@code-yeongyu/senpi 2026.6.6-3 → 2026.6.10-2

package/docs/compaction-guide.md

@@ -1,10 +1,10 @@
 # Compaction Guide
 
-Pi's compaction system helps you work on complex tasks that would otherwise exceed the LLM's context window. This guide explains how compaction works from a user perspective and how to get the most out of it.
+Senpi's compaction system helps you work on complex tasks that would otherwise exceed the LLM's context window. This guide explains how compaction works from a user perspective and how to get the most out of it.
 
 ## What is Compaction?
 
-LLMs have finite context windows. When conversations grow too long, pi uses compaction to summarize older messages while preserving recent ones. Think of it like taking notes during a long meeting: you write down the key decisions and next steps so you can continue the conversation without remembering every word that was said.
+LLMs have finite context windows. When conversations grow too long, senpi uses compaction to summarize older messages while preserving recent ones. Think of it like taking notes during a long meeting: you write down the key decisions and next steps so you can continue the conversation without remembering every word that was said.
 
 Compaction happens automatically when needed, or you can trigger it manually with the `/compact` command.
 
@@ -12,7 +12,7 @@ Compaction happens automatically when needed, or you can trigger it manually wit
 
 ### Automatic Compaction
 
-When the conversation approaches the context limit, pi automatically compacts older messages. You'll see a `[compaction]` message in the TUI with a summary like "Compacted from 45000 tokens". The conversation continues seamlessly.
+When the conversation approaches the context limit, senpi automatically compacts older messages. You'll see a `[compaction]` message in the TUI with a summary like "Compacted from 45000 tokens". The conversation continues without interruption.
 
 ### Manual Compaction
 
@@ -98,11 +98,11 @@ path/to/changed.ts
 
 ## Branch Summarization
 
-When you use `/tree` to switch to a different branch, pi offers to summarize the work you're leaving behind. This injects context from the abandoned branch into your new position.
+When you use `/tree` to switch to a different branch, senpi offers to summarize the work you're leaving behind. This injects context from the abandoned branch into your new position.
 
 ### User Experience
 
-After selecting a target in `/tree`, pi asks: "Summarize branch?" You have three options:
+After selecting a target in `/tree`, senpi asks: "Summarize branch?" You have three options:
 
 1. **No summary** - Switch immediately
 2. **Summarize** - Generate a summary using the default prompt
@@ -112,7 +112,7 @@ The summary appears as a `branch_summary` entry in your new branch, providing co
 
 ### Skipping the Prompt
 
-If you frequently switch branches and don't want the prompt, set `branchSummary.skipPrompt: true` in your settings. Pi will switch branches without asking.
+If you frequently switch branches and don't want the prompt, set `branchSummary.skipPrompt: true` in your settings. Senpi will switch branches without asking.
 
 ## Settings & Tuning
 
@@ -162,7 +162,7 @@ Check if compaction happened recently (look for the `[compaction]` marker). Expa
 
 ### Long Sessions Are Fine
 
-Compaction lets sessions run indefinitely. Don't worry about starting fresh sessions just to manage context. Pi handles it automatically.
+Compaction lets sessions run indefinitely. Don't worry about starting fresh sessions just to manage context. Senpi handles it automatically.
 
 ### If Something Gets Forgotten
 
@@ -235,6 +235,6 @@ Yes. The full history is in your session file. Use `/tree` to navigate to any po
 
 - [`compaction.md`](compaction.md) - Technical internals and extension hooks
 - [`settings.md`](settings.md) - Complete settings reference
-- [`tree.md`](tree.md) - Session tree navigation
+- [`sessions.md`](sessions.md) - Session tree navigation
 - [`extensions.md`](extensions.md) - Extension API for custom compaction
-- [`session.md`](session.md) - Session file format
+- [`session-format.md`](session-format.md) - Session file format

package/docs/compaction.md

@@ -13,7 +13,7 @@ For TypeScript definitions in your project, inspect `node_modules/@code-yeongyu/
 
