@earendil-works/pi-coding-agent 0.80.3 → 0.80.5

package/docs/models.md

@@ -139,7 +139,7 @@ Set `api` at provider level (default for all models) or model level (override pe
 | `headers` | Custom headers (see value resolution below) |
 | `authHeader` | Set `true` to add `Authorization: Bearer <apiKey>` automatically |
 | `models` | Array of model configurations |
-| `modelOverrides` | Per-model overrides for built-in models on this provider |
+| `modelOverrides` | Per-model overrides for built-in or extension-registered models on this provider |
 
 For providers with `models`, non-built-in provider configs need `baseUrl` and an `api` value at either provider or model level. `apiKey` is not required to load the file: models become available when auth is configured through `/login`/`auth.json`, CLI `--api-key`, or provider `apiKey`. If no auth is configured, the models load but stay unavailable in `/model` and `--list-models`.
 
@@ -293,7 +293,7 @@ Merge semantics:
 
 ## Per-model Overrides
 
-Use `modelOverrides` to customize specific built-in models without replacing the provider's full model list.
+Use `modelOverrides` to customize built-in models and matching extension-registered models without replacing the provider's full model list.
 
 ```json
 {
@@ -314,10 +314,10 @@ Use `modelOverrides` to customize specific built-in models without replacing the
 }
 ```
 
-`modelOverrides` supports these fields per model: `name`, `reasoning`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
+`modelOverrides` supports these fields per model: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
 
 Behavior notes:
-- `modelOverrides` are applied to built-in provider models.
+- `modelOverrides` are applied to built-in provider models and matching extension-registered provider models.
 - Unknown model IDs are ignored.
 - You can combine provider-level `baseUrl`/`headers` with `modelOverrides`.
 - Overriding `name` changes model matching and secondary detail text only; the footer and primary model lists continue to show the model `id`.

package/docs/packages.md

@@ -216,11 +216,11 @@ Filter what a package loads using the object form in settings:
 
 ## Enable and Disable Resources
 
-Use `pi config` to enable or disable extensions, skills, prompt templates, and themes from installed packages and local directories. Works for both global (`~/.pi/agent`) and project (`.pi/`) scopes.
+Use `pi config` to enable or disable extensions, skills, prompt templates, and themes from installed packages and local directories. `pi config` starts in global settings (`~/.pi/agent/settings.json`); press Tab to switch between global and project-local modes. Use `pi config -l` to start in project overrides (`.pi/settings.json`) with inherited global resources dimmed.
 
 ## Scope and Deduplication
 
-Packages can appear in both global and project settings. If the same package appears in both, the project entry wins. Identity is determined by:
+Packages can appear in both global and project settings. If the same package appears in both, the project entry wins unless the project entry has `autoload: false`, in which case it is applied as a delta over the global entry. Identity is determined by:
 
 - npm: package name
 - git: repository URL without ref

package/docs/rpc.md

@@ -808,7 +808,8 @@ Events are streamed to stdout as JSON lines during agent operation. Events do NO
 | Event | Description |
 |-------|-------------|
 | `agent_start` | Agent begins processing |
-| `agent_end` | Agent completes (includes all generated messages) |
+| `agent_end` | One low-level agent run completes (may still be followed by retry, compaction, or queued continuations) |
+| `agent_settled` | Agent run is fully settled; no automatic retry, compaction retry, or queued continuation remains |
 | `turn_start` | New turn begins |
 | `turn_end` | Turn completes (includes assistant message and tool results) |
 | `message_start` | Message begins |
@@ -834,15 +835,24 @@ Emitted when the agent begins processing a prompt.
 
