@hyperspaceng/neural-coding-agent 0.63.0 → 0.64.1

package/CHANGELOG.md

@@ -2,6 +2,118 @@
 
 ## [Unreleased]
 
+## [0.64.0] - 2026-03-29
+
+### New Features
+
+- Extensions and SDK callers can attach a `prepareArguments` hook to any tool definition, letting them normalize or migrate raw model arguments before schema validation. The built-in `edit` tool uses this to transparently support sessions created with the old single-edit schema. See [docs/extensions.md](docs/extensions.md)
+- Extensions can customize the collapsed thinking block label via `ctx.ui.setHiddenThinkingLabel()`. See [examples/extensions/hidden-thinking-label.ts](examples/extensions/hidden-thinking-label.ts) ([#2673](https://github.com/badlogic/pi-mono/issues/2673))
+
+### Breaking Changes
+
+- `ModelRegistry` no longer has a public constructor. SDK callers and tests must use `ModelRegistry.create(authStorage, modelsJsonPath?)` for file-backed registries or `ModelRegistry.inMemory(authStorage)` for built-in-only registries. Direct `new ModelRegistry(...)` calls no longer compile.
+
+### Added
+
+- Added `ToolDefinition.prepareArguments` hook to prepare raw tool call arguments before schema validation, enabling compatibility shims for resumed sessions with outdated tool schemas
+- Built-in `edit` tool now uses `prepareArguments` to silently fold legacy top-level `oldText`/`newText` into `edits[]` when resuming old sessions
+- Added `ctx.ui.setHiddenThinkingLabel()` so extensions can customize the collapsed thinking label in interactive mode, with a no-op in RPC mode and a runnable example extension in `examples/extensions/hidden-thinking-label.ts` ([#2673](https://github.com/badlogic/pi-mono/issues/2673))
+
+### Fixed
+
+- Fixed extension-queued user messages to refresh the interactive pending-message list so messages submitted while a turn is active are no longer silently dropped ([#2674](https://github.com/badlogic/pi-mono/pull/2674) by [@mrexodia](https://github.com/mrexodia))
+- Fixed monorepo `tsconfig.json` path mappings to resolve `@mariozechner/pi-ai` subpath exports to source files in development checkouts ([#2625](https://github.com/badlogic/pi-mono/pull/2625) by [@ferologics](https://github.com/ferologics))
+- Fixed TUI cell size response handling to consume only exact `CSI 6 ; height ; width t` replies, so bare `Escape` is no longer swallowed while waiting for terminal image metadata ([#2661](https://github.com/badlogic/pi-mono/issues/2661))
+- Fixed Kitty keyboard protocol keypad functional keys to normalize to logical digits, symbols, and navigation keys, so numpad input in terminals such as iTerm2 no longer inserts Private Use Area gibberish or gets ignored ([#2650](https://github.com/badlogic/pi-mono/issues/2650))
+
+## [0.63.2] - 2026-03-29
+
+### New Features
+
+- Extension handlers can now use `ctx.signal` to forward cancellation into nested model calls, `fetch()`, and other abort-aware work. See [docs/extensions.md#ctxsignal](docs/extensions.md#ctxsignal) ([#2660](https://github.com/badlogic/pi-mono/issues/2660))
+- Built-in `edit` tool input now uses `edits[]` as the only replacement shape, reducing invalid tool calls caused by mixed single-edit and multi-edit schemas ([#2639](https://github.com/badlogic/pi-mono/issues/2639))
+- Large multi-edit results no longer trigger full-screen redraws in the interactive TUI when the final diff is rendered ([#2664](https://github.com/badlogic/pi-mono/issues/2664))
+
+### Added
+
+- Added `ctx.signal` to `ExtensionContext` and wired it to the active agent turn so extension handlers can forward cancellation into nested model calls, `fetch()`, and other abort-aware work ([#2660](https://github.com/badlogic/pi-mono/issues/2660))
+
+### Fixed
+
+- Fixed built-in `edit` tool input to use `edits[]` as the only replacement shape, eliminating the mixed single-edit and multi-edit modes that caused repeated invalid tool calls and retries ([#2639](https://github.com/badlogic/pi-mono/issues/2639))
