@oh-my-pi/pi-coding-agent 14.4.0 → 14.4.3

package/CHANGELOG.md

@@ -1,19 +1,89 @@
 # Changelog
 
 ## [Unreleased]
+
+## [14.4.3] - 2026-04-26
+### Added
+
+- Added `irc` tool for agent-to-agent messaging with `list` and `send` operations, including optional broadcast to `all` and optional suppression of reply waits
+- Added `irc.enabled` tool setting (default `true`) to toggle agent-to-agent messaging
+- Added live in-chat rendering of IRC incoming and auto-reply messages so peer messages now appear in the session transcript
+
+### Changed
+
+- Changed peer-aware prompts for subagents to include currently live agent peers and IRC usage guidance when available
+- Changed the `/btw` helper to use a session-side ephemeral turn path that preserves streaming-context handling and updates the existing request handling behavior
+- Merged the `poll` and `cancel_job` tools into a single `job` tool that accepts `poll` and `cancel` arrays; the renamed tool reuses the richer poll renderer for both polling and cancellation calls
+
+### Fixed
+
+- Fixed IRC messaging to use a background ephemeral turn path so a recipient can reply even while its main loop is busy
+- Fixed `/btw` handling of empty prompts and missing model configuration by rejecting invalid requests before starting a stream
+- Fixed `/btw` request replacement so issuing a new query cleanly aborts the previous active request
+
+## [14.4.2] - 2026-04-26
+### Breaking Changes
+
+- Changed `/todo append` from JSON payload input to `/todo append [<phase>] <task...>` with optional quoted tokens and automatic phase creation
+
+### Added
+
+- Added `note` to todo-write operations so you can append follow-up text notes to a task via `op: "note"` and `text`
+- Added markdown note-block support to `/todo export` and `/todo import` so task notes are written as blockquote lines and reloaded with the todo list
+- Added `/todo export <path>` to write the current todo list as Markdown to a file, defaulting to `TODO.md` when no path is provided
+- Added `/todo import <path>` to replace the current todo list from a Markdown file, defaulting to `TODO.md` when no path is provided
+- Added live poll progress updates so the UI now emits intermediate job state while waiting for jobs to finish
+- Added a dedicated TUI renderer for the `poll` tool that displays job status, counts, duration, and result/error previews
+- Added a `/todo` slash command to view and modify todos with `edit`, `copy`, `start`, `done`, `drop`, `rm`, `append`, and `replace` operations
+- Added `/todo edit` to open the current todo list in `$EDITOR` as Markdown and sync the edited checklist back into the session
+- Added `/todo copy` to copy the rendered Markdown todo list to the clipboard
+
+### Changed
+
+- Changed todo list rendering and summaries to show a `+N` note marker on task lines and display attached notes for tasks in progress
+- Changed `/todo start`, `/todo done`, `/todo drop`, and `/todo rm` to resolve task/phase targets by fuzzy id/name matching instead of strict identifiers
+- Removed `/todo replace` from supported slash commands
+- Changed todo list restoration to include user todo-edit custom session entries so slash-command and editor-based todo updates persist after reload
+- Restored sensible defaults for `grep.contextBefore` (1) and `grep.contextAfter` (3) so grep matches show context lines by default after the `pre`/`post` parameters were folded into settings
+
+### Removed
+
+- Removed the `chunk` edit mode, chunk-aware `read` selectors, chunk-aware `grep` rendering, and the `omp read` chunk CLI subcommand
+- Removed the `read.prosechunks`, `read.explorechunks`, and `read.anchorstyle` settings
+- Removed the underlying `chunk` native module and AST-based chunk schema generation from `pi-natives`
+
+### Fixed
+
+- Fixed poll final output to reflect live job data from the async job manager, improving status and result visibility
+- Fixed job duration and output reporting to use current job snapshots instead of initial poll input metadata
+- Fixed `poll` wait duration parsing to fall back to `30s` when the provided value is an empty string
+
+## [14.4.1] - 2026-04-26
 ### Breaking Changes
 
 - Replaced the legacy `gh_repo_view`, `gh_issue_view`, `gh_pr_view`, `gh_pr_diff`, `gh_pr_checkout`, `gh_pr_push`, `gh_run_watch`, `gh_search_issues`, and `gh_search_prs` tool names with only `github`, which requires updating existing callers that invoked the old `gh_*` tools
 
