agent/extensions/dankvoice.ts

@@ -28,14 +28,21 @@
  *   DANKVOICE_CONFIG   settings file (default ~/.omp/cache/dankvoice.json)
  *   DANKVOICE_PLAYER   player binary, skipping detection
  *   DANKVOICE_VOICE    voice name ("" = server default)
- *   DANKVOICE_MAX      spoken-character cap per utterance (default 700)
+ *   DANKVOICE_MAX      spoken-character budget per answer (default 700)
  *   DANKVOICE_AUTO=1   start with auto-speak armed
  *
- * Utterances are synthesized to a temp WAV in $TMPDIR; the file is removed
+ * Long answers are cut into speakable segments by a state machine ported
- * when its player process exits. A new utterance interrupts the previous one
+ * from omp's built-in vocalizer: strong boundaries on [.!?…] runs followed
- * instead of queueing behind it. Output routing: a saved sink becomes
+ * by whitespace (so "!!!!!" and "..." stay one boundary), guards for
- * `pw-play --target <sink>` or `paplay --device=<sink>` (ffplay has no device
+ * abbreviations and decimals, code fences and tables swallowed, markdown
- * concept and ignores it); with no saved sink the player's own default applies.
+ * cleaned. Each segment is synthesized to a temp WAV in $TMPDIR and played
+ * to completion before the next request goes out — requests are strictly
+ * sequential, so audio never stacks. The chain runs detached from the event
+ * handler, so an utterance may outlive the harness handler timeout. A new
+ * utterance interrupts the previous one. Output routing: a saved sink
+ * becomes `pw-play --target <sink>` or `paplay --device=<sink>` (ffplay has
+ * no device concept and ignores it); with no saved sink the player's own
+ * default applies.
  */
 
 import { spawn, spawnSync, type ChildProcess } from "node:child_process";
@@ -185,25 +192,305 @@ export function playerFor(command: string, sink: string): Player {
   return { command, args: ["--target", sink] };
 }
 