+- Fixed edit tool TUI rendering to defer large multi-edit diffs to the settled result, avoiding full-screen redraws when the tool completes ([#2664](https://github.com/badlogic/pi-mono/issues/2664))
+
+## [0.63.1] - 2026-03-27
+
+### Added
+
+- Added `gemini-3.1-pro-preview-customtools` model availability for the `google-vertex` provider ([#2610](https://github.com/badlogic/pi-mono/pull/2610) by [@gordonhwc](https://github.com/gordonhwc))
+
+### Fixed
+
+- Documented `tool_call` input mutation as supported extension API behavior, clarified that post-mutation inputs are not re-validated, and added regression coverage for executing mutated tool arguments ([#2611](https://github.com/badlogic/pi-mono/issues/2611))
+- Fixed repeated compactions dropping messages that were kept by an earlier compaction by re-summarizing from the previous kept boundary and recalculating `tokensBefore` from the rebuilt session context ([#2608](https://github.com/badlogic/pi-mono/issues/2608))
+- Fixed interactive compaction UI updates so `ctx.compact()` rebuilds the chat through unified compaction events, manual compaction no longer duplicates the summary block, and the `trigger-compact` example only fires when context usage crosses its threshold ([#2617](https://github.com/badlogic/pi-mono/issues/2617))
+- Fixed interactive compaction completion to append a synthetic compaction summary after rebuilding the chat so the latest compaction remains visible at the bottom
+- Fixed skill discovery to stop recursing once a directory contains `SKILL.md`, and to ignore root `*.md` files in `.agents/skills` while keeping root markdown skill files supported in `~/.pi/agent/skills`, `.pi/skills`, and package `skills/` directories ([#2603](https://github.com/badlogic/pi-mono/issues/2603))
+- Fixed edit tool diff rendering for multi-edit operations with large unchanged gaps so distant edits collapse intermediate context instead of dumping the full unchanged middle block
+- Fixed edit tool error rendering to avoid repeating the same exact-match failure in both the preview and result blocks
+- Fixed auto-compaction overflow recovery for Ollama models when the backend returns explicit `prompt too long; exceeded max context length ...` errors instead of silently truncating input ([#2626](https://github.com/badlogic/pi-mono/issues/2626))
+- Fixed built-in tool overrides that reuse built-in parameter schemas to still honor custom `renderCall` and `renderResult` renderers in the interactive TUI, restoring the `minimal-mode` example ([#2595](https://github.com/badlogic/pi-mono/issues/2595))
+
+## [0.63.0] - 2026-03-27
+
+### Breaking Changes
+
+- `ModelRegistry.getApiKey(model)` has been replaced by `getApiKeyAndHeaders(model)` because `models.json` auth and header values can now resolve dynamically on every request. Extensions and SDK integrations that previously fetched only an API key must now fetch request auth per call and forward both `apiKey` and `headers`. Use `getApiKeyForProvider(provider)` only when you explicitly want provider-level API key lookup without model headers or `authHeader` handling ([#1835](https://github.com/badlogic/pi-mono/issues/1835))
+- Removed deprecated direct `minimax` and `minimax-cn` model IDs, keeping only `MiniMax-M2.7` and `MiniMax-M2.7-highspeed`. Update pinned model IDs to one of those supported direct MiniMax models, or use another provider route that still exposes the older IDs ([#2596](https://github.com/badlogic/pi-mono/pull/2596) by [@liyuan97](https://github.com/liyuan97))
+
+#### Migration Notes
+
+Before:
+
+```ts
+const apiKey = await ctx.modelRegistry.getApiKey(model);
+return streamSimple(model, messages, { apiKey });
+```
+
+After:
+
+```ts
+const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
+if (!auth.ok) throw new Error(auth.error);
+return streamSimple(model, messages, {
+  apiKey: auth.apiKey,
+  headers: auth.headers,
+});
+```
+
+### Added
+
+- Added `sessionDir` setting support in global and project `settings.json` so session storage can be configured without passing `--session-dir` on every invocation ([#2598](https://github.com/badlogic/pi-mono/pull/2598) by [@smcllns](https://github.com/smcllns))