 ## Overview
 
-Pi has two summarization mechanisms:
+Senpi has two summarization mechanisms:
 
 | Mechanism | Trigger | Purpose |
 |-----------|---------|---------|
@@ -76,7 +76,7 @@ What the LLM sees:
     prompt   from cmp          messages from firstKeptEntryId
 ```
 
-On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. Pi also recalculates `tokensBefore` from the rebuilt session context before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced.
+On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. Senpi also recalculates `tokensBefore` from the rebuilt session context before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced.
 
 ### Split Turns
 

package/docs/containerization.md

@@ -3,18 +3,18 @@
 Pi runs with all permissions by default, but in some cases, you will want to have more control over what directories Pi can write to and which accesses it has.
 
 There are two general options. You can either
-1. run the whole `pi` process inside an isolated environment, or
-2. run `pi` on the host and route tool execution into an isolated environment.
+1. run the whole `senpi` process inside an isolated environment, or
+2. run `senpi` on the host and route tool execution into an isolated environment.
 
 ## Choose a pattern
 
 | Pattern | What is isolated | Best for | Notes |
 | --- | --- | --- | --- |
-| OpenShell | Whole `pi` process in a policy-controlled sandbox | Local or remote managed sandbox | Requires an OpenShell gateway |
+| OpenShell | Whole `senpi` process in a policy-controlled sandbox | Local or remote managed sandbox | Requires an OpenShell gateway |
 | Gondolin extension | Built-in tools and `!` commands | Local micro-VM isolation while keeping auth on host | See [`examples/extensions/gondolin/`](../examples/extensions/gondolin/). |
-| Plain Docker | Whole `pi` process in a local container | Simple local isolation | Provider API keys enter the container. |
+| Plain Docker | Whole `senpi` process in a local container | Simple local isolation | Provider API keys enter the container. |
 
-Extensions run wherever the `pi` process runs. If you run host `pi` with a tool-routing extension, other custom extension tools still run on the host unless they also delegate their operations.
+Extensions run wherever the `senpi` process runs. If you run host `senpi` with a tool-routing extension, other custom extension tools still run on the host unless they also delegate their operations.
 
 ## OpenShell
 
@@ -29,21 +29,21 @@ openshell gateway add <gateway-url> --name <name>
 openshell gateway select <name>
 ```
 
-Launch `pi` inside an OpenShell sandbox:
+Launch `senpi` inside an OpenShell sandbox:
 
 ```bash
-openshell sandbox create --name pi-sandbox --from pi -- pi
+openshell sandbox create --name senpi-sandbox --from senpi -- senpi
 ```
 
-In this pattern, the whole `pi` process runs inside the sandbox.
+In this pattern, the whole `senpi` process runs inside the sandbox.
 Built-in tools, `!` commands, and extension tools execute inside the OpenShell boundary.
 
 If the gateway is remote, project files are not bind-mounted from the host, meaning writes in the sandbox are not reflected on your machine.
 Clone the repository inside the sandbox or use OpenShell file transfer commands:
 
 ```bash
-openshell sandbox upload pi-sandbox ./repo /workspace
-openshell sandbox download pi-sandbox /workspace/repo ./repo-out
+openshell sandbox upload senpi-sandbox ./repo /workspace
+openshell sandbox download senpi-sandbox /workspace/repo ./repo-out
 ```
 
 OpenShell providers can keep raw model API keys outside the sandbox.
@@ -53,13 +53,13 @@ Configure Pi to use the corresponding OpenAI-compatible or Anthropic-compatible
 ## Gondolin
 
 [Gondolin](https://github.com/earendil-works/gondolin) is a local Linux micro-VM.
-Use the [example extension](../examples/extensions/gondolin) when you want `pi` on the host but all built-in tools routed into the VM.
+Use the [example extension](../examples/extensions/gondolin) when you want `senpi` on the host but all built-in tools routed into the VM.
 
 Setup:
 
 ```bash
-cp -R packages/coding-agent/examples/extensions/gondolin ~/.pi/agent/extensions/gondolin
-cd ~/.pi/agent/extensions/gondolin
+cp -R packages/coding-agent/examples/extensions/gondolin ~/.senpi/agent/extensions/gondolin
+cd ~/.senpi/agent/extensions/gondolin
 npm install --ignore-scripts
 ```
 
@@ -67,7 +67,7 @@ Run from the project you want mounted:
 
 ```bash
 cd /path/to/project
-pi -e ~/.pi/agent/extensions/gondolin
+senpi -e ~/.senpi/agent/extensions/gondolin
 ```
 
 The extension mounts the host cwd at `/workspace` in the VM and overrides `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`.
@@ -78,9 +78,9 @@ Requirements: Node.js >= 23.6.0 for `@earendil-works/gondolin`, plus QEMU (requi
 
 ## Plain Docker
 
-Run the whole `pi` process in Docker when you want the simplest local container boundary.
+Run the whole `senpi` process in Docker when you want the simplest local container boundary.
 