-/** What a speech engine should say: prose only, no fences, no markup, bounded. */
+// ------------------------------------------------------------ segmenting
-export function stripForSpeech(text: string, maxChars: number = DEFAULT_MAX_CHARS): string {
+//
-  let out = text;
+// Ported from omp's built-in speak-aloud vocalizer (the `fHe` segmenter and
-  out = out.replace(/```[\s\S]*?```/g, " ");
+// its helpers in dist/cli.js). The same boundary rules as the stock path,
-  out = out.replace(/~~~[\s\S]*?~~~/g, " ");
+// kept deliberately: push() takes text and returns the segments that are
-  out = out.replace(/`([^`]*)`/g, "$1");
+// complete, flush() ends the message.
-  out = out.replace(/!\[[^\]]*\]\([^)]*\)/g, " ");
+
-  out = out.replace(/\[([^\]]*)\]\([^)]*\)/g, "$1");
+const SENTENCE_END = /[.!?\u2026]+[)\]"'\u00BB\u201D\u2019]*\s/g;
-  out = out.replace(/^\s{0,3}#{1,6}\s+/gm, "");
+const WEAK_BREAK = /[,;:\u2014\u2013]\s/g;
-  out = out.replace(/^\s*[-*+]\s+/gm, "");
+const ABBREVIATION = /(?:^|\s)(?:e\.g|i\.e|etc|vs|Mr|Mrs|Ms|Dr|St|No)\.$/i;
-  out = out.replace(/^\s*\|[-: |]+\|\s*$/gm, " ");
+const LINE_HEAD = /^(?:#{1,6}|[-*+]|-{2,}|\*{2,}|_{2,}|\d{1,3}|\d{1,3}[.)]|>+|`{1,2}|~{1,2})$/;
-  out = out.replace(/\|/g, " ");
+const HORIZONTAL_RULE = /^(?:-{3,}|\*{3,}|_{3,})\s*$/;
-  out = out.replace(/[*_]{1,3}([^*_]+)[*_]{1,3}/g, "$1");
+
-  out = out.replace(/\s+/g, " ").trim();
+const IMAGE_LINK = /!\[([^\]]*)\]\(([^()]*)\)/g;
-  if (out.length <= maxChars) return out;
+const LINK = /\[([^\]]+)\]\(([^()]*)\)/g;
-  const window = out.slice(0, maxChars);
+const BRACKETED_URL = /<(https?:\/\/[^\s>]+)>/g;
-  const cut = Math.max(window.lastIndexOf(". "), window.lastIndexOf("! "), window.lastIndexOf("? "));
+const BARE_URL = /\bhttps?:\/\/[^\s<>()"'\]]+|\bwww\.[\w-]+(?:\.[\w-]+)+[^\s<>()"'\]]*/g;
-  const clipped = cut > maxChars / 2 ? window.slice(0, cut + 1) : window.replace(/[,;:]\s*\S*$/, "");
+const INLINE_CODE = /`{1,2}([^`]+)`{1,2}/g;
-  return `${clipped.trim()} …`;
+const BOLD_MARKUP = /\*\*|__|~~/g;
+const STAR = /\*(?=\S)|(?<=\S)\*/g;
+const UNDERSCORE = /(^|\s)_+|_+(?=\s|$)/g;
+const HTML_TAG = /<\/?[a-zA-Z][^<>]*>/g;
+const EMPHASIS_RUN = /(^|\s)[-*_]{3,}(?=\s|$)/g;
+const DEEP_PATH = /(^|[\s("'`])((?:~|\.{1,2})?\/?[\w.@+-]+(?:\/[\w.@+-]+){2,}\/?)/g;
+const HAS_WORD = /[\p{L}\p{N}]/u;
+
+/** Speak a URL by host and a file path by its last segment. */
+export function spokenDomain(url: string): string {
+  return url.replace(/^[a-z][\w+.-]*:\/\//i, "").replace(/^www\./i, "").replace(/[/?#].*$/, "");
+}
+
+/** Final per-segment cleanup; empty when nothing speakable survived. */
+export function cleanForSpeech(text: string): string {
+  const out = text
+    .replace(IMAGE_LINK, "$1")
+    .replace(LINK, "$1")
+    .replace(BRACKETED_URL, (_match, url: string) => spokenDomain(url))
+    .replace(BARE_URL, (url: string) => spokenDomain(url))
+    .replace(INLINE_CODE, "$1")
+    .replace(BOLD_MARKUP, "")
+    .replace(STAR, "")
+    .replace(UNDERSCORE, "$1")
+    .replace(HTML_TAG, " ")
+    .replace(EMPHASIS_RUN, "$1")
+    .replace(DEEP_PATH, (_match, pre: string, path: string) => {
+      const parts = path.split("/").filter((part) => part.length > 0);
+      return pre + (parts[parts.length - 1] ?? path);
+    })
+    .replace(/\s+/g, " ")
+    .trim();
+  return HAS_WORD.test(out) ? out : "";
+}
+
+function sentenceBoundary(text: string, minChars: number): number {
+  SENTENCE_END.lastIndex = 0;
+  for (let match = SENTENCE_END.exec(text); match; match = SENTENCE_END.exec(text)) {
+    const end = match.index + match[0].length;
+    if (end < minChars) continue;
