@oh-my-pi/pi-coding-agent 16.4.3 → 16.4.4

package/src/tiny/message-preproc.ts

@@ -0,0 +1,155 @@
+/**
+ * Converts raw user text into bounded, low-noise input for tiny models.
+ *
+ * Tiny models copy literal noise verbatim and lose the task when only the head
+ * of a long message survives. The shared pipeline strips ANSI escapes, paired
+ * XML/tool envelopes, full commit hashes, and fenced code blocks, then preserves
+ * both ends with an explicit omission marker. Title generation, auto-thinking,
+ * and the title benchmark MUST use this same policy.
+ */
+
+/** Maximum characters emitted by {@link preprocessTinyMessage}. */
+export const MAX_TINY_MESSAGE_CHARS = 2000;
+
+/**
+ * Minimum length of code-stripped input below which we fall back to the
+ * original message. Guards against messages that are (almost) entirely a code
+ * block — stripping would otherwise leave the model nothing to title from.
+ */
+const MIN_STRIPPED_TITLE_CHARS = 12;
+/** Matches a fenced code block (3+ backticks), including an unterminated trailing fence. */
+const FENCED_CODE_BLOCK = /```+[\s\S]*?(?:```+|$)/g;
+/** Matches SGR ANSI escape sequences (colors/styles) that leak in from pasted terminal output. */
+const ANSI_ESCAPE = /\u001b\[[0-9;]*m/g;
+/** Matches a paired XML/HTML-ish block, e.g. `<user>…</user>` or a tool envelope. */
+const XML_BLOCK = /<([a-zA-Z][\w-]*)(?:\s[^>]*)?>[\s\S]*?<\/\1>/g;
+/** Matches a hex run long enough to be a full commit SHA rather than an ordinary word. */
+const LONG_HEX_RUN = /\b[0-9a-fA-F]{12,}\b/g;
+/** Short-hash prefix length kept after truncating a long hex run. */
+const SHORT_HASH_CHARS = 7;
+
+/** Drop SGR ANSI escape sequences. */
+export function stripAnsi(message: string): string {
+	return message.replace(ANSI_ESCAPE, "");
+}
+
+/**
+ * Remove paired XML/HTML-ish blocks (`<user>…</user>`, `<think>…</think>`,
+ * tool envelopes). Self-closing and unpaired inline tags (`<Header/>`, a lone
+ * `<div>`) are left in place — only fully paired blocks, whose contents would
+ * otherwise dominate the title, are dropped.
+ */
+export function stripXmlBlocks(message: string): string {
+	return message.replace(XML_BLOCK, " ");
+}
+
+/** Truncate full commit-hash-like hex runs (≥12 chars) to a short 7-char prefix. */
+export function shortenHashes(message: string): string {
+	return message.replace(LONG_HEX_RUN, match => match.slice(0, SHORT_HASH_CHARS));
+}
+
+/**
+ * Middle-truncate cleaned text, preserving 2/3 of the available space from the
+ * head and 1/3 from the tail. The omission marker counts toward the bound.
+ */
+export function truncateTinyMessage(message: string): string {
+	if (message.length <= MAX_TINY_MESSAGE_CHARS) return message;
+	let omitted = message.length - MAX_TINY_MESSAGE_CHARS;
+	let marker = "";
+	let headChars = 0;
+	let tailChars = 0;
+	// The omitted count changes the marker width; two passes converge because
+	// only the decimal digit count can change.
+	for (let pass = 0; pass < 2; pass++) {
+		marker = `\n[… ${omitted} chars omitted …]\n`;
+		const keptChars = Math.max(0, MAX_TINY_MESSAGE_CHARS - marker.length);
+		headChars = Math.ceil((keptChars * 2) / 3);
+		tailChars = keptChars - headChars;
+		omitted = message.length - headChars - tailChars;
+	}
+	marker = `\n[… ${omitted} chars omitted …]\n`;
+	return `${message.slice(0, headChars)}${marker}${message.slice(-tailChars)}`;
+}
+
+/**
+ * Strip fenced code blocks from a message before titling.
+ *
+ * Small title models latch onto literal text inside code blocks — e.g. a pasted
+ * UI mockup containing "Welcome to Claude Code v2.1.158" yields that string as