-`Dockerfile.pi`:
+`Dockerfile.senpi`:
 
 ```dockerfile
 FROM node:24-bookworm-slim
@@ -88,24 +88,24 @@ FROM node:24-bookworm-slim
 RUN apt-get update \
   && apt-get install -y --no-install-recommends bash ca-certificates git ripgrep \
   && rm -rf /var/lib/apt/lists/*
-RUN npm install -g --ignore-scripts @earendil-works/pi-coding-agent
+RUN npm install -g --ignore-scripts @code-yeongyu/senpi
 
 WORKDIR /workspace
-ENTRYPOINT ["pi"]
+ENTRYPOINT ["senpi"]
 ```
 
 Build and run:
 
 ```bash
-docker build -t pi-sandbox -f Dockerfile.pi .
+docker build -t senpi-sandbox -f Dockerfile.senpi .
 
 docker run --rm -it \
   -e ANTHROPIC_API_KEY \
   -v "$PWD:/workspace" \
-  -v pi-agent-home:/root/.pi/agent \
-  pi-sandbox
+  -v senpi-agent-home:/root/.senpi/agent \
+  senpi-sandbox
 ```
 
 The `-v "$PWD:/workspace"` mounts your current directory into the container at /workspace such that reads and writes in `/workspace` inside Docker directly affect your host files, like in the Gondolin example.
 
-Use a named volume for `/root/.pi/agent` if you want container-local settings and sessions. Mounting your host `~/.pi/agent` exposes host auth and session files to the container.
+Use a named volume for `/root/.senpi/agent` if you want container-local settings and sessions. Mounting your host `~/.senpi/agent` exposes host auth and session files to the container.

package/docs/custom-provider.md

@@ -372,12 +372,12 @@ interface OAuthCredentials {
 For providers with non-standard APIs, implement `streamSimple`. Study the existing provider implementations before writing your own:
 
 **Reference implementations:**
-- [anthropic.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/anthropic.ts) - Anthropic Messages API
-- [mistral.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/mistral.ts) - Mistral Conversations API
-- [openai-completions.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/openai-completions.ts) - OpenAI Chat Completions
-- [openai-responses.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/openai-responses.ts) - OpenAI Responses API
-- [google.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/google.ts) - Google Generative AI
-- [amazon-bedrock.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/providers/amazon-bedrock.ts) - AWS Bedrock
+- [anthropic.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/anthropic.ts) - Anthropic Messages API
+- [mistral.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/mistral.ts) - Mistral Conversations API
+- [openai-completions.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/openai-completions.ts) - OpenAI Chat Completions
+- [openai-responses.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/openai-responses.ts) - OpenAI Responses API
+- [google.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/google.ts) - Google Generative AI
+- [amazon-bedrock.ts](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/providers/amazon-bedrock.ts) - AWS Bedrock
 
 ### Stream Pattern
 
@@ -535,14 +535,14 @@ calculateCost(model, output.usage);
 
 ### Context Overflow Errors
 
-When a request exceeds the model's context window, pi can recover automatically by compacting the conversation and retrying. This recovery only kicks in if pi recognizes the failure as an overflow.
+When a request exceeds the model's context window, senpi can recover automatically by compacting the conversation and retrying. This recovery only kicks in if senpi recognizes the failure as an overflow.
 
 Detection runs on the finalized assistant message:
 
 - `stopReason === "error"`
-- `errorMessage` matches one of pi's known overflow patterns (see [`packages/ai/src/utils/overflow.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/utils/overflow.ts))
+- `errorMessage` matches one of senpi's known overflow patterns (see [`packages/ai/src/utils/overflow.ts`](https://github.com/code-yeongyu/senpi/blob/main/packages/ai/src/utils/overflow.ts))
 
-If your provider returns overflow errors with a message pi does not recognize, normalize the error from the same extension that registers the provider. Use a `message_end` handler to rewrite the assistant message so its `errorMessage` starts with a phrase pi recognizes. The generic fallback `context_length_exceeded` is the safest choice.
+If your provider returns overflow errors with a message senpi does not recognize, normalize the error from the same extension that registers the provider. Use a `message_end` handler to rewrite the assistant message so its `errorMessage` starts with a phrase senpi recognizes. The generic fallback `context_length_exceeded` is the safest choice.
 
 ```typescript
 const MY_PROVIDER_OVERFLOW_PATTERN = /your provider's overflow phrase/i;
@@ -574,7 +574,7 @@ export default function (pi: ExtensionAPI) {
 }
 ```
 
-`message_end` runs before pi tracks the assistant message for auto-compaction, so the rewritten `errorMessage` is what pi checks. With this in place, pi will:
+`message_end` runs before senpi tracks the assistant message for auto-compaction, so the rewritten `errorMessage` is what senpi checks. With this in place, senpi will:
 