+    if (ABBREVIATION.test(text.slice(0, end).trimEnd())) continue;
+    if ((text.slice(0, end).match(/`/g)?.length ?? 0) % 2 !== 0) continue;
+    return end;
+  }
+  return -1;
+}
+
+function firstWeakBreak(text: string, minChars: number): number {
+  WEAK_BREAK.lastIndex = 0;
+  for (let match = WEAK_BREAK.exec(text); match; match = WEAK_BREAK.exec(text)) {
+    const end = match.index + match[0].length;
+    if (end >= minChars) return end;
+  }
+  return -1;
+}
+
+function lastWeakBreakWithin(text: string, minChars: number, maxChars: number): number {
+  WEAK_BREAK.lastIndex = 0;
+  let found = -1;
+  for (let match = WEAK_BREAK.exec(text); match; match = WEAK_BREAK.exec(text)) {
+    const end = match.index + match[0].length;
+    if (end > maxChars) break;
+    if (end >= minChars) found = end;
+  }
+  return found;
+}
+
+function wordWrapCut(text: string, maxChars: number): number {
+  const space = text.lastIndexOf(" ", maxChars);
+  return space > 0 ? space + 1 : Math.min(maxChars, text.length);
+}
+
+type LineHead =
+  | { kind: "swallow" }
+  | { kind: "fence"; fence: string }
+  | { kind: "marker"; spoken: string }
+  | { kind: "prose"; text: string }
+  | { kind: "undecided" };
+
+/** Classify a line start: tables and fences swallow, list markers get spoken. */
+export function classifyLineHead(head: string): LineHead {
+  if (head === "|") return { kind: "swallow" };
+  if (/^(?:`{3}|~{3})/.test(head)) return { kind: "fence", fence: head.slice(0, 3) };
+  if (/^#{1,6}[ \t]/.test(head)) return { kind: "marker", spoken: "" };
+  if (/^[-*+][ \t]/.test(head)) return { kind: "marker", spoken: "" };
+  const ordered = /^(\d{1,3})[.)][ \t]/.exec(head);
+  if (ordered) return { kind: "marker", spoken: `${ordered[1]}, ` };
+  if (/^>+/.test(head) && !/^>+$/.test(head)) return { kind: "prose", text: head.replace(/^>+[ \t]?/, "") };
+  if (LINE_HEAD.test(head)) return { kind: "undecided" };
+  return { kind: "prose", text: head };
+}
+
+type SegmenterState = "linestart" | "prose" | "swallow" | "code";
+
+/** The built-in vocalizer's segmenter: streamed text in, speakable segments out. */
+export class SpeechSegmenter {
+  #state: SegmenterState = "linestart";
+  #head = "";
+  #fence = "";
+  #fenceLine = "";
+  #resume: SegmenterState = "linestart";
+  #buffer = "";
+  #started = false;
+
+  push(chunk: string): string[] {
+    const out: string[] = [];
+    for (const char of chunk) this.#feed(char, out);
+    this.#split(out);
+    return out;
+  }
+
+  flush(): string[] {
+    const out: string[] = [];
+    if (this.#state === "linestart" && this.#head.length > 0 && !HORIZONTAL_RULE.test(this.#head)) this.#buffer += this.#head;
+    this.#head = "";
+    this.#state = "linestart";
+    this.#emit(out);
+    return out;
+  }
+
+  /** Streaming idle flush: only cut a tail that already looks finished. */
+  flushIdle(): string[] {
+    const out: string[] = [];
+    const tail = this.#buffer.trimEnd();
+    if (!/[.!?\u2026][)\]"'\u00BB\u201D\u2019]*$/.test(tail) && tail.length < 24) return out;
+    this.#emit(out);
+    return out;
+  }
+
+  #feed(char: string, out: string[]): void {
+    switch (this.#state) {
+      case "linestart":
+        this.#feedLineStart(char, out);
+        return;
+      case "prose":
+        if (char === "\n") this.#endLine(out);
+        else this.#buffer += char;
+        return;
+      case "swallow":
+        if (char === "\n") this.#state = this.#resume;
+        return;
+      case "code":
+        this.#feedCode(char);
+        return;
+    }
+  }
+
+  #feedLineStart(char: string, out: string[]): void {
+    if (char === "\n") {
+      const head = this.#head;
+      this.#head = "";
