mercury-agent 0.4.7 → 0.4.9

package/container/Dockerfile.power

@@ -3,7 +3,7 @@
 # Extends Base with: python3 + pip + venv, build-essential, jq, ffmpeg, bubblewrap
 # The patch script, mrctl, and entrypoint are all inherited from Base — not duplicated here.
 ARG BASE_TAG
-FROM ghcr.io/michaelliv/mercury-agent:${BASE_TAG}-base
+FROM ghcr.io/avishai-tsabari/mercury-agent:${BASE_TAG}-base
 
 USER root
 RUN apt-get update && apt-get install -y --no-install-recommends \

package/docs/auth/dashboard.md

@@ -1,28 +1,28 @@
-# Dashboard Authentication
-
-The Mercury dashboard (`/dashboard/*`) is protected by `MERCURY_API_SECRET`. All htmx partial requests and the SSE events stream require a valid `mercury_token` session cookie.
-
-## How it works
-
-### Login route
-
-`GET /dashboard/login?token=<secret>` — the entry point for browser sessions.
-
-- Validates `token` against `MERCURY_API_SECRET` using `timingSafeEqual`
-- On success: sets `mercury_token` HttpOnly cookie and redirects to `/dashboard`
-- On failure: returns `401 Invalid or missing token`
-- Not protected by the dashboard auth middleware (it's the login endpoint itself)
-
-## Auth flow
-
-```
-User navigates to https://<host>:<port>/dashboard/login?token=<MERCURY_API_SECRET>
-  → agent sets mercury_token HttpOnly cookie
-  → 302 /dashboard
-  → dashboard loads, htmx requests include cookie ✅
-```
-
-## Key constraints
-
-- `MERCURY_API_SECRET` should be set to a long random string. `mercury setup` auto-generates one.
-- The cookie is HttpOnly — not accessible from JavaScript.
+# Dashboard Authentication
+
+The Mercury dashboard (`/dashboard/*`) is protected by `MERCURY_API_SECRET`. All htmx partial requests and the SSE events stream require a valid `mercury_token` session cookie.
+
+## How it works
+
+### Login route
+
+`GET /dashboard/login?token=<secret>` — the entry point for browser sessions.
+
+- Validates `token` against `MERCURY_API_SECRET` using `timingSafeEqual`
+- On success: sets `mercury_token` HttpOnly cookie and redirects to `/dashboard`
+- On failure: returns `401 Invalid or missing token`
+- Not protected by the dashboard auth middleware (it's the login endpoint itself)
+
+## Auth flow
+
+```
+User navigates to https://<host>:<port>/dashboard/login?token=<MERCURY_API_SECRET>
+  → agent sets mercury_token HttpOnly cookie
+  → 302 /dashboard
+  → dashboard loads, htmx requests include cookie ✅
+```
+
+## Key constraints
+
+- `MERCURY_API_SECRET` should be set to a long random string. `mercury setup` auto-generates one.
+- The cookie is HttpOnly — not accessible from JavaScript.