 ### Added
 
+- Added a `sed` verb to the `atom` edit tool for line-local substitutions using sed-style syntax (`s/pattern/replacement/`) with `g`, `i`, and `F` flags and model-tolerant delimiter choices
 - Added the unified `github` tool with op-based dispatch for repository, issue, pull request, search, checkout, push, and Actions watch workflows
 - Added `op` routing so callers can select `repo_view`, `issue_view`, `pr_view`, `pr_diff`, `pr_checkout`, `pr_push`, `search_issues`, `search_prs`, or `run_watch` through a single tool entry point
 
 ### Changed
 
+- Changed hashline-based read and match output formatting to use `LINE+ID|content` as the anchor/content separator, and updated match/context markers to `>` for matches and `:` for context
 - Updated GitHub CLI render output to show `GitHub <op>` for tool calls dispatched through `github` operations
 
+### Removed
+
+- Removed the built-in `taplo` Language Server entry from default LSP settings, so TOML files no longer have default TOML server startup
+
+### Fixed
+
+- Fixed `atom` `loc` parsing so path-qualified anchors like `path:263ti| ...` and single-anchor locs containing hyphens no longer mis-parse as ranges
+- Fixed hashline anchor handling in `atom` edits so a provided content hint after the anchor (`|` or `:` suffix) can rebond a stale hash to the intended line
+- Fixed `atom` `sed` execution to tolerate common model-emitted forms such as `/pat/rep/`, and to apply safe literal fallbacks for regex failures or metacharacter-heavy patterns while still erroring when no match is possible
+
 ## [14.4.0] - 2026-04-26
 
 ### Breaking Changes

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-coding-agent",
-	"version": "14.4.0",
+	"version": "14.4.3",
 	"description": "Coding agent CLI with read, bash, edit, write tools and session management",
 	"homepage": "https://github.com/can1357/oh-my-pi",
 	"author": "Can Boluk",
@@ -46,12 +46,12 @@
 	"dependencies": {
 		"@agentclientprotocol/sdk": "0.20.0",
 		"@mozilla/readability": "^0.6.0",
-		"@oh-my-pi/omp-stats": "14.4.0",
-		"@oh-my-pi/pi-agent-core": "14.4.0",
-		"@oh-my-pi/pi-ai": "14.4.0",
-		"@oh-my-pi/pi-natives": "14.4.0",
-		"@oh-my-pi/pi-tui": "14.4.0",
-		"@oh-my-pi/pi-utils": "14.4.0",
+		"@oh-my-pi/omp-stats": "14.4.3",
+		"@oh-my-pi/pi-agent-core": "14.4.3",
+		"@oh-my-pi/pi-ai": "14.4.3",
+		"@oh-my-pi/pi-natives": "14.4.3",
+		"@oh-my-pi/pi-tui": "14.4.3",
+		"@oh-my-pi/pi-utils": "14.4.3",
 		"@sinclair/typebox": "^0.34.49",
 		"@xterm/headless": "^6.0.0",
 		"ajv": "^8.20.0",

package/src/cli.ts

@@ -49,7 +49,6 @@ const commands: CommandEntry[] = [
 	{ name: "config", load: () => import("./commands/config").then(m => m.default) },
 	{ name: "grep", load: () => import("./commands/grep").then(m => m.default) },
 	{ name: "grievances", load: () => import("./commands/grievances").then(m => m.default) },
-	{ name: "read", load: () => import("./commands/read").then(m => m.default) },
 	{ name: "jupyter", load: () => import("./commands/jupyter").then(m => m.default) },
 	{ name: "plugin", load: () => import("./commands/plugin").then(m => m.default) },
 	{ name: "setup", load: () => import("./commands/setup").then(m => m.default) },

package/src/config/prompt-templates.ts

@@ -1,6 +1,5 @@
 import * as fs from "node:fs";
 import * as path from "node:path";
-import { type ChunkAnchorStyle, formatAnchor } from "@oh-my-pi/pi-natives";
 import {
 	getProjectDir,
 	getProjectPromptsDir,
@@ -55,42 +54,13 @@ prompt.registerHelper("href", (lineNum: unknown, content: unknown): string => {
 
 /**
  * {{hline lineNum "content"}} — format a full read-style line with prefix.
- * Returns `"lineNumBIGRAM:content"` (colon between anchor and content).
+ * Returns `"lineNumBIGRAM|content"` (pipe between anchor and content).
  */
 prompt.registerHelper("hline", (lineNum: unknown, content: unknown): string => {
 	const { ref, text } = formatHashlineRef(lineNum, content);
 	return `${ref}${HASHLINE_CONTENT_SEPARATOR}${text}`;
 });
 