+      if (head.length > 0 && !HORIZONTAL_RULE.test(head)) this.#buffer += head;
+      this.#endLine(out);
+      return;
+    }
+    this.#head += char;
+    const classified = classifyLineHead(this.#head);
+    if (classified.kind === "undecided") {
+      if (this.#head.length > 8) {
+        this.#buffer += this.#head;
+        this.#head = "";
+        this.#state = "prose";
+      }
+      return;
+    }
+    this.#head = "";
+    switch (classified.kind) {
+      case "prose":
+        this.#buffer += classified.text;
+        this.#state = "prose";
+        return;
+      case "marker":
+        this.#buffer += classified.spoken;
+        this.#state = "prose";
+        return;
+      case "swallow":
+        this.#state = "swallow";
+        this.#resume = "linestart";
+        return;
+      case "fence":
+        this.#fence = classified.fence;
+        this.#fenceLine = "";
+        this.#state = "swallow";
+        this.#resume = "code";
+        return;
+    }
+  }
+
+  #feedCode(char: string): void {
+    if (char === "\n") {
+      this.#fenceLine = "";
+      return;
+    }
+    if (this.#fenceLine.length < 3) {
+      this.#fenceLine += char;
+      if (this.#fenceLine === this.#fence) {
+        this.#state = "swallow";
+        this.#resume = "linestart";
+      }
+    }
+  }
+
+  #endLine(out: string[]): void {
+    this.#state = "linestart";
+    this.#emit(out);
+  }
+
+  #emit(out: string[]): void {
+    this.#split(out);
+    const segment = this.#buffer;
+    this.#buffer = "";
+    this.#pushSegment(segment, out);
+  }
+
+  #split(out: string[]): void {
+    for (;;) {
+      const buffer = this.#buffer;
+      const boundary = sentenceBoundary(buffer, this.#started ? 24 : 12);
+      if (boundary !== -1 && boundary <= 280) {
+        this.#cut(boundary, out);
+        continue;
+      }
+      if (!this.#started && buffer.length >= 40) {
+        const weak = firstWeakBreak(buffer, 12);
+        if (weak !== -1 && weak <= 140) {
+          this.#cut(weak, out);
+          continue;
+        }
+        if (buffer.length >= 140) {
+          this.#cut(wordWrapCut(buffer, 140), out);
+          continue;
+        }
+      }
+      if (this.#started && buffer.length >= 160) {
+        const weak = lastWeakBreakWithin(buffer, 24, 160);
+        if (weak !== -1) {
+          this.#cut(weak, out);
+          continue;
+        }
+      }
+      if (buffer.length > 280) {
+        const weak = lastWeakBreakWithin(buffer, 24, 280);
+        this.#cut(weak !== -1 ? weak : wordWrapCut(buffer, 280), out);
+        continue;
+      }
+      return;
+    }
+  }
+
+  #cut(end: number, out: string[]): void {
+    const head = this.#buffer.slice(0, end);
+    this.#buffer = this.#buffer.slice(end);
+    this.#pushSegment(head, out);
+  }
+
+  #pushSegment(raw: string, out: string[]): void {
+    const cleaned = cleanForSpeech(raw);
+    if (!cleaned) return;
+    out.push(cleaned);
+    this.#started = true;
+  }
+}
+
+/** A whole message to speakable segments: the segmenter run start to end. */
+export function segmentsForSpeech(text: string): string[] {
+  const segmenter = new SpeechSegmenter();
+  const segments = segmenter.push(text);
+  for (const tail of segmenter.flush()) segments.push(tail);
+  return segments;
+}
+
+/** The leading whole segments that fit the user's spoken-character budget. */
+export function budgetSegments(segments: string[], maxChars: number): string[] {
+  const chosen: string[] = [];
+  let used = 0;
+  for (const segment of segments) {
+    if (used + segment.length > maxChars) break;
+    used += segment.length;
+    chosen.push(segment);
+  }
+  return chosen;
 }
 
