dankvoice: speak long answers as sequential sentence-sized requests

agent_end awaited one whole-answer synthesis; long answers hit the
harness 30s extension-handler timeout (handler timed out after 30000ms)
and the single frank-tts request was the stall. Port the built-in
speak-aloud vocalizer's utterance segmenter (fHe in dist/cli.js) so
segmentation matches the known-working stock path: [.!?…]-run
boundaries, abbreviation/decimal/inline-code guards, fenced code and
tables swallowed, markup cleaned. Play segment N to player exit before
synthesizing N+1 (audio never stacks); fire-and-forget the chain so
utterances outlive the handler timeout; a run token retires superseded
chains. DANKVOICE_MAX becomes a per-answer budget of whole segments;
stripForSpeech is gone. Refs #23 follow-up.

agent/config.yml

@@ -1,6 +1,10 @@
 providers:
   openrouterVariant: online
   fetch: auto
+  maxInFlightRequests:
+    llamacpp (dankserver): 3
+    llamacpp (dankclaw): 2
+    llamacpp (dankclaw-3090): 3
 modelRoles:
   slow: llamacpp (dankclaw)/frank-dragoon:medium
   vision: llamacpp (dankclaw-3090)/frank-zealot:xhigh
@@ -13,7 +17,7 @@ modelRoles:
   default: llamacpp (dankserver)/frank-archon:medium
   smol: llamacpp (dankclaw-3090)/frank-zealot:medium
   web: web/searxng
-  speech: local/kokoro
+  speech: frank-tts (dankclaw)/frank-tts
   judge: openrouter/~typesafe/jev-latest:auto
   dictation: local/parakeet-tdt-0.6b-v3
   memory: llamacpp (dankclaw-3090)/frank-zealot:medium
@@ -145,17 +149,24 @@ display:
   subagentLivePreview: true
 task:
   showResolvedModelBadge: true
-  maxConcurrency: 3
+  maxConcurrency: 2
   agentModelOverrides:
     designer: llamacpp (dankclaw-3090)/frank-zealot
     librarian: llamacpp (dankclaw-3090)/frank-zealot
     reviewer: llamacpp (dankserver)/frank-archon
-    scout: llamacpp (dankserver)/frank-archon
+    scout: llamacpp (dankclaw-3090)/frank-zealot
     security-reviewer: llamacpp (dankclaw)/frank-dragoon
     sonic: llamacpp (dankclaw-3090)/frank-zealot
     task: llamacpp (dankserver)/frank-archon
   eager: default
   enableLsp: true
+  maxRuntimeMs: 1800000
+  softRequestBudget: 120
+  maxRecursionDepth: 1
+  disabledAgents: []
+  isolation:
+    enabled: true
+  completionProbe: false
 snapcompact:
   systemPrompt: none
   toolResults: false
@@ -203,8 +214,8 @@ vault:
 tts:
   localVoice: bm_george
 speech:
-  enabled: true
-  mode: yield
+  enabled: false
+  mode: all
   enhanced: true
   voice: am_fenrir
 secrets:
@@ -232,6 +243,7 @@ followUpMode: one-at-a-time
 tools:
   approvalMode: yolo
   format: auto
+  maxTimeout: 600
 marketplace:
   autoUpdate: notify
 bash:

agent/extensions/dankvoice.ts

@@ -0,0 +1,940 @@
+/**
+ * dankvoice — cloned-voice vocalization for omp, served by frank-tts.
+ *
+ * The built-in speak-aloud feature (`speech.enabled` / `speech.voice`) and the
+ * `omp say` CLI are gated to the bundled Kokoro voice enum, so the cloned
+ * voices on frank-tts (Dankclaw :7772, the `speech` model role in
+ * agent/models.yml) could only ever produce files. This extension adds the
+ * missing path — the TUI speaks with the cloned voices:
+ *
+ *   /say                   open the options menu
+ *   /say <text>            speak once through the speakers
+ *   /say on | off          arm/disarm auto-speak of the assistant's final answer
+ *   /say menu              the options menu (voice, output device, player, cap)
+ *   /say voice <name>      choose a voice (empty = whatever the server defaults to)
+ *   /say voices            list the voices frank-tts reports
+ *   /say stop              cut off the current utterance
+ *   /say status            voice, endpoint, player and device in use
+ *   /say help              the command list
+ *
+ * The endpoint comes from agent/models.yml — the provider block carrying
+ * `api: openai-speech`, i.e. the same row the speech role resolves — so this
+ * file carries no host address and no secret. Menu choices persist to
+ * ~/.omp/cache/dankvoice.json (runtime state, never tracked). Environment
+ * overrides win over the file, which wins over defaults:
+ *
+ *   DANKVOICE_URL      speech base URL (…/v1) instead of models.yml
+ *   DANKVOICE_MODEL    served model id (default: the id in that block)
+ *   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 budget per answer (default 700)
+ *   DANKVOICE_AUTO=1   start with auto-speak armed
+ *
+ * Long answers are cut into speakable segments by a state machine ported
+ * from omp's built-in vocalizer: strong boundaries on [.!?…] runs followed
+ * by whitespace (so "!!!!!" and "..." stay one boundary), guards for
+ * abbreviations and decimals, code fences and tables swallowed, markdown
+ * 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";
+import { mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import type { ExtensionAPI, ExtensionContext } from "@earendil-works/pi-coding-agent";
+
+const DEFAULT_MAX_CHARS = 700;
+const SYNTH_TIMEOUT_MS = 60_000;
+const VOICES_TIMEOUT_MS = 15_000;
+/** A voice name the shim must reject; its 400 body carries the real list. */
+const VOICE_PROBE = "_dankvoice_probe_";
+
+// ---------------------------------------------------------------- pure logic
+
+export interface SpeechTarget {
+  /** POST target for OpenAI speech synthesis. */
+  speechUrl: string;
+  /** GET target for the voice roster (frank-tts answers a bare JSON array). */
+  voicesUrl: string;
+  /** GET target for the liveness route of the same host:port. */
+  healthUrl: string;
+  /** Served model id to name in the request body. */
+  model: string;
+}
+
+export interface Player {
+  command: string;
+  args: string[];
+}
+
+export type SayAction =
+  | { kind: "menu" }
+  | { kind: "help" }
+  | { kind: "speak"; text: string }
+  | { kind: "on" }
+  | { kind: "off" }
+  | { kind: "stop" }
+  | { kind: "voices" }
+  | { kind: "status" }
+  | { kind: "voice"; name: string };
+
+/** `/say <args>` grammar: subcommands win, anything else is spoken text. */
+export function parseSayArgs(raw: string): SayAction {
+  const args = raw.trim();
+  const lower = args.toLowerCase();
+  if (lower === "" || lower === "menu") return { kind: "menu" };
+  if (lower === "help") return { kind: "help" };
+  if (lower === "on") return { kind: "on" };
+  if (lower === "off") return { kind: "off" };
+  if (lower === "stop") return { kind: "stop" };
+  if (lower === "voices") return { kind: "voices" };
+  if (lower === "status") return { kind: "status" };
+  if (lower === "voice" || lower.startsWith("voice ")) return { kind: "voice", name: args.slice(5).trim() };
+  return { kind: "speak", text: args };
+}
+
+/**
+ * Pull the speech endpoint out of agent/models.yml. The runner API lives on
+ * the MODEL row (`api: openai-speech`), the base URL on its provider, so this
+ * scan remembers the last provider base URL and model id seen and returns when
+ * a model row claims the speech runner API. A new provider key (indent two)
+ * resets both.
+ */
+export function resolveSpeechEndpoint(modelsYml: string): SpeechTarget | undefined {
+  let base: string | undefined;
+  let id: string | undefined;
+  for (const line of modelsYml.split(/\r?\n/)) {
+    const trimmed = line.trim();
+    if (!trimmed || trimmed.startsWith("#")) continue;
+    if (/^ {2}\S.*:\s*$/.test(line)) {
+      base = undefined;
+      id = undefined;
+      continue;
+    }
+    const providerUrl = trimmed.match(/^baseUrl:\s*(\S+)/);
+    if (providerUrl) {
+      base = providerUrl[1].replace(/\/+$/, "");
+      continue;
+    }
+    const modelId = trimmed.match(/^-\s*id:\s*(\S+)/);
+    if (modelId) {
+      id = modelId[1];
+      continue;
+    }
+    if (/^api:\s*openai-speech\s*$/.test(trimmed) && base) {
+      return {
+        speechUrl: `${base}/audio/speech`,
+        voicesUrl: `${base}/audio/voices`,
+        healthUrl: `${base.replace(/\/v1$/, "")}/health`,
+        model: id ?? "frank-tts",
+      };
+    }
+  }
+  return undefined;
+}
+
+/** OpenAI speech body; `voice` is sent only when named — the shim carries its own default. */
+export function speechBody(model: string, text: string, voice: string): Record<string, string> {
+  const body: Record<string, string> = { model, input: text, response_format: "wav" };
+  if (voice) body.voice = voice;
+  return body;
+}
+
+/** Voice names as frank-tts reports them: the invalid-voice 400 body carries `available_voices`. */
+export function parseVoices(payload: unknown): string[] {
+  // frank-tts answers GET /v1/audio/voices with a bare array and an unknown voice with
+  // {error:{available_voices:[…]}}; a flat body is accepted too.
+  if (typeof payload !== "object" || payload === null) return [];
+  let list: unknown;
+  if (Array.isArray(payload)) {
+    list = payload;
+  } else if ("error" in payload && typeof payload.error === "object" && payload.error !== null && "available_voices" in payload.error) {
+    list = payload.error.available_voices;
+  } else if ("available_voices" in payload) {
+    list = payload.available_voices;
+  } else if ("voices" in payload) {
+    list = payload.voices;
+  } else if ("data" in payload) {
+    list = payload.data;
+  }
+  if (!Array.isArray(list)) return [];
+  const names: string[] = [];
+  for (const entry of list) {
+    if (typeof entry === "string") {
+      names.push(entry);
+    } else if (typeof entry === "object" && entry !== null) {
+      const name = "id" in entry ? entry.id : "name" in entry ? entry.name : undefined;
+      if (typeof name === "string") names.push(name);
+    }
+  }
+  return names.filter((name) => name.length > 0);
+}
+
+/** Known players, PipeWire first (the workstations run WirePlumber); first existing wins. */
+export function availablePlayers(lookup: (command: string) => string | null): string[] {
+  return ["pw-play", "paplay", "ffplay"].filter((command) => lookup(command) !== null);
+}
+
+/** One player invocation: the saved sink becomes each player's routing dialect. */
+export function playerFor(command: string, sink: string): Player {
+  const base = command.split("/").pop() ?? command;
+  if (base === "ffplay") return { command, args: ["-nodisp", "-autoexit", "-loglevel", "quiet"] };
+  if (!sink) return { command, args: [] };
+  if (base === "paplay") return { command, args: [`--device=${sink}`] };
+  return { command, args: ["--target", sink] };
+}
+
+// ------------------------------------------------------------ segmenting
+//
+// Ported from omp's built-in speak-aloud vocalizer (the `fHe` segmenter and
+// its helpers in dist/cli.js). The same boundary rules as the stock path,
+// kept deliberately: push() takes text and returns the segments that are
+// complete, flush() ends the message.
+
+const SENTENCE_END = /[.!?\u2026]+[)\]"'\u00BB\u201D\u2019]*\s/g;
+const WEAK_BREAK = /[,;:\u2014\u2013]\s/g;
+const ABBREVIATION = /(?:^|\s)(?:e\.g|i\.e|etc|vs|Mr|Mrs|Ms|Dr|St|No)\.$/i;
+const LINE_HEAD = /^(?:#{1,6}|[-*+]|-{2,}|\*{2,}|_{2,}|\d{1,3}|\d{1,3}[.)]|>+|`{1,2}|~{1,2})$/;
+const HORIZONTAL_RULE = /^(?:-{3,}|\*{3,}|_{3,})\s*$/;
+
+const IMAGE_LINK = /!\[([^\]]*)\]\(([^()]*)\)/g;
+const LINK = /\[([^\]]+)\]\(([^()]*)\)/g;
+const BRACKETED_URL = /<(https?:\/\/[^\s>]+)>/g;
+const BARE_URL = /\bhttps?:\/\/[^\s<>()"'\]]+|\bwww\.[\w-]+(?:\.[\w-]+)+[^\s<>()"'\]]*/g;
+const INLINE_CODE = /`{1,2}([^`]+)`{1,2}/g;
+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. */
+export function lastAssistantText(messages: readonly unknown[]): string {
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const message = messages[i];
+    if (!message || typeof message !== "object" || !("role" in message) || message.role !== "assistant") continue;
+    if (!("content" in message)) continue;
+    const content = message.content;
+    if (typeof content === "string") return content;
+    if (!Array.isArray(content)) continue;
+    const parts: string[] = [];
+    for (const part of content) {
+      if (part && typeof part === "object" && "type" in part && part.type === "text" && "text" in part && typeof part.text === "string") {
+        parts.push(part.text);
+      }
+    }
+    const joined = parts.join("\n").trim();
+    if (joined) return joined;
+  }
+  return "";
+}
+
+/** Menu choices, persisted between sessions; every field optional. */
+export interface Settings {
+  voice?: string;
+  player?: string;
+  sink?: string;
+  maxChars?: number;
+  auto?: boolean;
+}
+
+/** Where menu choices live: DANKVOICE_CONFIG, else ~/.omp/cache/dankvoice.json. */
+export function settingsPath(env: NodeJS.ProcessEnv): string {
+  return env.DANKVOICE_CONFIG?.trim() || join(env.HOME ?? "", ".omp", "cache", "dankvoice.json");
+}
+
+export function readSettings(path: string): Settings {
+  try {
+    const parsed: unknown = JSON.parse(readFileSync(path, "utf8"));
+    if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) return {};
+    const raw = parsed as Record<string, unknown>;
+    const settings: Settings = {};
+    if (typeof raw.voice === "string") settings.voice = raw.voice;
+    if (typeof raw.player === "string") settings.player = raw.player;
+    if (typeof raw.sink === "string") settings.sink = raw.sink;
+    if (typeof raw.maxChars === "number" && Number.isFinite(raw.maxChars) && raw.maxChars > 0) settings.maxChars = Math.floor(raw.maxChars);
+    if (typeof raw.auto === "boolean") settings.auto = raw.auto;
+    return settings;
+  } catch {
+    return {};
+  }
+}
+
+/** A sink row from `wpctl list audio sinks`: `116<TAB>alsa_output…<TAB>audio/sink<TAB>*`. */
+export interface SinkRow {
+  id: string;
+  name: string;
+}
+
+export function parseSinkList(output: string): SinkRow[] {
+  const rows: SinkRow[] = [];
+  for (const line of output.split("\n")) {
+    const cols = line.split("\t").map((col) => col.trim());
+    if (cols.length < 3 || !cols[2]?.includes("audio/sink")) continue;
+    const id = cols[0] ?? "";
+    const name = cols[1] ?? "";
+    if (!id || !name) continue;
+    rows.push({ id, name });
+  }
+  return rows;
+}
+
+// ------------------------------------------------------------- live wiring
+
+interface Config {
+  target?: SpeechTarget;
+  player?: Player;
+  sink: string;
+  maxChars: number;
+  auto: boolean;
+  voice: string;
+}
+
+function lookupOnPath(command: string): string | null {
+  const found = spawnSync("sh", ["-c", `command -v ${command}`], { encoding: "utf8" });
+  return found.status === 0 && found.stdout.trim() ? found.stdout.trim() : null;
+}
+
+function readModelsYml(): string {
+  const path = process.env.DANKVOICE_MODELS ?? join(process.env.HOME ?? "", ".omp", "agent", "models.yml");
+  try {
+    return readFileSync(path, "utf8");
+  } catch {
+    return "";
+  }
+}
+
+function loadConfig(): Config {
+  const env = process.env;
+  const settings = readSettings(settingsPath(env));
+  const overrideUrl = env.DANKVOICE_URL?.trim().replace(/\/+$/, "");
+  const modelOverride = env.DANKVOICE_MODEL?.trim();
+  const fromYml = overrideUrl ? undefined : resolveSpeechEndpoint(readModelsYml());
+  const target: SpeechTarget | undefined = overrideUrl
+    ? {
+        speechUrl: `${overrideUrl}/audio/speech`,
+        voicesUrl: `${overrideUrl}/audio/voices`,
+        healthUrl: `${overrideUrl.replace(/\/v1$/, "")}/health`,
+        model: modelOverride || "frank-tts",
+      }
+    : fromYml
+      ? { ...fromYml, model: modelOverride || fromYml.model }
+      : undefined;
+  const playerCommand = env.DANKVOICE_PLAYER?.trim() || settings.player || availablePlayers(lookupOnPath)[0];
+  const sink = settings.sink ?? "";
+  const maxChars = Number(env.DANKVOICE_MAX);
+  return {
+    target,
+    player: playerCommand ? playerFor(playerCommand, sink) : undefined,
+    sink,
+    maxChars: Number.isFinite(maxChars) && maxChars > 0 ? Math.floor(maxChars) : (settings.maxChars ?? DEFAULT_MAX_CHARS),
+    auto: env.DANKVOICE_AUTO === "1" || (settings.auto ?? false),
+    voice: env.DANKVOICE_VOICE?.trim() ?? settings.voice ?? "",
+  };
+}
+
+/** PipeWire sinks via wpctl; empty when wireplumber is unreachable. */
+function listSinks(): SinkRow[] {
+  const probe = spawnSync("wpctl", ["list", "audio", "sinks"], { encoding: "utf8" });
+  return probe.status === 0 ? parseSinkList(probe.stdout) : [];
+}
+
+/** Synthesize one utterance into a WAV inside `dir`; throws with the endpoint's own message. */
+async function synthesize(target: SpeechTarget, body: Record<string, string>, dir: string, timeoutMs: number): Promise<string> {
+  const res = await fetch(target.speechUrl, {
+    method: "POST",
+    headers: { "content-type": "application/json" },
+    body: JSON.stringify(body),
+    signal: AbortSignal.timeout(timeoutMs),
+  });
+  const contentType = res.headers.get("content-type") ?? "";
+  if (!res.ok || contentType.includes("json")) {
+    let message = `frank-tts HTTP ${res.status}`;
+    try {
+      const payload: unknown = await res.json();
+      if (
+        typeof payload === "object" &&
+        payload !== null &&
+        "error" in payload &&
+        typeof payload.error === "object" &&
+        payload.error !== null &&
+        "message" in payload.error &&
+        typeof payload.error.message === "string"
+      ) {
+        message = payload.error.message;
+      }
+    } catch {
+      // keep the status-line message
+    }
+    throw new Error(message);
+  }
+  const bytes = new Uint8Array(await res.arrayBuffer());
+  if (bytes.byteLength === 0) throw new Error("frank-tts returned no audio");
+  const file = join(dir, `say-${Date.now()}.wav`);
+  writeFileSync(file, bytes);
+  return file;
+}
+
+/** frank-tts's roster route first; if it ever answers nothing, ask with a voice it must reject. */
+async function fetchVoices(target: SpeechTarget): Promise<string[]> {
+  const roster = await fetch(target.voicesUrl, { signal: AbortSignal.timeout(VOICES_TIMEOUT_MS) })
+    .then((res) => res.json())
+    .catch(() => undefined);
+  const listed = parseVoices(roster);
+  if (listed.length > 0) return listed;
+  const probe = await fetch(target.speechUrl, {
+    method: "POST",
+    headers: { "content-type": "application/json" },
+    body: JSON.stringify(speechBody(target.model, "voice list probe", VOICE_PROBE)),
+    signal: AbortSignal.timeout(VOICES_TIMEOUT_MS),
+  }).catch(() => undefined);
+  if (!probe) return [];
+  return parseVoices(await probe.json().catch(() => undefined));
+}
+
+/** Play a WAV and clean its temp directory up when the player exits. */
+function startPlayback(player: Player, file: string, dir: string): ChildProcess {
+  const child = spawn(player.command, [...player.args, file], { stdio: "ignore" });
+  const clean = () => {
+    try {
+      rmSync(file, { force: true });
+      rmSync(dir, { recursive: true, force: true });
+    } catch {
+      // temp files are not worth a toast
+    }
+  };
+  child.once("exit", clean);
+  child.once("error", clean);
+  return child;
+}
+
+export default function dankvoice(pi: ExtensionAPI) {
+  const cfg = loadConfig();
+  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 ? `🔊 ${voiceLabel()}` : undefined);
+
+  const stop = () => {
+    state.run += 1; // retire the live chain; its loop stops at the next gate
+    if (state.child && state.child.exitCode === null) state.child.kill("SIGTERM");
+    state.child = undefined;
+  };
+
+  const missingTarget = () => "dankvoice: no `api: openai-speech` provider in agent/models.yml (set DANKVOICE_URL)";
+
+  const persistSettings = (ctx: ExtensionContext) => {
+    const settings: Settings = {
+      voice: state.voice,
+      player: cfg.player?.command ?? "",
+      sink: cfg.sink,
+      maxChars: cfg.maxChars,
+      auto: state.auto,
+    };
+    try {
+      writeFileSync(settingsPath(process.env), `${JSON.stringify(settings, null, 2)}\n`);
+    } catch (error) {
+      ctx.ui.notify(`dankvoice: settings not saved: ${error instanceof Error ? error.message : String(error)}`, "warning");
+    }
+  };
+
+  const setVoice = (ctx: ExtensionContext, name: string) => {
+    state.voice = name;
+    reflectStatus();
+    ctx.ui.notify(name ? `dankvoice: voice = ${name}` : "dankvoice: voice = whatever frank-tts defaults to", "info");
+    persistSettings(ctx);
+  };
+
+  const setAuto = (ctx: ExtensionContext, on: boolean) => {
+    state.auto = on;
+    if (!on) stop();
+    reflectStatus();
+    ctx.ui.notify(
+      on ? `dankvoice: auto-speak armed (${voiceLabel()} @ ${cfg.target?.speechUrl ?? "no endpoint"})` : "dankvoice: auto-speak off",
+      "info",
+    );
+    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) {
+    if (!cfg.target) {
+      ctx.ui.notify(missingTarget(), "error");
+      return;
+    }
+    if (!cfg.player) {
+      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 run = state.run;
+    for (const segment of segments) {
+      if (state.run !== run) return;
+      const dir = mkdtempSync(join(tmpdir(), "dankvoice-"));
+      try {
+        const file = await synthesize(target, speechBody(target.model, segment, state.voice), dir, SYNTH_TIMEOUT_MS);
+        if (state.run !== run) {
+          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;
+      }
+    }
+  }
+
+  async function openMenu(ctx: ExtensionContext): Promise<void> {
+    const options = [
+      `Auto-speak: ${state.auto ? "on" : "off"} (toggle)`,
+      `Voice: ${voiceLabel()} (change)`,
+      `Output device: ${cfg.sink || "system default"} (change)`,
+      `Player: ${cfg.player?.command ?? "none"} (change)`,
+      `Spoken cap: ${cfg.maxChars} chars (change)`,
+      "Speak a test phrase",
+    ];
+    const choice = await ctx.ui.select("dankvoice — options", options);
+    if (!choice) return;
+    if (choice === options[0]) {
+      setAuto(ctx, !state.auto);
+      return;
+    }
+    if (choice === options[1]) {
+      if (!cfg.target) {
+        ctx.ui.notify(missingTarget(), "error");
+        return;
+      }
+      let voices: string[];
+      try {
+        voices = await fetchVoices(cfg.target);
+      } catch (error) {
+        ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error");
+        return;
+      }
+      const picked = await ctx.ui.select("dankvoice — voice", ["server default", ...voices]);
+      if (picked === undefined) return;
+      setVoice(ctx, picked === "server default" ? "" : picked);
+      return;
+    }
+    if (choice === options[2]) {
+      const picked = await ctx.ui.select("dankvoice — output device", ["system default", ...listSinks().map((sink) => sink.name)]);
+      if (picked === undefined) return;
+      cfg.sink = picked === "system default" ? "" : picked;
+      if (cfg.player) cfg.player = playerFor(cfg.player.command, cfg.sink);
+      ctx.ui.notify(`dankvoice: output device = ${cfg.sink || "system default"}`, "info");
+      persistSettings(ctx);
+      return;
+    }
+    if (choice === options[3]) {
+      const choices = [...new Set([cfg.player?.command, ...availablePlayers(lookupOnPath)].filter((c): c is string => Boolean(c)))];
+      if (choices.length === 0) {
+        ctx.ui.notify("dankvoice: no audio player found (pw-play, paplay or ffplay)", "error");
+        return;
+      }
+      const picked = await ctx.ui.select("dankvoice — player", choices);
+      if (picked === undefined) return;
+      cfg.player = playerFor(picked, cfg.sink);
+      ctx.ui.notify(`dankvoice: player = ${picked}`, "info");
+      persistSettings(ctx);
+      return;
+    }
+    if (choice === options[4]) {
+      const picked = await ctx.ui.select("dankvoice — spoken cap", ["300", "700", "1500", "3000"]);
+      const next = Number(picked);
+      if (!Number.isFinite(next) || next <= 0) return;
+      cfg.maxChars = next;
+      ctx.ui.notify(`dankvoice: cap = ${next} chars`, "info");
+      persistSettings(ctx);
+      return;
+    }
+    await speak(ctx, `dankvoice: ${voiceLabel()} through ${cfg.player?.command ?? "no player"}, checking.`);
+  }
+
+  pi.registerCommand("say", {
+    description:
+      "Speak with the fleet's cloned voices (frank-tts): /say (menu) | <text> | on | off | menu | voice <name> | voices | stop | status",
+    handler: async (args: string, ctx) => {
+      state.lastCtx = ctx;
+      const action = parseSayArgs(args);
+      switch (action.kind) {
+        case "menu":
+          await openMenu(ctx);
+          return;
+        case "help":
+          ctx.ui.notify(
+            "dankvoice: /say (menu) · /say <text> · /say on|off (auto-speak answers) · /say voice <name> · /say voices · /say stop · /say status",
+            "info",
+          );
+          return;
+        case "on":
+          setAuto(ctx, true);
+          return;
+        case "off":
+          setAuto(ctx, false);
+          return;
+        case "stop":
+          stop();
+          return;
+        case "voice":
+          setVoice(ctx, action.name);
+          return;
+        case "voices": {
+          if (!cfg.target) {
+            ctx.ui.notify(missingTarget(), "error");
+            return;
+          }
+          const voices: string[] = [];
+          try {
+            voices.push(...(await fetchVoices(cfg.target)));
+          } catch (error) {
+            ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error");
+            return;
+          }
+          ctx.ui.notify(
+            voices.length
+              ? `dankvoice voices: ${voices.join(", ")} — using ${voiceLabel()}`
+              : "dankvoice: frank-tts reported no voice list",
+            voices.length ? "info" : "warning",
+          );
+          return;
+        }
+        case "status":
+          ctx.ui.notify(
+            `dankvoice: voice ${voiceLabel()} · ${cfg.target?.speechUrl ?? "NO ENDPOINT"} · player ${cfg.player ? cfg.player.command : "NONE"} · device ${cfg.sink || "system default"} · auto-speak ${state.auto ? "on" : "off"} · cap ${cfg.maxChars} chars`,
+            "info",
+          );
+          return;
+        case "speak":
+          void speak(ctx, action.text).catch((error) => ctx.ui.notify(`dankvoice: ${error instanceof Error ? error.message : String(error)}`, "error"));
+          return;
+      }
+    },
+  });
+
+  pi.on("agent_end", (event, ctx) => {
+    state.lastCtx = ctx;
+    if (!state.auto) return;
+    // `willContinue` means the harness already scheduled a continuation
+    // (auto-retry, empty-stop retry): this is not the user-visible terminal
+    // 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;
+    // 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", () => {
+    stop();
+  });
+}