+- Added a startup onboarding hint in the interactive header telling users pi can explain its own features and documentation ([#2620](https://github.com/badlogic/pi-mono/pull/2620) by [@ferologics](https://github.com/ferologics))
+- Added `edit` tool multi-edit support so one call can update multiple separate, disjoint regions in the same file while matching all replacements against the original file content
+- Added support for `PI_TUI_WRITE_LOG` directory paths, creating a unique log file (`tui-<timestamp>-<pid>.log`) per instance for easier debugging of multiple pi sessions ([#2508](https://github.com/badlogic/pi-mono/pull/2508) by [@mrexodia](https://github.com/mrexodia))
+
+### Changed
+
+### Fixed
+
+- Fixed file mutation queue ordering so concurrent `edit` and `write` operations targeting the same file stay serialized in request order instead of being reordered during queue-key resolution
+- Fixed `models.json` shell-command auth and headers to resolve at request time instead of being cached into long-lived model state. pi now leaves TTL, caching, and recovery policy to user-provided wrapper commands because arbitrary shell commands need provider-specific strategies ([#1835](https://github.com/badlogic/pi-mono/issues/1835))
+- Fixed Google and Vertex cost calculation to subtract cached prompt tokens from billable input tokens instead of double-counting them when providers report `cachedContentTokenCount` ([#2588](https://github.com/badlogic/pi-mono/pull/2588) by [@sparkleMing](https://github.com/sparkleMing))
+- Added missing `ajv` direct dependency; previously relied on transitive install via `@mariozechner/pi-ai` which broke standalone installs ([#2252](https://github.com/badlogic/pi-mono/issues/2252))
+- Fixed `/export` HTML backgrounds to honor `theme.export.pageBg`, `cardBg`, and `infoBg` instead of always deriving them from `userMessageBg` ([#2565](https://github.com/badlogic/pi-mono/issues/2565))
+- Fixed interactive bash execution collapsed previews to recompute visual line wrapping at render time, so previews respect the current terminal width after resizes and split-pane width changes ([#2569](https://github.com/badlogic/pi-mono/issues/2569))
+- Fixed RPC `get_session_stats` to expose `contextUsage`, so headless clients can read actual current context-window usage instead of deriving it from token totals ([#2550](https://github.com/badlogic/pi-mono/issues/2550))
+- Fixed `pi update` for git packages to fetch only the tracked target branch with `--no-tags`, reducing unrelated branch and tag noise while preserving force-push-safe updates ([#2548](https://github.com/badlogic/pi-mono/issues/2548))
+- Fixed print and JSON modes to emit `session_shutdown` before exit, so extensions can release long-lived resources and non-interactive runs terminate cleanly ([#2576](https://github.com/badlogic/pi-mono/issues/2576))
+- Fixed GitHub Copilot OpenAI Responses requests to omit the `reasoning` field entirely when no reasoning effort is requested, avoiding `400` errors from Copilot `gpt-5-mini` rejecting `reasoning: { effort: "none" }` during internal summary calls ([#2567](https://github.com/badlogic/pi-mono/issues/2567))
+- Fixed blockquote text color breaking after inline links (and other inline elements) due to missing style restoration prefix
+- Fixed slash-command Tab completion from immediately chaining into argument autocomplete after completing the command name, restoring flows like `/model` that submit into a selector dialog ([#2577](https://github.com/badlogic/pi-mono/issues/2577))
+- Fixed stale content and incorrect viewport tracking after TUI content shrinks or transient components inflate the working area ([#2126](https://github.com/badlogic/pi-mono/pull/2126) by [@Perlence](https://github.com/Perlence))
+- Fixed `@` autocomplete to debounce editor-triggered searches, cancel in-flight `fd` lookups cleanly, and keep suggestions visible while results refresh ([#1278](https://github.com/badlogic/pi-mono/issues/1278))
+
 ## [0.62.0] - 2026-03-23
 