-/**
- * {{anchor name checksum}} — render a branch anchor tag using the current anchor style.
- * Style is resolved from the template context (`anchorStyle`) or defaults to "full".
- */
-prompt.registerHelper("anchor", function (this: prompt.TemplateContext, name: string, checksum: string): string {
-	const style = (this.anchorStyle as ChunkAnchorStyle) ?? "full";
-	return formatAnchor(name, checksum, style);
-});
-
-/**
- * {{sel "parent_Name.child_Name"}} — render a chunk path for `sel` fields in examples.
- * In `full` style the path is returned as-is (`class_Server.fn_start`).
- * In `kind` style each segment is trimmed to its kind prefix (`class.fn`).
- * In `bare` style the path is omitted (the model uses only `crc` to identify chunks).
- */
-prompt.registerHelper("sel", function (this: prompt.TemplateContext, chunkPath: string): string {
-	const style = (this.anchorStyle as ChunkAnchorStyle) ?? "full";
-	if (style === "full") return chunkPath;
-	if (style === "bare") return "";
-	// kind: trim each segment to its kind prefix (before the first `_`)
-	return chunkPath
-		.split(".")
-		.map(seg => {
-			const idx = seg.indexOf("_");
-			return idx === -1 ? seg : seg.slice(0, idx);
-		})
-		.join(".");
-});
-
 const INLINE_ARG_SHELL_PATTERN = /\$(?:ARGUMENTS|@(?:\[\d+(?::\d*)?\])?|\d+)/;
 const INLINE_ARG_TEMPLATE_PATTERN = /\{\{[\s\S]*?(?:\b(?:arguments|ARGUMENTS|args)\b|\barg\s+[^}]+)[\s\S]*?\}\}/;
 

package/src/config/settings-schema.ts

@@ -955,12 +955,12 @@ export const SETTINGS_SCHEMA = {
 	// Edit tool
 	"edit.mode": {
 		type: "enum",
-		values: ["replace", "patch", "hashline", "chunk", "vim", "apply_patch", "atom"] as const,
+		values: ["replace", "patch", "hashline", "vim", "apply_patch", "atom"] as const,
 		default: "hashline",
 		ui: {
 			tab: "editing",
 			label: "Edit Mode",
-			description: "Select the edit tool variant (replace, patch, hashline, chunk, vim, or apply_patch)",
+			description: "Select the edit tool variant (replace, patch, hashline, vim, or apply_patch)",
 		},
 	},
 
@@ -1021,7 +1021,7 @@ export const SETTINGS_SCHEMA = {
 		ui: {
 			tab: "editing",
 			label: "Hash Lines",
-			description: "Include line hashes in read output for hashline edit mode (LINE+ID\\tcontent)",
+			description: "Include line hashes in read output for hashline edit mode (LINE+ID|content)",
 		},
 	},
 
@@ -1046,38 +1046,6 @@ export const SETTINGS_SCHEMA = {
 		},
 	},
 
-	"read.prosechunks": {
-		type: "boolean",
-		default: false,
-		ui: {
-			tab: "editing",
-			label: "Prose Chunks",
-			description: "Enable chunk rendering for prose files in chunk edit mode",
-		},
-	},
-
-	"read.explorechunks": {
-		type: "boolean",
-		default: false,
-		ui: {
-			tab: "editing",
-			label: "Explore Chunks",
-			description: "Show chunk tree without checksums for read-only agents like explore",
-		},
-	},
-
-	"read.anchorstyle": {
-		type: "enum",
-		values: ["full", "kind", "bare"],
-		default: "full",
-		ui: {
-			tab: "editing",
-			label: "Anchor Style",
-			description: "Render chunk anchors with full names, kind prefixes, or checksum-only tags",
-			submenu: true,
-		},
-	},
-
 	// LSP
 	"lsp.enabled": {
 		type: "boolean",
@@ -1238,7 +1206,7 @@ export const SETTINGS_SCHEMA = {
 
 	"grep.contextBefore": {
 		type: "number",
-		default: 0,
+		default: 1,
 		ui: {
 			tab: "tools",
 			label: "Grep Context Before",
@@ -1249,7 +1217,7 @@ export const SETTINGS_SCHEMA = {
 
 	"grep.contextAfter": {
 		type: "number",
-		default: 0,
+		default: 3,
 		ui: {
 			tab: "tools",
 			label: "Grep Context After",
@@ -1278,6 +1246,16 @@ export const SETTINGS_SCHEMA = {
 		},
 	},
 
