@inetafrica/open-claudia 3.1.7 → 3.1.8

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## v3.1.8 — Hosted pods can actually send voice notes
+
+- **FFMPEG is discovered on PATH.** Provisioned pods ship `/usr/bin/ffmpeg` but never set `FFMPEG=` in config, and `config.js` read only the explicit setting — so `FFMPEG` resolved empty and every TTS route (`pocketToVoice`, ElevenLabs, `say`) silently returned null: voice input got text-only replies. `FFMPEG` now falls back to PATH discovery via the existing `executableCandidate` helper; an explicit `FFMPEG=` still wins.
+- **The system prompt's voice-notes flag reflects real TTS capability.** It gated on `WHISPER_CLI && FFMPEG` — the pre-gateway local-Whisper world — so whisper-less hosted pods told the model "Voice notes: disabled" and it refused user requests (the smart-euvy report), even with working gateway speech. New `media.canSpeak()` mirrors the actual pocket → ElevenLabs → macOS `say` fallback chain and now drives the flag; local Whisper is irrelevant to speaking.
+- **New `open-claudia say "<text>"` CLI verb.** `send-voice` needs a ready-made ogg and the model had no way to synthesize one on request. `say` runs `textToVoice` and sends the result through the loopback voice path (same egress guardrail), and is documented in the Delivery prompt block.
+- Regression coverage in `test-media-speech.js`: a whisper-less pod shape must report `canSpeak() === true`, the prompt gate must key on it, and FFMPEG resolution precedence (explicit > PATH discovery > empty) is asserted via subprocess config loads.
+
 ## v3.1.7 — CI spawn-race hardening (first published build of the v3.1.5 changes)
 
 - v3.1.6 also never published. The loaded shared CI runner (node cold-boot 100-370ms vs ~50ms locally) keeps picking off the next-tightest spawn-timing test: this time `test-utility-provider-policy`'s shutdown-drain case, which flat-slept 100ms then cancelled — killing the fake agent before it booted, so its SIGTERM handler never wrote the expected signal capture (pipeline 10383; the v3.1.6 run-lifecycle fix itself passed there).

package/bin/cli.js

@@ -277,6 +277,24 @@ switch (command) {
     break;
   }
 
+  case "say": {
+    const text = args.slice(1).join(" ").trim();
+    if (!text) {
+      console.error('Usage: open-claudia say "<text>"');
+      process.exit(2);
+    }
+    (async () => {
+      const { textToVoice } = require(path.join(botDir, "core", "media"));
+      const voicePath = await textToVoice(text);
+      if (!voicePath) {
+        console.error("No TTS route available — configure the speech gateway, ElevenLabs, or run on macOS.");
+        process.exit(1);
+      }
+      sendViaLoopback("send-voice", [voicePath]);
+    })();
+    break;
+  }
+
   case "tw":
   case "transcript-window": {
     require("./transcript-window").run(args.slice(1));
@@ -441,6 +459,7 @@ Send tools (only work inside an active bot-spawned task):
   open-claudia send-file <path> [caption]
   open-claudia send-photo <path> [caption]
   open-claudia send-voice <path>
+  open-claudia say "<text>"          Synthesize the text (TTS) and send it as a voice note
 
 Memory tools:
   open-claudia transcript-search <query>     Ranked FTS5 search over indexed transcripts

package/core/config.js

@@ -137,7 +137,9 @@ const TRANSCRIPT_MAX_ENTRY_CHARS = parseInt(config.TRANSCRIPT_MAX_ENTRY_CHARS ||
 const TRANSCRIPTS_DIR = config.TRANSCRIPTS_DIR || process.env.TRANSCRIPTS_DIR || path.join(CONFIG_DIR, "transcripts");
 const WHISPER_CLI = config.WHISPER_CLI || "";
 const WHISPER_MODEL = config.WHISPER_MODEL || "";
-const FFMPEG = config.FFMPEG || "";
+// Hosted pods ship /usr/bin/ffmpeg but never set FFMPEG=, so without PATH
+// discovery every TTS route silently no-ops (smart-euvy "voice notes disabled").
+const FFMPEG = config.FFMPEG || executableCandidate("ffmpeg") || "";
 const ELEVENLABS_API_KEY = config.ELEVENLABS_API_KEY || process.env.ELEVENLABS_API_KEY || "";
 const ELEVENLABS_VOICE_ID = config.ELEVENLABS_VOICE_ID || process.env.ELEVENLABS_VOICE_ID || "EXAVITQu4vr4xnSDxMaL";
 const ELEVENLABS_MODEL = config.ELEVENLABS_MODEL || process.env.ELEVENLABS_MODEL || "eleven_v3";

