feat: add seamless text and voice chat

agent/agent.py

@@ -80,7 +80,8 @@ SYSTEM_PROMPT = textwrap.dedent("""\
       no markdown, and no formatting except the Azure delivery markers below.
     - Spell out numbers when it sounds more natural ("twenty twenty-six"
       instead of "2026").
-    - If you need to ask a question, ask exactly one.
+    - Make reasonable assumptions and answer directly. Ask a follow-up only
+      when it is genuinely impossible to proceed without one.
     - Be warm and direct. Don't be sycophantic or overly formal.
     - If you don't know something, say so briefly and move on.
 
@@ -144,7 +145,7 @@ SYSTEM_PROMPT = textwrap.dedent("""\
     - User says "look up the price of a PS5" → CALL dispatch_task with
       description="Find the current retail price of a PlayStation 5"
     After calling dispatch_task, tell the user "I'll get on that for you"
-    and keep the conversation going. The result comes back automatically — when
+    without asking for more permission or details. The result comes back automatically — when
     you receive it, share the findings naturally in your conversational style.
     You can have multiple tasks running at once.
 
@@ -612,29 +613,41 @@ async def handle_job(ctx: JobContext) -> None:
         ),
     )
 
-    # Listen for data messages (voice switching) from the web UI.
+    # Listen for conversation controls (voice selection and voice/text mode).
     # Defined here so it captures this job's session via closure.
     def _on_room_data(packet) -> None:
         topic = getattr(packet, "topic", None)
-        if topic and topic != "voice-control":
+        if topic and topic not in ("voice-control", "conversation-control"):
             return
         try:
             msg = json.loads(packet.data.decode("utf-8"))
         except (json.JSONDecodeError, UnicodeDecodeError):
             return
-        if msg.get("type") != "set_voice":
+
+        if msg.get("type") == "set_mode":
+            mode = msg.get("mode")
+            if mode not in ("voice", "text"):
+                return
+            voice_enabled = mode == "voice"
+            logger.info("Switching conversation mode to %s", mode)
+            if not voice_enabled:
+                asyncio.create_task(session.interrupt())
+            session.input.set_audio_enabled(voice_enabled)
+            session.output.set_audio_enabled(voice_enabled)
             return
-        voice = msg.get("voice", "")
-        if not voice:
-            return
-        logger.info("Switching TTS voice to %s", voice)
-        try:
-            tts = session.tts
-            if hasattr(tts, "update_options"):
-                tts.update_options(voice=voice)
-                logger.info("Voice updated to %s", voice)
-        except Exception as e:  # noqa: BLE001
-            logger.warning("Failed to update voice: %s", e)
+
+        if msg.get("type") == "set_voice":
+            voice = msg.get("voice", "")
+            if not voice:
+                return
+            logger.info("Switching TTS voice to %s", voice)
+            try:
+                active_tts = session.tts
+                if hasattr(active_tts, "update_options"):
+                    active_tts.update_options(voice=voice)
+                    logger.info("Voice updated to %s", voice)
+            except Exception as e:  # noqa: BLE001
+                logger.warning("Failed to update voice: %s", e)
 
     ctx.room.on("data_received", _on_room_data)
 

agent/task_worker.py

@@ -65,8 +65,8 @@ class TaskWorker:
                     model=model,
                     messages=messages,
                     tools=tools or None,
-                    max_tokens=500,
-                    temperature=0.7,
+                    max_tokens=700,
+                    temperature=0.3,
                     extra_body={"chat_template_kwargs": {"enable_thinking": False}},
                 )
             except Exception as e:
@@ -102,18 +102,72 @@ class TaskWorker:
                 if not text:
                     reg.fail(self.task_id, "LLM returned empty response")
                     return
+                if self._is_deferred_answer(text):
+                    reg.add_step(
+                        self.task_id,
+                        "thinking",
+                        "Draft deferred the work; continuing automatically.",
+                    )
+                    if iteration == max_iterations - 1:
+                        reg.fail(self.task_id, "Could not produce a complete answer")
+                        return
+                    messages.extend(
+                        [
+                            {"role": "assistant", "content": text},
+                            {
+                                "role": "user",
+                                "content": (
+                                    "Do not ask me a follow-up or offer to continue later. "
+                                    "Continue the task now, run any more targeted tool calls "
+                                    "you need, make reasonable assumptions, and only finish "
+                                    "when you have directly answered the original request."
+                                ),
+                            },
+                        ]
+                    )
+                    continue
                 reg.add_step(self.task_id, "text", text)
                 reg.complete(self.task_id, text)
                 return
 
         reg.fail(self.task_id, f"Reached max iterations ({max_iterations})")
 