 1. Detect the overflow from `errorMessage`.
 2. Drop the failed assistant message from live context.
@@ -584,7 +584,7 @@ export default function (pi: ExtensionAPI) {
 Guard the rewrite carefully:
 
 - Scope it to your provider (`message.provider` and `ctx.model?.provider`) so unrelated errors from other providers are untouched.
-- Match a provider-specific pattern, not pi's generic overflow patterns. Rewriting rate-limit or throttling errors (`rate limit`, `too many requests`) would falsely trigger compaction instead of pi's normal retry-with-backoff path.
+- Match a provider-specific pattern, not senpi's generic overflow patterns. Rewriting rate-limit or throttling errors (`rate limit`, `too many requests`) would falsely trigger compaction instead of senpi's normal retry-with-backoff path.
 - Skip when `errorMessage` already includes `context_length_exceeded` so the handler is idempotent.
 
 ### Registration
@@ -603,7 +603,7 @@ pi.registerProvider("my-provider", {
 
 ## Testing Your Implementation
 
-Test your provider against the same test suites used by built-in providers. Copy and adapt these test files from [packages/ai/test/](https://github.com/earendil-works/pi-mono/tree/main/packages/ai/test):
+Test your provider against the same test suites used by built-in providers. Copy and adapt these test files from [packages/ai/test/](https://github.com/code-yeongyu/senpi/tree/main/packages/ai/test):
 
 | Test | Purpose |
 |------|---------|
@@ -612,7 +612,7 @@ Test your provider against the same test suites used by built-in providers. Copy
 | `abort.test.ts` | AbortSignal handling |
 | `empty.test.ts` | Empty/minimal responses |
 | `context-overflow.test.ts` | Context window limits |
-| `image-limits.test.ts` | Image input handling |
+| `images.test.ts` | Image input handling |
 | `unicode-surrogate.test.ts` | Unicode edge cases |
 | `tool-call-without-result.test.ts` | Tool call edge cases |
 | `image-tool-result.test.ts` | Images in tool results |

package/docs/development.md

@@ -41,7 +41,7 @@ Three execution modes: npm install, standalone binary (`bun build --compile`), t
 **Always use `src/config.ts`** for package assets:
 
 ```typescript
-import { getPackageDir, getThemeDir } from "./config.js";
+import { getPackageDir, getThemesDir } from "./config.js";
 ```
 
 Never use `__dirname` directly for package assets.
@@ -56,10 +56,12 @@ Never use `__dirname` directly for package assets.
 
 ```bash
 npm test            # Vitest across workspaces (skips live-API; default test runner)
-./pi-test.sh        # Live-API integration suite (env-gated; requires API keys)
+./pi-test.sh        # Launch the CLI from source via tsx for manual testing (--no-env unsets API keys)
 npm run check       # Biome + tsgo + browser-smoke + web-ui check (pre-commit equivalent)
 ```
 
+Live-API tests are env-gated vitest tests. Set `PI_ENABLE_LIVE_API_TESTS=1` (or a per-provider flag from `packages/ai/test/live-api-gates.ts`) plus the provider API keys, then run `npm test`.
+
 Run a specific test:
 
 ```bash

package/docs/docs.json

@@ -19,6 +19,10 @@
           "title": "Providers",
           "path": "providers.md"
         },
+        {
+          "title": "Security",
+          "path": "security.md"
+        },
         {
           "title": "Containerization",
           "path": "containerization.md"

package/docs/extensions.md

@@ -2,7 +2,7 @@
 
 # Extensions
 
-Extensions are TypeScript modules that extend pi's behavior. They can subscribe to lifecycle events, register custom tools callable by the LLM, add commands, and more.
+Extensions are TypeScript modules that extend senpi's behavior. They can subscribe to lifecycle events, register custom tools callable by the LLM, add commands, and more.
 
 > **Placement for /reload:** Put extensions in `~/.senpi/agent/extensions/` (global) or `.senpi/extensions/` (project-local) for auto-discovery. Use `senpi -e ./path.ts` only for quick tests. Extensions in auto-discovered locations can be hot-reloaded with `/reload`.
 
@@ -102,14 +102,14 @@ export default function (pi: ExtensionAPI) {
 Test with `--extension` (or `-e`) flag:
 