agent/managed-skills/audit-never-run-container-deploy/SKILL.md

@@ -0,0 +1,77 @@
+---
+name: audit-never-run-container-deploy
+description: "Audit a locally built podman/quadlet deploy path that has never actually run: prove base-image assumptions, env-file reader divergence, and image-hash coverage before the first deploy."
+---
+
+# Audit a never-run container deploy path
+
+A deployable that has never been built or started has never been *executed*: every
+fault in it is invisible to tests that stub the runtime. Audit it as static code
+against the tools it calls, then prove each suspicion cheaply against the real
+tool. The faults worth hunting are the ones that **report success while doing
+nothing** — those are the ones that survive a green `/health` and a green e2e run.
+
+## The three fault classes (all measured 2026-10-18, frank-tts-engine)
+
+1. **A command the base image does not ship.** e.g. `adduser` in a `RUN` line
+   against a trimmed `ubuntu:24.04` — absent, and not pulled in by
+   `ca-certificates curl libgomp1`. Dies at build time (loud), but only the first
+   time anyone builds it.
+   Prove it in the base, never from memory:
+   `podman run --rm <base> sh -c "command -v adduser || echo absent; useradd --system --uid 10000 --home-dir /app --shell /usr/sbin/nologin tts && id tts"`
+   Note the accepted cosmetic warning (`uid 10000 is greater than SYS_UID_MAX 999`)
+   in a comment, or a future agent "fixes" it by dropping `--system` and the uid
+   stops matching the sibling container.
+2. **Two readers of one env file disagree.** systemd units that pass
+   `EnvironmentFile=` hand it to podman `--env-file`, which does **no shell
+   parsing** — it takes the literal remainder of the line — while bash `source`
+   strips one quoting layer. So `WARM_TEXT="Warm up, one two three."` reaches the
+   container *with its quotes*, and a script that interpolates it into a JSON body
+   produces invalid JSON: the container boots, `active`, every voice registered,
+   every voice cold. Fix in the consumer: strip exactly one matched pair **only**
+   when both ends are the same quote AND the inner content carries another quote or
+   backslash (never mangle a value that legitimately contains quotes), then escape.
+3. **A build-skip hash that under-covers the image.** `build_compose_image`-style
+   helpers skip `podman build` when a label hash matches; hashing the `Containerfile`
+   alone means editing a `COPY`'d app/script rebuilds **nothing** — deploy reports
+   success, `/health` answers, container serves old code. Each case arm must name
+   the paths its `Containerfile` copies (`extra=(…)`) and hash Containerfile+extras.
+   Arms that have no extras keep their old hash, so they do not needlessly rebuild.
+
+## Test it as behaviour, never as a grep of the handler
+
+- Drive the **real** function: `awk '/^build_compose_image\(\) \{/,/^\}/' deploy-remote.sh > bci.sh`,
+  `source` it, put a stub `podman` first on `PATH`, assert the observable question —
+  *did the deploy ask podman to build, or did it skip?*
+- Stub traps that cost real time: podman is invoked `podman image inspect <image> --format …`
+  so the tag is **`$3`**, not `$2`; tags contain `/` so a state file named after one
+  needs `${tag//\//_}` or the write silently lands in a nonexistent directory and
+  every image looks permanently unbuilt; `--label cfhash=…` arrives **before** `-t <tag>`,
+  so collect the label and write it after the arg loop.
+- For an env-file bug, write one test that reads the file **both** ways — `source`
+  and the `--env-file` way (parse `KEY=literal remainder`) — and assert the program
+  receives the same value in both shapes, including a value that carries its own
+  quotes and a backslash. A suite that only sources the file is how the bug shipped.
+- Prove red: `git show HEAD:scripts/deploy-remote.sh > scripts/deploy-remote.sh`,
+  run the new test (must fail at the exact intended step), restore. Keep each fix in
+  its own commit and run the seam at each one so the branch bisects.
+
+## Base-image and host facts to check while auditing
+
+- `useradd` lives in `login(1)` (base carries it); `adduser` does not.
+- Rootless podman **cannot raise rlimits** — `--ulimit nofile=…` above the host hard
+  limit dies at container create, not at runtime.
+- A referenced `Network=` `.network` file the generator cannot find means the
+  container unit is **not produced at all**.
+- Two containers talk by DNS name only if they attach to a **common** network;
+  check both unit files rather than trusting a comment that says they share one.
+- Container DNS name + the network that owns it, never `host.containers.internal`
+  or a published loopback port, for service-to-service traffic.
+
+## Do not
+
+- Do not deploy the audited thing because the audit is finished: first build of a
+  heavy image (recursive source clone ~10 min) plus a new unit on a host serving
+  people is the operator's call.
+- Do not add a Prometheus target for a container with no `/metrics` — say the probe
+  is a decision (blackbox HTTP), do not fake a scrape.

agent/managed-skills/bounding-subagent-runtime/SKILL.md

@@ -1,82 +1,32 @@
 ---
 name: bounding-subagent-runtime
-description: "Cap and diagnose runaway or hung omp subagents: task.maxRuntimeMs, softRequestBudget, agentIdleTtlMs, per-agent model overrides, the cfg save-approval quirk, and the finished-work-but-never-exits nested-fanout deadlock."
+description: "Cap and diagnose runaway or hung omp subagents: task.maxRuntimeMs, softRequestBudget, maxConcurrency, maxRecursionDepth (the 0-trap), per-provider in-flight ceilings."
 ---
 
-# Bounding subagent runtime (omp harness)
+## When
+Subagent runs long, fan out too wide, or you must (re)declare the fleet's subagent limit policy. Also when asked "what limits can subagents have".
 
-Use when a `task`/`eval` subagent runs absurdly long (tens of minutes on a small job),
-when it **finishes its deliverable and still never exits**, when you want a hard cap
-before spawning, or when you must tell a busy agent to stop.
+## Read first
+- Repo KB page `omp-docs/pi/subagent-limits.md` — the live policy of record (values + rationale + deliberately-not-set list). Do not re-derive; read it.
+- `cfg://task` and `cfg://providers/maxInFlightRequests` — effective values, not the stock defaults.
 
-## The knobs (`cfg://task/...`)
-
-| Key | Default | Meaning |
+## The knobs (cfg:// writes; `/save` suffix persists)
+| Knob | Effect | Gotcha |
 |---|---|---|
-| `maxRuntimeMs` | `0` (unlimited) | **Hard wall-clock limit per subagent (ms).** The only true time cap. |
-| `softRequestBudget` | `200` | Soft cap on assistant **requests** per run; force-stop at **1.5×**. |
-| `softRequestBudgetNotice` | `true` | Injects one "wrap up" steering message at the soft mark. |
-| `agentIdleTtlMs` | `420000` | Parks an **idle** agent after 7 min. Useless against a busy-but-slow agent. |
-| `completionProbe` | `true` | Asks a working subagent to self-report completeness at 2/5/10 requests. |
-| `maxConcurrency` | `32` (often lowered) | Concurrent subagents; sizes GPU/endpoint load. |
-| `agentModelOverrides` | `{}` | Per-agent model routing, e.g. `{"scout":"provider/model-id"}`. |
-| `tools.maxTimeout` | `0` | Caps the timeout the agent may set on a **tool**, not on the agent. |
+| `task.maxConcurrency` | session semaphore; excess queues | stock default 32 — "2" is not a default |
+| `task.maxRecursionDepth` | nesting cap | predicate is `depth < n`; **1 = children cannot spawn (correct for "no nesting"); 0 disables spawning for the MAIN session too — never reach for 0**; negative = unlimited |
+| `task.maxRuntimeMs` | hard wall clock, overrun = `aborted` | default 0 = off |
+| `task.softRequestBudget` | wrap-up notice at N, force-yield at 1.5N | scout/sonic may impose lower built-ins |
+| `task.agentIdleTtlMs` | park idle finished agents | `<= 0` disables parking |
+| `providers.maxInFlightRequests` | concurrent LLM requests per provider id | keys are the quoted block labels from `agent/models.yml` (e.g. `"llamacpp (dankclaw-3090)"`), flat map lookup; absent/≤0 = unlimited; scope = this machine's config root only — other workstations and non-omp clients are NOT counted; excess queues |
+| `tools.maxTimeout` | ceiling on any agent-requested tool timeout | kills `timeout: 0` runaways |
+| `task.isolation.enabled` | makes per-spawn `isolated` flag available | opt-in per spawn, not a blanket sandbox; needs git repo; off in plan mode |
+| `task.completionProbe` | periodic completeness side-requests | token sink on shared endpoints |
 
-Reasonable fleet defaults: `maxRuntimeMs = 900000` (15 min), leave the request budget
-alone unless the failure mode is a looping search agent (then lower it — request count,
-not the clock, is what bounds a 200-call research loop).
+## Verify semantics from the bundle, not the label
+Setting descriptions lie by omission. `~/.bun/install/global/node_modules/@oh-my-pi/pi-coding-agent/dist/cli.js`:
+- depth gate: `grep -o '.\{130\}xC\b.\{130\}'` finds `U_(n,s)`; `grep -o 'function U_(e,t){.\{0,60\}'` → `e<0||t<e` (n=cap, s=taskDepth).
+- in-flight lookup: `grep -o '.\{150\}axInFlightRequests.\{200\}'` → flat `[providerId]` lookup, non-number/≤0 = unlimited, clamp ≥1.
 
-**Verify the cap instead of assuming it.** `read cfg://task/maxRuntimeMs` at the start of
-any session that plans to rely on it. A session-only write is gone next session, and an
-unanswered `/save` approval means the value never persisted — so the fleet can run hours
-with the cap at `0` while everyone believes it is 15 minutes. Nothing else bounds a child.
-
-## Three failure modes, three different fixes
-
-- **Runaway loop** (hundreds of sequential tool calls): lower `softRequestBudget`; the
-  clock cap only truncates it late.
-- **Slow model, legitimate work** (dozens of calls on a low-t/s endpoint = an hour of wall
-  clock): fix routing, not the clock — check `cfg://task/agentModelOverrides` and move the
-  agent class onto a faster/shared endpoint. Watch the slot math: subagent endpoints share
-  KV slots with the interactive session, so `maxConcurrency + 1` sequences on an N-slot
-  endpoint degrades everyone's decode.
-- **Finished work, no exit (nested fan-out deadlock).** A subagent that spawned **its own**
-  children blocks on their barriers. If those children die out-of-band (killed, starved, or
-  waiting on an answer whose subject changed mid-flight), the parent waits forever with its
-  deliverable already written. No instruction text prevents this — not the repo AGENTS.md,
-  not the task prompt; only the clock cap or a kill ends it.
-
-  Signature: parent and children report **the same elapsed wall clock**, and the parent's
-  on-disk output is complete. Census (agent registry + `ps`): group by elapsed time, look
-  for identical `etimes` across a parent/child set, then judge the **artifacts** instead of
-  the process — balanced code fences, no truncated tables, trailing newline, front matter or
-  the page's H1+status convention intact. Complete artifacts + still "running" = deadlock,
-  not work.
-
-  Repair: kill the **subtree** and confirm the children leave (a killed parent does not
-  cancel children that came from a separate `tasks[]` batch). Then **flatten**: the
-  top-level session does the fan-out and children never spawn children. Re-run only the
-  slices whose artifacts are missing — integrate from what is already on disk.
-
-## cfg write mechanics (bit me once)
-
-- `write cfg://task/maxRuntimeMs 900000` → applies **session-only**, replies "NOT saved".
-- Persist = `write cfg://task/maxRuntimeMs/save` with the same content, and that write
-  needs its **own interactive approval**. If the approval prompt is not answered in time
-  the value stays session-only and the tool says *NEVER retry unless the user asks* —
-  report it in the reply instead.
-- Revert a session value by writing the old value back (e.g. `0`).
-
-## Order of operations when one is already running late
-
-1. `read proc://` → registry of running agents; `read proc://<id>` for status/output.
-2. `read agent://<id>` → live progress ("Latest assistant text") — often shows it is
-   mid-batch, not hung. If the latest text is already a wrap-up/summary, treat it as
-   **done** and collect its output instead of waiting for an exit event.
-3. `write agent://<id>` an explicit wrap-up order: stop searching, answer what is
-   sourced, mark the rest `NOT VERIFIED — needs <what>`, cap the report length.
-4. Only then `write proc://<id>/kill` — the cap does **not** retroactively bind agents
-   spawned before the change, so a long runner must be ordered or killed, never just
-   re-configured. After any kill, re-read the registry: unreaped children and orphaned
-   host-side processes (a scratch server holding GPU/RAM) are the expensive residue, and
-   `pkill -f` patterns that also match production services are forbidden — kill by pid.
+## Landing a policy change
+cfg `/save` writes persist immediately; `agent/config.yml` is machine-live tier (heartbeat commits it). Human-facing policy changes land as an `omp-docs` page update via branch → PR (docs tier), `git worktree add` from `origin/main` if the current checkout is branch-locked by workspace policy.

agent/managed-skills/corpus-voice-skill-rewrite/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: corpus-voice-skill-rewrite
+description: "Rewrite a skill to emulate an author corpus's voice: full read, style-DNA distillation from writing-for-agents levers, positive-phrasing pass, sharpened completion criteria"
+---
+
+# Corpus-voice skill rewrite
+
+Rewrite a skill so it reads as if a chosen author wrote it. Done for `grilling` against the `mattpocock/skills` corpus (2026-10-18, command-center PR #20); behaviour preserved, voice swapped.
+
+## Where the corpus lives
+
+Installed third-party skills: `~/.agents/skills/<name>/SKILL.md` (the skills-CLI global store; `~/.agents/.skill-lock.json` names sources). Whole mattpocock corpus ≈ 2,800 lines — small enough to read inline in ~4 `cat` batches via bash; do NOT delegate the reading, style lives in the exact prose.
+
+Read the author's own meta-skill FIRST if one exists (`writing-for-agents` for mattpocock — it states his levers explicitly), then the corpus practicing them.
+
+## Style DNA checklist (mattpocock; generalise per author)
+
+- **Leading words**: compact pretrained concepts repeated as tokens, never sentences (_red_, _seam_, _fog of war_, _brief_, _frontier_). Define each once, reuse everywhere. Prefer words already in the author's other skills so the corpus shares one language.
+- **Vocabulary-first**: bolded glossary terms, then used exactly; explicit "_Avoid_: component, service".
+- **Positive phrasing**: prohibitions rewritten as target behaviours; keep a prohibition only when no positive form exists (hard guardrails).
+- **Sharpened completion criteria**: fuzzy bounds ("understanding reached") → checkable + exhaustive ("frontier empty and nothing sits blocked", "one artefact per question, counted before sending").
+- **Zero history**: no provenance, attribution, or absorbed-from lineage in the body.
+- **No-op hunting**: delete harness defaults and anything the environment already confesses (formats, rendering, caps). Gotchas the environment CANNOT confess (exclusive dialogs, Esc-abort semantics) stay inline — they're the cache worth keeping.
+
+## Procedure
+
+1. Read entire corpus; tabulate levers with per-skill evidence before writing.
+2. Rewrite preserving settled behaviour 1:1 — voice only; diff the two versions for semantic drift.
+3. Audit pass: grep the new text for history words (extracted/absorbed/from/upstream), machine-specific constants, repo-specific paths.
+4. Run repo checks, commit as `style(<scope>)`, note the lever→instance mapping in the PR comment so the reviewer can grade the emulation.

agent/managed-skills/frank-tts-add-cloned-voice/SKILL.md

@@ -1,125 +1,81 @@
 ---
 name: frank-tts-add-cloned-voice
-description: "Add or repair a cloned voice on the dank fleet: /home/dank/voices/<name> pack, name rules, boot-warm registration, and the under-a-second proof"
+description: "Add or repair a cloned voice on the dank fleet: pack builder, the reference.wav contract, the boot warm hook (argv-cap and env-quote laws), and how to prove a voice really answers."
 ---
 
-Use for "give frank-tts a new voice", "voice X is missing/unknown", or "the first
-request of the day takes 5 s". Runbook of record: vault pages [[Frank TTS]] (voice
-packs, naming) and [[Frank TTS Engine]] (the warm registry). Everything below runs
-as the deploy user on **Dankclaw** (`ssh -o BatchMode=yes dankclaw '…'`); the
-containers are **rootless** (`systemctl --user …`, `podman …` without sudo).
+# Adding (or repairing) a cloned voice on the dank fleet
 
-## Naming (the question that gets asked first)
+Repo law lives in `serverAppConfigs-docs/Dankclaw/Voice Packs.md` and
+`Frank TTS Engine.md` — read those for the pack format. This skill is the
+**operating sequence plus the traps that cost real time on 2026-10-18**.
 