+ * the title instead of the surrounding intent. Removing fenced blocks leaves the
+ * prose that actually describes the task. Inline code (single backticks) is kept
+ * — it is short, high-signal context like `/login`.
+ *
+ * Falls back to the original message when stripping leaves too little to title
+ * (a message that is essentially just a code block).
+ */
+export function stripCodeBlocks(message: string): string {
+	const cleaned = message
+		.replace(FENCED_CODE_BLOCK, " ")
+		.replace(/[ \t]+/g, " ")
+		.replace(/\n{3,}/g, "\n\n")
+		.trim();
+	return cleaned.length >= MIN_STRIPPED_TITLE_CHARS ? cleaned : message;
+}
+
+/** Clean noise from message content without applying the length bound. */
+export function cleanTinyMessage(message: string): string {
+	return stripCodeBlocks(shortenHashes(stripXmlBlocks(stripAnsi(message))));
+}
+
+/** Apply the shared tiny-model cleanup and middle-truncation policy. */
+export function preprocessTinyMessage(message: string): string {
+	return truncateTinyMessage(cleanTinyMessage(message));
+}
+
+/** Envelope produced by {@link formatTitleConversationContext}. Anchored to both
+ *  ends so ordinary user text merely containing a chat snippet never matches. */
+const CHAT_CONTEXT_ENVELOPE = /^\s*<chat>[\s\S]*<\/chat>\s*$/;
+/** Structural tags emitted by {@link formatTitleConversationContext}. */
+const CHAT_SCAFFOLD_TAG = /<\/?(?:chat|user|assistant|think)>/g;
+
+/** True when `message` is a preformatted replan context from
+ *  {@link formatTitleConversationContext} — already cleaned per turn and
+ *  bounded, so it must bypass {@link preprocessTinyMessage} (whose paired-tag
+ *  stripping would consume the entire envelope). */
+export function isPreformattedChatContext(message: string): boolean {
+	return CHAT_CONTEXT_ENVELOPE.test(message);
+}
+
+/** Drop the `<chat>`/`<user>`/`<assistant>`/`<think>` scaffolding, keeping turn
+ *  text. Used for token-level signal checks on preformatted contexts. */
+export function stripChatScaffolding(message: string): string {
+	return message.replace(CHAT_SCAFFOLD_TAG, " ");
+}
+
+/** Wrap a preprocessed user message for title generation. Preformatted replan
+ *  contexts pass through untouched. */
+export function formatTitleUserMessage(message: string): string {
+	if (isPreformattedChatContext(message)) return message;
+	return `<user>\n${preprocessTinyMessage(message)}\n</user>`;
+}
+
+/** One recent conversation turn supplied to title refresh after replanning. */
+export interface TitleConversationTurn {
+	role: "user" | "assistant";
+	text?: string;
+	thinking?: string;
+}
+
+/** Format preprocessed recent context for title generation after a todo replan. */
+export function formatTitleConversationContext(turns: readonly TitleConversationTurn[]): string {
+	const formattedTurns: string[] = [];
+	for (const turn of turns) {
+		const sections: string[] = [];
+		// Clean raw content before adding structural tags so paired-tag stripping
+		// cannot consume the `<user>`/`<assistant>` scaffolding added below.
+		const text = cleanTinyMessage(turn.text ?? "").trim();
+		if (text) sections.push(text);
+		const thinking = turn.role === "assistant" ? cleanTinyMessage(turn.thinking ?? "").trim() : "";
+		if (thinking) sections.push(`<think>\n${thinking}\n</think>`);
+		if (sections.length === 0) continue;
+		formattedTurns.push(`<${turn.role}>\n${sections.join("\n\n")}\n</${turn.role}>`);
+	}
+	if (formattedTurns.length === 0) return "";
+	return truncateTinyMessage(`<chat>\n${formattedTurns.join("\n\n")}\n</chat>`);
+}