 ### agent_end
 
-Emitted when the agent completes. Contains all messages generated during this run.
+Emitted when one low-level agent run completes. Contains all messages generated during this run. If `willRetry` is true, an automatic retry will follow.
 
 ```json
 {
   "type": "agent_end",
-  "messages": [...]
+  "messages": [...],
+  "willRetry": false
 }
 ```
 
+### agent_settled
+
+Emitted after the full session-level run settles. At this point Pi will not continue automatically through retry, compaction retry, or queued follow-up messages.
+
+```json
+{"type": "agent_settled"}
+```
+
 ### turn_start / turn_end
 
 A turn consists of one assistant response plus any resulting tool calls and results.

package/docs/sdk.md

@@ -405,6 +405,32 @@ If no model is provided:
 2. Uses default from settings
 3. Falls back to first available model
 
+To match CLI model parsing, use the exported resolver helpers:
+
+```typescript
+import {
+  resolveCliModel,
+  resolveModelScopeWithDiagnostics,
+} from "@earendil-works/pi-coding-agent";
+
+const cliModel = resolveCliModel({
+  cliModel: "anthropic/claude-opus-4-5:high",
+  modelRegistry,
+});
+if (cliModel.error) throw new Error(cliModel.error);
+if (cliModel.warning) console.warn(cliModel.warning);
+
+const { scopedModels, diagnostics } = await resolveModelScopeWithDiagnostics(
+  ["anthropic/*:high", "gpt-5"],
+  modelRegistry,
+);
+for (const diagnostic of diagnostics) {
+  console.warn(diagnostic.message);
+}
+```
+
+`resolveCliModel()` uses all registered models so `--api-key` style first-time setup can resolve a model before stored auth exists. `resolveModelScopeWithDiagnostics()` matches `--models` and `enabledModels` semantics while returning warnings instead of printing them.
+
 > See [examples/sdk/02-custom-model.ts](../examples/sdk/02-custom-model.ts)
 
 ### API Keys and OAuth
@@ -578,6 +604,27 @@ const { session } = await createAgentSession({ resourceLoader: loader });
 
 Extensions can register tools, subscribe to events, add commands, and more. See [extensions.md](extensions.md) for the full API.
 
+**Named inline extensions:** By default, inline factories display as `<inline:1>`, `<inline:2>`, etc. in the startup Extensions list. To show a descriptive name instead, wrap the factory:
+
+```typescript
+import type { InlineExtension } from "@earendil-works/pi-coding-agent";
+
+const myProvider: InlineExtension = {
+  name: "my-provider",
+  factory: (pi) => {
+    pi.on("agent_start", () => {
+      console.log("[my-provider] Agent starting");
+    });
+  },
+};
+
+const loader = new DefaultResourceLoader({
+  extensionFactories: [myProvider],
+});
+```
+
+This displays as `<inline:my-provider>` instead of `<inline:1>`. Bare factory functions are still accepted for backward compatibility.
+
 **Event Bus:** Extensions can communicate via `pi.events`. Pass a shared `eventBus` to `DefaultResourceLoader` if you need to emit or listen from outside:
 
 ```typescript
@@ -1104,6 +1151,8 @@ AgentSessionRuntime
 // Auth and Models
 AuthStorage
 ModelRegistry
+resolveCliModel
+resolveModelScopeWithDiagnostics
 
 // Resource loading
 DefaultResourceLoader
@@ -1133,6 +1182,7 @@ createGrepTool, createFindTool, createLsTool
 type CreateAgentSessionOptions
 type CreateAgentSessionResult
 type ExtensionFactory
+type InlineExtension
 type ExtensionAPI
 type ToolDefinition
 type Skill

package/docs/session-format.md

@@ -255,7 +255,7 @@ Extension state persistence. Does NOT participate in LLM context.
 {"type":"custom","id":"h8i9j0k1","parentId":"g7h8i9j0","timestamp":"2024-12-03T14:20:00.000Z","customType":"my-extension","data":{"count":42}}
 ```
 
-Use `customType` to identify your extension's entries on reload.
+Use `customType` to identify your extension's entries on reload. Interactive mode can render custom entries via `pi.registerEntryRenderer(customType, renderer)`, but they still do not participate in LLM context.
 