 ```bash
-pi -e ./my-extension.ts
+senpi -e ./my-extension.ts
 ```
 
 ## Extension Locations
 
 > **Security:** Extensions run with your full system permissions and can execute arbitrary code. Only install from sources you trust.
 
-Extensions are auto-discovered from trusted locations. Project-local `.pi/extensions` entries load only after the project is trusted.
+Extensions are auto-discovered from trusted locations. Project-local `.senpi/extensions` entries load only after the project is trusted.
 
 | Location | Scope |
 |----------|-------|
@@ -268,8 +268,9 @@ Run `npm install` in the extension directory, then imports from `node_modules/`
 ### Lifecycle Overview
 
 ```
-pi starts
+senpi starts
   │
+  ├─► project_trust (user/global and CLI extensions only, before project resources load)
   ├─► session_start { reason: "startup" }
   └─► resources_discover { reason: "startup" }
       │
@@ -334,6 +335,25 @@ exit (Ctrl+C, Ctrl+D, SIGHUP, SIGTERM)
   └─► session_shutdown
 ```
 
+### Startup Events
+
+#### project_trust
+
+Fired before senpi decides whether to trust a project with dynamic configs (`.senpi` or `.agents/skills`). It runs during startup and when session replacement (for example `/resume`) enters a cwd whose trust has not been resolved in the current process. Only user/global extensions and CLI `-e` extensions participate; project-local extensions are not loaded until after trust is resolved.
+
+```typescript
+pi.on("project_trust", async (event, ctx) => {
+  // event.cwd - current working directory
+  // ctx has a limited trust context: cwd, mode, hasUI, and select/confirm/input/notify UI helpers
+  if (await ctx.ui.confirm("Trust project?", event.cwd)) {
+    return { trusted: "yes", remember: true };
+  }
+  return { trusted: "undecided" };
+});
+```
+
+A `project_trust` handler must return `{ trusted: "yes" | "no" | "undecided" }`. A user/global or CLI extension that returns `"yes"` or `"no"` owns the decision; the first yes/no decision wins and suppresses the built-in trust prompt. Use `remember: true` to persist a yes/no decision; otherwise it applies only to the current process. Return `"undecided"` to let later handlers or the built-in trust flow decide. Check `ctx.hasUI` before prompting. If no handler returns yes/no, normal trust resolution continues: saved `trust.json` decisions apply first, then `defaultProjectTrust` controls whether senpi asks, trusts, or declines by default.
+
 ### Resource Events
 
 #### resources_discover
@@ -474,7 +494,7 @@ pi.on("before_agent_start", async (event, ctx) => {
   // event.systemPrompt - current chained system prompt for this handler
   //   (includes changes from earlier before_agent_start handlers)
   // event.systemPromptOptions - structured options used to build the system prompt
-  //   .customPrompt - any custom system prompt (from --system-prompt, SYSTEM.md, or custom templates)
+  //   .customPrompt - any custom system prompt (from --system-prompt or custom templates)
   //   .selectedTools - tools currently active in the prompt
   //   .toolSnippets - one-line descriptions for each tool
   //   .promptGuidelines - custom guideline bullets
@@ -496,7 +516,7 @@ pi.on("before_agent_start", async (event, ctx) => {
 });
 ```
 
-The `systemPromptOptions` field gives extensions access to the same structured data Pi uses to build the system prompt. This lets you inspect what Pi has loaded — custom prompts, guidelines, tool snippets, context files, skills — without re-discovering resources or re-parsing flags. Use it when your extension needs to make deep, informed changes to the system prompt while respecting user-provided configuration.
+The `systemPromptOptions` field gives extensions access to the same structured data senpi uses to build the system prompt. This lets you inspect what senpi has loaded — custom prompts, guidelines, tool snippets, context files, skills — without re-discovering resources or re-parsing flags. Use it when your extension needs to make deep, informed changes to the system prompt while respecting user-provided configuration.
 
 Inside `before_agent_start`, `event.systemPrompt` and `ctx.getSystemPrompt()` both reflect the chained system prompt as of the current handler. Later `before_agent_start` handlers can still modify it again.
 
@@ -602,7 +622,7 @@ pi.on("context", async (event, ctx) => {
 
 Fired after the provider-specific payload is built, right before the request is sent. Handlers run in extension load order. Returning `undefined` keeps the payload unchanged. Returning any other value replaces the payload for later handlers and for the actual request.
 