-A voice is addressed **by its directory name** — `voice=narrator1` on
-`POST /v1/audio/speech` (omp's TTS device may send `voice_id`, same value). Use:
+## Stack, fast
 
-- `^[a-z0-9][a-z0-9._-]*$`, **lowercase**, ≤ 64 chars. No slash, no `..`, no
-  space, no uppercase; must not start with `.`/`_`/`-`.
-- Why lowercase rather than just "alphanumeric": the shim accepts
-  `[A-Za-z0-9][A-Za-z0-9._-]{0,63}` (`app.py`, `VOICE_NAME_RE`) but the **engine
-  lowercases names**, so `Narrator1` resolves on one side and not the other. The
-  boot warmer refuses a mixed-case pack loudly instead of half-working.
-- Names are user-visible: a 400 carries them in `available_voices`. Fleet
-  convention is `narrator1`, `narrator2`, … for the open-notebook podcast
-  speakers — open-notebook is configured with exactly `narrator1/2/3`, so renaming
-  those breaks podcast rendering, not just TTS — and a lowercase personal name for
-  a person's own voice.
+- `frank-tts-engine` — arm A `qwentts.cpp tts-server`, container-internal `:8880`,
+  publishes **no port**. Reach it with `podman exec frank-tts-engine curl …`.
+- `frank-tts` — OpenAI façade on host `:7772`; resolves voice **by name**.
+- Packs: `/home/dank/voices/<name>/` with `reference.wav` (+ manifest, `.spk`,
+  `.rvq`). Builder: `scripts/build-voice-pack.sh` (crop 19.84–25 s, first 10 s of
+  any source is forbidden).
+- Weights: `/home/dank/models/Qwen3-TTS-GGUF/` —
+  `scripts/download-frank-tts-engine-qwentts.sh [--verify-only]` (1.4 GiB, ~18 s
+  on the LAN; verifies byte count + Hub LFS sha256).
 
-## Pack layout (host state — never commit it)
+## Sequence
 
-`/home/dank/voices/<name>/` is a voice **iff** it holds `reference.wav`:
+1. Build the pack (dry-run first — sizes are arithmetic and asserted).
+2. Deploy the engine only if its files changed:
+   `./scripts/deploy.sh dankclaw --service frank-tts-engine`
+   (first run builds the image: ~10 min recursive source clone).
+3. Register/warm: `podman exec frank-tts-engine /app/warm-voices.sh`
+   — registers **every** pack each run (the engine replaces a name it already
+   holds; `tools/tts-server.cpp:148`), then synthesizes twice per voice.
+4. Prove from the consumer side, not the config:
+   `curl -s localhost:7772/v1/audio/voices` then a real
+   `POST /v1/audio/speech` and listen to the bytes.
 
-```
-reference.wav    24 kHz mono pcm_s16le, 18-25 s of clean single-speaker audio
-reference.spk    engine x-vector: enc_dim 2048 f32 = 8192 B
-reference.rvq    RVQ codes: 22 B per 12.5 Hz frame (5456-6864 B)
-manifest.json    source path + sha256, crop start/end, engine commit, name
-```
+## Trap 1 — the kernel's argument cap (this broke the first deploy)
 
-Build it; do not hand-assemble and never fabricate `.spk`/`.rvq` from a WAV:
+`/usr/bin/curl: Argument list too long` in the warm log ⇒ a request body was
+passed as **one argv string**. Linux caps a single argument at
+`MAX_ARG_STRLEN = 131 072 bytes`; a ~1 MB `reference.wav` base64's to ~1.27 MB.
+curl never runs, and hooks report it as `HTTP no response` while `/health` is
+green. Fix = write the body to a file and use `--data-binary @file`; feed the
+payload through a redirection, not `$(base64 …)`.
+Regression-test shape: **real** curl + real listener + a fixture >128 KB, so the
+kernel (not a stub) produces the failure. Any pack over ~96 KB trips it.
 
-```bash
-scripts/build-voice-pack.sh --all /home/dank/voices       # everything in VOICE_PACKS
-scripts/build-voice-pack.sh --source SRC --offset SEC --duration SEC --sha256 HEX NAME /home/dank/voices
-scripts/build-voice-pack.sh --dry-run ...                  # validate + crop, no extractor
-```
+## Trap 2 — two readers of the env file disagree about quotes
 
-Knobs live in `scripts/voice-packs.env` (one `_SOURCE`/`_OFFSET`/`_DURATION`/
-`_SHA256` set per voice). Three things it enforces that an operator gets wrong:
+`bash set -a; source` strips `"…"`. podman's `--env-file` (how the unit really
+reads it) does **not**. A value interpolated into a JSON body therefore arrives
+quoted and invalidates it. Test both readers, not just `source`.
 
-1. **The 10-second gate.** A crop starting inside the first 10 s of the source is
-   refused before anything is written (project source-material law), and the
-   manifest is re-checked against the source's sha256 afterwards.
-2. **The effective crop window is 19.84-25 s, not 18-25 s.** An 18.0 s crop is a
-   legal `reference.wav` but yields only 22 × 225 = 4 950 B of `.rvq`, under the
-   5 456 B floor the codec config implies — so the builder says so up front.
-3. **It never deletes.** An existing pack is refused unless `--force`, and
-   `--force` moves the old directory to `$PACKS_DIR/.AGENTTRASH/<voice>-<UTC>/`.
+## Trap 3 — locally built images skip rebuilds on a stale hash
 
-Files must be world-readable (the container runs as uid 10000): `644` files,
-`755` dirs. `mkdir -p /home/dank/voices` as the deploy user if it is absent —
-rootless podman auto-creates a missing bind source **root-owned**, and the
-endpoint then sees no voices at all.
+`build_compose_image` compares a `cfhash` label; it must cover every file the
+`Containerfile` `COPY`s, or an edited `app.py`/hook deploys "successfully" while
+the container runs old code.
 
-## Register and warm (the part people forget)
+## Measured numbers (2026-10-18, deployed build — retire the trial's ladder)
 
-The engine keeps its voice registry **in memory**, and the **first synthesis of a
-registered voice decodes the whole reference clip** to snapshot codec state:
-6.2-8.0 s, first audio byte at ~5 530 ms. Later requests restore in 0.5 ms.
-Re-registering does **not** warm — only synthesizing does. So:
+| thing | value |
+|---|---|
+| first synthesis of a freshly registered voice | 1 883 ms |
+| later short requests | 1 226–1 283 ms |
+| ~110-word request (repeat) | 9.4 s / 9.8 s — tracks generated audio, not state |
+| whole boot warm, 3 packs | 15.2 s |
+| engine resident | ~4.0 GiB |
 
-```bash
-# registers every pack that has a reference.wav, then speaks the warm sentence once
-podman exec frank-tts-engine /app/warm-voices.sh
-systemctl --user --no-pager --full status frank-tts-engine.service | tail -20
-```
+The trial's `6.2–8.0 s cold → 0.5 ms warm` claim does **not** reproduce; warming
+is for registration (registry is memory-only, re-register ≠ warm) plus ~0.6 s.
 
-The unit's
-`ExecStartPost=-/usr/bin/podman exec frank-tts-engine /app/warm-voices.sh` does
-the same at every boot, so a fresh boot is already warm; the explicit call above
-is for **adding one voice to a running engine** and needs no restart — a restart
-drops every registration and re-pays the cold cost for the whole library. The
-`podman exec` form is not cosmetic: the engine **publishes no port**, so there is
-no host address to curl.
+## Ops notes
 
-## Proof (do not report "added" without it)
-
-```bash
-curl -s localhost:7772/v1/audio/voices                        # name is listed
-time curl -s -o /tmp/a.wav localhost:7772/v1/audio/speech \
-  -H 'content-type: application/json' \
-  -d '{"model":"tts-1","voice":"NAME","input":"Checking the cloned voice.","response_format":"wav"}'
-time curl -s -o /tmp/b.wav localhost:7772/v1/audio/speech \
-  -H 'content-type: application/json' \
-  -d '{"model":"tts-1","voice":"NAME","input":"And the second request.","response_format":"wav"}'
-file /tmp/a.wav /tmp/b.wav                                    # really audio
-```
-
-The warmer's journal lines carry `voice NAME cold=…ms warm=…ms` — quote that pair.
-Note that streaming and buffered output differ at the same seed (92.2 % of samples,
--41.6 dB RMS): never compare two paths or two "identical" renders, only that each
-is audio and that the second request is fast.
-
-## Failure modes worth naming
-
-- `400 unknown voice …; available voices: …` → the name is not a pack: wrong
-  spelling/case, missing `reference.wav`, or `/home/dank/voices` root-owned/empty.
-  Trust the 400's list over any manifest.
-- 400 with `(none: no voice pack with a reference.wav in /voices)` → mount problem,
-  not a voice problem.
-- First request slow **after** a boot → the warm pass failed; read the unit's
-  journal (the warmer exits 0 and logs when there is no voice directory, so
-  silence there is not success either).
-- Endpoint answers but synthesis fails 502 → the façade must dial
-  `http://frank-tts-engine:8880` over the shared bridge
-  (`frank-tts-engine.network`); a `host.containers.internal` / `127.0.0.1:8880`
-  upstream can never work between containers, because netavark DNATs published
-  ports only.
-
-## Never
-
-Never write under `/voices` from the endpoint (mounted `:ro` by design), never
-`git add` a voice pack, never `rm` a pack (repo policy: move to `.AGENTTRASH/`),
-and never benchmark against this endpoint while it serves — stop and mask the
-units first.
+- `systemctl --user stop` **removes** the quadlet container — `podman start` then
+  finds nothing. To run the engine without its `ExecStartPost` hook, use a
+  separate container, not stop+start.
+- `podman cp` of a fixed script into a running container is a **trial only**: the
+  layer dies with the container. Merge + redeploy to make it durable.
+- Nothing on the voice pair exposes `/metrics`; Prometheus can't scrape it (a
+  blackbox HTTP probe on 7772 is the only honest option).

agent/managed-skills/frank-tts-consumer-voice-triage/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: frank-tts-consumer-voice-triage
+description: "Triage a consumer (OpenWebUI, omp, open-notebook) rejecting or ignoring a frank-tts voice name: prove whether the server or the browser-side Kokoro.js engine produced the error."
+---
+
+# frank-tts consumer voice triage
+
+A consumer says a voice name is invalid, speaks in the wrong voice, or is
+silent. `frank-tts` (`192.168.0.143:7772`, shim
+`dankclaw/voiceservice/app.py`) resolves `voice=<name>` against
+`/home/dank/voices/<name>/reference.wav` and answers **400 + the list of
+voices that exist** for a name it cannot resolve — never a silent fallback.
+Any error naming a *different* voice list did not come from it.
+
+**Signature that decides the case immediately:** an enum of ~29 names
+`af_heart, af_alloy, … am_*, bf_*, bm_* … bm_fable` is **Kokoro's fixed pack**,
+the voice list of **Kokoro.js running in the browser** (OpenWebUI ships it
+in its own front end as TTS engine value `browser-kokoro`, with a personal
+"Kokoro.js dtype" setting; model `onnx-community/Kokoro-82M-v1.0-ONNX`).
+`narrator1/2/3` are frank-tts cloned voices. Kokoro cannot clone.
+
+## Instrument ladder (stop at the first that answers)
+
+1. **What the endpoint actually accepts** (never infer from a consumer's text):
+   `curl -s http://127.0.0.1:7772/v1/audio/voices` → JSON array of pack names.
+2. **Speak with the consumer's exact body, from inside the consumer's
+   container** — same network, same shape. Write the JSON to a file and
+   `--data-binary @file` (nested `sh -c` quoting silently sends an empty
+   body and yields a bogus `400 malformed request body`):
+   ```
+   printf '%s' '{"model":"frank-tts","input":"probe","voice":"narrator1","response_format":"mp3","speed":1.0}' > /tmp/p.json
+   podman cp /tmp/p.json <consumer>:/tmp/p.json
+   podman exec <consumer> curl -sS -o /tmp/o.bin -w 'http=%{http_code} type=%{content_type} bytes=%{size_download}\n' \
+     -X POST http://host.containers.internal:7772/v1/audio/speech \
+     -H 'Content-Type: application/json' --data-binary @/tmp/p.json
+   ```
+   `200 audio/mpeg|audio/wav` ⇒ the server path is healthy; the failure is elsewhere.
+3. **Did the request arrive at all?** `podman logs --tail 400 <consumer> | grep -c audio/speech`.
+   A server-path failure leaves a log line **and** a frank-tts error body; a
+   client-side engine leaves **neither**. This contrast is the discriminator.
+4. **Where the rejection string lives** (proves the emitter without guessing):
+   ```
+   podman exec <consumer> sh -c 'grep -ho ".\{200\}Should be one of.\{80\}" /app/build/_app/immutable/chunks/*.js | head'
+   podman exec <consumer> sh -c 'grep -ho ".\{60\}af_heart.\{200\}" /app/build/_app/immutable/chunks/*.js | head -2'
+   ```
+   Matched inside the front-end bundle ⇒ browser-side validator, not the API.
+5. **Config authority sweep** (OpenWebUI): admin config is the `config`
+   table (one key per row, JSON `value`; expected
+   `audio.tts.engine=openai`, `audio.tts.model`, `audio.tts.voice`,
+   `audio.tts.openai.api_base_url`); per-user overrides are the `settings`
+   JSON column of table `user` (singular, no `is_active`; some rows hold the
+   string `null` → guard it). `audio.stt.*` and `audio.tts.*` are separate.
+   No `sqlite3` CLI in the image or on the host: `podman exec -i <c> python -`
+   with the stdlib module. **`podman exec` needs `-i` to accept a heredoc
+   script** — without it the script is silently dropped and you get no output.
+
+## Known traps
+
+- OpenWebUI is a **rootless** quadlet: `sudo podman …` reports *no such
+  container*. Read it rootless.
+- `podman ps` in this podman build has no `.ImageName` field — use `{{.Image}}`.
+- The in-browser engine choice is **per-browser storage**: empty
+  `user.settings` + correct admin config + zero backend hits is the normal
+  shape of this bug. Fix is UI: Settings → Audio → TTS Engine → **Default**.
+- `GET /api/config` publishes no `audio` block, and nonexistent `/api/...`
+  paths return the SPA HTML with `200` — never conclude "config missing" from
+  an HTML body.
+- TTS is memory-registry sensitive: the engine's voice registry is
+  memory-only, so "every name returns 400" after a restart points at the warm
+  pass, not at the caller (see [[frank-tts-add-cloned-voice]]).
+
+## Local playback side (omp `/say`, manual probes)
+
+If synthesis succeeds (`200`, sane WAV bytes) but nothing is audible, the
+fault is the PipeWire graph, not the endpoint:
+`wpctl status` (default sink marked `*`, and *Default Configured Devices* —
+a remembered-but-offline `bluez_output.*` there is the classic silent
+route), `wpctl get-volume @DEFAULT_AUDIO_SINK@`, `pw-play -v <file>` (expect
+`stream drained` + exit 0), and target a device explicitly with
+`pw-play --target <node-id>` to identify which hardware is live. A one-word
+clip (~0.7 s) is easy to miss — probe with a multi-second sentence.

agent/managed-skills/gitea-api-pr-operations/SKILL.md

@@ -1,105 +1,64 @@
 ---
 name: gitea-api-pr-operations
-description: "Open, list, merge, and verify pull requests (and diagnose issue-API scope failures) on the Dankclaw Gitea via its REST API from a workstation, keeping the token out of argv (curl -K config file, mode 600) — includes the credential-store extraction one-liner, the merge endpoint's Do-field law and Content-Type-header trap, the suggested-URL-is-not-a-PR gotcha, and the insufficient-token-scope trap."
+description: "Open, list, merge, and diagnose issues/PRs on the Dankclaw Gitea API (192.168.0.143:3000, repo dank/command-center) with the token stored in ~/.config/secrets/gitea — incl. the required merge payload and where review comments actually live on 1.27.3."
 ---
 
-# Gitea API PR operations (Dankclaw)
+# Gitea API PR operations (Dankclaw `dank/command-center`)
 
-`git push` on this fleet prints `Create a new pull request for ...` — that is a
-**suggestion, not a PR**. Verify (`GET /pulls?state=open` → expect `[]`) before
-claiming a PR "should exist"; create it via the API when asked.
+## Where
+- Token: `~/.config/secrets/gitea` (`http://user:TOKEN@192.168.0.143` single line).
+  Extract WITHOUT echoing:
+  `tok=$(sed -nE 's#^http://[^:/@]+:([^@]+)@192\.168\.0\.143.*#\1#p' ~/.config/secrets/gitea | head -1)`
+- Build a 600-perm temp curl config and use `curl -K`:
+  `cfg=$(mktemp) && chmod 600 "$cfg" && printf 'header = "Authorization: token %s"\n' "$tok" > "$cfg"`
+  Delete `$cfg` after use. NEVER pass `-H "Authorization: token $tok"` (the literal
+  header lands in transcript + logs). NEVER echo the token.
+- Base URL: `http://192.168.0.143:3000/api/v1/repos/dank/command-center`.
 
-## Endpoint + auth
-- API base: `http://192.168.0.143:3000/api/v1/repos/dank/<repo>`
-- Token lives in the git credential store configured by
-  `git config --get credential.helper` → `store --file ~/.config/secrets/gitea`,
-  line format `http://user:TOKEN@192.168.0.143:3000`.
-- The repo-local `.env` `GITEA_TOKEN` (main checkout, gitignored) carries
-  **`read:issue` too** (measured 2026-10-18): filing issues needs THAT token,
-  the credential-store one 403s on issues.
+## Recipes (all verified live 2026-10-18)
+- **Open PR** (token only needed for private repos; this one reads publicly but
+  POST needs auth): `POST /pulls` JSON `{title, head, base:"main", body}`.
+- **PATCH PR title/body**: `PATCH /pulls/<n>` with JSON body `{title}` and/or
+  `{body}`. Returns 201 with the full PR. Use `jq -n --arg` to build JSON; for
+  multi-line bodies write the text to a temp file and `--arg b "$(cat b.txt)"`.
+  (jq CLI: a bare `---` argument after the program is parsed as a flag → error;
+  fold footers into the --arg string instead.)
+- **List open PRs**: `GET /pulls?state=open` → `jq -r '.[] | "#\(.number) \(.head.ref) \(.title)"'`.
+- **Read PR**: `GET /pulls/<n>` (no token; public repo) → `jq -c '{state,merged,mergeable,head:.head.ref}'`.
+- **MERGE**: `POST /pulls/<n>/merge` with `-H 'Content-Type: application/json'`
+  and body **`{"Do":"merge"}`** — this build REQUIRES the `Do` field:
+  `{}` or `{"DoNotMerge":false,...}` → 422; `{"Do":"merge"}` → 200 +
+  `{"state":"closed","merged":true,"merge_commit_sha":"..."}`. Verify with a
+  plain GET /pulls/<n> afterwards (merge endpoint's own stdout may not parse).
+  Merge is the `--no-ff` merge commit on main; then `git -C ~/.omp fetch && git
+  merge --ff-only origin/main` propagates the live deployment.
+- **Issues**: same shape at `/issues` (`POST {title, body}`), `/issues/<n>/comments`
+  (`POST {body}`, `PATCH .../comments/<id>`) — both work with the temp-cfg auth.
 
-Extract the token (the `http://` scheme contains a colon — scheme-stripping
-awk regexes silently grab the port instead; use this anchored sed):
+## Review comments: the API lies on 1.27.3 (learned 2026-10-18)
+- `GET /pulls/<n>/comments` (inline review comments) → **404 `not found` on every
+  route** (token or not, `?pull_request_id=` or not) even when a review with
+  comments exists.
+- `GET /pulls/<n>/reviews` works (shows `state`, `comments_count`) but bodies are empty.
+- **The comments are readable from the PR HTML**:
+  `curl -sS http://192.168.0.143:3000/dank/command-center/pulls/<n> -o /tmp/pr.html`
+  then extract `<div class="content comment-content">` blocks
+  (python: `re.finditer(r'comment-content', src)` → widen ±800 chars, strip tags).
+  Duplicates appear (suggested-change UI shows text twice); dedupe mentally.
+- Per-conversation resolve API also 404s — flag resolutions in an issue comment instead.
 
-```bash
-tok=$(sed -nE 's#^http://[^:/@]+:([^@]+)@192\.168\.0\.143.*#\1#p' ~/.config/secrets/gitea | head -1)
-[ -n "$tok" ] && echo "token-extracted(len=${#tok})"   # length check, never echo the value
-```
+## Body-footer law (AGENTS.md)
+Every issue/PR body ends with `---` line then `cwd: <wd> · session: <id>`. Keep
+it inside the --arg string (not a `---` CLI arg).
 