+	"irc.enabled": {
+		type: "boolean",
+		default: true,
+		ui: {
+			tab: "tools",
+			label: "IRC",
+			description: "Enable agent-to-agent IRC messaging via the irc tool",
+		},
+	},
+
 	// Optional tools
 	"notebook.enabled": {
 		type: "boolean",
@@ -1433,6 +1411,18 @@ export const SETTINGS_SCHEMA = {
 		},
 	},
 
+	"async.pollWaitDuration": {
+		type: "enum",
+		values: ["5s", "10s", "30s", "1m", "5m"] as const,
+		default: "30s",
+		ui: {
+			tab: "tools",
+			label: "Poll Wait Duration",
+			description: "How long the poll tool waits for background job updates before returning the current state",
+			submenu: true,
+		},
+	},
+
 	"bash.autoBackground.enabled": {
 		type: "boolean",
 		default: false,

package/src/config/settings.ts

@@ -326,7 +326,7 @@ export class Settings {
 
 	/**
 	 * Get the edit variant for a specific model.
-	 * Returns "patch", "replace", "hashline", "chunk", "vim", "apply_patch", or null (use global default).
+	 * Returns "patch", "replace", "hashline", "vim", "apply_patch", or null (use global default).
 	 */
 	getEditVariantForModel(model: string | undefined): EditMode | null {
 		if (!model) return null;

package/src/edit/index.ts

@@ -10,7 +10,6 @@ import {
 } from "../lsp";
 import applyPatchDescription from "../prompts/tools/apply-patch.md" with { type: "text" };
 import atomDescription from "../prompts/tools/atom.md" with { type: "text" };
-import chunkEditDescription from "../prompts/tools/chunk-edit.md" with { type: "text" };
 import hashlineDescription from "../prompts/tools/hashline.md" with { type: "text" };
 import patchDescription from "../prompts/tools/patch.md" with { type: "text" };
 import replaceDescription from "../prompts/tools/replace.md" with { type: "text" };
@@ -27,15 +26,6 @@ import {
 	executeAtomSingle,
 	resolveAtomEntryPaths,
 } from "./modes/atom";
-import {
-	type ChunkParams,
-	type ChunkToolEdit,
-	chunkEditParamsSchema,
-	executeChunkSingle,
-	parseChunkEditPath,
-	resolveAnchorStyle,
-	resolveChunkAutoIndent,
-} from "./modes/chunk";
 import {
 	executeHashlineSingle,
 	HashlineMismatchError,
@@ -53,7 +43,6 @@ export * from "./diff";
 export * from "./line-hash";
 export * from "./modes/apply-patch";
 export * from "./modes/atom";
-export * from "./modes/chunk";
 export * from "./modes/hashline";
 export * from "./modes/patch";
 export * from "./modes/replace";
@@ -66,19 +55,11 @@ type TInput =
 	| typeof patchEditSchema
 	| typeof hashlineEditParamsSchema
 	| typeof atomEditParamsSchema
-	| typeof chunkEditParamsSchema
 	| typeof vimSchema
 	| typeof applyPatchSchema;
 
 type VimParams = Static<typeof vimSchema>;
-type EditParams =
-	| ReplaceParams
-	| PatchParams
-	| HashlineParams
-	| AtomParams
-	| ChunkParams
-	| VimParams
-	| ApplyPatchParams;
+type EditParams = ReplaceParams | PatchParams | HashlineParams | AtomParams | VimParams | ApplyPatchParams;
 type EditToolResultDetails = EditToolDetails | VimToolDetails;
 
 type EditModeDefinition = {
@@ -325,39 +306,6 @@ export class EditTool implements AgentTool<TInput> {
 
 	#getModeDefinition(): EditModeDefinition {
 		return {
-			chunk: {
-				description: (session: ToolSession) =>
-					prompt.render(chunkEditDescription, {
-						anchorStyle: resolveAnchorStyle(session.settings),
-						chunkAutoIndent: resolveChunkAutoIndent(),
-					}),
-				parameters: chunkEditParamsSchema,
-				execute: (
-					tool: EditTool,
-					params: EditParams,
-					signal: AbortSignal | undefined,
-					batchRequest: LspBatchRequest | undefined,
-					onUpdate?: (partialResult: AgentToolResult<EditToolDetails, TInput>) => void,
-				) => {
-					const { edits, path: topPath } = params as ChunkParams & { path?: string };
-					const resolved = resolveEntryPaths(edits as ChunkToolEdit[], topPath);
-					const byFile = groupBy(resolved, (e: ChunkToolEdit) => parseChunkEditPath(e.path).filePath);
-					const entries = [...byFile.entries()].map(([filePath, fileEdits]) => ({
-						path: filePath,
-						run: (br: LspBatchRequest | undefined) =>
-							executeChunkSingle({
-								session: tool.session,
-								path: filePath,
-								edits: fileEdits,
-								signal,
-								batchRequest: br,
-								writethrough: tool.#writethrough,
-								beginDeferredDiagnosticsForPath: p => tool.#beginDeferredDiagnosticsForPath(p),
-							}),
-					}));
-					return executePerFile(entries, batchRequest, onUpdate);
-				},
-			},
 			patch: {
 				description: () => prompt.render(patchDescription),
 				parameters: patchEditSchema,