-This hook can rewrite provider-level system instructions or remove them entirely. Those payload-level changes are not reflected by `ctx.getSystemPrompt()`, which reports Pi's system prompt string rather than the final serialized provider payload.
+This hook can rewrite provider-level system instructions or remove them entirely. Those payload-level changes are not reflected by `ctx.getSystemPrompt()`, which reports senpi's system prompt string rather than the final serialized provider payload.
 
 ```typescript
 pi.on("before_provider_request", (event, ctx) => {
@@ -786,7 +806,7 @@ pi.on("user_bash", (event, ctx) => {
   // Option 1: Provide custom operations (e.g., SSH)
   return { operations: remoteBashOps };
 
-  // Option 2: Wrap pi's built-in local bash backend
+  // Option 2: Wrap senpi's built-in local bash backend
   const local = createLocalBashOperations();
   return {
     operations: {
@@ -872,6 +892,12 @@ Current run mode: `"tui"`, `"rpc"`, `"json"`, or `"print"`. Use `ctx.mode === "t
 
 Current working directory.
 
+### ctx.isProjectTrusted()
+
+Returns whether project-local trust is active for the current session context. This includes temporary trust decisions and CLI trust overrides, not just saved decisions in the global trust store.
+
+Use this before reading project-local extension configuration that should only be honored for trusted projects.
+
 ### ctx.sessionManager
 
 Read-only access to session state. See [Session Format](session-format.md) for the full SessionManager API and entry types.
@@ -919,7 +945,7 @@ Control flow helpers.
 
 ### ctx.shutdown()
 
-Request a graceful shutdown of pi.
+Request a graceful shutdown of senpi.
 
 - **Interactive mode:** Deferred until the agent becomes idle (after processing all queued steering and follow-up messages).
 - **RPC mode:** Deferred until the next idle state (after completing the current command response, when waiting for the next command).
@@ -964,7 +990,7 @@ ctx.compact({
 
 ### ctx.getSystemPrompt()
 
-Returns Pi's current system prompt string.
+Returns senpi's current system prompt string.
 
 - During `before_agent_start`, this reflects chained system-prompt changes made so far for the current turn.
 - It does not include later `context` message mutations.
@@ -984,7 +1010,7 @@ Command handlers receive `ExtensionCommandContext`, which extends `ExtensionCont
 
 ### ctx.getSystemPromptOptions()
 
-Returns the base inputs Pi currently uses to build the system prompt.
+Returns the base inputs senpi currently uses to build the system prompt.
 
 ```typescript
 const options = ctx.getSystemPromptOptions();
@@ -1319,7 +1345,7 @@ pi.sendUserMessage("What is 2+2?");
 // With content array (text + images)
 pi.sendUserMessage([
   { type: "text", text: "Describe this image:" },
-  { type: "image", source: { type: "base64", mediaType: "image/png", data: "..." } },
+  { type: "image", data: "base64-encoded-data", mimeType: "image/png" },
 ]);
 
 // During streaming - must specify delivery mode
@@ -1848,13 +1874,13 @@ Extensions can override built-in tools (`read`, `bash`, `edit`, `write`, `grep`,
 
 ```bash
 # Extension's read tool replaces built-in read
-pi -e ./tool-override.ts
+senpi -e ./tool-override.ts
 ```
 
 Alternatively, use `--no-builtin-tools` to start without any built-in tools while keeping extension tools enabled:
 ```bash
 # No built-in tools, only extension tools
-pi --no-builtin-tools -e ./my-extension.ts
+senpi --no-builtin-tools -e ./my-extension.ts
 ```
 
 See [examples/extensions/tool-override.ts](../examples/extensions/tool-override.ts) for a complete example that overrides `read` with logging and access control.
@@ -1905,7 +1931,7 @@ pi.registerTool({
 
 **Operations interfaces:** `ReadOperations`, `WriteOperations`, `EditOperations`, `BashOperations`, `LsOperations`, `GrepOperations`, `FindOperations`
 
-For `user_bash`, extensions can reuse pi's local shell backend via `createLocalBashOperations()` instead of reimplementing local process spawning, shell resolution, and process-tree termination.
+For `user_bash`, extensions can reuse senpi's local shell backend via `createLocalBashOperations()` instead of reimplementing local process spawning, shell resolution, and process-tree termination.
 