-## Keep the token out of argv (repo secret law)
-`curl -H "Authorization: token $tok"` is world-readable in `/proc/<pid>/cmdline`.
-Use a mode-600 config file:
-
-```bash
-cfg=$(mktemp); chmod 600 "$cfg"
-printf 'header = "Authorization: token %s"\n' "$tok" > "$cfg"
-```
-
-- POST JSON needs a second header line: `header = "Content-Type: application/json"`.
-  There IS NO `content-type` config option — curl rejects the file.
-- `rm -f "$cfg"` when done (a mode-600 token file left in /tmp is its own leak).
-
-## Operations
-```bash
-# list open PRs
-curl -sS -K "$cfg" ".../pulls?state=open" | jq -r '.[] | [.number,.head.name,.base.name,.title] | @tsv'
-# create (build the payload as a FILE, see below)
-curl -sS -K "$cfg" -o /tmp/pr.json -w '%{http_code}\n' -X POST -d @/tmp/pr-payload.json ".../pulls"
-# verify: 201 is not enough — check mergeable
-curl -sS -K "$cfg" ".../pulls/1" | jq '{number,state,merged,mergeable,base:.base.ref,head:.head.ref,url:.html_url}'
-```
-
-## Merging: the field is `Do`, and it is a STRING naming the strategy
-
-Measured 2026-10-18 on Gitea at 192.168.0.143:3000 (`POST .../pulls/<n>/merge`).
-`MergePullRequestOption` is `{From, To, When, Do}` — **there is no `DoMerge` and
-no `merge_method`**. Every wrong shape is a 422 with a distinct message, so read it:
-
-|body sent|http|message|
-|---|---|---|
-|`{"DoMerge":true,"merge_method":"merge"}`|422|`[Do]: Required`|
-|`{"Do":true,"merge_method":"merge"}`|422|`[]: json: cannot unmarshal JSON boolean into Go string within "/Do"`|
-|`{"Do":"true"}`|422|`[Do]: In…` (validation: not a strategy name)|
-|form body `Do=true&merge_method=merge`|422|`[Do]: Required` (the value must be a strategy name)|
-|`{"Do":"merge"}`|**200**|merged|
-
-```bash
-curl -sS -K "$cfg" -H 'Content-Type: application/json' -X POST -d '{"Do":"merge"}' ".../pulls/4/merge"
-# then prove it: .merged true, .state closed, .merge_commit_sha set, and origin/main moved
-curl -sS ".../pulls/4" | jq -c '{number,state,merged,merge_commit_sha}'
-```
-
-Strategy names: `merge`, `rebase`, `rebase-merge`, `squash`, `manually` — a
-strategy the repo does not allow is rejected too.
-
-**Merge trap (measured 2026-10-18):** on `POST /merge` the `Content-Type` header
-must go on the **command line** (`-H 'Content-Type: application/json'`). Same
-curl that succeeds on `POST /pulls` with Content-Type supplied only via the `-K`
-config file returns **405 with an EMPTY body** on `/merge`. A 405 there is this
-trap (or a base-moved mergeability recheck — GET the PR, see `mergeable:true`,
-then retry with `-H`), NOT a permission problem.
-
-## Building issue/PR bodies without quote carnage
-Hand-written `jq -n --arg t "..." '{title:$t, body:"..."}'` one-liners with long
-markdown bodies WILL break on a stray quote (and the broken quoting can swallow
-the following commands). Build bodies as files (heredoc or write tool), then:
-```bash
-b=$(jq -Rs . body.md)
-jq -n --arg t "$title" --argjson b "$b" '{title:$t, body:$b, head:"<branch>", base:"main"}' > payload.json
-curl ... -d @payload.json
-```
-
-## Gotchas measured 2026-10-14 / 2026-10-17 / 2026-10-18
-- Unauthenticated/bad token → HTTP 401 body `{"message":"not found"}`; `jq '.[]|[.number,..]'` then fails with *cannot index "not found"* — that is an auth failure, not a missing repo.
-- **Insufficient token scope ≠ missing data.** The credential-store token
-  (measured 2026-10-17) carries only `write:repository,write:user`; the issues
-  API answers HTTP 403 `{"message":"token does not have at least one of required
-  scope(s), required=[read:issue], token scope=write:repository,write:user"}`.
-  jq surfaces that JSON as the *cannot index* error — do NOT conclude the issue
-  list is empty, and note POSTs under this token create NOTHING (verify, don't
-  assume retry safety). Filing issues needs a fresh token minted in the Gitea
-  web UI with `read:issue`+`write:issue` (Frank-class credential action; ask) —
-  OR use the main-checkout `.env` `GITEA_TOKEN`, which already has issue scope.
-  PR endpoints work fine with either token (`pulls` POST/GET/merge all 200/201).
-- On the created-PR response `.head.name` can be null; verify with the `GET /pulls/<n>` and use `.head.ref`.
-- **Swagger JSON is disabled on this instance** — `/api/swagger.v1.json`, `/api/swagger.json` and `/api/v1/swagger.json` all 404. Do not go looking for the schema there; the 422 messages name the field and its Go type, which is the faster instrument.
+## Gotchas
+- Content-Type: POSTs with `-d @file.json` MUST carry
+  `-H 'Content-Type: application/json'` on the command line. `-H` entries put in
+  the curl config file are ignored for this (header ordering quirk).
+- `xdg-open <pr-url>` lands the PR in Frank's Firefox the moment it is opened —
+  law, not courtesy.
+- `jq: cannot index "not found" with "user"` = endpoint 404'd into an error
+  object; check `-w '%{http_code}'` before blaming jq.
+- The token in `.git/config`'s remote URL is the same secret; the credential
+  file (`~/.config/secrets/gitea`) is the one git actually consults (global
+  credential.helper) and the one to reuse for API calls.

agent/managed-skills/gitea-pr-api-cycle/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: gitea-pr-api-cycle
+description: "Open/update/merge PRs and issues on the Dankclaw Gitea API (192.168.0.143:3000, dank/command-center) with the token-safe curl+jq sequence, including the {\"Do\":\"merge\"} merge payload and post-merge live-checkout fast-forward."
+---
+
+# Gitea PR/issue cycle — dank/command-center
+
+Friction-earned 2026-10-18 across PRs #15–#20 and issue #18: three separate fumbles (jq trailer flag, 422 merge payload, silent -o/-w swallowing) codified once.
+
+## Where
+- API base: `http://192.168.0.143:3000/api/v1/repos/dank/command-center/{pulls,issues}`
+- Token: never inline, never echoed. Extract from the git credential file into a 600-perm temp curl config:
+  `tok=$(sed -nE 's#^http://[^:/@]+:([^@]+)@192\.168\.0\.143.*#\1#p' ~/.config/secrets/gitea | head -1)`
+  `cfg=$(mktemp); chmod 600 "$cfg"; printf 'header = "Authorization: token %s"\n' "$tok" > "$cfg"` → `curl -K "$cfg"`; `rm -f "$cfg"` when done.
+- Unauthenticated GET works for state reads (`GET /pulls/N` → `jq -c '{state,merged,merge_commit_sha}'`).
+
+## Body construction (the two traps)
+- Build JSON with `jq -n --arg t <title> --arg b "$(cat b.txt)" '{title:$t, head:<branch>, base:"main", body:$b}'`; write the body to a temp file first (`printf '%s' … > b.txt`). NEVER pass `---` as a bare jq argument — jq parses it as a flag (`unknown flag: ---`). The AGENTS.md attribution trailer (`---` + `cwd: … · session: …`) goes INSIDE the body string.
+- Always capture status explicitly: `-o r.json -w '%{http_code}'` and print it; a bare `-o` hides failures (a 422 looked like success-with-no-output once).
+
+## Merge (the 422 trap)
+`POST /pulls/N/merge` requires body `{"Do":"merge"}` — `Do` is the Required field on this Gitea. `{}`, `{"DoNotMerge":false}`, `{"merge_style":…}` all return 422 (`"[Do]: Required"`). Success may return an EMPTY body — verify by GET afterwards (`state=closed, merged=true`), not by the POST response.
+- Merge only with Frank's explicit per-PR OK (repo law).
+- Post-merge the live deployment must follow: `git -C ~/.omp fetch -q origin && git -C ~/.omp merge --ff-only origin/main` (the checkout IS the deployment; branch is `main`).
+
+## PR etiquette per AGENTS.md
+- Immediately after opening: `xdg-open <PR-URL>` lands it in Frank's Firefox.
+- Redesign mid-review: amend + `git push -f` the branch, then PATCH the PR body (`/pulls/N`, `{"body":…}`) so title/body match the net diff — verify `{number,state,mergeable}` in the response.
+- Issue creation identical shape: `POST /issues` with `{title, body}`, expect 201; PATCH same endpoint `/issues/N` to fix bodies retroactively, then GET-readback verify.

agent/managed-skills/gitea-review-comment-html-scrape/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gitea-review-comment-html-scrape
+description: "Read inline review comments on the Dankclaw Gitea when pulls/N/comments 404s (Gitea 1.27.3): scrape comment-content blocks and diff anchors from the PR HTML page"
+---
+
+# Gitea review-comment extraction when the API 404s
+
+On the Dankclaw Gitea (192.168.0.143:3000, Gitea 1.27.3) the review-comment API is dead for inline comments:
+`/api/v1/repos/{owner}/{repo}/pulls/{N}/comments` returns 404 `not found` **even with a valid token**, and `pulls/comments?pull_id=` / `?pull_request_id=` variants 404 too. `/pulls/{N}/reviews` works but its bodies are empty for inline reviews (read `comments_count` for how many exist); `/issues/{N}/comments` shows only conversation comments, never inline ones.
+
+## Procedure
+
+1. Confirm the review exists and how many inline comments it holds:
+   `curl -sS http://192.168.0.143:3000/api/v1/repos/dank/command-center/pulls/{N}/reviews | jq -c '.[] | {id, state, comments_count}'`
+2. Scrape the PR page instead (no token needed for a public repo):
+   `curl -sS http://192.168.0.143:3000/dank/command-center/pulls/{N} -o /tmp/pr.html`
+3. Extract each comment's text — every inline comment renders a `comment-content` block; dedupe (each comment appears twice in the HTML):
+
+```python
+import re, html
+src = open('/tmp/pr.html').read()
+seen = set()
+for m in re.finditer(r'comment-content', src):
+    t = html.unescape(re.sub(r'<[^>]+>', ' ', src[m.start()-100:m.start()+800]))
+    t = re.sub(r'\s+', ' ', t).strip()[:400]
+    if t not in seen:
+        seen.add(t); print('>>', t)
+```
+
+The comment text appears twice back-to-back inside each block ("text text") — read it once. Blocks start after `Copy Link|Copy Source`; ignore those chrome words.
+
+4. **Locate the file/line anchor** (comment-content blocks carry no `data-path`/`data-line` attrs on this build): search the raw HTML for the comment string, walk *backward* ~4–7 KB, strip tags; the nearby `agent/...` path, `@@ -a,b +c,d @@` hunk header, and surrounding diff context lines identify the anchored file and the quoted source line.
+
+## Replying / housekeeping
+
+- Per-conversation resolve API does not exist on this build (404s) — reply to the round as a normal issue comment (`POST /repos/{o}/{r}/issues/{N}/comments`, token via `curl -K` temp cfg, `header = "Authorization: token …"`, 600 perms, `jq -n --arg b "$(cat b.txt)" '{body:$b}'`) listing which note got which fix commit.
+- Edit a posted comment: `PATCH /repos/{o}/{r}/issues/{N}/comments/{id}` with `{"body": ...}` — use to fix your own typos rather than double-posting.
+- Token source on this box: `~/.config/secrets/gitea` (grep the remote-URL pattern); never echo it.
+
+## Why this works
+
+The PR page is server-rendered with full inline comment bodies; Gitea's "Copy Source" UI element guarantees the raw text is present pre-markdown-render.

agent/managed-skills/niri-config-edit-validate/SKILL.md

@@ -22,7 +22,7 @@ description: "Locate, edit, validate, and commit niri compositor config on Frank
 - Preset list order = cycle order for `Mod+R` (`switch-preset-column-width`); `Mod+Shift+R` cycles backwards. WITH custom preset lists the cycle contains ONLY the configured presets — no implicit full/maximize tail (verified: [0.25, 0.5] cycles period 2). Maximize = separate `Mod+F` `maximize-column`. Built-in defaults without the node: 1/3, 1/2, 2/3.
 - WITHOUT `preset-window-heights`, `switch-preset-window-height` FALLS BACK to the width presets — user sees width-fractions as heights; define the node explicitly to stop it.
 - Ground truth for node placement: the binary's embedded template — `grep -a -B4 -A8 "preset-column-widths {" $(which niri)`.
-- Window outlines: base geometry (`width`, `off`) lives in `cfg/layout.kdl` `focus-ring`/`border`; COLORS effectively live in `noctalia.kdl` (see include-order law). `border { off }` + focus-ring active = the visible outline.
+- Window outlines: base geometry (`width`, `off`) lives in `cfg/layout.kdl` `focus-ring`/`border`; COLORS effectively live in `noctalia.kdl` (see include-order law). `border { off }` + focus-ring active = the visible outline. Frank's look since 2026-10-18: amber-orange `#ff8c00`, width 4 (`active`+`urgent` in noctalia.kdl; tab-indicator/insert-hint/recent-windows stay red `#f43841` by choice).
 
 ## Workflow
 1. Edit the live file under `~/.config/niri/cfg/` (symlinked = repo file; except `noctalia.kdl`, edit live then `cp` to mirror).

agent/managed-skills/noctalia-bar-layout-edit/SKILL.md

@@ -1,50 +1,52 @@
 ---
 name: noctalia-bar-layout-edit
-description: "Edit/verify Noctalia v5 bar layout and clock widgets (multi-timezone instances, capsule groups); GUI→repo propagation chain, settings.toml symlink audit, and clobber-recovery via dangling stashes on Frank's dotfiles workstations"
+description: "Edit/verify Noctalia v5 bar layout and clock widgets (multi-timezone instances, capsule groups); GUI-repo propagation chain, settings.toml symlink audit, and stash-clobber recovery on Frank's dotfiles workstations"
 ---
 
-# Noctalia v5 bar layout edit
-
 Bar widget layout on Frank's noctalia v5 workstations is GUI-override state, not config.toml.
 
 ## Where
-- Layout file: `~/.local/state/noctalia/settings.toml` → `[bar.<name>]` keys `start` / `center` / `end` (arrays of widget ids; `[widget.<id>]` subtables hold per-widget settings).
-- On Frank's boxes this file MUST be a **symlink into the command-center repo** (e.g. `~/.omp/dotfiles/noctalia/.local/state/noctalia/settings.toml`) — edit the repo file, not the link path (atomic-rename writes through the link path would replace the symlink).
+- Layout file: `~/.local/state/noctalia/settings.toml` -> `[bar.<name>]` keys `start` / `center` / `end` (arrays of widget ids; `[widget.<id>]` subtables hold per-widget settings).
+- On Frank's boxes this file MUST be a **symlink into the command-center repo** (e.g. `~/.omp/dotfiles/noctalia/.local/state/noctalia/settings.toml`) - edit the repo file, not the link path (atomic-rename writes through the link path would replace the symlink).
 - Layer order: built-in defaults < `~/.config/noctalia/config.toml` (+`[include]`) < `settings.toml` (wins). Noctalia writes through symlinks and keeps them.
-- Defaults when a key is absent: `start = ["launcher","wallpaper","workspaces"]`, `center = ["clock"]`.
-- **Noctalia rewrites this file itself** (GUI actions + normalizes keys/format, e.g. strips `{:%...}` braces, reorders widget lists). Always re-read the exact lines immediately before editing; stale line anchors WILL drift between reads.
+- Defaults when a key is absent: `start = ["launcher","wallpaper","workspaces"]`, `center = ["clock"]`, `end = ["notifications","clipboard","network","bluetooth","tray","battery","session","control-center","clock"]`.
 
-## GUI→repo propagation (checkout-is-deployment)
-- `~/.config/noctalia/config.toml` is symlinked into the repo → GUI settings writes land in the repo working tree automatically.
-- `~/.local/state/noctalia/settings.toml` can SILENTLY become a plain file (observed 2026-10-17; hardlink/symlink wiring decays) → GUI bar-layout changes then diverge from the repo with no signal. AUDIT: `readlink ~/.local/state/noctalia/settings.toml` must print the repo path; if it's a plain file and repo copy is content-identical, re-arm: `ln -sfn <repo-path> <live-path>` + `noctalia config validate`.
-- Landing in the working tree ≠ propagated: other boxes only see it after commit + push to Gitea main. `live-sync.path` (PR #15; DirectoryNotEmpty on `dotfiles/`) commits dotfiles-tier writes within ~2 s once deployed — until it is active on a box, the hourly heartbeat leaves up to 59 min of exposure, and on 2026-10-18 exactly that window let a trunk-sync stash destroy months of GUI layout work. Until verified active (`systemctl --user status live-sync.path`), commit GUI layout edits the same session yourself. Noctalia's runtime churn (wallpaper path, nightlight, panel positions) rides along; normal.
-- niri has NO settings GUI; niri "GUI changes" don't exist, and `niri msg output ...` runtime overrides are not persisted. niri cfg mirror↔live links also decay (all inodes decoupled once) → audit by CONTENT: `diff` every `~/.config/niri/cfg/*.kdl` against its `dotfiles/zz-blankpad/niri/...` mirror, never trust links.
+## Clobber window and recovery (2026-10-18 incident law)
+- GUI-built layout is **working-tree-only until the hourly live-sync heartbeat commits it**. A merge/sync session that "clears the dirty tree" can `git stash` those edits, and later stash operations can destroy the entries - customizations then vanish from the live bar with the repo copy stale.
+- Never blame the GUI or noctalia first: diff live file vs `HEAD`, check heartbeat commits (`git log -- dotfiles/noctalia/.local/state/noctalia/settings.toml`), then the stash chain.
+- Destroyed stashes are recoverable: `git fsck --lost-found` lists dangling commits; `git show <dangling>:dotfiles/noctalia/.local/state/noctalia/settings.toml` dumps each candidate; pick by `[bar.default]` richness (capsule groups, extra clock instances). Validate a candidate in a sandboxed `XDG_*_HOME` before touching the live file.
+- After recovery, commit the file immediately so the window closes.
 
-## If the bar got wiped (recovery)
-- The working-tree file is often the ONLY copy of GUI work; a `git checkout`/stash/merge clobber is survivable because git objects outlive stash entries: `git fsck --lost-found`, inspect `git log -1 --format='%ci %s' <dangling>` (newest `WIP on` stash commits hold the last good settings.toml), dump with `git show <c>:dotfiles/noctalia/.local/state/noctalia/settings.toml`.
-- Before restoring: back up the clobbered file to `.AGENTTRASH/`; validate the candidate in a sandbox (`XDG_CONFIG_HOME=… XDG_STATE_HOME=… noctalia config validate` — plugin-widget "unrecognized type" warnings there are offline-CLI blindness, not blockers); restore via `cp` onto the repo path (cp writes through the symlink; `mv` would replace it); prove visually with `noctalia msg screenshot-fullscreen`; commit immediately.
-- Cross-check the recovered layout against Frank's old screenshots in `~/Pictures/screenshot_*.png` (crop top ~7% with magick) — they are ground truth for what the bar should look like.
+## Widgets (v5 census, verified 2026-10-17)
+- Full roster in `settings.toml` widget_order plus docs: activity, backlinks, battery, bluetooth, brief, bright, cat, cheatsheet, chart, clipby, clipboard, control-center, cpu, controls, cava (now playing), disk, gpu, help, keyboard, language, launcher, mediaplayer, memory, mic, network, night-light, noctalia-palette, notification-history, notifications, niri-colors, power-section, power-profile, screenrecord, scratchpad, screenshot, session, shell (custom shell command), slowouts, slowouts-visible (per-output bar assignment), speedtest, swayosd-*, taskbar, tray, voiceline, volume, wallpaper, weather, workspaces.
+- `clock` widget: `format` (chrono strftime), `schema` (12/24), `multi_line`, `show_seconds`, `popup`, and **timezone** = IANA name. Multiple clock widget instances are supported: ids like `clock`, `clock-utc`, `clock-sea` each get a `[widget.<id>]` subtable -> one capsule per instance. This is how multi-timezone (Seattle work + UTC dev) lands: add `clock` + `clock-utc` to `end` (or `center`), set `timezone = "Etc/UTC"` on the utc one.
+- `cat` widget: shows random ASCII art, `rows` setting (4-10).
+- `shell` widget: `command`, `run interval` (seconds), `icon`, `terminal`; output lands in its capsule popup - can wrap any CLI (hyprstatus-style).
+- `taskbar` widget: shows window buttons **only on outputs where `niri-bridged` is enabled** (noctalia-launcher enables it). Buttons render **icon-only** (app icon from icon theme; fallback = first letter of title); the window title string is NOT shown in the bar. Hover tooltip carries title + app_name. Per-widget settings: `show_icons`, `show_actions`, `disable_middle_click`, `preferred_app_names` (map app_name -> icon for missing icons).
+- Widget ids usable in `[bar.*].start|center|end` are restricted to "bar widgets" (`is_bar_widget` allowlist in `bar.rs`); non-bar widget ids are silently dropped at load. `group:<id>` entries render capsule groups.
+- Capsule groups: `[bar.<name>.capsule_groups]` id = `["widget",...]`.
+- Niri layout law for bars: window width must stay **odd** (strut = (W-1)/2); bars reserve via layer-shell, niri's reserved area = layer surface size, so bar height changes need no niri edit.
 
-## Apply/verify loop (no restart, no reload IPC)
-1. Edit the repo `settings.toml`.
-2. `noctalia config validate` (checks merged layers; also `noctalia config export [full] | yq -p toml` to inspect effective values).
-3. Both layers are file-watched → hot-reload. Prove visually: `noctalia msg screenshot-fullscreen` saves a PNG to `~/Pictures`; read the image and inspect the bar.
-4. **Screenshot race:** the `ok` return precedes the PNG write. Never chain `noctalia msg screenshot-fullscreen && magick "$(ls -t ~/Pictures/screenshot_*.png | head -1)" ...` in one command — you crop the PREVIOUS capture. List `ls -t` in a separate later call and crop the named file.
-5. Crop for reading: `magick <png> -crop 100%x8%+0+0 +repage /tmp/strip.png`, then read the strip; cross-check clocks against `date -u` / `date`.
+## Bar styles (GUI-visible, settings.toml keys)
+- `[bar.*]`: `thickness`, `font_family`, `font_weight`, `font_size`, `opacity`, `border_width`, `border_offset`, `rounded`, `paddings`, `icon_ratio`, `follow_layout`, `output`, `exclusive`, `layer` (`bottom` = below window layer; `overlay` = above windows), `position` (`top`/`bottom`).
+- Per-monitor bars: add a `[bar.<name>]` with `output = "<monitor>"` and `follow_layout = true` (niri) -> per-workspace strut follows tall windows on that monitor. This is the mechanism for "bar shrinks when a window is tall" (the bar is a layer-shell strut, NOT a niri layer rule).
+- The GUI "Bar" page is the reference list; anything absent from settings.toml is a built-in default.
 
-## Clock widgets
-- `[widget.clock]` settings: `format`, `vertical_format`, `tooltip_format`, `timezone` (IANA id, e.g. `"UTC"`, `""` = system local). Tokens are strftime-compatible (`%H` 24h, `%I:%M %p` 12h, `%F` ISO date); `{:%...}` brace fields optional; `\n` = second line. Docs: docs.noctalia.dev → bar/widgets/clock + configuration/date-format-tokens.
-- **One timezone per widget; multiple instances allowed:** any `[widget.<id>]` needs `type = "clock"` for custom ids (bare `clock` id infers it). Each instance converts independently — e.g. local 12h + `timezone = "UTC"` 24h side by side.
-- Placement: add ids to `[bar.<name>]` start/center/end, or to a capsule group: `[[bar.default.capsule_group]]` with `id = "g1"` + `members = [...]`, referenced from `start` as `"group:g1"` (member order = left-to-right inside the capsule).
-- Local date + local 12h fit in ONE widget (same tz); the UTC 24h clock must be a second widget.
-- Expect the date widget (local) and UTC clock to disagree on the day after ~5 PM Seattle — that's correct UTC, not a bug; offer `%F` inside the UTC widget if it irks.
+## Slowouts (window-height-aware bars/panels)
+- `slowouts` = hidden engine (not a bar capsule): `[slowouts]` keys `enabled`, `duration`, `easing`, `trigger_offset`; per-monitor `[slowouts.<monitor-name>]` overrides (e.g. `DP-1`) with the same keys plus `edge`.
+- `position = "top"` + `exclusive = false` + slowouts on the monitor -> panel hides when a window touches its edge, re-reveals otherwise. `slowouts-visible` = toggle capsule.
+- **Slowouts needs niri workspace-autoresize ON** (niri `workspace-autoresize` = "per-workspace" in cfg/layout.kdl `output ... { workspace-autoresize per-workspace }`): noctalia computes hide from workspace height < panel bottom edge; uniform-strut layouts never trigger it.
+- Per-output bars: slowouts config keys are monitor names, so one `[bar.<x>]` with `output` + `exclusive=false` + `layer=overlay` per slowout monitor is the supported shape.
 
