminal-setup.md

@@ -2,6 +2,18 @@
 
 Pi uses the [Kitty keyboard protocol](https://sw.kovidgoyal.net/kitty/keyboard-protocol/) for reliable modifier key detection. Most modern terminals support this protocol, but some require configuration.
 
+## Capability Overrides
+
+Pi auto-detects OSC 8 hyperlinks, inline image protocols, and truecolor. If detection fails behind a terminal proxy or multiplexer, use these advanced overrides:
+
+| Capability | Environment variable | JSON setting |
+|------------|----------------------|--------------|
+| OSC 8 hyperlinks | `PI_HYPERLINKS=1\|0\|auto` | `terminal.hyperlinks: true\|false\|"auto"` |
+| Inline images | `PI_IMAGE_PROTOCOL=kitty\|iterm2\|none\|auto` | `terminal.images: "kitty"\|"iterm2"\|false\|"auto"` |
+| Truecolor | `PI_TRUE_COLOR=1\|0\|auto` | `terminal.trueColor: true\|false\|"auto"` |
+
+Settings take precedence over environment variables; unset or `auto` preserves detection. Only force capabilities supported by the complete terminal path, since unsupported escape sequences can corrupt rendering.
+
 ## Kitty
 
 Works out of the box.
@@ -118,6 +130,21 @@ Add to `keybindings.json`:
 }
 ```
 
+## Zed (Integrated Terminal)
+
+Add these key bindings to your Zed `keymap.json`:
+
+```json
+{
+  "context": "Terminal",
+  "bindings": {
+    "shift-enter": ["terminal::SendText", "\u001b[13;2u"],
+    "ctrl--": ["terminal::SendText", "\u001b[45;5u"],
+    "ctrl-alt-]": ["terminal::SendText", "\u001b[93;7u"]
+  }
+}
+```
+
 ## Windows Terminal
 
 Pi uses Windows-style keybindings when running natively on Windows or in WSL:

package/docs/usage.md

@@ -22,10 +22,11 @@ The editor can be replaced temporarily by built-in UI such as `/settings` or by
 | File reference | Type `@` to fuzzy-search project files |
 | Path completion | Press Tab to complete paths |
 | Multi-line input | Shift+Enter, or Ctrl+Enter on Windows Terminal |
-| Copy response | Ctrl+X copies the last assistant message; in `/tree`, it copies the selected message |
+| Copy response | Ctrl+X copies the selected message in `/tree`; otherwise it copies the last assistant message, or the active fullscreen text selection when `fullscreenCopyOnSelect` is disabled |
 | Images | Paste with Ctrl+V, Alt+V on Windows, or drag into the terminal |
 | Shell command | `!command` runs and sends output to the model |
 | Hidden shell command | `!!command` runs without sending output to the model |
+| Manual continue | Type `.` alone to resume the most recent intent without sending a new user message |
 | External editor | Ctrl+G opens `externalEditor`, `$VISUAL`, `$EDITOR`, Notepad on Windows, or `nano` elsewhere |
 | Shortcut overlay | Type `?` on an empty editor to show a dismissible shortcut grid |
 | Startup tips | A rotating `Tip:` line in the startup banner and under the working status teaches features; disable with `"tips": false` |
@@ -40,12 +41,13 @@ Type `/` in the editor to open command completion. Extensions can register custo
 |---------|-------------|
 | `/login`, `/logout` | Manage OAuth or API-key credentials |
 | [`/llama`](llama-cpp.md) | Download, load, and unload llama.cpp router models |
-| `/model` | Switch models |
+| `/model` | Switch models; Ctrl+S in the picker saves the startup default |
+| `/thinking` | Switch thinking level; Ctrl+S in the picker saves the startup default |
 | `/scoped-models` | Enable/disable models for Ctrl+P cycling |
 | `/reasoning [on\|off]` | Show or toggle reasoning for the current model |
 | `/efforts [level]` | Show or set reasoning effort (graded models only) |
 | `/fast [on\|off]` | Toggle fast mode (OpenAI Codex models, persisted per model) |
-| `/settings` | Thinking level, theme, message delivery, transport |
+| `/settings` | Theme, message delivery, transport, and other preferences |
 | `/resume` | Pick from previous sessions |
 | `/new` | Start a new session |
 | `/name <name>` | Set session display name |

package/docs/windows.md

@@ -30,7 +30,7 @@ Or enable both while comparing behavior:
 
 The `!` and `!!` editor commands still use Bash.
 
-With `experimental.bashEvalOnly` enabled, both `bash` and `powershell` run only inside eval cells; see [Settings](settings.md#tools).
+Whenever the `eval` tool is available, both `bash` and `powershell` run only inside eval cells; see [Settings](settings.md#tools).
 
 ## Custom Bash Path
 

package/node_modules/@anthropic-ai/claude-agent-sdk/bridge.d.ts

@@ -158,12 +158,29 @@ export type AttachBridgeSessionOptions = {
      * then answers with a "not supported in this context" error.
      */
     onStopTask?: (taskId: string) => Promise<void>;
+    /**
+     * `background_tasks` from claude.ai — the client's Ctrl+B. With a
+     * toolUseId, background the single foreground task that tool_use block
+     * started and return whether one was found; without, background every
+     * foreground task and return true. May answer asynchronously (e.g. by
+     * delegating to `Query.backgroundTasks()`); a rejection is sent as an
+     * error reply. Omit if the host has no task registry — the CLI then
+     * answers with a "not supported in this context" error.
+     */
+    onBackgroundTasks?: (toolUseId: string | undefined) => boolean | Promise<boolean>;
     onSetModel?: (model: string | undefined) => {
         ok: true;
+        notices?: string[];
+    } | {
+        ok: false;
+        error: string;
+    } | void | Promise<{
+        ok: true;
+        notices?: string[];
     } | {
         ok: false;
         error: string;
-    } | void;
+    }>;
     onSetMaxThinkingTokens?: (tokens: number | null | undefined, thinkingDisplay?: 'summarized' | 'omitted' | null) => void;
     /**
      * `set_permission_mode` from claude.ai. Return an error verdict to send