package/src/tiny/text.ts

@@ -1,70 +1,4 @@
-export const MAX_TITLE_INPUT_CHARS = 2000;
-
-/**
- * Minimum length of code-stripped input below which we fall back to the
- * original message. Guards against messages that are (almost) entirely a code
- * block — stripping would otherwise leave the model nothing to title from.
- */
-const MIN_STRIPPED_TITLE_CHARS = 12;
-/** Matches a fenced code block (3+ backticks), including an unterminated trailing fence. */
-const FENCED_CODE_BLOCK = /```+[\s\S]*?(?:```+|$)/g;
-
-export function truncateTitleInput(message: string): string {
-	return message.length > MAX_TITLE_INPUT_CHARS ? `${message.slice(0, MAX_TITLE_INPUT_CHARS)}…` : message;
-}
-
-/**
- * Strip fenced code blocks from a message before titling.
- *
- * Small title models latch onto literal text inside code blocks — e.g. a pasted
- * UI mockup containing "Welcome to Claude Code v2.1.158" yields that string as
- * the title instead of the surrounding intent. Removing fenced blocks leaves the
- * prose that actually describes the task. Inline code (single backticks) is kept
- * — it is short, high-signal context like `/login`.
- *
- * Falls back to the original message when stripping leaves too little to title
- * (a message that is essentially just a code block).
- */
-export function stripCodeBlocks(message: string): string {
-	const cleaned = message
-		.replace(FENCED_CODE_BLOCK, " ")
-		.replace(/[ \t]+/g, " ")
-		.replace(/\n{3,}/g, "\n\n")
-		.trim();
-	return cleaned.length >= MIN_STRIPPED_TITLE_CHARS ? cleaned : message;
-}
-
-/** Prepare a raw user message for titling: drop code blocks, then bound length. */
-export function prepareTitleInput(message: string): string {
-	return truncateTitleInput(stripCodeBlocks(message));
-}
-
-export function formatTitleUserMessage(message: string): string {
-	return `<user-message>\n${prepareTitleInput(message)}\n</user-message>`;
-}
-
-/** Single recent conversation turn supplied to title refresh after replanning. */
-export interface TitleConversationTurn {
-	role: "user" | "assistant";
-	text?: string;
-	thinking?: string;
-}
-
-/** Format recent user/assistant context for title generation after a todo replan. */
-export function formatTitleConversationContext(turns: readonly TitleConversationTurn[]): string {
-	const formattedTurns: string[] = [];
-	for (const turn of turns) {
-		const sections: string[] = [];
-		const text = turn.text?.trim();
-		if (text) sections.push(text);
-		const thinking = turn.role === "assistant" ? turn.thinking?.trim() : undefined;
-		if (thinking) sections.push(`<thinking>\n${thinking}\n</thinking>`);
-		if (sections.length === 0) continue;
-		formattedTurns.push(`<${turn.role}>\n${sections.join("\n\n")}\n</${turn.role}>`);
-	}
-	if (formattedTurns.length === 0) return "";
-	return prepareTitleInput(`<conversation>\n${formattedTurns.join("\n\n")}\n</conversation>`);
-}
+import { cleanTinyMessage, isPreformattedChatContext, stripChatScaffolding } from "./message-preproc";
 
 /**
  * Greeting / acknowledgement / filler tokens. A first user message composed
@@ -191,7 +125,11 @@ const COMMON_TITLE_ACRONYMS = new Set<string>([
  * the next message instead.
  */
 export function isLowSignalTitleInput(message: string): boolean {
-	const tokens = stripCodeBlocks(message).toLowerCase().match(TITLE_WORD);
+	// Preformatted replan contexts are already cleaned per turn; only the
+	// scaffolding tags are dropped so the turn text drives the signal check
+	// (cleanTinyMessage would strip the paired <chat> envelope to nothing).
+	const cleaned = isPreformattedChatContext(message) ? stripChatScaffolding(message) : cleanTinyMessage(message);
+	const tokens = cleaned.toLowerCase().match(TITLE_WORD);
 	if (!tokens) return true;
 	return tokens.every(token => FILLER_TITLE_TOKENS.has(token) || /^\d+$/.test(token));
 }
@@ -200,14 +138,18 @@ export function isLowSignalTitleInput(message: string): boolean {
  * Sentinel a capable title model may emit when a message carries no concrete
  * task. Treated as "no title yet" so the caller can defer titling. Backstop for
  * the deterministic {@link isLowSignalTitleInput} filter; kept in sync with the
- * `none` instruction in `prompts/system/title-system.md`.
+ * `<title/>` instruction in `prompts/system/title-system.md`.
  */
 export const NO_TITLE_SENTINEL = "none";
 