-## Taskbar recipes
-- Move window indicator beside workspaces: put `"taskbar"` in `start` after `"workspaces"`.
-- Combine workspaces+windows into ONE widget: `[widget.taskbar] group_by_workspace = true` — per-workspace capsules with disc labels (focused/occupied/empty/urgent colors); `workspace_group_content = "icons"|"count"|"dots"` (count/dots: left-click activates the workspace); `hide_empty_workspaces`, `show_workspace_label`, `minimal`, `workspace_label_placement = corner|centered|inside`. Requires compositor per-window workspace assignment (niri: yes; LabWC: no → stays flat).
+## Layout modes and window title decorations
+- `[layout]`: `mode` (`tiling`|`floating`|`monocle`), `pseudotiled`, `focus_bar` (window-title bar at top, center, layer-shell; style via `[ui.controls...]`/bar-ish settings), `window_follows_cursor`, `gaps`, `border_width`, `rounded`, `blur`, `opacity`, `borderless_csd`, `show_native_decoration`.
+- `focus_bar` is the noctalia analog of niri's drawn window title, but ONE global bar (no per-window arrows). True per-window title tags = niri `draw-with-border` on window rules; noctalia adds no per-window decoration (it's a bar app + portal, composites nothing).
+- Floating mode: right-click desktop / `SUPER+Shift+F` / toggle widget; widgets `floating-directories`, `floating-files`, `pins` (sticky notes), `canvas`, `sketchpad`, `post-its`. Float windows snap to screen quarters (`SUPER+Ctrl+Alt+Arrows`) and tile into current layout (`SUPER+Shift+T`). `[layout.floating.files]` = icon/view/sort/preview size.
+- `[bar.*].window_display` = `disabled`|`icons`|`text`|`combined` - per-window chips in the bar strip (niri only; this is what niri-taskbar could not do). Values: `disabled`|`icons`|`centered`|`inside`. Requires compositor per-window workspace assignment (niri: yes; LabWC: no -> stays flat).
 - The `workspaces` widget itself has no window display; styles are regular/minimal/focus_hint only.
 
 ## Law
 - Full widget/setting tables: https://docs.noctalia.dev/noctalia/bar/ and .../bar/widgets/<name>/ . Commit bar changes atomically to the command-center repo (checkout is the deployment).
-- **Ask before applying.** Frank asks "how do I X" questions about the live bar; answer with the exact snippet + file, apply ONLY on explicit go. A settings.toml edit is a live-deployment change, not a demo. (Exception: restoring Frank's own layout after data loss, on his ask.)
-- Git `M` on settings.toml usually carries noctalia's own runtime churn (wallpaper path, nightlight, panel positions) alongside your edit — mention it when committing.
+- **Ask before applying.** Frank asks "how do I X" questions about the live bar; answer with the exact snippet + file, apply ONLY on explicit go. A settings.toml edit is a live-deployment change, not a demo.
+- Git `M` on settings.toml usually carries noctalia's own runtime churn (wallpaper path, nightlight, panel positions) alongside your edit - mention it when committing.
+- Right after building layout in the GUI, commit settings.toml (or trigger `scripts/live-sync.sh`) before any branch/merge work: the uncommitted-GUI-edit window is exactly where the 2026-10-18 clobber happened.

agent/managed-skills/omp-extension-live-tui-verify/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: omp-extension-live-tui-verify
+description: "Verify an omp extension's slash commands and event hooks against a real TUI session: pty submit semantics, observable side-effect instrument, transient-toast trap, agent_end willContinue law, PipeWire output triage."
+---
+
+Verify that a `.ts` file in `agent/extensions/` actually works inside the interactive TUI — the black-box bats seam cannot see harness-side wiring (event names, arg passing, mode gating), and it will pass beside a dead hook.
+
+Distinct from `omp-tui-live-visual-verify` (config/theme rendering proven by screenshot): here the instrument is **observable side effects**, not pixels, because extension notifications are transient toasts that vanish before the pty buffer is read.
+
+## 1. Launch the exact build under test
+
+```bash
+omp --no-extensions --no-session -e /abs/path/agent/extensions/<name>.ts
+```
+as a **pty service** (`pty: true`, `ready: {"log": "╭|❯|Tip:|─", "timeout": 60}`).
+`--no-extensions` + explicit `-e` proves the file loads by path and nothing else interferes. Neutral cwd (`/tmp`) so repo state cannot color the run.
+
+## 2. Submit input correctly (the costly gotcha)
+
+`write proc://<id>` with a trailing `\n` does **not** submit — the text just sits in the composer.
+
+- **Works:** two writes — first `"/cmd args"` (no terminator), then a **separate** write whose whole content is `\r`.
+- **Broken:** `"/cmd args\r"` in one write. It still submits, but the trailing `\r` arrives inside the command args. Symptom: `unknown voice 'narrator1\r'`, an unexpected extra utterance, or a chat message whose transcript line ends in a literal `\r`. That is a harness artifact — never "fix" it by stripping control characters in the extension (`.trim()` already covers what a keyboard can produce).
+
+## 3. Instrument with a stub, never with ears or eyes
+
+Point the extension's player/handler at a script that appends evidence:
+
+```bash
+#!/usr/bin/env bash
+echo "$1" >> /tmp/stub.log; cp "$1" "/tmp/out-$$.wav"; exit 0
+```
+Run the TUI with that stub in the env the extension reads (`DANKVOICE_PLAYER=…` style). Then every assertion is a file: `wc -l` of the log (how many times it fired), `ffprobe -show_entries format=duration` (what it produced), `ls -d <tmp-glob>` (that cleanup ran).
+
+Sequence per behavior: command → CR → short `sleep` → count. **Count before and after** each command; the delta is the only honest proof a subcommand stayed silent.
+
+## 4. Discriminate "fired twice" from "fired once per turn"
+
+Stray CR writes can create extra empty turns, each with its own `agent_end` — two utterances for one intended prompt is usually **two turns**, not a duplicate speak. Confirm by counting assistant turns in the transcript (`read proc://<id>`), and by matching each clip's duration to its own answer's length.
+
+## 5. Event-hook contract traps
+
+- `agent_end` payload (`dist/types/extensibility/shared-events.d.ts`): `{ type, messages: AgentMessage[], willContinue? }`. **`willContinue: true` means the harness already scheduled a continuation** (auto-retry / empty-stop retry) — a subscriber that narrates or notifies there speaks an answer the model is about to redo. Gate on it.
+- Read the real event/payload shape from `~/.bun/install/global/node_modules/@oh-my-pi/pi-coding-agent/dist/types/…`; grep `dist/cli.js` for the literal event names to confirm they exist.
+- A driver test that *calls* the handler by hand proves nothing about emission — that is exactly the gap this live check closes.
+
+## 6. Audio output goes silent while every command reports success
+
+`pw-play` exits 0 and prints `stream drained` even when nobody hears anything. Triage order:
+
+```bash
+wpctl status                       # Sinks, the `*` default, and live Streams
+wpctl get-volume @DEFAULT_AUDIO_SINK@
+```
+- A **`Default Configured Devices` entry naming a `bluez_output.*` node that is not in the Sinks list** = remembered-but-offline Bluetooth: the classic silent-route cause.
+- Confirm the stream really links: a short clip can vanish before inspection, so use a multi-second clip and read `wpctl status` mid-play, or target explicitly: `pw-play --target <node-id> <file>` (node ids from `wpctl status`; `wpctl inspect <id>` gives `node.name`).
+- Prove the synth path independently of the player: `curl -o x.wav …` then `file x.wav` (expect `RIFF … WAVE … PCM`).
+
+## 7. Land it
+
+Live result belongs in the commit message, the reference page, and the work log — and the guard the live check uncovered gets its own behavior test (assert observable output only: fired count, payload content, silence).
+
+## Cleanup
+
+`/exit` or `proc://<id>/kill` the service; move stub scripts, logs, and clips to `~/.AGENTTRASH/<date>-<topic>/` — never `rm`. Kill background jobs that keep playing to the operator's speakers.

agent/managed-skills/omp-models-yml-runner-api-placement/SKILL.md

@@ -1,12 +1,14 @@
 ---
 name: omp-models-yml-runner-api-placement
-description: Add or edit a non-chat (tts/image/embedding) model row in ~/.omp/agent/models.yml without disabling every custom provider
+description: "Add or edit a non-chat (tts/image/embedding) model row in ~/.omp/agent/models.yml, wire the speech role, and diagnose a failing speech device without blaming a healthy endpoint"
 ---
 
 # Scope
 
 `~/.omp/agent/models.yml` (or `models.yaml`) on a workstation: adding a **runner**
-model row (TTS / image / embedding / rerank / video) alongside chat providers.
+model row (TTS / image / embedding / rerank / video) alongside chat providers,
+flipping `config.yml` `modelRoles` at it, and diagnosing a speech device that
+refuses to speak.
 
 # The landmine
 
@@ -63,9 +65,52 @@ yielding.
 # Speech transport contract (`openai-speech`)
 
 Body is `{model, input, response_format, voice?, speed?}`; `voice` is forwarded
-only when explicitly set; `sample_rate`/`bit_rate` **throw**
+**only** when the caller passed `voice_id`; `sample_rate`/`bit_rate` **throw**
 (`openai-speech does not support sampleRate`). Codec comes from the
 `output_path` suffix; 15 000-character cap. An unknown `voice` name is a server
 error, not a fallback — and `auth: none` makes a dead endpoint read as
 *available*, so point `modelRoles.speech` at such a provider only after it has
 answered a real synthesis.
+
+# Three speech-role laws (bundle-read + measured 2026-10-18)
+
+1. **No setting carries a voice for `openai-speech`.** The transport builds the
+   body with `voice` from the call's `voice_id` and nothing else.
+   `tts.localVoice` is the *local Kokoro backend's* key; `speech.voice` is the
+   TUI's **speak-aloud** voice, an enum of Kokoro names that never reaches an
+   HTTP request (setting it to a pack name breaks the vocalizer and does nothing
+   for synthesis — read `cfgSpeechVoice` in `dist/cli.js` before believing
+   otherwise). So a voice-less call is the harness's **normal** shape: a
+   voice-required endpoint needs a server-side default (fleet answer:
+   `DEFAULT_VOICE` in `scripts/frank-tts.env`, journal marks the line
+   `(default)`, unknown names still 400 with the list).
+2. **An explicit role has no fallback candidate.** `modelRoles.speech` set to one
+   model yields exactly one candidate, so a dead endpoint or an unresolvable
+   selector fails with *"No available speech model matches the speech role"*
+   instead of degrading to Kokoro. Loud-by-design; do not "fix" it by adding a
+   fallback in the client.
+3. **`models.yml` loads at process start; `config.yml` is read live.** A session
+   older than the new row fails exactly like a dead endpoint while a fresh
+   process succeeds in the same minute.
+
+# Diagnosing "speech device won't speak" — in this order
+
+1. `curl` the endpoint directly with a real voice name. 200 + audio ⇒ the service
+   is fine and the fault is harness-side; stop touching the server.
+2. Control test in the *same* session: point `modelRoles.speech` at
+   `local/kokoro` and call the device. It works ⇒ `config.yml` is live-read and
+   the runner selector or its voice argument is the problem, not the endpoint.
+   Revert the role immediately after.
+3. Distinguish stale registry from dead endpoint with a fresh process:
+   `omp -p --no-session --no-extensions --no-skills --no-rules --tools tts --cwd /tmp
+   'Call the tts tool exactly once with text="…" output_path=/tmp/x.wav
+   voice_id=<name> — then reply with the tool result line.'`
+   Succeeds ⇒ the long-lived session predates the `models.yml` row; restart it.
+4. Cross-check server-side, never trust the client's echo: the façade/access log
+   line and the engine's own ledger must carry the same byte count the tool
+   printed. (`model=…` in a tool result is what the client *requested*; a server
+   line is the fact.)
+5. For harness-behaviour claims, read the bundle rather than reasoning from the
+   tool description: `/home/blank/.bun/install/global/node_modules/@oh-my-pi/pi-coding-agent/dist/cli.js`,
+   e.g. `grep -o -E '.{300}response_format:[a-zA-Z$]+.{250}'` for the speech body
+   builder, `grep -o -E 'cfgSpeechVoice:.{0,400}'` for what a settings key feeds.

agent/managed-skills/one-decision-per-ask-question/SKILL.md

@@ -1,27 +0,0 @@
----
-name: one-decision-per-ask-question
-description: "Use when putting decisions to Frank via the ask tool or a grilling round — exactly one work item per question, rounds may group many single-item questions."
----
-
-# One Decision, One Work Item, One Question
-
-Friction-earned rule (corrected twice on 2026-10-18, during the voice/TTS planning).
-
-## Rules
-
-- Each question addresses **exactly one work item**. A round may contain many questions covering different work items; a question may not.
-- Never merge two artefacts into one option because they share an implementation dependency. Sharing an endpoint, a service, or a build step is NOT grounds for one question. (`frank-tts` serving both a podcast and an audiobook generator produced exactly this bug.)
-- Never offer something Frank did not ask for inside another question's option text. If an idea is mine, it gets its own question or stays out of the plan; it never rides along as "…and also X" in an option label or preview.
-- Do not derive option wording from my own scaffolding (todo text, my table row labels, my runbook headings). Derive it from his stated goal.
-- Mark the recommended option; a bare "yes" must accept it.
-- Facts are mine to fetch (subagent/scout), never a question for him. Only decisions go to him.
-- A question whose answer depends on an unsettled fact or another open question belongs to a **later round**, not this one.
-
-## Anti-patterns that triggered this
-
-- One option: "Audiobook/podcast factory — open-notebook + EPUB→narration builder." Two products, one shared dependency, zero requests for the second one. He answered "I never asked for audiobook generation."
-- One question: "Is the deliverable the podcast, or the platform (harness voice + OpenWebUI + alerts)?" Four work items in one question. Rejected: "You're lumping multiple asks into one question. Ask me per item."
-
-## Check before sending
-
-For each question: can I name the single artefact it decides? If two names come to mind, split it.

agent/managed-skills/openwebui-tts-chain-audit/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: openwebui-tts-chain-audit
+description: Audit/repair OpenWebUI TTS on Dankclaw when cloned voices get rejected by a 29-name Kokoro enum or synthesis is silent; rootless DB + endpoint probes
+---
+
+Audit OpenWebUI's TTS/STT wiring on Dankclaw when a voice is rejected, synthesis is silent, or someone asks "is the cloned voice wired correctly". Not for model-picker/ACL issues (openwebui-picker-acl-repair owns those).
+
+## Shape of the stack
+- Container `open-webui` runs **rootless as `dank`** on Dankclaw: `ssh dankclaw 'podman exec open-webui ...'` (NO sudo: `sudo podman` sees an empty world). Host port 3005.
+- Server-side config = `webui.db` `config` table (admin), per-user overrides = `user.settings` JSON column. Settings changed via UI persist per-user; admin page persists to `config`.
+- Cloned voices live behind the frank-tts façade `:7772` (`/v1/audio/speech`, `/v1/audio/voices`); voices resolve to `/home/dank/voices/<name>/reference.wav`.
+
+## The trap (2026-10-18 law)
+`Error: Voice "narrator1" not found. Should be one of: af_heart, ...` (29 names) is **OpenWebUI's bundled in-browser Kokoro** (`browser-kokoro`) rejecting client-side — frank-tts never sees the request. Signature: container logs show zero `audio/speech` hits. Fix = the personal dropdown Settings -> Audio -> TTS Engine -> Default (empty string), not any deploy.
+
+## Probe sequence (read-only, safe)
+1. Admin truth:
+   `podman exec open-webui python -c "import sqlite3; c=sqlite3.connect('/app/backend/data/webui.db'); [print(k,'=',v) for k,v in sorted(dict(c.execute('SELECT key,value FROM config')).items()) if 'audio' in k or 'tts' in k.lower()]"`
+   Expect: `audio.tts.engine=openai`, `audio.tts.openai.api_base_url=http://host.containers.internal:7772/v1`, `audio.tts.model=frank-tts`, `audio.tts.voice=<cloned name>`.
+2. User overrides — a user pinned to `browser-kokoro` beats admin config. CAUTION: `user.settings` can be SQL NULL or the JSON string `"null"`:
+   `... for uid,s in c.execute('SELECT id,settings FROM user'): d=json.loads(s) if s else None; d=d if isinstance(d,dict) else {}; hits={k:v for k,v in d.items() if 'audio' in k or 'tts' in k.lower()} ...`
+3. Endpoint truth: `curl -s http://127.0.0.1:7772/v1/audio/voices` (roster), then POST the exact OpenWebUI body `{"model":"frank-tts","input":"probe","voice":"narrator1","response_format":"mp3","speed":1.0}` to `/v1/audio/speech` — expect `200 audio/mpeg`.
+4. Contrast logic: server-path failure leaves a container log line AND a façade error; browser-kokoro failure leaves neither.
+
+## Law
+- Full contract + diagnosis live in serverAppConfigs docs (`Dankclaw/OpenWebUI.md` § Text-to-speech, `Dankclaw/Frank TTS.md` troubleshooting). Docs are the source; this skill is just the probe route.
+- Rootless gotcha generalizes: any Dankclaw service probe through podman goes WITHOUT sudo unless the unit is a system quadlet.

agent/managed-skills/skills-cli-retroactive-store-wiring/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: skills-cli-retroactive-store-wiring
+description: "Retroactively register hand-copied skills with the vercel-labs skills CLI (global store + lockfile), wire omp via the agents provider (no repo symlinks), and extract authored overrides without twins"
+---
+
+# Skills CLI retroactive store wiring (omp tiers)
+
+Retrofit provenance for hand-copied skills and wire them for omp on Dank workstations. Executed 2026-10-18 on blankpad; doctrine doc: `omp-docs/tools/vercel-labs-skills/skill-store-wiring.md` (repo).
+
+## Tier law (final design — do NOT reintroduce per-skill symlinks in the repo)
+| Tier | Path | Owner |
+|---|---|---|
+| Store | `~/.agents/skills/` + lockfile `~/.agents/.skill-lock.json` (v3) | `skills` CLI |
+| Authored | `<repo>/agent/skills/` real dirs | Frank, branch → PR |
+| Managed | `~/.omp/agent/managed-skills/` | `manage_skill` only |
+
+omp has NO agent id in the skills CLI (79-agent registry in `dist/cli.mjs`; `-a pi` writes `~/.agents/skills` too — pi detector keys on `~/.pi/agent`). omp reads the store DIRECTLY via its `agents` provider (`skills.enableAgentsUser`, default true; check with `read cfg://skills`). Precedence: authored (native, 100) > skillshare > ... > agents provider > managed (5). Identical copies collapse by realpath; differing same-named copies survive namespaced `agents/<name>` with a startup warning — so when authoring an override, REMOVE the store twin (`npx -y skills remove <name> -g`; prunes lockfile too) or `skills update -g` resurrects a twin.
+
+## Procedure (retroactive registration)
+1. List the repo/live skill dirs to register; identify true sources (per-skill — e.g. `find-skills` is `vercel-labs/skills`, not `mattpocock/skills`).
+2. Drift check FIRST, per skill, before anything moves: `diff -rq <live>/<name> ~/.agents/skills/<name>` after canonical install; abort-and-report on drift (byte-identical = clean cutover).
+3. Canonical install (scratch dir with a package.json; global scope): `npx -y skills add <owner>/<repo> --all -g` (+ per extra source `npx -y skills add vercel-labs/skills --skill find-skills --agent universal -g`). Artifacts: store dirs + `~/.agents/.skill-lock.json`; verify `jq '.skills|length'`.
+4. Authored extraction (only for skills the user will customize): copy dir into repo `agent/skills/<name>/`, add an "Authored override" note after frontmatter, then `npx -y skills remove <name> -g` and confirm `jq '.skills|has("<name>")' == false`.
+5. Clear repo copies of store-managed skills (repo records authored overrides ONLY). Live cutover after merge: move old dirs to /tmp snapshot, `git merge --ff-only origin/main` in the live checkout.
+6. `skills ls` from a repo containing `agent/skills` mislabels skills as Eve project skills (path collision) — attribution noise, ignore.
+7. Fresh-box recipe (three commands, no wiring): add `--all -g`, add find-skills, `remove grilling -g`.
+
+## Gotchas
+- Eve/Codex `agents/openai.yaml` files ride along from upstream; omp ignores them — prune from authored dirs (they get swept off disk elsewhere, leaving phantom ` D` in git status).
+- `skills remove` prunes only global scope if `-g` given; check lockfile after.
+- Mid-run doc readers (subagents) may see pre-cutover trees — send them a correction message, don't let stale advice ship in issue bodies.

agent/memories/sharpshooter/omp-32c11n2wnglul/state.json

@@ -1,6 +1,6 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792368375152,
+	"lastConsolidatedAt": 1792395788647,
 	"lastResult": {
 		"at": 1791599865775,
 		"sessions": 1,

agent/memories/sharpshooter/serverAppConfig-eu5lc7uqff33/state.json

@@ -1,4 +1,4 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792359704968
+	"lastConsolidatedAt": 1792386375195
 }

agent/memories/sharpshooter/tmp-1tpw73408x3e/state.json

@@ -1,4 +1,4 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792359739617
+	"lastConsolidatedAt": 1792396789735
 }

agent/memories/sharpshooter/wt-20261017-181502-6d1fc1f-1oq2osmoyw03k/architecture.md

@@ -1,118 +1,70 @@
-## Runtime Stack
+## Subagent routing (harness law, 2026-10-18)
 
-**llama.cpp** is the inference runtime for all `frank-zealot`-class endpoints. The `frank-zealot` service runs llama.cpp master (0.5.0-dev, commit `5fc4f3c`), CUDA sm_86 build, under a root systemd unit.
+**No subagent class may route to `frank-archon`** — the operator session lives there and
+the endpoint runs 3 sequences (`--max-num-seqs 3`), so `task.maxConcurrency + 1` children
+eat the parent's own KV slots. Violation cost: three doc children + parent = 4 sequences
+on 3 slots, children ran 2 h 27 m / 2 h 45 m, the interactive session starved.
+Routing and bounds live in `~/.omp/agent/config.yml` (`task:` block — the owner; verified
+with `read cfg://task/agentModelOverrides`): heavy writers (`task`, `scout`) → frank-dragoon
+(2 slots, idle, slow card ⇒ slice work smaller), bursty readers (`reviewer`, `sonic`,
+`designer`, `librarian`) → frank-zealot (2 slots, also the compaction hub and every
+tiny/smol/plan/commit/memory role). Caps: `maxConcurrency: 2`, `maxRuntimeMs: 1800000`,
+`softRequestBudget: 120`, `maxRecursionDepth: 1` (children never spawn children).
+`cfg://.../save` approvals auto-deny after a hardcoded 10 s dialog — after Frank has
+approved a change, edit `config.yml` directly and validate the YAML; a running session
+picks global-config edits up at once. Full procedure: managed skill
+`bounding-subagent-runtime`.
 