 /** The text the assistant last actually said; tool-only messages do not count. */
@@ -408,14 +695,16 @@ function startPlayback(player: Player, file: string, dir: string): ChildProcess
 
 export default function dankvoice(pi: ExtensionAPI) {
   const cfg = loadConfig();
-  const state: { auto: boolean; voice: string; child?: ChildProcess; lastCtx?: ExtensionContext } = {
+  const state: { auto: boolean; voice: string; child?: ChildProcess; run: number; lastCtx?: ExtensionContext } = {
     auto: cfg.auto,
     voice: cfg.voice,
+    run: 0,
   };
   const voiceLabel = () => state.voice || "server default";
   const reflectStatus = () => state.lastCtx?.ui.setStatus("dankvoice", state.auto ? `🔊 ${voiceLabel()}` : undefined);
 
   const stop = () => {
+    state.run += 1; // retire the live chain; its loop stops at the next gate
     if (state.child && state.child.exitCode === null) state.child.kill("SIGTERM");
     state.child = undefined;
   };
@@ -455,9 +744,12 @@ export default function dankvoice(pi: ExtensionAPI) {
     persistSettings(ctx);
   };
 
+  /**
+   * Speak one answer as strictly sequential requests: synthesize a segment,
+   * play it to the end, only then ask for the next — audio never stacks.
+   * Superseded chains (new utterance, /say stop, disarm) exit at the gates.
+   */
   async function speak(ctx: ExtensionContext, text: string) {
-    const spoken = stripForSpeech(text, cfg.maxChars);
-    if (!spoken) return;
     if (!cfg.target) {
       ctx.ui.notify(missingTarget(), "error");
       return;
@@ -466,19 +758,36 @@ export default function dankvoice(pi: ExtensionAPI) {
       ctx.ui.notify("dankvoice: no audio player found (pw-play, paplay or ffplay)", "error");
       return;
     }
+    const target = cfg.target;
+    const player = cfg.player;
+    const segments = budgetSegments(segmentsForSpeech(text), cfg.maxChars);
+    if (segments.length === 0) return;
     stop();
-    const dir = mkdtempSync(join(tmpdir(), "dankvoice-"));
+    const run = state.run;
-    try {
+    for (const segment of segments) {
-      const file = await synthesize(cfg.target, speechBody(cfg.target.model, spoken, state.voice), dir, SYNTH_TIMEOUT_MS);
+      if (state.run !== run) return;
-      state.child = startPlayback(cfg.player, file, dir);
+      const dir = mkdtempSync(join(tmpdir(), "dankvoice-"));
-    } catch (error) {
-      stop();
       try {
-        rmSync(dir, { recursive: true, force: true });
+        const file = await synthesize(target, speechBody(target.model, segment, state.voice), dir, SYNTH_TIMEOUT_MS);
-      } catch {
+        if (state.run !== run) {
-        // ignore
+          rmSync(dir, { recursive: true, force: true });
+          return;
+        }
+        await new Promise<void>((resolve) => {
+          const child = startPlayback(player, file, dir);
+          state.child = child;
+          child.once("exit", () => resolve());
+          child.once("error", () => resolve());
+        });
+      } catch (error) {
+        try {
+          rmSync(dir, { recursive: true, force: true });
+        } catch {
+          // temp files are not worth a toast
+        }
+        ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error");
+        return;
       }
-      ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error");
     }
   }
 
@@ -603,13 +912,13 @@ export default function dankvoice(pi: ExtensionAPI) {
           );
           return;
         case "speak":
-          await speak(ctx, action.text);
+          void speak(ctx, action.text).catch((error) => ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error"));
           return;
       }
     },
   });
 
-  pi.on("agent_end", async (event, ctx) => {
+  pi.on("agent_end", (event, ctx) => {
     state.lastCtx = ctx;
     if (!state.auto) return;
     // `willContinue` means the harness already scheduled a continuation
@@ -617,7 +926,12 @@ export default function dankvoice(pi: ExtensionAPI) {
     // settle, so narrating it would speak an answer the model is about to redo.
     if (event.willContinue) return;
     if (ctx.mode === "print" || ctx.mode === "json") return;
-    await speak(ctx, lastAssistantText(event.messages));
+    // Fire-and-forget: a multi-segment utterance legitimately outlives the
+    // harness's handler timeout, and blocking here would only produce a
+    // spurious "handler timed out" toast while playback continues anyway.
+    void speak(ctx, lastAssistantText(event.messages)).catch((error) =>
+      ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error"),
+    );
   });
 
   pi.on("session_shutdown", () => {

omp-docs/core/dankvoice.md

@@ -9,8 +9,8 @@ tags:
   - voice
   - frank-tts
   - dankclaw
-verified: 2026-10-18
+verified: 2026-10-19
-timestamp: 2026-10-18
+timestamp: 2026-10-19
 ---
 