 ### CustomMessageEntry
 
@@ -306,15 +306,24 @@ Entries form a tree:
 
 ## Context Building
 
-`buildSessionContext()` walks from the current leaf to the root, producing the message list for the LLM:
+`buildContextEntries()` walks from the current leaf to the root, producing the active entry list while honoring compaction:
 
 1. Collects all entries on the path
-2. Extracts current model and thinking level settings
-3. If a `CompactionEntry` is on the path:
-   - Emits the summary first
-   - Then messages from `firstKeptEntryId` to compaction
-   - Then messages after compaction
-4. Converts `BranchSummaryEntry` and `CustomMessageEntry` to appropriate message formats
+2. If a `CompactionEntry` is on the path:
+   - Includes the compaction entry first
+   - Then entries from `firstKeptEntryId` to compaction
+   - Then entries after compaction
+3. Preserves non-message entries in the selected range so interactive mode can render them
+
+`buildSessionContext()` builds on that entry list to produce the message list for the LLM:
+
+1. Extracts current model and thinking level settings from the full path
+2. Converts selected entries to messages:
+   - `message` -> stored `AgentMessage`
+   - `compaction` -> `compactionSummary`
+   - `branch_summary` -> `branchSummary`
+   - `custom_message` -> `CustomMessage`
+   - `custom` -> no context message
 
 ## Parsing Example
 
@@ -401,6 +410,7 @@ Key methods for working with sessions programmatically.
 - `branchWithSummary(entryId, summary, details?, fromHook?)` - Branch with context summary
 
 ### Instance Methods - Context & Info
+- `buildContextEntries()` - Get active branch entries with compaction applied
 - `buildSessionContext()` - Get messages, thinkingLevel, and model for LLM
 - `getEntries()` - All entries (excluding header)
 - `getHeader()` - Session header metadata

package/docs/settings.md

@@ -31,6 +31,7 @@ Use `/trust` in interactive mode to save a project trust decision for future ses
 | `defaultModel` | string | - | Default model ID |
 | `defaultThinkingLevel` | string | - | `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"` |
 | `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output |
+| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses |
 | `thinkingBudgets` | object | - | Custom token budgets per thinking level |
 
 #### thinkingBudgets

package/docs/usage.md

@@ -52,7 +52,7 @@ Type `/` in the editor to open command completion. Extensions can register custo
 | `/export [file]` | Export session to HTML or JSONL |
 | `/import <file>` | Import and resume a session from a JSONL file |
 | `/share` | Upload as private GitHub gist with shareable HTML link |
-| `/reload` | Reload keybindings, extensions, skills, prompts, and context files |
+| `/reload` | Reload keybindings, extensions, skills, prompts, themes, and context files |
 | `/hotkeys` | Show all keyboard shortcuts |
 | `/changelog` | Display version history |
 | `/quit` | Quit pi |

package/examples/extensions/README.md

@@ -112,6 +112,7 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 | Extension | Description |
 |-----------|-------------|
 | `message-renderer.ts` | Custom message rendering with colors and expandable details via `registerMessageRenderer` |
+| `entry-renderer.ts` | TUI-only session entry rendering via `appendEntry` and `registerEntryRenderer` |
 | `event-bus.ts` | Inter-extension communication via `pi.events` |
 
 ### Session Metadata

package/examples/extensions/custom-provider-anthropic/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.80.3",
+  "version": "0.80.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.80.3",
+      "version": "0.80.5",
       "dependencies": {
         "@anthropic-ai/sdk": "^0.52.0"
       }

package/examples/extensions/custom-provider-anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-anthropic",
   "private": true,
-  "version": "0.80.3",
+  "version": "0.80.5",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/custom-provider-gitlab-duo/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-gitlab-duo",
   "private": true,
-  "version": "0.80.3",
+  "version": "0.80.5",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/entry-renderer.ts