package/docs/container-lifecycle.md

@@ -176,8 +176,8 @@ Message received
 export MERCURY_CONTAINER_TIMEOUT_MS=600000
 
 # Use a preset image from GitHub Container Registry
-export MERCURY_AGENT_IMAGE=ghcr.io/michaelliv/mercury-agent:latest   # Full (default)
-export MERCURY_AGENT_IMAGE=ghcr.io/michaelliv/mercury-agent:minimal  # Lightweight
+export MERCURY_AGENT_IMAGE=ghcr.io/avishai-tsabari/mercury-agent:latest   # Full (default)
+export MERCURY_AGENT_IMAGE=ghcr.io/avishai-tsabari/mercury-agent:minimal  # Lightweight
 ```
 
 ## Sandboxing (Bubblewrap)
@@ -204,8 +204,8 @@ Mercury publishes two image presets to GitHub Container Registry:
 
 | Preset | Size | Contents |
 |--------|------|----------|
-| `ghcr.io/michaelliv/mercury-agent:latest` | ~2.8GB | Full devcontainer: Bun, Node.js, Python, Go, git, build tools |
-| `ghcr.io/michaelliv/mercury-agent:minimal` | ~1.9GB | Lightweight runtime: Bun + pi + Chromium deps |
+| `ghcr.io/avishai-tsabari/mercury-agent:latest` | ~2.8GB | Full devcontainer: Bun, Node.js, Python, Go, git, build tools |
+| `ghcr.io/avishai-tsabari/mercury-agent:minimal` | ~1.9GB | Lightweight runtime: Bun + pi + Chromium deps |
 
 Images are published on each release. Version-specific tags are also available (e.g., `:0.2.0`, `:0.2.0-minimal`).
 

package/examples/extensions/voice-synth/index.ts

@@ -1,94 +1,94 @@
-import { mkdirSync, statSync, writeFileSync } from "node:fs";
-import path from "node:path";
-import type {
-  MercuryExtensionAPI,
-  MercuryExtensionContext,
-} from "mercury-agent/extensions/types";
-import type { MercuryTtsConfig } from "mercury-agent/tts";
-import { synthesizeSpeech } from "mercury-agent/tts";
-import type { EgressFile } from "mercury-agent/types";
-
-const EXT = "voice-synth";
-
-/** Prefer `voice-synth.mode`; fall back to legacy `voice-synth.auto`. */
-function readVoiceSynthMode(
-  ctx: MercuryExtensionContext,
-  spaceId: string,
-): "on_demand" | "auto" {
-  const mode = ctx.db.getSpaceConfig(spaceId, `${EXT}.mode`);
-  if (mode === "auto" || mode === "on_demand") return mode;
-  const legacy = ctx.db.getSpaceConfig(spaceId, `${EXT}.auto`);
-  return legacy === "true" ? "auto" : "on_demand";
-}
-
-function toTtsConfig(ctx: MercuryExtensionContext): MercuryTtsConfig {
-  const c = ctx.config;
-  return {
-    ttsProvider: c.ttsProvider,
-    azureSpeechKey: c.azureSpeechKey,
-    azureSpeechRegion: c.azureSpeechRegion,
-    googleApplicationCredentials: c.googleApplicationCredentials,
-    ttsMaxChars: c.ttsMaxChars,
-  };
-}
-
-export default function setup(mercury: MercuryExtensionAPI) {
-  mercury.config("mode", {
-    description:
-      "on_demand: TTS only when the agent runs `mrctl tts synthesize` (default). auto: attach a TTS MP3 to every assistant reply.",
-    default: "on_demand",
-    validate: (v) => v === "on_demand" || v === "auto",
-  });
-
-  mercury.config("auto", {
-    description:
-      "Legacy: prefer voice-synth.mode. Used only when mode is unset; true equals mode=auto.",
-    default: "false",
-    validate: (v) => v === "true" || v === "false",
-  });
-
-  mercury.skill("./skill");
-
-  mercury.on("after_container", async (event, ctx) => {
-    if (readVoiceSynthMode(ctx, event.spaceId) !== "auto") return undefined;
-    if (!event.reply?.trim()) return undefined;
-    if (event.error) return undefined;
-
-    if (
-      !ctx.hasCallerPermission(event.spaceId, event.callerId, "tts.synthesize")
-    ) {
-      ctx.log.warn("voice-synth.auto skipped: caller lacks tts.synthesize", {
-        extension: EXT,
-        spaceId: event.spaceId,
-      });
-      return undefined;
-    }
-
-    const outDir = path.join(event.workspace, "outbox");
-    mkdirSync(outDir, { recursive: true });
-    const filename = `tts-${Date.now()}.mp3`;
-    const absPath = path.join(outDir, filename);
-
-    try {
-      const { buffer } = await synthesizeSpeech(toTtsConfig(ctx), {
-        text: event.reply,
-        language: "auto",
-      });
-      writeFileSync(absPath, buffer);
-      const st = statSync(absPath);
-      const file: EgressFile = {
-        path: absPath,
-        filename,
-        mimeType: "audio/mpeg",
-        sizeBytes: st.size,
-      };
-      return { files: [file] };
-    } catch (e) {