 # dankvoice
@@ -54,9 +54,38 @@ player and device — the audible proof whenever a session "has say on" but
 stays silent.
 
 Auto-speak is skipped in `print`/`json` mode so benches and pipelines stay
-silent. Markdown is stripped before synthesis — fenced code is dropped, links
+silent. A long answer is never one monolithic synthesis request; see
-collapse to their label, bullets and table pipes disappear — and the utterance
+[Segmentation](#segmentation) for how utterances are cut and played.
-is truncated at a sentence boundary inside the cap.
+
+## Segmentation
+
+Utterances are cut by a state machine ported from the harness's own
+speak-aloud vocalizer (the minified `fHe` class in the agent bundle's
+`dist/cli.js`), kept deliberately in lockstep with the stock path:
+
+* A strong boundary is a run of `[.!?…]` followed by whitespace — so
+  `!!!!!` and `...` are one boundary, never a pile of cuts.
+* Boundaries after `e.g.`, `etc.`, `Mr.` and friends, or inside inline
+  code, don't count; decimals (`3.5`, `1,5`) survive because a boundary
+  requires trailing whitespace.
+* Line starts are classified: table rows and fenced code are swallowed
+  whole (their content is never read aloud), heading and bullet markers
+  vanish, ordered-list markers speak their number ("1, …"), quote markers
+  strip.
+* Per segment, markdown is cleaned: links collapse to their label, URLs
+  to their host, deep paths to their last segment; emphasis markup dies.
+* Segments aim for one sentence; run-ons break at commas or word wraps
+  before 280 characters.
+
+Playback is strictly sequential: segment N+1 is synthesized only after
+segment N's player process exited, so audio never stacks. The chain runs
+detached from `agent_end` (fire-and-forget) and may legitimately outlive
+the harness's 30 s handler timeout — the old awaiting design produced a
+"handler timed out after 30000ms" toast on long answers. A new utterance,
+`/say stop`, or disarming auto-speak retires the live chain through a run
+token: the current player is killed and pending segments are skipped.
+`DANKVOICE_MAX` is a per-answer character budget: the leading whole
+segments that fit are spoken, the rest are dropped.
 
 ## Endpoint resolution
 
@@ -73,7 +102,7 @@ resolves, so no host address and no credential appears in this file. From
 | `DANKVOICE_CONFIG` | `~/.omp/cache/dankvoice.json` | persisted menu choices (voice, player, sink, cap, auto) |
 | `DANKVOICE_VOICE` | empty (server default) | default voice name |
 | `DANKVOICE_AUTO=1` | off | start with auto-speak armed |
-| `DANKVOICE_MAX` | `700` | spoken characters per utterance |
+| `DANKVOICE_MAX` | `700` | spoken character budget per answer (whole leading segments) |
 | `DANKVOICE_PLAYER` | detect | player binary, skipping detection |
 | `DANKVOICE_MODELS` | `~/.omp/agent/models.yml` | YAML to read the endpoint from |
 
@@ -86,7 +115,7 @@ if wireplumber is unreachable the menu offers only "system default". Each
 utterance is written to `$TMPDIR/dankvoice-*/say-<ms>.wav` and the file plus
 its directory are removed when the player process exits.
 
-## Verified facts (2026-10-18)
+## Verified facts (2026-10-18, 2026-10-19)
 
 * **Extension discovery** — any `.ts` file in `~/.omp/agent/extensions/` loads
   at startup: a probe file there printed `loaded 2026-10-19T02:36:55Z` from a
@@ -118,6 +147,12 @@ its directory are removed when the player process exits.
   menu is used by later utterances and survives a fresh load via the settings
   file; a device chosen in the menu appears in the player invocation as
   `--target <sink>`.
+* **Segmented playback** — driver scenarios 2026-10-19: "First stop here.
+  Second one goes!!! Really? Third ... done" produced exactly 3 sequential
+  requests and 3 plays; "Model 3.5 ships today. Version 1,5 too." produced
+  exactly 2 (decimals never split); the markdown fixture's fenced code and
+  URL never reached the fixture endpoint; with `DANKVOICE_MAX=60` only the
+  leading segment was spoken. `bats tests/dankvoice.bats` 17/17.
 
 ## Limits
 
@@ -141,6 +176,12 @@ its directory are removed when the player process exits.
 * `omp --help` (extension discovery flags, `say`, `plugin`) and
   `@earendil-works/pi-coding-agent` `dist/core/extensions/types.d.ts`
   (`ExtensionAPI.on/registerCommand`, `ExtensionMode = "tui" | "rpc" | "json" | "print"`).
+* The stock speak-aloud implementation — vocalizer pipeline `I6o` and
+  utterance segmenter `fHe` — in `@oh-my-pi/pi-coding-agent`'s
+  `dist/cli.js`, read off the minified bundle 2026-10-19; the enhanced
+  rewrite ("with the tiny/smol model before synthesis") is that bundle's
+  own `speech.enhanced` description. dankvoice ports the mechanical half
+  only: no LLM rewrite happens before frank-tts.
 * Gitea issue #21 on `dank/command-center` (the work item this page ships with).
 * Gitea issue #23 on `dank/command-center` (the options-menu work item).
 