package/src/edit/line-hash.ts

@@ -667,66 +667,13 @@ export const HASHLINE_BIGRAMS = [
 
 export const HASHLINE_BIGRAMS_COUNT = HASHLINE_BIGRAMS.length;
 
-/**
- * 40 common English BPE bigrams used by chunk checksums (`path#checksum`).
- * Kept separate from {@link HASHLINE_BIGRAMS} because the chunk checksum
- * format is `path#bigram1bigram2` (4 chars from a 1600-code namespace) and
- * is independent of the line-anchor format.
- *
- * Order is stable forever — changing it invalidates every saved chunk path.
- */
-export const CHUNK_BIGRAMS = [
-	"th",
-	"he",
-	"in",
-	"er",
-	"an",
-	"re",
-	"on",
-	"at",
-	"en",
-	"nd",
-	"ti",
-	"es",
-	"or",
-	"te",
-	"of",
-	"ed",
-	"is",
-	"it",
-	"al",
-	"ar",
-	"st",
-	"to",
-	"nt",
-	"ng",
-	"se",
-	"ha",
-	"as",
-	"ou",
-	"io",
-	"le",
-	"ve",
-	"co",
-	"me",
-	"de",
-	"hi",
-	"ri",
-	"ro",
-	"ic",
-	"ne",
-	"ea",
-] as const;
-
-export const CHUNK_BIGRAMS_COUNT = CHUNK_BIGRAMS.length;
-
 /**
  * Regex source matching exactly one bigram from {@link HASHLINE_BIGRAMS}.
  * Used by hashline parsers — keep in sync with the alphabet array above.
  */
 export const HASHLINE_BIGRAM_RE_SRC = `(?:${HASHLINE_BIGRAMS.join("|")})`;
 
-export const HASHLINE_CONTENT_SEPARATOR = ":";
+export const HASHLINE_CONTENT_SEPARATOR = "|";
 
 const RE_SIGNIFICANT = /[\p{L}\p{N}]/u;
 
@@ -756,11 +703,19 @@ export function formatLineHash(line: number, lines: string): string {
 	return `${line}${computeLineHash(line, lines)}`;
 }
 
+/**
+ * Formats a single line with a hashline anchor.
+ * Returns `LINE+ID|TEXT` (e.g., `42nd|function hi() {\n2er|  return;\n3in|}`)
+ */
+export function formatHashLine(lineNumber: number, line: string): string {
+	return `${lineNumber}${computeLineHash(lineNumber, line)}${HASHLINE_CONTENT_SEPARATOR}${line}`;
+}
+
 /**
  * Format file text with hashline prefixes for display.
  *
- * Each line becomes `LINE+ID:TEXT` where LINENUM is 1-indexed.
- * No padding on line numbers; colon separator between anchor and content.
+ * Each line becomes `LINE+ID|TEXT` where LINENUM is 1-indexed.
+ * No padding on line numbers; pipe separator between anchor and content.
  *
  * @param text - Raw file text string
  * @param startLine - First line number (1-indexed, defaults to 1)
@@ -769,15 +724,10 @@ export function formatLineHash(line: number, lines: string): string {
  * @example
  * ```
  * formatHashLines("function hi() {\n  return;\n}")
- * // "1th:function hi() {\n2er:  return;\n3in:}"
+ * // "1th|function hi() {\n2er|  return;\n3in|}"
  * ```
  */
 export function formatHashLines(text: string, startLine = 1): string {
 	const lines = text.split("\n");
-	return lines
-		.map((line, i) => {
-			const num = startLine + i;
-			return `${formatLineHash(num, line)}${HASHLINE_CONTENT_SEPARATOR}${line}`;
-		})
-		.join("\n");
+	return lines.map((line, i) => formatHashLine(startLine + i, line)).join("\n");
 }