-## Model Inventory
+## Documentation law (2026-10-18)
 
-### frank-zealot (Dankclaw: 192.168.0.143:7771)
+**One fact, one owner.** The `serverAppConfigs` repo owns every fleet fact;
+`AGENTS.md` restates only what a deploy gate or the harness needs and otherwise
+links. `serverAppConfigs-docs/` (Obsidian vault) carries the lore: one page per
+endpoint (`[[frank-archon]]`, `[[frank-dragoon]]`, `[[frank-zealot]]`) holding
+Current shape, **Eras** (one row per payload swap: dates, payload, runtime,
+shape, why replaced, rollback), Laws, wire contract, files. `log.md` records
+incidents and laws only — no per-swap ledgers, no bench tables. A retired
+payload is an Eras row, never a page of its own. `scripts/<service>.env` beats
+any page: where they disagree, the page is the bug.
 
-**Ternary-Bonsai-2-27B-PQ2_0.gguf** (prism-ml/Ternary-Bonsai-2-27B-gguf)
+## Model swaps (2026-10-18)
 
-- Runtime: llama.cpp
-- Format: PQ2_0 quantized GGUF
-- 27B parameter class
-- Vision: native BF16 mmproj projector for image input
-- MTP: OFF (no `nextn` tensors in checkpoint)
-- Context: 256k per-slot window (`--ctx-size 401408 --parallel 2` = 200,704 tokens effective)
-- Batch: 4096 / ubatch 2048 (CUDA optimum)
-- Log verbosity: 4
-- Ports: 7771 on Dankclaw
+Swap the model, don't instrument the swap: edit the trio
+(`scripts/<svc>.env` + serve script + unit) → `./tests/run.sh` → PR →
+`deploy.sh <host> --service <svc>` → `/health` + one chat / tool-call / vision
+probe → done. **No benchmarks, A/Bs, ladders, or acceptance tables unless
+Frank explicitly asks for data.** If a payload misbehaves, revert the commit and
+redeploy. When a bench IS ordered, the GPU-safety procedure (stop + mask, no
+scratch ports, never `systemctl disable`) is `AGENTS.md` → *Model swaps*
+and *Deployment completeness*. 
 
-### frank-dragoon (Dankclaw: 192.168.0.143:7770)
+## Where facts live
 
-**Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated** (`.hgn` format)
+|Need|Owner|
+|---|---|
+|Topology, ports, payload, shape|repo `AGENTS.md` → Fleet topology; `scripts/<svc>.env` is the authority|
+|Endpoint lore, eras, laws, rollback|vault `serverAppConfigs-docs/LLM/<endpoint>.md`|
+|Harness model entries (`contextWindow`, `maxTokens`, `reasoningContentField`, `modelRoles`)|`~/.omp/agent/models.yml`|
+|Incidents and operational laws|vault `serverAppConfigs-docs/log.md`|
+|Service/infra pages|vault `Dankclaw/`, `Dankserver/`, `Infrastructure/`, `Architecture/`|
 
-- Runtime: halogen-flash-server 0.16.2 (digest-pinned `ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84…`)
-- Format: v2 `.hgn` (flash-server exclusive)
-- MTP head: INSIDE checkpoint (`HALOGEN_MTP_HEAD` unset)
-- Vision: ON (v2 tower loads beside checkpoint)
-- Base: abliterated (27B-era was censored finetune)
-- Slots: 2 × 262,144 ctx (KV pool 524,288 positions)
-- Server sampler: 1.0/0.95/20
-- Prompt cache: ON by default
+Models.yml resolution rules that are harness-local: a default model resolves as
+a `defaultProvider` + `defaultModel` pair; a subagent override is a bare model
+`id` and resolves only when unique across providers; two ports on one host need
+two provider blocks — the file cannot express "same host, different port".
 
-### frank-archon (Dankserver: 192.168.0.235:7770)
+There is **no audio input anywhere in the fleet** (gone with the Gemma4
+retirement, 2026-10-01). All three chat endpoints take text + images.
 
-**StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe** (`.rad` format)
+## Retired laws
 
-- Runtime: radiance 1.0.13 (digest-pinned `stilldeadcode/radiance@sha256:4c3f484564…`)
-- Format: fp8-KV `.rad` (121,969,901,568 B = 116,322 MiB)
-- MTP head: MTP depth 2, MNBT 2048, Froggeric v22.5 template
-- Vision: 27-layer Qwen-VL tower native
-- KV: 3 × 200,000 fp8-KV (`--max-num-seqs 3`)
-- 30,720 MiB of 30,969 MiB claimable
-- 44 GiB/rank pinned host pool, PLE pinned to RAM
-- Base-alignment: censored (abliterated family lives on frank-dragoon)
-
-## Resolution Rules
-
-Official model ids are StarCraft unit names, on the wire since 2026-10-09, and since 2026-10-10 they are also the SERVICE names: `frank-archon` → `192.168.0.235:7770`, `frank-dragoon` → `192.168.0.143:7770`, `frank-zealot` → `192.168.0.143:7771`.
-
-The default model resolves as a `defaultProvider` + `defaultModel` pair (provider must serve the model); a subagent override uses a bare model `id`, which resolves only when unique across providers. Two ports on one host need two providers — the file cannot express "same host, different port".
-
-When renaming a service, retiring an endpoint, or moving a model: update the provider block, model `id`, `contextWindow`, `maxTokens`, `input` in `models.yml`, then fix every `modelRoles` entry that named the old endpoint — a role pointing at a provider the file does not define fails at call time. As of 2026-10-06 **all three endpoints accept images** (`input: [text, image]`) — `frank-dragoon` returned to vision with the flash-server v2 swap, while `frank-archon` takes them natively and `frank-zealot` through its BF16 mmproj.
-
-Reasoning channel differs by runtime: llama.cpp AND SGLang (qwen3 parser, live-verified) emit `reasoning_content`, vLLM emits `reasoning` — `models.yml` sets `reasoningContentField` per endpoint to match.
-
-There is **no audio** input anywhere in the fleet: that capability left with the FLM NPU endpoint on 2026-09-11, returned 2026-09-17 with the Gemma4 projector's audio encoder, and left again with the Gemma4 retirement on 2026-10-01.
-
-## Boot Persistence & Self-Healing (MANDATORY)
-
-Every deployed, working Podman container MUST have a self-healing, boot-persistent Quadlet unit. A container that runs only from `compose.yaml` or a manual `podman run` dies silently at reboot — rootless Podman does not auto-start bare containers, and `restart: unless-stopped` does not survive the explicit stop that shutdown performs. Never report such a service as "up".
-
-Unit requirements:
-
-- **Boot persistence** — `[Install] WantedBy=default.target`, installed to `~/.config/containers/systemd/<name>.container`, enabled in the user manager, with linger on for the deploy user (`loginctl show-user dank -p Linger` → `Linger=yes`).
-- **Self-healing** — `Restart=always` (or `on-failure`) with a short `RestartSec`; quadlet health check where the service has one.
-- **Repo provenance** — the `.container` file lives in this repo (`<host>/<svc>/quadlet/`), is installed by the deployer, and is covered by the quadlet test seam. The host-side unit is generated state; the repo file is the source of truth.
-
-Before declaring a service deployed: `systemctl --user is-enabled <name>` → `enabled`, `is-active` → `active`, and the container answers its health check.
-
-A running container with no unit is a gap: write the unit, test it, deploy it.
-
-This rule exists because reboots found gaps twice (2026-08-26: Caddy as a bare compose container never returned; 2026-09-11: five observability services had no units). The observability services now have units under `dankclaw/observability/quadlet/` and their compose definitions were removed — one owner per container name. The stack is **configured and delivering as of 2026-09-17**: a Grafana datasource and the `llm-fleet` dashboard are provisioned from `shared/grafana/provisioning/`, `shared/prometheus/rules/llm-fleet.yml` loads 5 alert rules + 1 recording rule, and firing rules are delivered: Prometheus → Alertmanager (`dankclaw/observability/quadlet/alertmanager.container`, loopback :9093) → host-side Signal relay (`scripts/signal-relay.py`, user unit, 192.168.0.143:18093 — the host LAN IP, the one bind a container can reach as `host.containers.internal`; iptables admits loopback, the host and the podman bridge subnet only) → signal-cli account 318311.
-
-Prometheus targets read down for structural reasons (HTML-scraped "probes", Gitea metrics off); the remedy is a blackbox exporter. See `serverAppConfigs-docs/Infrastructure/Observability.md`.
-
-## Benchmarking Policy (MANDATORY)
-
-**STOP the production service BEFORE benchmarking** — these servers serve real users, and a bench beside a live service starves the GPU and corrupts results. Use the runtime's own harness: `llama-bench` for the llama.cpp endpoints; a live llama.cpp server also reports honest per-request numbers in the `/completion` `timings` object (prefill/decode rates, `draft_n`, `draft_n_accepted`), which is how frank-dragoon and frank-zealot were measured. Rolling your own bench requires asking first.
-
-Scratch ports are not used on LLM hosts — a test process cannot share the single GPU anyway; validate against the service itself.
-
-A gufo-era law: **`gufo bench` cannot rank speculative-decode settings, and will invert the ranking.**
-
-Measured 2026-09-28 on frank-dragoon at depth 32768: its corpus reports `acceptance=0.933 ± 0.000` with an **identical trace sha256** across draft widths, i.e. the same highly-predictable text every run, and 93 % of every proposal accepted. It reported 29–37 t/s decode where real traffic gives ~15 t/s, and it made `--draft-tokens 16` look 6 % faster than 7 when real text made it 14 % *slower*. Use it for shape, not for A/B. For an A/B, replay **real** text through the live server and read the `Server-Timing` header — but note the unit rides in the **name** half (`ttft;dur=402.485`), so splitting on `=` alone keys the dict `ttft;dur` and every lookup silently returns nothing. Generate **at least 128 tokens** for the measurement: at 8 tokens, `inter_token` is first-token noise and the run-to-run spread swamps every real difference.
-
-This covers **any GPU experiment, not just benchmarks** — including a bare 2-rank RCCL/`torch.distributed` probe. On 2026-09-16 one such probe was run against the live service "because it only needs 200 MB of VRAM"; the host went hard down ~20 minutes later (no ARP reply, 100% ICMP loss from two subnets, no recovery — a power cycle was required). A hung AQL dispatch wedging the GPU driver is the plausible mechanism, and this host has precedent for going unreachable until a power cycle. If an experiment needs GPUs, stop and mask first, or use a host that serves nobody. Telling an off machine from a wedged one: `ip neigh show <ip>` from a peer — FAILED means off/NIC dead, while a merely wedged kernel usually still answers ARP.
-
-1. Stop and mask (self-healing would restart it):
-   - Dankclaw `frank-dragoon` (root unit, halogen podman on the iGPU):
-     `sudo systemctl stop frank-dragoon && sudo systemctl mask frank-dragoon`
-   - Dankclaw `frank-zealot` (root unit, llama.cpp on the 3090):
-     `sudo systemctl stop frank-zealot && sudo systemctl mask frank-zealot`
-   - Dankserver `frank-archon` (root unit, radiance on both R9700s, TP=2):
-     `sudo systemctl stop frank-archon && sudo systemctl mask frank-archon`
-2. Bench.
-   NOTE: `systemctl mask` FAILS on a relinked unit (the unit file in `/etc/systemd/system/` is itself a symlink into the checkout — mask refuses to replace it). Stop is enough for the bench window; the deploy restores the unit, so re-deploy after benching instead of unmasking.
-3. Unmask and start; verify `curl http://192.168.0.<host>:7770/health`.
-
-**CRITICAL:** never `systemctl disable` a system unit on these hosts — it deletes the unit file from `/etc/systemd/system/`, not just the symlink. `mask` symlinks to `/dev/null` and is safe/reversible.
-
-## Subagent Lifecycle (MANDATORY)
-
-A subagent that appears stuck must have an explicit recovery path defined before the subagent is considered deployed. "Stuck" includes: silent completion halt, repeated identical responses, or extended latency without token emission.
-
-Recovery requirements:
-
-- **Explicit timeout** — a hard timeout (≤30s) on the subagent's response channel, with a defined action (retry, fallback, or escalate).
-- **State checkpoint** — the subagent maintains checkpoints at decision boundaries, allowing resumption from a known good state.
-- **Health signal** — the subagent publishes a heartbeat (≤5s interval) that triggers the recovery path when missed.
-
-A subagent without these three properties is a gap: write the timeout, add the checkpoint, wire the heartbeat, then deploy.
-
-This rule exists because subagent hangs were observed in early deployments (2026-09-xx: silent completion halt; 2026-09-xx: repeated identical responses). The deployment script must verify the heartbeat channel is live before reporting "deployed".
-
-Before declaring a subagent deployed: verify the heartbeat endpoint returns within the timeout window, and confirm the recovery path is wired (retry/fallback/escalation logic exists in the codepath).
-
-A subagent without a heartbeat or recovery path is a gap: wire the heartbeat, add the recovery path, then deploy.
+- The old "Benchmarking Policy (MANDATORY)" wording demanded a bench harness per
+  payload; superseded 2026-10-18 by the swap law above.
+- A "Subagent Lifecycle (MANDATORY)" rule (heartbeat ≤5 s, checkpoints, hard
+  timeout) was recorded here 2026-09 and **never implemented anywhere**; it
+  described nothing that exists and is deleted 2026-10-18. Do not re-add it
+  without a real implementation.
+- The fleet model inventory that used to live in this memory file drifted out of
+  date within hours (it still claimed Bonsai-2-**27B** at `--ctx-size 401408`
+  and a dragoon 524,288-position pool). Memory files do not get deploys — the
+  repo does. That is why it is pointers now.

agent/memories/sharpshooter/wt-20261017-181502-6d1fc1f-1oq2osmoyw03k/product.md

@@ -1,7 +1,24 @@
 ## Voice Generation
 
 - Custom voice source material must exclude the first 10 seconds of any audio sample file used to generate voices; this is a project-wide invariant across all source files, not a per-file exception.
+- Voice selector valid options: af_heart, af_alloy, af_aoede, af_bella, af_jessica, af_kore, af_nicole, af_nova, af_river, af_sarah, af_sky, am_adam, am_echo, am_eric, am_fenrir, am_liam, am_michael, am_onyx, am_puck, am_santa, bf_emma, bf_isabella, bm_george, bm_lewis, bf_alice, bf_lily, bm_daniel, bm_fable.
+
+## Input Capabilities
+
+All endpoints accept text input with optional image input: `frank-dragoon` returned to vision with the flash-server v2 swap, while `frank-archon` takes them natively and `frank-zealot` through its BF16 mmproj.
+
+There is no audio input anywhere in the fleet: that capability left with the FLM NPU endpoint on 2026-09-11, returned 2026-09-17 with the Gemma4 projector's audio encoder, and left again with the Gemma4 retirement on 2026-10-01.
+
+## Voice Usage Notes
+
+- Voice generator output does not affect token counting or inference costs — all voices are rendered post-inference.
+- Voice quality varies by source sample: exclude the first 10 seconds of any audio sample file used to generate voices; this is a project-wide invariant across all source files, not a per-file exception.
+- Voice selection is client-side only; the server does not generate or return audio data.
+
+## Load Management
+
+- Subagent settings must prevent frank-archon from being overwhelmed; concurrent request handling prioritizes endpoint stability over throughput.
 
 ## Podcast
 
-- Podcast functionality is sourced from open-notebook; this is a project decision established before this document was created.
+- Podcast functionality is sourced from open-notebook; this is a project decision established before this document was created.

agent/memories/sharpshooter/wt-20261017-181502-6d1fc1f-1oq2osmoyw03k/state.json

@@ -1,8 +1,8 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792370846394,
+	"lastConsolidatedAt": 1792396748497,
 	"lastResult": {
-		"at": 1792370515419,
+		"at": 1792393886960,
 		"sessions": 1,
 		"deltas": 1,
 		"model": "frank-zealot"

agent/memories/sharpshooter/wt-20261018-170616-7c8a99d-3bf6g32a51amg/product.md

@@ -1,2 +1,3 @@
 ## top bar
 - Preserve top bar customizations; customizations lost or obliterated on subsequent runs
+- Todo list updates as tasks change, not waiting for entire bill of tasks to finish

agent/memories/sharpshooter/wt-20261018-170616-7c8a99d-3bf6g32a51amg/state.json

@@ -1,8 +1,8 @@
 {
 	"v": 1,
-	"lastConsolidatedAt": 1792370776395,
+	"lastConsolidatedAt": 1792381281460,
 	"lastResult": {
-		"at": 1792370420509,
+		"at": 1792381281460,
 		"sessions": 1,
 		"deltas": 1,
 		"model": "frank-zealot"

agent/memories/sharpshooter/wt-20261018-170616-7c8a99d-3bf6g32a51amg/style.md

@@ -1,2 +1,2 @@
 ## window outlines
-- Window outline color is amber, and outline thickness is thickened
+- Window outline color is amber, and outline thickness is thickened

agent/memories/sharpshooter/wt-20261018-200946-7c8a99d-rvvnarlmu3eg/state.json

@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792381246498
+}

agent/memories/sharpshooter/wt-20261018-204442-7c8a99d-2u1dm4kttza8t/product.md

@@ -0,0 +1,3 @@
+# Output behavior
+
+Output must not be shaken off during presentation. Output remains anchored until explicitly confirmed.

agent/memories/sharpshooter/wt-20261018-204442-7c8a99d-2u1dm4kttza8t/state.json

@@ -0,0 +1,10 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792396722373,
+	"lastResult": {
+		"at": 1792396071933,
+		"sessions": 1,
+		"deltas": 1,
+		"model": "frank-zealot"
+	}
+}

agent/memories/sharpshooter/wt-20261018-204447-7c8a99d-16nzh99q92y2e/state.json

@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792381487662
+}

agent/memories/sharpshooter/wt-20261018-204501-6d1fc1f-3fct0wvty8jvu/state.json

@@ -0,0 +1,10 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792393561866,
+	"lastResult": {
+		"at": 1792381870670,
+		"sessions": 1,
+		"deltas": 1,
+		"model": "frank-zealot"
+	}
+}

agent/memories/sharpshooter/wt-20261018-220616-6d1fc1f-1tzr10loz2ao2/state.json

@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792388836682
+}

agent/memories/sharpshooter/wt-20261019-001426-7c8a99d-3m7k3cagiow5n/queue/01a15302-f12d-77d8-9a33-be31a1a05528/00mvexe0pf-6ozb.json

@@ -0,0 +1 @@
+{"v":1,"kind":"product_decision","statement":"Limit on zealot set to 3, dragoon set to 2, archon set to 3","source":"explicit_user","evidence":"make the limit on zealot 3, dragoon 2, archon 3","friction":{"corrective":false,"regression":false,"subtle":false},"sessionId":"01a15302-f12d-77d8-9a33-be31a1a05528","ts":1792394470419}