omp-docs/log.md

@@ -12,6 +12,29 @@ timestamp: 2026-08-28
 # Bundle Change Log
 
 
+## 2026-10-19 — dankvoice: segmented sequential speech, copied from the bundle's vocalizer
+
+Silent-answer incident follow-up: `agent_end` awaiting one whole-answer
+synthesis hit the harness's 30 s extension-handler timeout
+(`handler timed out after 30000ms`) on long answers, and the single frank-tts
+request for the entire answer was the stall. Instead of inventing a heuristic,
+ported the utterance-splitting state machine out of the built-in speak-aloud
+vocalizer (minified class `fHe` in `dist/cli.js`): strong boundaries are
+`[.!?…]+` runs followed by whitespace — `!!!!!`/`...` stay one cut — with
+abbreviation and inline-code guards; `3.5`/`1,5` survive because a boundary
+needs trailing whitespace; fenced code and tables swallow whole; headings and
+bullets vanish, ordered markers speak their number ("1, "); links collapse to
+labels, URLs to hosts, paths to basenames; run-ons break at commas or word
+wraps before 280 chars. `speak()` now synthesizes segment N+1 only after
+segment N's player exited — strictly sequential, audio never stacks — and
+`agent_end`/`/say <text>` fire-and-forget a chain retired through a run token
+by `/say stop`, disarming, or a newer utterance. `DANKVOICE_MAX` became a
+per-answer budget of whole leading segments; the hand-rolled `stripForSpeech`
+truncator is gone. No LLM "humanization" rewrite happens (the bundle's
+`speech.enhanced` rewrites with the tiny/smol model; dankvoice speaks
+mechanically cleaned text through the cloned voices). Tests: two new driver
+scenarios plus two rewrites, 17/17 in `tests/dankvoice.bats`.
+
 ## 2026-10-18 — dankvoice: `/say` options menu with output-device routing (Refs #23)
 
 Added `/say menu` (bare `/say` now opens it; `help` keeps the text listing), the

tests/dankvoice.bats

@@ -189,6 +189,12 @@ if (!say) {
     case "truncate":
       await say.handler("Sentence one is here. ".repeat(40), ctx);
       break;
+    case "sentences":
+      await say.handler("First stop here. Second one goes!!! Really? Third ... done", ctx);
+      break;
+    case "decimals":
+      await say.handler("Model 3.5 ships today. Version 1,5 too.", ctx);
+      break;
     case "noplayer":
       await say.handler("speak anyway", ctx);
       break;
@@ -280,13 +286,34 @@ say_run() {
 
 @test "markdown never reaches the speech engine" {
   say_run markdown
-  [[ "$output" == *"input=Title Use pw-play here. see docs and bold a b"* ]]
+  [[ "$output" == *"input=Title"* ]]
+  [[ "$output" == *"input=Use pw-play here."* ]]
+  [[ "$output" == *"input=see docs and bold"* ]]
+  [[ "$output" != *"npm i x"* ]]
+  [[ "$output" != *"example.test"* ]]
 }
 
-@test "an over-long utterance is bounded and cut at a sentence boundary" {
+@test "the spoken budget keeps only the leading whole segments" {
   DANKVOICE_MAX=60 say_run truncate
-  [[ "$output" == *"here. …"* ]]
+  [[ "$output" == *"CALLS 1"* ]]
-  [ "$(grep -o 'Sentence one is here\.' <<<"$output" | wc -l)" -le 4 ]
+  [[ "$output" == *"PLAYS 1"* ]]
+  [[ "$output" == *"input=Sentence one is here."* ]]
+}
+
+@test "a long answer is spoken as sequential sentence-sized requests" {
+  say_run sentences
+  [[ "$output" == *"CALLS 3"* ]]
+  [[ "$output" == *"PLAYS 3"* ]]
+  [[ "$output" == *"input=First stop here."* ]]
+  [[ "$output" == *"input=Second one goes!!! Really?"* ]]
+  [[ "$output" == *"input=Third ... done"* ]]
+}
+
+@test "decimals and comma-decimals never split a sentence" {
+  say_run decimals
+  [[ "$output" == *"CALLS 2"* ]]
+  [[ "$output" == *"input=Model 3.5 ships today."* ]]
+  [[ "$output" == *"input=Version 1,5 too."* ]]
 }
 
 @test "a missing player is reported, not swallowed" {