 The bash tool also supports a spawn hook to adjust the command, cwd, or env before execution:
 
@@ -2244,7 +2270,7 @@ ctx.ui.setFooter((tui, theme) => ({
 ctx.ui.setFooter(undefined);  // Restore built-in footer
 
 // Terminal title
-ctx.ui.setTitle("pi - my-project");
+ctx.ui.setTitle("senpi - my-project");
 
 // Editor text
 ctx.ui.setEditorText("Prefill text");
@@ -2255,6 +2281,7 @@ ctx.ui.pasteToEditor("pasted content");
 
 // Stack custom autocomplete behavior on top of the built-in provider
 ctx.ui.addAutocompleteProvider((current) => ({
+  triggerCharacters: ["#"],
   async getSuggestions(lines, line, col, options) {
     const beforeCursor = (lines[line] ?? "").slice(0, col);
     const match = beforeCursor.match(/(?:^|[ \t])#([^\s#]*)$/);
@@ -2303,7 +2330,7 @@ Custom working-indicator frames are rendered verbatim. If you want colors, add t
 
 ### Autocomplete Providers
 
-Use `ctx.ui.addAutocompleteProvider()` to stack custom autocomplete logic on top of the built-in slash-command and path provider.
+Use `ctx.ui.addAutocompleteProvider()` to stack custom autocomplete logic on top of the built-in slash-command and path provider. Set `triggerCharacters` for custom natural triggers such as `$`.
 
 Typical pattern:
 
@@ -2315,6 +2342,7 @@ Typical pattern:
 ```typescript
 pi.on("session_start", (_event, ctx) => {
   ctx.ui.addAutocompleteProvider((current) => ({
+    triggerCharacters: ["#"],
     async getSuggestions(lines, cursorLine, cursorCol, options) {
       const line = lines[cursorLine] ?? "";
       const beforeCursor = line.slice(0, cursorCol);
@@ -2567,6 +2595,7 @@ All examples in [examples/extensions/](../examples/extensions/).
 | `shutdown-command.ts` | Graceful shutdown command | `registerCommand`, `shutdown()` |
 | **Events & Gates** |||
 | `permission-gate.ts` | Block dangerous commands | `on("tool_call")`, `ui.confirm` |
+| `project-trust.ts` | Decide or defer project trust from a user/global or CLI extension | `on("project_trust")`, trust UI, required trust result |
 | `protected-paths.ts` | Block writes to specific paths | `on("tool_call")` |
 | `confirm-destructive.ts` | Confirm session changes | `on("session_before_switch")`, `on("session_before_fork")` |
 | `dirty-repo-guard.ts` | Warn on dirty git repo | `on("session_before_*")`, `exec` |
@@ -2607,7 +2636,6 @@ All examples in [examples/extensions/](../examples/extensions/).
 | `interactive-shell.ts` | Persistent shell session | `on("user_bash")` |
 | `sandbox/` | Sandboxed tool execution | Tool operations |
 | `gondolin/` | Route built-in tools and `!` commands into a Gondolin micro-VM | Tool operations, built-in tool overrides, `on("user_bash")` |
-| `subagent/` | Spawn sub-agents | `registerTool`, `exec` |
 | **Games** |||
 | `snake.ts` | Snake game | `registerCommand`, `ui.custom`, keyboard handling |
 | `space-invaders.ts` | Space Invaders game | `registerCommand`, `ui.custom` |

package/docs/index.md

@@ -10,13 +10,13 @@ Install with npm:
 npm install -g @code-yeongyu/senpi
 ```
 
-To uninstall pi itself, use npm for curl and npm installs:
+To uninstall senpi itself, use the package manager that installed it:
 
 ```bash
-npm uninstall -g @earendil-works/pi-coding-agent
+npm uninstall -g @code-yeongyu/senpi
 ```
 
-For pnpm, Yarn, or Bun installs, use the matching global remove command: `pnpm remove -g @earendil-works/pi-coding-agent`, `yarn global remove @earendil-works/pi-coding-agent`, or `bun uninstall -g @earendil-works/pi-coding-agent`.
+For pnpm, Yarn, or Bun installs, use the matching global remove command: `pnpm remove -g @code-yeongyu/senpi`, `yarn global remove @code-yeongyu/senpi`, or `bun uninstall -g @code-yeongyu/senpi`.
 
 Then run it in a project directory:
 
@@ -33,7 +33,8 @@ For the full first-run flow, see [Quickstart](quickstart.md).
 - [Quickstart](quickstart.md) - install, authenticate, and run a first session.
 - [Using Senpi](usage.md) - interactive mode, slash commands, context files, and CLI reference.
 - [Providers](providers.md) - subscription and API-key setup for built-in providers.
-- [Containerization](containerization.md) - sandbox pi with OpenShell, Gondolin, or Docker.
+- [Security](security.md) - project trust, sandbox boundaries, and vulnerability reporting.
+- [Containerization](containerization.md) - sandbox senpi with OpenShell, Gondolin, or Docker.
 - [Settings](settings.md) - global and project settings.
 - [Keybindings](keybindings.md) - default shortcuts and custom keybindings.
 - [Sessions](sessions.md) - session management, branching, and tree navigation.