agent/memories/sharpshooter/wt-20261019-001426-7c8a99d-3m7k3cagiow5n/state.json

@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792394427081
+}

agent/memories/sharpshooter/wt-20261019-004309-7c8a99d-u0xusjwyvzai/state.json

@@ -0,0 +1,4 @@
+{
+	"v": 1,
+	"lastConsolidatedAt": 1792396749853
+}

agent/models.yml

@@ -24,27 +24,13 @@ providers:
         # compactionModel candidate keeps the wire model id valid there.
         compactionModel: llamacpp (dankclaw-3090)/frank-zealot
         name: "frank-archon"
-        # Dankserver: BOTH Radeon AI PRO R9700s (gfx1201, TP=2 over the
-        # 2026-09-20 board swap's root ports, wht6 wire). Engine:
-        # radiance (StillDeadcode, Apache-2.0) from the digest-pinned
-        # stilldeadcode/radiance image (index digest sha256:4c3f4845..., 287
-        # MiB, kernels prebuilt for gfx1201), plain `podman run` through
-        # scripts/serve-frank-archon.sh, root unit (User=dank, dank's
-        # rootless podman storage). Serving the OFFICIAL
-        # Qwen/Qwen3.8-Flash-Next-FP8 at NATIVE modelopt block-FP8
-        # precision — a rad-convert no-recipe pure copy into
-        # qwen4exp-fp8-native.rad (172.76 GiB measured by plan-only), built by
-        # scripts/build-frank-archon-rad.sh against a staging dir whose
-        # config.json drops quantization_config so the shipped qwen4exp
-        # plugin's (qwen4exp, "") selection key matches; per-weight
-        # encodings are untouched. Experts stream from a 40 GiB/rank
-        # pinned host pool; the 47.7 GiB PLE ngram table is pinned in RAM
-        # (Frank's call); KV fp8; MTP depth 3 (the checkpoint's own mtp.*
-        # head); prefix cache 4 GiB host + 64 GiB disk. Chat template:
-        # froggeric's fixed qwen3.8 v22.5
-        # (scripts/qwen38-froggeric-v22.5.jinja) via
-        # --override-chat-template. Rollback: git tag
-        # frank-archon-freetoken-pr587-20261005 (FreeToken, one card).
+        # Dankserver: BOTH Radeon AI PRO R9700s (gfx1201, TP=2, wht6 wire) on
+        # the digest-pinned radiance image, plain `podman run` under a root
+        # unit. Payload, shape, eras, laws, rollback:
+        # serverAppConfigs-docs/LLM/frank-archon.md — and
+        # scripts/frank-archon.env is the authority for every number there.
+        # contextWindow MUST quote the engine's --max-model-len: radiance
+        # refuses a longer prompt and never truncates.
         contextWindow: 200000
         # maxTokens must survive the harness compaction gap AND the chars/4
         # token-estimate under-run on code-heavy prompts. The clamp is
@@ -105,40 +91,22 @@ providers:
         # compaction model candidate so the wire model id stays valid
         # there even from a frank-dragoon session.
         compactionModel: llamacpp (dankclaw-3090)/frank-zealot
-        # halogen-flash-server 0.16.2 (ghcr.io/peonist-ai/
-        # halogen-flash-server@sha256:0c61bf84, digest-pinned) serving the
-        # Quat3rnion NATIVE v2 ABLITERATED conversion of orcarouter's pinned
-        # BF16 Qwen3.8-Flash-Next (qwen38-flash-next-v2-abliterated.hgn,
-        # ~62 GiB resident, + REQUIRED n-gram table + vision tower, both
-        # hardlinked from the swift15 dir) on the Strix Halo iGPU: TWO slots
-        # over ONE 401,408-position KV pool (= 2 x ctx, raised 2026-10-18) at
-        # HALOGEN_CTX=200704 (the ceiling lowered from the card's 262,144 on
-        # 2026-10-17; ~10.8 GiB reserved where 200,704 cost 5.5, 262,144 cost
-        # 7.2 and 524,288 measured 14.6), with the MTP head ALWAYS ON
-        # (HALOGEN_SPEC_ADAPT=0 — the default adaptive policy halves
-        # decode). Measured 2026-10-17: 50 t/s greedy decode, 1,604 t/s
-        # cold prefill at 59k, NIAH 18/18. ABLITERATED base (no refusals:
-        # 0/5 on the hostile census) and VISION ON (OpenAI image_url
-        # parts; >=256 px images or it answers "video"). Runbook:
-        # serverAppConfigs-docs/LLM/frank-dragoon-flash-server-v2-native.md.
-        # Window the harness may fill — deliberately BELOW the engine
-        # ceiling (HALOGEN_CTX=200704, lowered from 262,144 on 2026-10-17):
-        # the clamp below leaves the 45k gap that absorbs the estimate error.
-        # Both slots SHARE one 401,408-position KV pool — exactly two full
-        # windows — so TWO maximum-length conversations can be resident at the
-        # same time (at the old pool == ctx 200,704 only two of <=100k could).
-        # The per-request ceiling is unchanged, so this window is unchanged.
+        # halogen flash-server on the Strix Halo iGPU. Payload, shape, eras,
+        # laws, rollback: serverAppConfigs-docs/LLM/frank-dragoon.md — and
+        # scripts/frank-dragoon.env is the authority for every number there.
+        # contextWindow sits deliberately BELOW the engine ceiling
+        # (HALOGEN_CTX): the clamp below leaves the gap that absorbs the
+        # harness's chars/4 under-count, so a window equal to the ceiling
+        # would make every long request a guaranteed 400.
         contextWindow: 155648
         # The clamp is max_tokens = min(maxTokens, contextWindow − est −
         # 4096); the chars/4 est UNDER-counts the rendered prompt by ~3 %
         # on code/agent traffic (measured 2026-10-07: est 152,938 ->
         # server 157,388). Worst-case request = window − 4096 + 3 % est
-        # error ≈ 156.2k, inside the 200,704 engine ceiling with ~44k
-        # margin (robust to a ~25 % under-count). Compaction fires at 85 %
-        # of the window = 132,300 est ≈ 136k measured — the 180k target of
-        # the 262,144 era is unreachable now (the window itself is 155,648)
-        # — and rides on frank-zealot: input ≈ threshold − keepRecent(20k)
-        # ≈ 112k, inside its 200,704 slot.
+        # error ≈ 156.2k, inside the engine ceiling with ~44k of margin
+        # (robust to a ~25 % under-count). Compaction fires at 85 % of the
+        # window and rides on frank-zealot: input ≈ threshold −
+        # keepRecent(20k), comfortably inside its per-slot window.
         # HALOGEN_MAX_TOKENS_CAP in frank-dragoon.env must stay >= this.
         maxTokens: 45056
         reasoning: true
@@ -183,33 +151,14 @@ providers:
         # config.yml (192.168.0.143:7771 — this endpoint); the
         # compactionModel candidate keeps the wire model id valid there.
         compactionModel: llamacpp (dankclaw-3090)/frank-zealot
-        # Dankclaw's RTX 3090: llama.cpp PrismML fork build (vendor 10777,
-        # commit e3de71522 — the ONLY loader for this payload's custom tensor
-        # type 142 + prism.hadamard.* metadata, and the minimum build that
-        # pairs MTP with a quantized V cache) serving
-        # prism-ml/Ternary-Bonsai-2-9B-gguf at PQ2_0 (2,675,410,720 B) WITH the
-        # MTP head in the file — qwen35 hybrid, 32 layers (8 full-attention +
-        # 24 Gated DeltaNet), 4 KV heads x 256 dim, native 262,144 — in THREE
-        # conversations (--ctx-size 786432 / --parallel 3), each slot at the
-        # model's TRAINED window.
-        # KV is q8_0 K + q8_0 V (17 KiB/token over the 8 full layers =
-        # 13,056 MiB pool, ledger-exact); f16 KV would bill 26,112 MiB and
-        # cannot boot this card. Boot ledger 17,876 used / 6,249 free. Vision
-        # through the publisher's Q8_0 mmproj (624,229,664 B — Q8_0 is the
-        # publisher's requirement for concurrent image requests), whose
-        # worst-case lands outside the engine's fit projection. **MTP OFF —
-        # measured, not assumed**: the draft context bills its own f16 KV over
-        # the WHOLE pool (3,072 MiB) and at ubatch 2048 that squeeze halves
-        # decode (167.2 → 109.2 t/s); SPEC_TYPE=draft-mtp + UBATCH_SIZE=1024 is
-        # the 213.5 t/s arm if the card ever has room. 2026-10-18 swap from
-        # Ternary-Bonsai-2-27B PQ2_0 at 2 × 200,704. Measured: 167.2 t/s
-        # single-stream greedy decode, 280.2 t/s across three concurrent
-        # streams, 2,877 t/s prefill at 106,418. Base-alignment: censored base
-        # lineage; unlike the 27B there is NO CRACK re-export matching this
-        # file. Runbook:
-        # serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai9-mtp.md.
-        # contextWindow is the PER-SLOT window (= the native 262,144): a longer
-        # prompt needs compaction — llama.cpp answers a 400, never truncates.
+        # Dankclaw's RTX 3090 llama.cpp endpoint (PrismML fork build — the only
+        # loader for this payload's custom tensor type). Shape, payload, eras,
+        # laws, rollback: serverAppConfigs-docs/LLM/frank-zealot.md, and
+        # scripts/frank-zealot.env is the authority for every number there.
+        # contextWindow is the PER-SLOT window: llama.cpp divides --ctx-size
+        # across slots and answers a longer prompt with a 400, never a
+        # truncation, so this value must follow every reslice (live now:
+        # 2 x 262,144 over exact f16 KV, 68afc6d).
         contextWindow: 262144
         # Prompt + budget must fit inside the slot window; thinking counts
         # against the budget. Compaction fires at 85 % of the window =
@@ -269,14 +218,19 @@ providers:
   # when explicitly set, and sampleRate/bitRate are REJECTED outright (the
   # transport throws "openai-speech does not support sampleRate"), so the
   # codec comes from the output_path suffix and the only tunable that matters
-  # is the voice name — which must be a real pack name (narrator1/2/3); an
-  # unknown name is an engine error, not a fallback.
-  # DELIBERATELY NOT WIRED YET: config.yml `modelRoles.speech` still points at
-  # local/kokoro. Flip it to "frank-tts (dankclaw)/frank-tts" only after the
-  # service is deployed and has answered a real synthesis, because `auth: none`
-  # makes the provider read as AVAILABLE even while the container is down — the
-  # role would then fail instead of falling back to Kokoro. The same flip must
-  # re-key `speech.voice` (now am_fenrir, a Kokoro voice) to a pack name.
+  # is the voice name — and it comes from ONE place: the tool's `voice_id`
+  # argument. No setting feeds it (`speech.voice` is the speak-aloud Kokoro enum,
+  # `tts.localVoice` is the local backend's), so a call that omits voice_id arrives
+  # at 7772 with no `voice` key and the endpoint answers 400 "unknown voice None;
+  # available voices: narrator1, narrator2, narrator3". Say the voice in the call.
+  # WIRED 2026-10-18: `config.yml` `modelRoles.speech` is this row, flipped only
+  # after the service was deployed and answered real synthesis (two packs,
+  # different bytes, 24 kHz PCM16, RTF 0.57). Why the gate existed: `auth: none`
+  # makes this provider read as AVAILABLE even while the container is down, and an
+  # explicit speech role has NO fallback candidate, so a dead 7772 fails the device
+  # loudly instead of quietly narrating in Kokoro. Reverting is ONE key:
+  # `modelRoles.speech: local/kokoro`. `speech.voice` stays a Kokoro name either
+  # way — it was never this endpoint's voice.
   # SCHEMA LAW, learned the hard way (2026-10-18): provider-level `api` must be
   # a CHAT transport — the models.yml schema accepts only the chat/judge APIs
   # there, and naming a runner API (`openai-speech`) at provider level fails the

agent/skills/grilling/SKILL.md

@@ -3,30 +3,44 @@ name: grilling
 description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
 ---
 
-> **Authored override.** Extracted 2026-10-18 from `mattpocock/skills` (identical to upstream at extraction) into the command-center repo so Frank can customize it. Removed from the `skills` CLI global store (`~/.agents/.skill-lock.json` pruned) so `skills update -g` never resurrects a duplicate. Edits to this file are repo prose: branch → PR → Frank OK.
+# Grilling
 
-Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
+Interview the user relentlessly until nothing is silently assumed and you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
 
-Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
+A decision is **frontier** when it can be asked now, without an answer you haven't heard yet. The interview is done when the frontier is empty: every branch of the tree visited.
 
-Format a round like so:
+## Rounds
 
-```
-❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
+Work the tree in **rounds**: ask the whole frontier at once, then wait. A decision whose answer hangs on an open question or an unfetched fact joins a later round.
 
-➡️ <your recommended answer>
+Ask each closed decision - anything expressible as 2–5 options - through the `ask` tool:
 
----
+- **One artefact per question**, counted before sending. Name the artefact each question decides; two names means two questions. Shared plumbing (an endpoint, a service, a build step) still leaves two artefacts.
+- Recommended answer first, marked `recommended: 0`, which labels it "(Recommended)" for one-glance acceptance. Every reply names what was picked, so the record is unambiguous.
+- Options quote the user's goal. Their words, their stated goal, ground the wording; your todo text and table rows stay out of it.
+- Your own idea is welcome: it gets its own recommended question. Attach it to its own question, so it rides there on its merits.
+- `multi: true` for pick-many, `header` for the branch chip, `preview` when the decision needs code or config in front of the user.
 
-❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
+Open narrative - "walk me through the deploy flow" - has no options to offer; ask it as prose in chat. Without an `ask` tool the whole round degrades to text: `❓ **Q1 — title**: body`, then `➡️ recommendation`, phrased so one bare "yes" accepts every recommendation.
 
-➡️ <your recommended answer>
-```
+The dialog is exclusive: dispatch scouts before the `ask` call in the same message, or they wait behind it; their results land between rounds. Esc ends the run outright, with no turn to wrap up, so the ledger is what survives it.
 
-Word each question so "yes" accepts your recommended answer.
+## The ledger
 
-Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.
+The tree lives in the `todo` list while the interview runs, so the user watches it fall:
 
-Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait.
+- One task per decision, filed under the phase for its branch; `via: <parent decision>` in the task text carries the edge.
+- `pending` is the frontier; `block` with a one-line reason waits on a fact or an open decision; `done` is settled. Unblock the moment the dependency settles.
 
-The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
+Write `local://grilling-state.md` at the end of every round: the tree, each decision's verdict and one-line rationale. It is the durable copy of the interview; keep it current so an Esc costs one round.
+
+## Facts are yours, decisions are theirs
+
+- Environment facts (filesystem, repo, live config): dispatch a **scout** per fact-cluster, batched into one `task` call, before the round's `ask`. Cluster tightly; doing so keeps each scout more aware of possible adjacencies.
+- Outside-world facts: call `web_search` directly, do not delegate to a subagent.
+- Cheap lookups: `read`/`grep` inline.
+- The main session is where questions happen: every spawn carries the exact facts to return, and comes back into the next round.
+
+## Definition of Done
+
+The frontier is empty and nothing sits blocked. Distil the ledger into a **brief**: one line per decision, verdict plus rationale, grouped by branch. Put it in chat, then one closing `ask`: "Proceed on this brief?" Nothing executes before that yes. After it, fold the brief into the project's knowledge base, or a log markdown file, wherever the project keeps its decisions.

dotfiles/noctalia/.local/state/noctalia/settings.toml

@@ -275,13 +275,13 @@ transition = [ "fade" ]
     interval_seconds = 1200
 
     [wallpaper.default]
-    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_73qev3.jpg"
+    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_nzz3gy.jpg"
 
     [wallpaper.last]
-    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_73qev3.jpg"
+    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_nzz3gy.jpg"
 
     [wallpaper.monitors.DP-1]
-    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_73qev3.jpg"
+    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_nzz3gy.jpg"
 
     [wallpaper.monitors.DP-2]
     path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_oxex69.jpg"
@@ -290,7 +290,7 @@ transition = [ "fade" ]
     path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_v9e2w3.jpg"
 
     [wallpaper.monitors.eDP-1]
-    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_73qev3.jpg"
+    path = "/home/blank/.local/share/noctalia/wallpapers/wallhaven_nzz3gy.jpg"
 
 [weather]
 unit = "imperial"

omp-docs/core/dankvoice.md

@@ -0,0 +1,192 @@
+---
+type: reference
+title: dankvoice
+description: omp extension that speaks assistant output with the fleet's cloned voices through frank-tts.
+tags:
+  - omp
+  - extension
+  - tts
+  - voice
+  - frank-tts
+  - dankclaw
+verified: 2026-10-19
+timestamp: 2026-10-19
+---
+
+# dankvoice
+
+`agent/extensions/dankvoice.ts` adds cloned-voice speech to the interactive
+harness: `/say` opens the options menu, `/say <text>` speaks through the
+speakers and `/say on` narrates the assistant's final answer after every
+turn, all served by **frank-tts** (Dankclaw :7772, the `speech` model role
+in [agent/models.yml](/core/index.md)).
+
+## Why it exists
+
+Nothing built into the harness can pronounce Frank's cloned voices.
+
+| Surface | Engine | Verdict |
+|---|---|---|
+| TUI speak-aloud (`speech.enabled`, `speech.voice`) | bundled Kokoro ONNX worker, `synthesizeStream(voice, speed, signal)` | Kokoro voice enum only; never consults `models.yml` or the speech role |
+| `omp say [TEXT]` | same local backend (`--model` = *local* model key) | `omp say --voice narrator1 "test"` → `error: Expected --voice to be one of: af_heart, af_bella, af_nicole, af_kore, af_sarah, am_michael, am_fenrir, am_puck, bf_emma, bm_george, bm_fable` (verified 2026-10-18) |
+| `tts` tool / `xd://tts` device (`modelRoles.speech`) | frank-tts over OpenAI `/v1/audio/speech` | cloned voices work, but only as a **file** — nothing plays them |
+
+`dankvoice` is not a patch to that vocalizer (harness code, not ours); it is a
+second transport that happens to speak, so Kokoro stays available for quick
+local speech and the cloned voices carry the real narration.
+
+## Commands
+
+| Command | Effect |
+|---|---|
+| `/say` \| `/say menu` | options menu (`ctx.ui.select`): auto-speak toggle, voice, output device, player, spoken cap, test phrase |
+| `/say <text>` | synthesize once and play; interrupts whatever is playing |
+| `/say on` \| `/say off` | arm/disarm auto-speak of the assistant's final text at `agent_end`; the footer shows `🔊 <voice>` while armed |
+| `/say voice <name>` | pick a voice; an empty name defers to the server's own default |
+| `/say voices` | list what frank-tts reports |
+| `/say stop` | cut the current utterance |
+| `/say status` \| `/say help` | endpoint, voice, player, device, cap |
+
+Menu choices persist to `~/.omp/cache/dankvoice.json` (runtime state, never
+tracked); the environment overrides the file, the file overrides defaults.
+"Speak a test phrase" synthesizes a short line through the current voice,
+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. A long answer is never one monolithic synthesis request; see
+[Segmentation](#segmentation) for how utterances are cut and played.
+
+## 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
+
+The base URL is **read from `agent/models.yml`**, from the provider block whose
+model row carries `api: openai-speech` — the same row the `speech` role
+resolves, so no host address and no credential appears in this file. From
+`baseUrl: http://192.168.0.143:7772/v1` it derives
+`POST …/v1/audio/speech`, `GET …/v1/audio/voices` and `GET …/health`.
+
+| Environment | Default | Meaning |
+|---|---|---|
+| `DANKVOICE_URL` | models.yml | speech base URL (`…/v1`), bypasses the YAML read |
+| `DANKVOICE_MODEL` | the id in that block (`frank-tts`) | model named in the request body |
+| `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 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 |
+
+Player detection order is `pw-play` → `paplay` → `ffplay` (PipeWire first:
+the workstations run WirePlumber). A saved output device routes the player
+explicitly — `pw-play --target <sink>` or `paplay --device=<sink>`; ffplay
+has no device concept and ignores it — while an unset device leaves the
+player's own default. Sinks are enumerated with `wpctl list audio sinks`;
+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, 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
+  fresh `omp -p` run. `omp --help` documents `--no-extensions` (discovery off,
+  explicit `-e/--extension` and `--hook` still load) and `plugin install|link`.
+* **Endpoint** — resolving the live `agent/models.yml` yields
+  `speechUrl http://192.168.0.143:7772/v1/audio/speech`,
+  `voicesUrl …/v1/audio/voices`, `healthUrl …/health`, `model frank-tts`.
+* **Roster** — `GET /v1/audio/voices` answers the bare JSON array
+  `["narrator1","narrator2","narrator3"]`; `/health` answers
+  `{"status":"ok","backend":"omni-http","voices":[…]}`. `GET /v1/voices` and
+  `GET /v1/models` are **404** on this shim, and an unknown voice answers
+  `400 unknown voice 'zzz'; available voices: …` with `available_voices` in the
+  body — which is the fallback the extension uses if the roster route ever
+  disappears.
+* **Omitting `voice` is legal** — frank-tts fills its `DEFAULT_VOICE` since the
+  2026-10-18 voice-pack work, so an unset voice synthesizes instead of failing.
+* **Speech** — `/say "dankvoice live smoke test"` produced a 99,884 B / 2.08 s
+  WAV and `/say voice narrator2` + `/say "cloned voice check"` a 69,164 B /
+  1.44 s WAV (durations from `ffprobe`), each handed to the player; temp
+  directories were gone afterwards.
+* **Auto-speak** — verified in a real TUI session: `/say on` armed the footer
+  (`🔊 narrator1`), the next finished turn synthesized and played the answer
+  (1.20 s WAV), and an unknown voice name answers with the roster instead of
+  speaking. An `agent_end` carrying `willContinue` (the harness scheduled an
+  auto-retry) is never narrated — only the terminal settle speaks.
+* **Menu** — verified via driver scenarios 2026-10-18 (Refs #23): the menu
+  lists auto-speak/voice/device/player/cap/test-phrase; a voice chosen in the
+  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
+
+* The TUI's own speak-aloud feature still narrates in Kokoro: its voice list is
+  a compile-time enum in the harness bundle, and no setting routes it to
+  frank-tts. Cloned voices live only on this file-producing/speaking path and
+  on the `tts` tool. See [Handy](/tools/handy.md) for the STT half.
+* `agent_end` narrates the final message text only — mid-turn tool chatter is
+  never spoken.
+* frank-tts is LAN-only: no Caddy vhost fronts :7772, so this extension is
+  usable on the home network.
+* Deployment, packs and the voice registry are owned by the
+  `serverAppConfigs` repo (`serverAppConfigs-docs/Dankclaw/Frank TTS.md`), not
+  by this one.
+
+## Citations
+
+* Live probes on the workstation, 2026-10-18: `omp say --voice narrator1 …`,
+  `curl http://192.168.0.143:7772/health`, `/v1/audio/voices`,
+  `/v1/audio/…/speech` (invalid voice), `ffprobe` on the produced WAVs.
+* `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).
+
+## See Also
+
+* [Core Documentation](/core/index.md) — the live harness configuration.
+* [Handy](/tools/handy.md) — offline speech-to-text, the input half of voice.
+* `serverAppConfigs-docs/Dankclaw/Frank TTS.md` — the frank-tts service runbook.

omp-docs/core/index.md

@@ -13,6 +13,7 @@ These files define the structural conventions that govern the agent system itsel
 * [AGENTS.md Format Specification](agents-md-format.md) — Canonical structure and conventions for the system-level instruction file that governs agent behavior.
 * [AGENTS.md Index](index-doc.md) — Overview of the cached tool documentation system and how to add new entries.
 * [Pi Settings System](settings.md) — pi-era `settings.json` record (archive): providers, models, packages, subagent overrides.
+* [dankvoice](dankvoice.md) — Cloned-voice vocalization extension: `/say` and auto-speak over frank-tts, endpoint read from `agent/models.yml`.
 
 ## Change Tracking
 

omp-docs/log.md

@@ -11,6 +11,48 @@ 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
+pi-peon-style settings surface: auto-speak toggle, voice picked from the frank-tts
+roster, **output device** (PipeWire sinks via `wpctl` → `pw-play --target` /
+`paplay --device=`), player binary, spoken-char cap, and a "speak a test phrase"
+utterance that proves the audio path audibly. Choices persist to
+`~/.omp/cache/dankvoice.json` (`DANKVOICE_CONFIG`); env now wins over that file,
+which wins over defaults — answering the silent-session incident where
+PipeWire's remembered Bluetooth route played synthesized answers into nowhere.
+`detectPlayer` becomes `availablePlayers` + `playerFor`. Tests gain a fixture
+`wpctl`, a scripted `select` in the driver, and three menu scenarios: 15 green
+in `tests/dankvoice.bats`, 51 green suite-wide.
+
+## 2026-10-18 — dankvoice: the cloned voices finally speak in the TUI (Refs #21)
+
+Nothing in the harness could pronounce them: the TUI vocalizer and `omp say` gate `--voice` against the bundled Kokoro enum (`omp say --voice narrator1 "test"` → `error: Expected --voice to be one of: af_heart, …`), so frank-tts was reachable only as a file. Added `agent/extensions/dankvoice.ts` — `/say <text>`, `/say on|off` (narrate the final answer at `agent_end`), `/say voice|voices|stop|status` — synthesizing over the OpenAI speech route and playing through `pw-play`/`paplay`/`ffplay`, with the endpoint read from the `api: openai-speech` row of `agent/models.yml` (no host, no secret in the file). Verified live in a real TUI session on the workstation: roster `GET /v1/audio/voices` → `narrator1, narrator2, narrator3`; `/say` produced 99,884 B / 2.08 s and 69,164 B / 1.44 s WAVs handed to the player, temp dirs cleaned afterwards; `/say on` armed the footer (`🔊 narrator1`) and each following finished turn spoke its answer (1.20 s WAV), an unknown voice name answered with the roster instead of speaking, and an `agent_end` carrying `willContinue` (the harness scheduled an auto-retry) is deliberately never narrated. Extension discovery itself proved with a probe file in `~/.omp/agent/extensions/` loaded by a fresh `omp -p` run. Reference page [dankvoice](core/dankvoice.md), registered in the core index; black-box seam `tests/dankvoice.bats` (12 tests).
+
 ## 2026-10-18 — Noctalia bar layout clobbered by trunk-sync stash, recovered from dangling objects
 
 Frank's months of GUI-built bar customizations (cat/clock/clock-utc/weather start, taskbar center, capsule groups g1–g4, control-cheat-sheet, thickness/font-scale/opacity styling) vanished from the live bar at 16:46. Root cause: the layout existed **only in the working tree** — the repo copy of `settings.toml` carried a stale plain layout because GUI edits hadn't been committed inside the hourly heartbeat window — and a trunk-sync session clearing the dirty tree for `origin/main` stashed it; the stash entry was subsequently destroyed (three `WIP on main` stashes within 60 s, all later dropped). Recovery: `git fsck --lost-found` surfaced the destroyed stash as dangling commit `7fe3ed8` (16:46:09); candidate validated in a sandboxed `XDG_*_HOME` before restore, clobbered file preserved to `.AGENTTRASH/`, layout restored through the symlink target and proven by screenshot, committed as `c87b378` — the durable copy the layout never had. Lessons codified into managed skills: trunk-sync must preservation-**commit** every dirty deployment path (never stash, never `stash clear`), and GUI layout edits get committed the same session they're made.

omp-docs/pi/index.md

@@ -28,7 +28,8 @@
 
 ## Subagent Architecture
 
-- [Pi Subagents](/pi/packages/pi-subagents.md) — Core subagent delegation system. Chains, parallel execution, TUI clarification.
+- [OMP Subagent Limits & Fan-out Policy](/pi/subagent-limits.md) — Live caps: concurrency 2, no nested spawns (and the `maxRecursionDepth: 0` trap), per-endpoint in-flight ceilings, isolation policy.
+- [Pi Subagents](/pi/packages/pi-subagents.md) — (historical) pi-era delegation system. Chains, parallel execution, TUI clarification.
 