@@ -0,0 +1,41 @@
+/**
+ * Custom entry rendering example.
+ *
+ * Shows how to render durable extension data inside the chat without sending it
+ * to the LLM. Custom entries are stored in the session via pi.appendEntry() and
+ * rendered in interactive mode via pi.registerEntryRenderer().
+ *
+ * Usage: /status-card [message]
+ */
+
+import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
+import { Box, Text } from "@earendil-works/pi-tui";
+
+interface StatusCardData {
+	message: string;
+	timestamp: number;
+}
+
+export default function (pi: ExtensionAPI) {
+	pi.registerEntryRenderer<StatusCardData>("status-card", (entry, { expanded }, theme) => {
+		const data = entry.data ?? { message: "No data", timestamp: Date.now() };
+		const box = new Box(1, 1, (text) => theme.bg("customMessageBg", text));
+		box.addChild(new Text(`${theme.fg("accent", "[status]")} ${data.message}`, 0, 0));
+
+		if (expanded) {
+			box.addChild(new Text(theme.fg("dim", new Date(data.timestamp).toLocaleString()), 0, 0));
+		}
+
+		return box;
+	});
+
+	pi.registerCommand("status-card", {
+		description: "Render a durable status card that is not sent to the LLM",
+		handler: async (args) => {
+			pi.appendEntry<StatusCardData>("status-card", {
+				message: args.trim() || "Status card",
+				timestamp: Date.now(),
+			});
+		},
+	});
+}

package/examples/extensions/gondolin/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-gondolin",
-	"version": "0.80.3",
+	"version": "0.80.5",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-gondolin",
-			"version": "0.80.3",
+			"version": "0.80.5",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-gondolin",
 	"private": true,
-	"version": "0.80.3",
+	"version": "0.80.5",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/question.ts

@@ -47,6 +47,7 @@ export default function question(pi: ExtensionAPI) {
 		label: "Question",
 		description: "Ask the user a question and let them pick from options. Use when you need user input to proceed.",
 		parameters: QuestionParams,
+		executionMode: "sequential",
 
 		async execute(_toolCallId, params, _signal, _onUpdate, ctx) {
 			if (ctx.mode !== "tui") {

package/examples/extensions/reload-runtime.ts

@@ -12,7 +12,7 @@ export default function (pi: ExtensionAPI) {
 	// Command entrypoint for reload.
 	// Treat reload as terminal for this handler.
 	pi.registerCommand("reload-runtime", {
-		description: "Reload extensions, skills, prompts, and themes",
+		description: "Reload extensions, skills, prompts, themes, and context files",
 		handler: async (_args, ctx) => {
 			await ctx.reload();
 			return;
@@ -24,7 +24,7 @@ export default function (pi: ExtensionAPI) {
 	pi.registerTool({
 		name: "reload_runtime",
 		label: "Reload Runtime",
-		description: "Reload extensions, skills, prompts, and themes",
+		description: "Reload extensions, skills, prompts, themes, and context files",
 		parameters: Type.Object({}),
 		async execute() {
 			pi.sendUserMessage("/reload-runtime", { deliverAs: "followUp" });

package/examples/extensions/sandbox/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-sandbox",
-	"version": "1.10.3",
+	"version": "1.10.5",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-sandbox",
-			"version": "1.10.3",
+			"version": "1.10.5",
 			"dependencies": {
 				"@anthropic-ai/sandbox-runtime": "^0.0.26"
 			}

package/examples/extensions/sandbox/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-sandbox",
 	"private": true,
-	"version": "1.10.3",
+	"version": "1.10.5",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/with-deps/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-with-deps",
-  "version": "0.80.3",
+  "version": "0.80.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-with-deps",
-      "version": "0.80.3",
+      "version": "0.80.5",
       "dependencies": {
         "ms": "^2.1.3"
       },

package/examples/extensions/with-deps/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-with-deps",
   "private": true,
-  "version": "0.80.3",
+  "version": "0.80.5",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/sdk/12-full-control.ts

@@ -26,7 +26,7 @@ if (process.env.MY_ANTHROPIC_KEY) {
 // Model registry with no custom models.json
 const modelRegistry = ModelRegistry.inMemory(authStorage);
 
-const model = getModel("anthropic", "claude-sonnet-4-20250514");
+const model = getModel("anthropic", "claude-sonnet-4-5");
 if (!model) throw new Error("Model not found");
 