+    @staticmethod
+    def _is_deferred_answer(text: str) -> bool:
+        """Reject drafts that ask permission or defer the requested work."""
+        lowered = text.lower()
+        deferral_phrases = (
+            "would you like me",
+            "do you want me",
+            "should i ",
+            "shall i ",
+            "if you'd like",
+            "if you would like",
+            "let me know if",
+            "i need to perform",
+            "i need more information",
+            "i can refine",
+            "i can search",
+            "i can provide",
+            "need a more targeted search",
+        )
+        return "?" in text or any(phrase in lowered for phrase in deferral_phrases)
+
     def _system_prompt(self) -> str:
+        today = datetime.now(timezone.utc).strftime("%B %d, %Y")
         return (
-            "You are Hope's research assistant working on a background task. "
-            "Use your tools to gather information thoroughly. When you have "
-            "enough, provide a final answer in 1-3 sentences suitable for "
-            "speaking aloud. Plain text only, no markdown or formatting."
+            "You are Hope's autonomous research assistant working on a background task. "
+            f"Today is {today}. Use your tools until you have directly completed the request. "
+            "Never ask the user a follow-up question, ask permission to search again, or offer "
+            "to finish later; make reasonable assumptions and continue autonomously. If a web "
+            "search is broad or inconclusive, immediately run a more targeted query and scrape "
+            "the most promising result pages, including today's date and specific reputable "
+            "sources when freshness matters. For headline "
+            "requests, return concrete named events rather than links to news homepages, and "
+            "respect any requested item count exactly. Only "
+            "produce a final answer once it fulfills the original request. The final answer must "
+            "be 1-3 concise sentences suitable for speaking aloud, with plain text only and no "
+            "markdown or formatting."
         )
 
     def _load_tools(self) -> list[dict]:
@@ -157,7 +211,7 @@ class TaskWorker:
                 "type": "function",
                 "function": {
                     "name": "web_search",
-                    "description": "Search the web for current information using Firecrawl.",
+                    "description": "Search the web for current information. Returns titles, descriptions, and URLs.",
                     "parameters": {
                         "type": "object",
                         "properties": {"query": {"type": "string"}},
@@ -165,6 +219,18 @@ class TaskWorker:
                     },
                 },
             },
+            {
+                "type": "function",
+                "function": {
+                    "name": "web_scrape",
+                    "description": "Read the full content of a promising URL returned by web_search.",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {"url": {"type": "string"}},
+                        "required": ["url"],
+                    },
+                },
+            },
         ]
 
     async def _execute_tool(self, name: str, args: dict) -> str:
@@ -227,18 +293,46 @@ class TaskWorker:
                 async with httpx.AsyncClient(timeout=30) as client:
                     resp = await client.post(
                         f"{firecrawl_base}/v1/search",
-                        json={"query": query, "limit": 3},
+                        json={"query": query, "limit": 5},
                     )
                     if resp.status_code == 200:
                         data = resp.json()
                         items = data.get("data", [])
-                        lines = [
-                            f"{r.get('title', '')}: {r.get('description', '')}"
-                            for r in items[:3]
-                        ]
+                        lines = []
+                        for item in items[:5]:
+                            title = (item.get("title") or "Untitled").strip()
+                            description = (item.get("description") or "").strip()
+                            url = (item.get("url") or "").strip()
+                            lines.append(f"{title}: {description}")
+                            if url:
+                                lines.append(f"URL: {url}")
                         return "\n".join(lines) or "No results found."
                     return f"Search failed (HTTP {resp.status_code})."
 
+            elif name == "web_scrape":
+                url = args.get("url", "")
+                if not url:
+                    return "A URL is required."
+                firecrawl_base = os.environ.get("FIRECRAWL_BASE", "")
+                if not firecrawl_base:
+                    return "Web scraping is not configured."
+                async with httpx.AsyncClient(timeout=90) as client:
+                    resp = await client.post(
+                        f"{firecrawl_base}/v1/scrape",
+                        json={"url": url, "formats": ["markdown"], "timeout": 60000},
+                    )
+                    if resp.status_code != 200:
+                        return f"Scrape failed (HTTP {resp.status_code})."
+                    data = resp.json()
+                    if not data.get("success"):
+                        return f"Scrape failed: {data.get('error', 'unknown error')}"
+                    result = data.get("data", {})
+                    markdown = (result.get("markdown") or "").strip()
+                    if not markdown:
+                        return "No page content was extracted."
+                    title = (result.get("metadata", {}).get("title") or "").strip()
+                    return f"Page: {title}\n\n{markdown[:8000]}"
+
             else:
                 return f"Unknown tool: {name}"