 ## Architecture
 

omp-docs/pi/subagent-limits.md

@@ -0,0 +1,97 @@
+---
+type: reference
+title: OMP Subagent Limits & Fan-out Policy
+description: The live caps on omp subagents — concurrency 2, no nested spawns, per-endpoint in-flight ceilings, 30-min runtime, soft request budget, and the isolated-workspace policy; includes the maxRecursionDepth=0 trap.
+tags:
+  - omp
+  - subagents
+  - config
+  - fleet
+timestamp: 2026-10-19
+---
+
+# OMP Subagent Limits & Fan-out Policy
+
+Enforced caps on subagents spawned through the `task` tool / eval `agent()`+`workpool()`
+from this workstation (config root `agent/config.yml`, machine-live tier — the live-sync
+heartbeat commits it). Set 2026-10-19; values verified against the live config and the
+enforcement code in the installed bundle (`@oh-my-pi/pi-coding-agent/dist/cli.js`).
+
+## The caps in force
+
+| Key | Value | Default | Effect |
+|---|---|---|---|
+| `task.maxConcurrency` | 2 | 32 | Session-scoped semaphore; excess spawns queue, never drop. |
+| `task.maxRecursionDepth` | 1 | 2 | Subagents cannot spawn their own subagents. See depth semantics. |
+| `task.maxRuntimeMs` | 1800000 | 0 (off) | Hard 30-min wall clock per subagent; overrun = `aborted`. |
+| `task.softRequestBudget` | 120 | 200 | Wrap-up notice at 120 assistant requests; force-stopped to yield at 180 (1.5×). |
+| `task.agentIdleTtlMs` | 420000 | same | Finished subagents parked to disk after 7 min idle (revivable via `agent://`). |
+| `task.enableEffort` | false | false | Per-spawn `effort` hint hidden from the schema. |
+| `task.isolation.enabled` | true | false | `isolated: true` spawns run in a copy of the checkout; only successful patches land (merge=patch, apply). Opt-in per spawn. |
+| `task.completionProbe` | false | true | No periodic completeness side-requests into running subagents. |
+| `tools.maxTimeout` | 600 | 0 (off) | No agent may request a tool timeout above 10 min; kills `timeout: 0` runaways. |
+| `providers.maxInFlightRequests` | see below | {} (unlimited) | Per-provider ceiling on concurrent LLM requests, shared across local omp processes. |
+
+## Depth semantics — never set `maxRecursionDepth: 0`
+
+Bundle predicate (`U_`): a session at `taskDepth` *s* keeps the `task` tool iff
+`n < 0 || s < n` where `n = maxRecursionDepth`. The preflight repeats the check
+(`Cannot spawn another agent at task depth s; maximum depth is n`).
+
+- `n = 1` → main (depth 0) spawns; children (depth 1) have `task` stripped. **This is
+  "no nested subagents".**
+- `n = 0` → `0 < 0` fails → **not even the main session can spawn anything.** Don't.
+- `n < 0` → cap disabled.
+
+## Per-endpoint in-flight ceilings
+
+```yaml
+providers:
+  maxInFlightRequests:
+    "llamacpp (dankserver)": 3      # main session + up to 2 task/reviewer subagents
+    "llamacpp (dankclaw)": 2        # frank-dragoon: security-reviewer + fallbacks
+    "llamacpp (dankclaw-3090)": 3   # frank-zealot: scout/sonic/librarian/designer + smol/tiny/plan/commit/vision roles
+```
+
+- Keys are **provider ids** = the quoted block labels in `agent/models.yml`
+  (one provider per host:port). The consumer does a flat map lookup by provider id;
+  absent or ≤0 = unlimited, otherwise clamped to ≥1.
+- Scope is **per machine, per config root**: it bounds what *this workstation's* omp
+  processes put on each endpoint. Other workstations, OpenWebUI, and any non-omp
+  client are not counted. Requests past the ceiling queue, never fail.
+- `web/searxng` intentionally uncapped.
+
+## Isolation note
+
+`task.isolation.enabled: true` makes the per-spawn `isolated` flag available — it is
+**opt-in per spawn**, not a blanket sandbox. Requires a git repo; unavailable in plan
+mode; baseline snapshot capped at 1 GiB; backends resolve via `isolation.backend: auto`
+(overlayfs/reflink/rcopy chain on this box). Given *the checkout is the deployment*,
+prefer `isolated: true` for any subagent that edits tracked files.
+
+## Deliberately not set
+
+- `bash.gitGuard` — offered 2026-10-19, declined; destructive-git protection stays opt-in.
+- `task.disabledAgents` — no bundled agent type warrants a ban.
+- `task.agentAccountPools`, `tier.subagent` — no-op against keyless local endpoints.
+- `PI_TASK_MAX_OUTPUT_BYTES` / `PI_TASK_MAX_OUTPUT_LINES` — 500 KB / 5000 line defaults are sane.
+- `before_subagent_spawn` hook — programmable spawn policy; revisit if these caps prove insufficient.
+
+## Verification
+
+`cfg://task`, `cfg://providers/maxInFlightRequests` reflect all rows above; persisted
+copies in `agent/config.yml`. Depth semantics confirmed against the shipped bundle, not
+just the setting description.
+
+# Citations
+
+- `agent/config.yml` (live config, this repo)
+- `agent/models.yml` — provider id block labels
+- `@oh-my-pi/pi-coding-agent/dist/cli.js` — `U_` depth predicate, in-flight map lookup
+- omp docs: `omp://tools/task.md` § Limits & Caps
+
+# See Also
+
+- [/pi/statusline.md](/pi/statusline.md) — the omp-era bundle-audit page pattern this page follows
+- [/pi/packages/pi-subagents.md](/pi/packages/pi-subagents.md) — retired pi-era subagent system (historical)
+- [/system/index.md](/system/index.md) — fleet endpoints these ceilings target

tests/dankvoice.bats

@@ -0,0 +1,354 @@
+#!/usr/bin/env bats
+# tests/dankvoice.bats — black-box tests for agent/extensions/dankvoice.ts
+#
+# The extension's contract, from outside: it registers a `say` command and an
+# `agent_end` listener; what is observable is (a) the JSON it POSTs to the
+# speech route, (b) the file it hands to the player, and (c) the notifications
+# and select-lists it renders. A fixture HTTP server stands in for frank-tts
+# (it answers the speech route with a fixed WAV, the roster route with a JSON
+# array, and everything else with 404), a stub player stands in for pw-play
+# (it records its full argv and copies the .wav it was given), and a fixture
+# `wpctl` in $WORK/bin stands in for wireplumber's sink enumeration.
+#
+# Driven by env: DV_EXT (extension under test), DV_STUB / DV_STUB_LOG / DV_COPY
+# (player fixture), DV_PWPLAY (stub aliased as pw-play), DV_WPCTL (the sink
+# name the fixture wpctl reports), DV_MODELS (models.yml fixture),
+# DANKVOICE_CONFIG (settings file), DV_PLAYER_BIN (player command override),
+# DV_SELECT (pipe-separated answers fed to ctx.ui.select in order), DV_MODE
+# (the harness mode reported to the extension).
+
+setup() {
+  REPO="$(cd "$BATS_TEST_DIRNAME/.." && pwd)"
+  WORK="$(mktemp -d)"
+
+  export DV_EXT="$REPO/agent/extensions/dankvoice.ts"
+  export DV_STUB="$WORK/player.sh"
+  export DV_STUB_LOG="$WORK/player.log"
+  export DV_COPY="$WORK/played.wav"
+  export DV_EMPTY_BIN="$WORK/emptybin"
+  mkdir -p "$DV_EMPTY_BIN"
+
+  cat > "$DV_STUB" <<'SH'
+#!/usr/bin/env bash
+printf '%s\n' "$*" >> "$DV_STUB_LOG"
+for arg in "$@"; do case "$arg" in *.wav) cp "$arg" "$DV_COPY" ;; esac; done
+sleep 0.1
+SH
+  chmod +x "$DV_STUB"
+
+  # the same stub reachable under the canonical player names, plus a fixture
+  # wpctl so output-device enumeration is deterministic on any machine
+  mkdir -p "$WORK/bin"
+  ln -s "$DV_STUB" "$WORK/bin/pw-play"
+  export DV_PWPLAY="$WORK/bin/pw-play"
+  export DV_WPCTL="alsa_output.usb-KT.0"
+  cat > "$WORK/bin/wpctl" <<'WPC'
+#!/usr/bin/env bash
+printf '57\talsa_output.pci-0000_07_00.6.HiFi__Speaker__sink\taudio/sink\t\n116\t%s\taudio/sink\t*\n' "$DV_WPCTL"
+WPC
+  chmod +x "$WORK/bin/wpctl"
+
+  # settings live in an isolated file so menu choices never leak between tests
+  export DANKVOICE_CONFIG="$WORK/settings.json"
+
+  # models.yml fixture: a chat provider first, the speech provider second
+  export DV_MODELS="$WORK/models.yml"
+  cat > "$DV_MODELS" <<'YML'
+providers:
+  "chat (box)":
+    baseUrl: http://10.0.0.1:9999/v1
+    models:
+      - id: chatmodel
+        api: openai-completions
+  "speech (box)":
+    baseUrl: http://127.0.0.1:1/v1
+    auth: none
+    models:
+      - id: speechmodel
+        api: openai-speech
+YML
+
+  cat > "$WORK/driver.ts" <<'TS'
+// Black-box driver: stand up the frank-tts fixture, load the extension against
+// it, invoke one scenario, print what the endpoint received and what got played.
+import { createServer } from "node:http";
+import { existsSync, readFileSync, statSync } from "node:fs";
+import { dirname } from "node:path";
+
+const scenario = process.argv[2] ?? "speak";
+const AUDIO = Buffer.from([0x52, 0x49, 0x46, 0x46, 8, 0, 0, 0, 0x57, 0x41, 0x56, 0x45, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]);
+const received: Array<{ url: string | undefined; body: string }> = [];
+
+const server = createServer((req, res) => {
+  const chunks: Buffer[] = [];
+  req.on("data", (chunk: Buffer) => chunks.push(chunk));
+  req.on("end", () => {
+    const body = Buffer.concat(chunks).toString("utf8");
+    received.push({ url: req.url, body });
+    if (req.url?.endsWith("/audio/voices")) {
+      res.setHeader("content-type", "application/json");
+      res.end(JSON.stringify(["narrator1", "narrator2"]));
+      return;
+    }
+    if (req.url?.endsWith("/audio/speech")) {
+      res.setHeader("content-type", "audio/wav");
+      res.end(AUDIO);
+      return;
+    }
+    res.statusCode = 404;
+    res.end("{}");
+  });
+});
+await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
+const port = (server.address() as { port: number }).port;
+
+if (scenario === "endpoint") {
+  process.env.DANKVOICE_MODELS = process.env.DV_MODELS;
+} else {
+  process.env.DANKVOICE_URL = `http://127.0.0.1:${port}/v1`;
+}
+if (scenario === "noplayer") process.env.PATH = process.env.DV_EMPTY_BIN ?? "/nonexistent-bin";
+else process.env.PATH = `${dirname(process.env.DV_STUB ?? ".")}/bin:${process.env.PATH ?? ""}`;
+process.env.DANKVOICE_PLAYER = scenario === "noplayer" ? "" : process.env.DV_PLAYER_BIN ?? process.env.DV_STUB;
+
+const extension = await import(process.env.DV_EXT as string);
+const commands = new Map<string, { handler: (args: string, ctx: unknown) => Promise<void> }>();
+const events = new Map<string, (event: unknown, ctx: unknown) => Promise<void> | void>();
+extension.default({
+  registerCommand: (name: string, options: { handler: (args: string, ctx: unknown) => Promise<void> }) => commands.set(name, options),
+  on: (event: string, handler: (event: unknown, ctx: unknown) => Promise<void> | void) => events.set(event, handler),
+});
+const answers = (process.env.DV_SELECT ?? "").split("|").filter((answer) => answer !== "");
+let answerIndex = 0;
+const ctx = {
+  mode: process.env.DV_MODE ?? "tui",
+  ui: {
+    notify: (message: string, level?: string) => console.log(`NOTIFY ${level ?? "info"} ${message}`),
+    setStatus: (key: string, text?: string) => console.log(`STATUS ${key} ${text ?? ""}`),
+    select: (title: string, options: string[]) => {
+      console.log(`SELECT ${title} ${options.join("|")}`);
+      const answer = answerIndex < answers.length ? answers[answerIndex] : undefined;
+      answerIndex += 1;
+      return Promise.resolve(answer ?? options[0]);
+    },
+  },
+};
+const say = commands.get("say");
+const agentEnd = events.get("agent_end");
+const answer = (text: string) => ({ messages: [{ role: "assistant", content: [{ type: "text", text }] }] });
+const settle = () => new Promise((resolve) => setTimeout(resolve, 800));
+
+if (!say) {
+  console.log("COMMANDS none");
+} else {
+  console.log(`COMMANDS ${[...commands.keys()].join(",")} EVENTS ${[...events.keys()].join(",")}`);
+  switch (scenario) {
+    case "speak":
+      await say.handler("hello world", ctx);
+      break;
+    case "voice":
+      await say.handler("voice narrator2", ctx);
+      await say.handler("good morning", ctx);
+      break;
+    case "menu":
+      await say.handler("menu", ctx);
+      break;
+    case "empty":
+      await say.handler("", ctx);
+      break;
+    case "devicemenu":
+      await say.handler("menu", ctx);
+      await say.handler("hello world", ctx);
+      break;
+    case "auto":
+      await say.handler("on", ctx);
+      await agentEnd?.(answer("the answer"), ctx);
+      await settle();
+      await say.handler("off", ctx);
+      await agentEnd?.(answer("the second answer"), ctx);
+      break;
+    case "continuation":
+      await say.handler("on", ctx);
+      await agentEnd?.({ ...answer("not yet"), willContinue: true }, ctx);
+      await settle();
+      await agentEnd?.(answer("the settled answer"), ctx);
+      break;
+    case "printmode":
+      await say.handler("on", ctx);
+      await agentEnd?.(answer("quiet"), ctx);
+      break;
+    case "voices":
+      await say.handler("voices", ctx);
+      break;
+    case "endpoint":
+      await say.handler("status", ctx);
+      break;
+    case "markdown":
+      await say.handler("## Title\n\nUse `pw-play` here.\n\n```bash\nnpm i x\n```\n\nsee [docs](http://example.test) and **bold**\n- a\n- b", ctx);
+      break;
+    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;
+  }
+  await settle();
+}
+
+for (const call of received) {
+  const parsed: unknown = JSON.parse(call.body === "" ? "{}" : call.body);
+  const field = (key: string): string => {
+    if (parsed && typeof parsed === "object" && key in parsed) {
+      const value = parsed[key];
+      if (typeof value === "string") return value;
+    }
+    return "-";
+  };
+  console.log(`CALL ${call.url} model=${field("model")} format=${field("response_format")} voice=${field("voice")} input=${field("input")}`);
+}
+console.log(`CALLS ${received.length}`);
+const log = process.env.DV_STUB_LOG && existsSync(process.env.DV_STUB_LOG) ? readFileSync(process.env.DV_STUB_LOG, "utf8").trim() : "";
+console.log(`PLAYS ${log === "" ? 0 : log.split("\n").length}`);
+if (log !== "") for (const line of log.split("\n")) console.log(`PLAYER ${line}`);
+if (process.env.DV_COPY && existsSync(process.env.DV_COPY)) console.log(`COPIED ${statSync(process.env.DV_COPY).size}`);
+server.close();
+TS
+
+  export DV_DRIVER="$WORK/driver.ts"
+}
+
+teardown() {
+  rm -rf "$WORK"
+}
+
+say_run() {
+  run env DV_SELECT="${2:-}" bun "$DV_DRIVER" "$1"
+}
+
+@test "the extension registers the say command and an agent_end listener" {
+  say_run speak
+  [ "$status" -eq 0 ]
+  [[ "$output" == *"COMMANDS say EVENTS agent_end"* ]]
+}
+
+@test "speaking posts the text to the speech route" {
+  say_run speak
+  [ "$status" -eq 0 ]
+  [[ "$output" == *"CALL /v1/audio/speech model=frank-tts format=wav voice=- input=hello world"* ]]
+}
+
+@test "one utterance is played once, as exactly the bytes the endpoint sent" {
+  say_run speak
+  [[ "$output" == *"PLAYS 1"* ]]
+  [[ "$output" == *"COPIED 24"* ]]
+}
+
+@test "the voice is named in the request only when the user chose one" {
+  say_run speak
+  [[ "$output" == *"voice=- input=hello world"* ]]
+  say_run voice
+  [[ "$output" == *"voice=narrator2 input=good morning"* ]]
+  [[ "$output" == *"NOTIFY info dankvoice: voice = narrator2"* ]]
+}
+
+@test "auto-speak narrates the final answer once and stays silent after it is disarmed" {
+  say_run auto
+  [[ "$output" == *"PLAYS 1"* ]]
+  [[ "$output" == *"input=the answer"* ]]
+  [[ "$output" != *"the second answer"* ]]
+  [[ "$output" == *"STATUS dankvoice 🔊"* ]]
+}
+
+@test "auto-speak stays silent outside the interactive modes" {
+  DV_MODE=print say_run printmode
+  [[ "$output" == *"PLAYS 0"* ]]
+  [[ "$output" != *"input=quiet"* ]]
+}
+
+@test "the voice list comes from the endpoint roster route" {
+  say_run voices
+  [[ "$output" == *"CALL /v1/audio/voices"* ]]
+  [[ "$output" == *"dankvoice voices: narrator1, narrator2"* ]]
+}
+
+@test "the endpoint is taken from the speech row of the models file, never the chat provider" {
+  say_run endpoint
+  [[ "$output" == *"http://127.0.0.1:1/v1/audio/speech"* ]]
+  [[ "$output" != *"10.0.0.1"* ]]
+}
+
+@test "markdown never reaches the speech engine" {
+  say_run markdown
+  [[ "$output" == *"input=Title"* ]]
+  [[ "$output" == *"input=Use pw-play here."* ]]
+  [[ "$output" == *"input=see docs and bold"* ]]
+  [[ "$output" != *"npm i x"* ]]
+  [[ "$output" != *"example.test"* ]]
+}
+
+@test "the spoken budget keeps only the leading whole segments" {
+  DANKVOICE_MAX=60 say_run truncate
+  [[ "$output" == *"CALLS 1"* ]]
+  [[ "$output" == *"PLAYS 1"* ]]
+  [[ "$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" {
+  say_run noplayer
+  [[ "$output" == *"NOTIFY error dankvoice: no audio player found"* ]]
+  [[ "$output" == *"PLAYS 0"* ]]
+}
+
+@test "a scheduled continuation is never narrated as the final answer" {
+ say_run continuation
+ [[ "$output" == *"PLAYS 1"* ]]
+ [[ "$output" == *"input=the settled answer"* ]]
+ [[ "$output" != *"input=not yet"* ]]
+}
+
+@test "the menu lists every knob and a plain /say opens it" {
+  say_run menu
+  [[ "$output" == *"SELECT dankvoice — options Auto-speak: off (toggle)|Voice: server default (change)|Output device: system default (change)|Player: $DV_STUB (change)|Spoken cap: 700 chars (change)|Speak a test phrase"* ]]
+  [[ "$output" == *"NOTIFY info dankvoice: auto-speak armed (server default @ http://127.0.0.1:"* ]]
+  say_run empty
+  [[ "$output" == *"SELECT dankvoice — options"* ]]
+}
+
+@test "a voice picked from the menu is spoken by every later request" {
+  say_run menu "Voice: server default (change)|narrator2"
+  [[ "$output" == *"SELECT dankvoice — voice server default|narrator1|narrator2"* ]]
+  [[ "$output" == *"NOTIFY info dankvoice: voice = narrator2"* ]]
+  say_run speak
+  [[ "$output" == *"voice=narrator2 input=hello world"* ]]
+}
+
+@test "a device chosen from the menu becomes the player's output target" {
+  DV_PLAYER_BIN="$DV_PWPLAY" say_run menu "Output device: system default (change)|$DV_WPCTL"
+  [[ "$output" == *"SELECT dankvoice — output device system default|alsa_output.pci-0000_07_00.6.HiFi__Speaker__sink|$DV_WPCTL"* ]]
+  [[ "$output" == *"NOTIFY info dankvoice: output device = $DV_WPCTL"* ]]
+  DV_PLAYER_BIN="$DV_PWPLAY" say_run speak
+  [[ "$output" == *"PLAYER --target $DV_WPCTL"* ]]
+}