 // In-memory settings with overrides

package/examples/sdk/README.md

@@ -116,7 +116,7 @@ await session.prompt("Hello");
 | `thinkingLevel` | From settings/"off" | off, low, medium, high |
 | `tools` | `["read", "bash", "edit", "write"]` built-ins | Allowlist tool names across built-in, extension, and custom tools |
 | `customTools` | `[]` | Additional tool definitions |
-| `resourceLoader` | DefaultResourceLoader | Resource loader for extensions, skills, prompts, themes |
+| `resourceLoader` | DefaultResourceLoader | Resource loader for extensions, skills, prompts, themes, and context files |
 | `sessionManager` | `SessionManager.create(cwd)` | Persistence |
 | `settingsManager` | `SettingsManager.create(cwd, agentDir)` | Settings overrides |
 

package/npm-shrinkwrap.json

@@ -1,17 +1,17 @@
 {
 	"name": "@earendil-works/pi-coding-agent",
-	"version": "0.80.3",
+	"version": "0.80.5",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "@earendil-works/pi-coding-agent",
-			"version": "0.80.3",
+			"version": "0.80.5",
 			"license": "MIT",
 			"dependencies": {
-				"@earendil-works/pi-agent-core": "^0.80.3",
-				"@earendil-works/pi-ai": "^0.80.3",
-				"@earendil-works/pi-tui": "^0.80.3",
+				"@earendil-works/pi-agent-core": "^0.80.5",
+				"@earendil-works/pi-ai": "^0.80.5",
+				"@earendil-works/pi-tui": "^0.80.5",
 				"@silvia-odwyer/photon-node": "0.3.4",
 				"chalk": "5.6.2",
 				"cross-spawn": "7.0.6",
@@ -474,11 +474,11 @@
 			}
 		},
 		"node_modules/@earendil-works/pi-agent-core": {
-			"version": "0.80.3",
-			"resolved": "https://registry.npmjs.org/@earendil-works/pi-agent-core/-/pi-agent-core-0.80.3.tgz",
+			"version": "0.80.5",
+			"resolved": "https://registry.npmjs.org/@earendil-works/pi-agent-core/-/pi-agent-core-0.80.5.tgz",
 			"license": "MIT",
 			"dependencies": {
-				"@earendil-works/pi-ai": "^0.80.3",
+				"@earendil-works/pi-ai": "^0.80.5",
 				"ignore": "7.0.5",
 				"typebox": "1.1.38",
 				"yaml": "2.9.0"
@@ -488,8 +488,8 @@
 			}
 		},
 		"node_modules/@earendil-works/pi-ai": {
-			"version": "0.80.3",
-			"resolved": "https://registry.npmjs.org/@earendil-works/pi-ai/-/pi-ai-0.80.3.tgz",
+			"version": "0.80.5",
+			"resolved": "https://registry.npmjs.org/@earendil-works/pi-ai/-/pi-ai-0.80.5.tgz",
 			"license": "MIT",
 			"dependencies": {
 				"@anthropic-ai/sdk": "0.91.1",
@@ -512,8 +512,8 @@
 			}
 		},
 		"node_modules/@earendil-works/pi-tui": {
-			"version": "0.80.3",
-			"resolved": "https://registry.npmjs.org/@earendil-works/pi-tui/-/pi-tui-0.80.3.tgz",
+			"version": "0.80.5",
+			"resolved": "https://registry.npmjs.org/@earendil-works/pi-tui/-/pi-tui-0.80.5.tgz",
 			"license": "MIT",
 			"dependencies": {
 				"get-east-asian-width": "1.6.0",

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@earendil-works/pi-coding-agent",
-	"version": "0.80.3",
+	"version": "0.80.5",
 	"description": "Coding agent CLI with read, bash, edit, write tools and session management",
 	"type": "module",
 	"piConfig": {
@@ -39,9 +39,9 @@
 		"prepublishOnly": "npm run clean && npm run build && npm run shrinkwrap"
 	},
 	"dependencies": {
-		"@earendil-works/pi-agent-core": "^0.80.3",
-		"@earendil-works/pi-ai": "^0.80.3",
-		"@earendil-works/pi-tui": "^0.80.3",
+		"@earendil-works/pi-agent-core": "^0.80.5",
+		"@earendil-works/pi-ai": "^0.80.5",
+		"@earendil-works/pi-tui": "^0.80.5",
 		"@silvia-odwyer/photon-node": "0.3.4",
 		"chalk": "5.6.2",
 		"cross-spawn": "7.0.6",