 export function normalizeGeneratedTitle(value: string | null | undefined, sourceText?: string): string | null {
 	const firstLine = value?.trim().split(/\r?\n/, 1)[0]?.trim();
 	if (!firstLine) return null;
-	const title = firstLine
+	const unquoted = firstLine.replace(/^["']|["']$/g, "").trim();
+	if (/^<title\s*\/>$/i.test(unquoted)) return null;
+	const title = unquoted
+		.replace(/^<title>/i, "")
+		.replace(/<\/title>$/i, "")
 		.replace(/^["']|["']$/g, "")
 		.replace(/[.!?]$/, "")
 		.trim();

package/src/tiny/worker.ts

@@ -6,7 +6,7 @@ import type {
 	StoppingCriteria as TransformersStoppingCriteria,
 } from "@huggingface/transformers";
 import { getTinyModelsCacheDir, prompt } from "@oh-my-pi/pi-utils";
-import tinyTitleSystemPrompt from "../prompts/system/tiny-title-system.md" with { type: "text" };
+import titleSystemPrompt from "../prompts/system/title-system.md" with { type: "text" };
 import {
 	errorMessage,
 	errorText,
@@ -21,13 +21,14 @@ import {
 } from "../subprocess/worker-runtime";
 import { resolveTinyModelDevicePreference, type TinyModelDevice, tinyModelDeviceLoadOrder } from "./device";
 import { resolveTinyModelDtypeOverride, type TinyModelDtype } from "./dtype";
+import { formatTitleUserMessage } from "./message-preproc";
 import {
 	getTinyLocalModelSpec,
 	type TinyLocalModelKey,
 	type TinyTitleLocalModelKey,
 	type TinyTitleLocalModelSpec,
 } from "./models";
-import { formatTitleUserMessage, normalizeGeneratedTitle } from "./text";
+import { normalizeGeneratedTitle } from "./text";
 import type { TinyTitleTransport, TinyTitleWorkerInbound } from "./title-protocol";
 
 const TITLE_PREFILL = "<title>";
@@ -36,7 +37,7 @@ const TITLE_MAX_NEW_TOKENS = 20;
 const STOP_DECODE_WINDOW_TOKENS = 32;
 const MEMORY_COMPLETION_DEFAULT_MAX_NEW_TOKENS = 256;
 const COMPLETION_MAX_NEW_TOKENS = 1024;
-const TINY_TITLE_SYSTEM_PROMPT = prompt.render(tinyTitleSystemPrompt);
+const TINY_TITLE_SYSTEM_PROMPT = prompt.render(titleSystemPrompt);
 
 const tinyModelDevicePreference = resolveTinyModelDevicePreference();
 const tinyModelDtypeOverride = resolveTinyModelDtypeOverride();
@@ -230,6 +231,8 @@ function buildPrompt(generator: TextGenerationPipeline, message: string, systemP
 function extractTinyTitle(text: string, sourceText: string): string | null {
 	const titleStart = text.lastIndexOf(TITLE_PREFILL);
 	const withoutPrefix = titleStart >= 0 ? text.slice(titleStart + TITLE_PREFILL.length) : text;
+	// Self-closing tag: <title/> or <title /> (only when the prefill is present).
+	if (titleStart >= 0 && /^\s*\/>/.test(withoutPrefix)) return null;
 	const closeIndex = withoutPrefix.indexOf(TITLE_CLOSE);
 	const withoutClose = closeIndex >= 0 ? withoutPrefix.slice(0, closeIndex) : withoutPrefix;
 	const tagIndex = withoutClose.indexOf("<");