 ### New Features

package/README.md

@@ -1,9 +1,9 @@
 <!-- OSS_WEEKEND_START -->
 # 🏖️ OSS Weekend
 
-**Issue tracker reopens Monday, March 30, 2026.**
+**Issue tracker reopens Monday, April 6, 2026.**
 
-OSS weekend runs Sunday, March 22, 2026 through Monday, March 30, 2026. New issues are auto-closed during this time. For support, join [Discord](https://discord.com/invite/3cU7Bz4UPx).
+OSS weekend runs Friday, March 27, 2026 through Monday, April 6, 2026. New issues are auto-closed during this time. For support, join [Discord](https://discord.com/invite/3cU7Bz4UPx).
 <!-- OSS_WEEKEND_END -->
 
 ---
@@ -395,7 +395,7 @@ import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "
 const { session } = await createAgentSession({
   sessionManager: SessionManager.inMemory(),
   authStorage: AuthStorage.create(),
-  modelRegistry: new ModelRegistry(authStorage),
+  modelRegistry: ModelRegistry.create(authStorage),
 });
 
 await session.prompt("What files are in the current directory?");

package/dist/core/agent-session.d.ts

@@ -38,10 +38,15 @@ export interface ParsedSkillBlock {
 export declare function parseSkillBlock(text: string): ParsedSkillBlock | null;
 /** Session-specific events that extend the core AgentEvent */
 export type AgentSessionEvent = AgentEvent | {
-    type: "auto_compaction_start";
-    reason: "threshold" | "overflow";
+    type: "queue_update";
+    steering: readonly string[];
+    followUp: readonly string[];
 } | {
-    type: "auto_compaction_end";
+    type: "compaction_start";
+    reason: "manual" | "threshold" | "overflow";
+} | {
+    type: "compaction_end";
+    reason: "manual" | "threshold" | "overflow";
     result: CompactionResult | undefined;
     aborted: boolean;
     willRetry: boolean;
@@ -131,6 +136,7 @@ export interface SessionStats {
         total: number;
     };
     cost: number;
+    contextUsage?: ContextUsage;
 }
 export declare class AgentSession {
     readonly agent: Agent;
@@ -179,6 +185,7 @@ export declare class AgentSession {
     constructor(config: AgentSessionConfig);
     /** Model registry for API key resolution and model discovery */
     get modelRegistry(): ModelRegistry;
+    private _getRequiredRequestAuth;
     /**
      * Install tool hooks once on the Agent instance.
      *
@@ -190,6 +197,7 @@ export declare class AgentSession {
     private _installAgentToolHooks;
     /** Emit an event to all listeners */
     private _emit;
+    private _emitQueueUpdate;
     private _lastAssistantMessage;
     /** Internal handler for agent events - shared by subscribe and reconnect */
     private _handleAgentEvent;
@@ -384,8 +392,8 @@ export declare class AgentSession {
     private _emitModelSelect;
     /**
      * Set model directly.
-     * Validates API key, saves to session and settings.
-     * @throws Error if no API key available for the model
+     * Validates that auth is configured, saves to session and settings.
+     * @throws Error if no auth is configured for the model
      */
     setModel(model: Model<any>): Promise<void>;
     /**
@@ -395,7 +403,7 @@ export declare class AgentSession {
      * @returns The new model info, or undefined if only one model available
      */
     cycleModel(direction?: "forward" | "backward"): Promise<ModelCycleResult | undefined>;
-    private _getScopedModelsWithApiKey;
+    private _getScopedModelsWithAuth;
     private _cycleScopedModel;
     private _cycleAvailableModel;
     /**