package/core/media.js

@@ -129,6 +129,15 @@ async function pocketToVoice(clean) {
   }
 }
 
+// True when at least one textToVoice route can produce audio. Mirrors the
+// pocket -> ElevenLabs -> say fallback chain; local Whisper is deliberately
+// irrelevant here (hosted pods speak via the gateway without it).
+function canSpeak() {
+  if (!FFMPEG) return false;
+  if (TTS_PROVIDER !== "elevenlabs" && speechBearerToken() && SPEECH_SERVICE_URL) return true;
+  return Boolean(ELEVENLABS_API_KEY || TTS_CMD);
+}
+
 // Natural voice via ElevenLabs, falling back to macOS `say` only on no-key/error.
 async function textToVoice(text) {
   const clean = cleanForTTS(text);
@@ -194,4 +203,4 @@ async function synthSentenceMp3(text) {
   }
 }
 
-module.exports = { transcribeAudio, transcribeAudioLocal, textToVoice, splitSentences, synthSentenceMp3, pocketToVoice, speechBearerToken, TTS_CMD };
+module.exports = { transcribeAudio, transcribeAudioLocal, textToVoice, splitSentences, synthSentenceMp3, pocketToVoice, speechBearerToken, canSpeak, TTS_CMD };

package/core/system-prompt.js

@@ -3,7 +3,8 @@
 
 const fs = require("fs");
 const path = require("path");
-const { SOUL_FILE, CRONS_FILE, VAULT_FILE, FILES_DIR, BOT_DIR, WHISPER_CLI, FFMPEG, config } = require("./config");
+const { SOUL_FILE, CRONS_FILE, VAULT_FILE, FILES_DIR, BOT_DIR, config } = require("./config");
+const { canSpeak } = require("./media");
 const CONFIG_DIR = require("../config-dir");
 const { currentState, getProjectKey, getProviderSession } = require("./state");
 const { currentAdapter, currentChannelId, currentUserId } = require("./context");
@@ -198,7 +199,9 @@ ${listing}`;
 
 function buildCoreInstructionsUncached() {
   const soul = loadSoul();
-  const hasVoice = WHISPER_CLI && FFMPEG;
+  // Gate on actual TTS capability, not local Whisper: hosted pods hear and
+  // speak through the speech gateway with no whisper binary installed.
+  const hasVoice = canSpeak();
   return `
 ${soul}
 ${buildPersonaBlock()}
@@ -230,6 +233,7 @@ Reply normally in your final answer. To send a file, image, or voice clip back t
 - \`open-claudia send-file <path> [caption]\` — any document/binary
 - \`open-claudia send-photo <path> [caption]\` — image with inline preview
 - \`open-claudia send-voice <path>\` — ogg/opus voice note
+- \`open-claudia say "<text>"\` — synthesize the text and send it as a voice note (use this when asked for a voice reply)
 Never print or embed bot tokens in prompts, commands, logs, or messages.
 
 ## Background work

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inetafrica/open-claudia",
-  "version": "3.1.7",
+  "version": "3.1.8",
   "description": "An always-on, provider-agnostic coding-agent harness for Claude Code and OpenAI Codex via chat",
   "main": "bot.js",
   "bin": {

package/test-provider-language.js

@@ -179,7 +179,14 @@ assert.match(pkg.description, /provider-agnostic coding-agent harness/i);
 // v3.1.6 run-lifecycle fix itself passed there). Audited all 13 fake-agent
 // test files and hardened the three racy ones (utility-policy, enforcer,
 // subagent): wait on boot captures / generous deadlines, never tight sleeps.
-assert.strictEqual(pkg.version, "3.1.7", "release version must remain unchanged without explicit approval");
+// 3.1.8 approved by Sumeet 2026-07-21 ("Yeh"): pod voice-note fix. Pods ship
+// /usr/bin/ffmpeg but never set FFMPEG=, so every TTS route silently no-opped,
+// and the system-prompt voice flag still gated on local Whisper — hosted bots
+// told users voice notes were disabled despite a working speech gateway.
+// Fix: FFMPEG PATH discovery in config, media.canSpeak() drives the prompt
+// flag, and a new `open-claudia say "<text>"` verb synthesizes + sends a
+// voice note on request.
+assert.strictEqual(pkg.version, "3.1.8", "release version must remain unchanged without explicit approval");
 for (const keyword of ["claude", "codex", "coding-agent", "provider-agnostic"]) {
   assert.ok(pkg.keywords.includes(keyword), `package keyword missing: ${keyword}`);
 }