-      ctx.log.error("voice-synth TTS failed", {
-        extension: EXT,
-        error: e instanceof Error ? e.message : String(e),
-      });
-      return undefined;
-    }
-  });
-}
+import { mkdirSync, statSync, writeFileSync } from "node:fs";
+import path from "node:path";
+import type {
+  MercuryExtensionAPI,
+  MercuryExtensionContext,
+} from "mercury-agent/extensions/types";
+import type { MercuryTtsConfig } from "mercury-agent/tts";
+import { synthesizeSpeech } from "mercury-agent/tts";
+import type { EgressFile } from "mercury-agent/types";
+
+const EXT = "voice-synth";
+
+/** Prefer `voice-synth.mode`; fall back to legacy `voice-synth.auto`. */
+function readVoiceSynthMode(
+  ctx: MercuryExtensionContext,
+  spaceId: string,
+): "on_demand" | "auto" {
+  const mode = ctx.db.getSpaceConfig(spaceId, `${EXT}.mode`);
+  if (mode === "auto" || mode === "on_demand") return mode;
+  const legacy = ctx.db.getSpaceConfig(spaceId, `${EXT}.auto`);
+  return legacy === "true" ? "auto" : "on_demand";
+}
+
+function toTtsConfig(ctx: MercuryExtensionContext): MercuryTtsConfig {
+  const c = ctx.config;
+  return {
+    ttsProvider: c.ttsProvider,
+    azureSpeechKey: c.azureSpeechKey,
+    azureSpeechRegion: c.azureSpeechRegion,
+    googleApplicationCredentials: c.googleApplicationCredentials,
+    ttsMaxChars: c.ttsMaxChars,
+  };
+}
+
+export default function setup(mercury: MercuryExtensionAPI) {
+  mercury.config("mode", {
+    description:
+      "on_demand: TTS only when the agent runs `mrctl tts synthesize` (default). auto: attach a TTS MP3 to every assistant reply.",
+    default: "on_demand",
+    validate: (v) => v === "on_demand" || v === "auto",
+  });
+
+  mercury.config("auto", {
+    description:
+      "Legacy: prefer voice-synth.mode. Used only when mode is unset; true equals mode=auto.",
+    default: "false",
+    validate: (v) => v === "true" || v === "false",
+  });
+
+  mercury.skill("./skill");
+
+  mercury.on("after_container", async (event, ctx) => {
+    if (readVoiceSynthMode(ctx, event.spaceId) !== "auto") return undefined;
+    if (!event.reply?.trim()) return undefined;
+    if (event.error) return undefined;
+
+    if (
+      !ctx.hasCallerPermission(event.spaceId, event.callerId, "tts.synthesize")
+    ) {
+      ctx.log.warn("voice-synth.auto skipped: caller lacks tts.synthesize", {
+        extension: EXT,
+        spaceId: event.spaceId,
+      });
+      return undefined;
+    }
+
+    const outDir = path.join(event.workspace, "outbox");
+    mkdirSync(outDir, { recursive: true });
+    const filename = `tts-${Date.now()}.mp3`;
+    const absPath = path.join(outDir, filename);
+
+    try {
+      const { buffer } = await synthesizeSpeech(toTtsConfig(ctx), {
+        text: event.reply,
+        language: "auto",
+      });
+      writeFileSync(absPath, buffer);
+      const st = statSync(absPath);
+      const file: EgressFile = {
+        path: absPath,
+        filename,
+        mimeType: "audio/mpeg",
+        sizeBytes: st.size,
+      };
+      return { files: [file] };
+    } catch (e) {
+      ctx.log.error("voice-synth TTS failed", {
+        extension: EXT,
+        error: e instanceof Error ? e.message : String(e),
+      });
+      return undefined;
+    }
+  });
+}

package/examples/extensions/voice-transcribe/scripts/transcribe.py

@@ -117,7 +117,7 @@ def _run_transformers(audio_path: str, model_id: str) -> str:
         model=model_id,
         device=device,
     )
-    result = pipe(audio_path)
+    result = pipe(audio_path, return_timestamps=True)
     if isinstance(result, dict):
         return (result.get("text") or "").strip()
     return str(result).strip()

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mercury-agent",
-  "version": "0.4.7",
+  "version": "0.4.9",
   "description": "Personal AI assistant for chat platforms (WhatsApp, Slack, Discord, Telegram)",
   "license": "MIT",
   "author": "Avishai Tsabari",

package/resources/templates/mercury.example.yaml

@@ -57,7 +57,7 @@
 #   # auto_compact_threshold: 50
 
 # agent:
-#   image: ghcr.io/michaelliv/mercury-agent:latest
+#   image: ghcr.io/avishai-tsabari/mercury-agent:latest
 #   container_timeout_ms: 300000
 #   container_bwrap_docker_compat: false