package/src/tools/image-gen.ts

@@ -831,11 +831,10 @@ function buildOpenAIImageHeaders(model: Model, apiKey: string, sessionId: string
 
 	if (model.api === "openai-codex-responses" || model.provider === "openai-codex") {
 		const accountId = getCodexAccountId(apiKey);
-		if (!accountId) {
-			throw new Error("Failed to extract accountId from OpenAI Codex token");
-		}
 		headers.delete("x-api-key");
-		headers.set(OPENAI_HEADERS.ACCOUNT_ID, accountId);
+		if (accountId) {
+			headers.set(OPENAI_HEADERS.ACCOUNT_ID, accountId);
+		}
 		headers.set(OPENAI_HEADERS.BETA, OPENAI_HEADER_VALUES.BETA_RESPONSES);
 		headers.set(OPENAI_HEADERS.ORIGINATOR, OPENAI_HEADER_VALUES.ORIGINATOR_CODEX);
 		headers.set("User-Agent", `pi/${packageJson.version} (${os.platform()} ${os.release()}; ${os.arch()})`);

package/src/utils/title-generator.ts

@@ -12,8 +12,9 @@ import { resolveRoleSelection } from "../config/model-resolver";
 import type { Settings } from "../config/settings";
 import titleMarkerInstruction from "../prompts/system/title-marker-instruction.md" with { type: "text" };
 import titleSystemPrompt from "../prompts/system/title-system.md" with { type: "text" };
+import { formatTitleUserMessage } from "../tiny/message-preproc";
 import { isTinyTitleLocalModelKey, ONLINE_TINY_TITLE_MODEL_KEY } from "../tiny/models";
-import { formatTitleUserMessage, isLowSignalTitleInput, normalizeGeneratedTitle } from "../tiny/text";
+import { isLowSignalTitleInput, normalizeGeneratedTitle } from "../tiny/text";
 import { tinyTitleClient } from "../tiny/title-client";
 
 const TITLE_SYSTEM_PROMPT = prompt.render(titleSystemPrompt);
@@ -33,7 +34,7 @@ const TERMINAL_TITLE_CONTROL_CHARS = /[\u0000-\u001f\u007f-\u009f]/g;
 const TITLE_MAX_TOKENS = 1024;
 
 /** Matches the title the model wraps in `<title>...</title>`. */
-const TITLE_MARKER_GLOBAL_RE = /<title>([\s\S]*?)<\/title>/gi;
+const TITLE_MARKER_GLOBAL_RE = /<title>([\s\S]*?)<\/title>|<title\s*\/>|<title>\s*$/gi;
 const TITLE_VISIBILITY_SENTINEL = "\uE000omp-title-visible\uE000";
 const THINKING_TAG_ENVELOPE_RE = /<(think|thinking|reasoning)>\s*[\s\S]*?<\/\1>/gi;
 const THINKING_FENCE_ENVELOPE_RE = /```(?:thinking|reasoning)\b[\s\S]*?```/gi;
@@ -263,8 +264,8 @@ function extractVisibleMarkedTitle(text: string): string | undefined {
 	TITLE_MARKER_GLOBAL_RE.lastIndex = 0;
 	let marker: RegExpExecArray | null = TITLE_MARKER_GLOBAL_RE.exec(text);
 	while (marker !== null) {
-		const title = marker[1];
-		if (title !== undefined && isVisibleTitleMarker(text, marker.index)) return title.trim();
+		const content = marker[1];
+		if (isVisibleTitleMarker(text, marker.index)) return content?.trim() ?? "";
 		marker = TITLE_MARKER_GLOBAL_RE.exec(text);
 	}
 	return undefined;

package/src/prompts/system/tiny-title-system.md

@@ -1,8 +0,0 @@
-You generate concise terminal session titles.
-
-Input is one user message inside `<user-message>` tags.
-
-Return one specific 3-7 word title in sentence case (capitalize only the first word and proper nouns; keep ALL-CAPS acronyms like `CNPG`, `API`, `JWT` verbatim).
-Continue the assistant response after `<title>` and close it with `</title>`.
-
-NEVER include quotes, punctuation, markdown, commentary, or a second line.