package/docs/json.md

@@ -4,31 +4,37 @@
 senpi --mode json "Your prompt"
 ```
 
-Outputs all session events as JSON lines to stdout. Useful for integrating pi into other tools or custom UIs.
+Outputs all session events as JSON lines to stdout. Useful for integrating senpi into other tools or custom UIs.
 
 ## Event Types
 
-Events are defined in [`AgentSessionEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/agent-session.ts#L102):
+Events are defined in [`AgentSessionEvent`](../src/core/agent-session.ts):
 
 ```typescript
 type AgentSessionEvent =
+  // All AgentEvent variants; agent_end additionally carries willRetry: boolean
   | AgentEvent
   | { type: "queue_update"; steering: readonly string[]; followUp: readonly string[] }
   | { type: "compaction_start"; reason: "manual" | "threshold" | "overflow" }
-  | { type: "compaction_end"; reason: "manual" | "threshold" | "overflow"; result: CompactionResult | undefined; aborted: boolean; willRetry: boolean; errorMessage?: string }
+  | { type: "compaction_progress"; reason: "manual" | "threshold" | "overflow"; delta?: string; text?: string }
+  | { type: "compaction_end"; reason: "manual" | "threshold" | "overflow"; result: CompactionResult | undefined; aborted: boolean; willRetry: boolean; requestId?: string; accepted?: boolean; rejectionCause?: "cancelled-by-extension" | "would-overflow" | "circuit-breaker" | "per-turn-cap"; errorMessage?: string }
+  | { type: "session_info_changed"; name: string | undefined }
+  | { type: "thinking_level_changed"; level: "off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max" }
+  | SystemPromptChangeEvent           // type: "system_prompt_change"
+  | ExtensionToolHookLifecycleEvent   // type: "tool_hook_status"
   | { type: "auto_retry_start"; attempt: number; maxAttempts: number; delayMs: number; errorMessage: string }
   | { type: "auto_retry_end"; success: boolean; attempt: number; finalError?: string };
 ```
 
-`queue_update` emits the full pending steering and follow-up queues whenever they change. `compaction_start` and `compaction_end` cover both manual and automatic compaction.
+`queue_update` emits the full pending steering and follow-up queues whenever they change. `compaction_start`, `compaction_progress`, and `compaction_end` cover both manual and automatic compaction. `session_info_changed` fires when the session display name changes, `thinking_level_changed` when the thinking level changes, `system_prompt_change` (see `SystemPromptChangeEvent` in [`extensions/types.ts`](../src/core/extensions/types.ts)) when a model switch changes the active system prompt, and `tool_hook_status` (see `ExtensionToolHookLifecycleEvent` in [`extensions/runner.ts`](../src/core/extensions/runner.ts)) for extension tool hook start/end phases.
 
-Base events from [`AgentEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/agent/src/types.ts#L179):
+Base events from [`AgentEvent`](../../agent/src/types.ts):
 
 ```typescript
 type AgentEvent =
   // Agent lifecycle
   | { type: "agent_start" }
-  | { type: "agent_end"; messages: AgentMessage[] }
+  | { type: "agent_end"; messages: AgentMessage[] }  // in JSON mode also: willRetry: boolean
   // Turn lifecycle
   | { type: "turn_start" }
   | { type: "turn_end"; message: AgentMessage; toolResults: ToolResultMessage[] }
@@ -44,16 +50,16 @@ type AgentEvent =
 
 ## Message Types
 
-Base messages from [`packages/ai/src/types.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/ai/src/types.ts#L134):
-- `UserMessage` (line 134)
-- `AssistantMessage` (line 140)
-- `ToolResultMessage` (line 152)
+Base messages from [`packages/ai/src/types.ts`](../../ai/src/types.ts):
+- `UserMessage`
+- `AssistantMessage`
+- `ToolResultMessage`
 
-Extended messages from [`packages/coding-agent/src/core/messages.ts`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/messages.ts#L29):
-- `BashExecutionMessage` (line 29)
-- `CustomMessage` (line 46)
-- `BranchSummaryMessage` (line 55)
-- `CompactionSummaryMessage` (line 62)
+Extended messages from [`packages/coding-agent/src/core/messages.ts`](../src/core/messages.ts):
+- `BashExecutionMessage`
+- `CustomMessage`
+- `BranchSummaryMessage`
+- `CompactionSummaryMessage`
 
 ## Output Format