Phase 3 — WS frame + REST fallbacka

app/core/agent_runner.py

@@ -287,7 +287,6 @@ async def _run_agent_with_tools(
                 return final_text
 
             for call in response.tool_calls:
-                call_id = str(call.get("id", ""))
                 call_name = str(call.get("name", ""))
                 call_args = call.get("args", {})
                 logger.info(

app/core/brief_agent.py

@@ -0,0 +1,222 @@
+"""Brief agent — produces plain-text home and project status briefs.
+
+Read-only tool subset only. Never calls _normalize_tagged_list_lines —
+the brief prompt forbids XML tags, so skipping post-processing is intentional.
+"""
+
+from __future__ import annotations
+
+from collections.abc import AsyncGenerator
+from datetime import date
+from typing import Any
+
+from app.agents.note_agent import NOTE_READ_TOOLS
+from app.agents.project_agent import PROJECT_READ_TOOLS
+from app.agents.task_agent import TASK_READ_TOOLS
+from app.agents.timeline_agent import TIMELINE_READ_TOOLS
+from app.core.deep_agent import (
+    _language_instruction,
+    _proactive_hints_injection,
+    _read_only_memory_tools,
+    _relational_memory_injection,
+    _run_single_agent_stream,
+    _trace_id_from_context,
+)
+from app.core.langfuse_client import compile_prompt, get_prompt_or_fallback
+
+_LANGUAGE_NAMES: dict[str, str] = {
+    "en": "English", "it": "Italian", "es": "Spanish",
+    "fr": "French", "de": "German",
+    "english": "English", "italian": "Italian", "italiano": "Italian",
+    "spanish": "Spanish", "español": "Spanish",
+    "french": "French", "français": "French",
+    "german": "German", "deutsch": "German",
+}
+
+_HOME_BRIEF_FALLBACK = """\
+You are the user's personal assistant producing a short daily brief.
+
+ROLE
+Act like a calm, attentive secretary writing a stand-up note for your boss.
+Warm and human, never breezy. Never cheerful filler, never emojis, never
+"here is your brief" meta-text. The user is opening the app mid-workday and
+is probably stressed — your job is to lower cognitive load, not add noise.
+
+TOOLS — always call before writing
+Pull fresh data every run. Do not invent counts or titles. Use at minimum:
+- list_tasks_due_today — tasks the user owes today
+- list_timelines_today — events starting or ending today
+- list_all_projects — projects currently in progress or at risk
+- memory_list_blocks / memory_get — personal context about people, clients,
+  payment habits, working preferences
+If a tool returns nothing, simply omit that topic. Never report zeros.
+
+WHAT TO INCLUDE
+1. Tasks due today (title + priority; group the 1-2 most important).
+2. Timeline events starting or ending today (and anything that starts/ends
+   tomorrow if the user has a very light day).
+3. Active projects that need a nudge — stalled, blocked, or awaiting input.
+4. Memory-aware colour where it sharpens the brief. Examples:
+   - "Client Rossi tends to pay late — the Acme invoice is 6 days out."
+   - "You usually dislike meetings before 10:00 — the call at 09:30 is unusual."
+   Only add a memory line when it changes what the user does. Do not pad.
+
+WHAT TO OMIT
+- Zero-counts ("no overdue items", "0 meetings today").
+- Statistics ("2 active projects, 3 completed tasks").
+- Headers, titles, greetings, sign-offs, dates, emojis, slang.
+- Meta-phrases ("here is", "let me know if", "hope this helps").
+- XML/HTML tags of any kind. Plain prose only.
+
+LIGHT-DAY CLAUSE
+If tasks + events + active-project-nudges together produce fewer than two
+sentences of content, also list 1-2 projects in status on_hold or waiting
+and ask a single, specific question about them — e.g. "Is the Bianchi
+redesign still paused, or ready to pick back up?" One question max, grounded
+in a real project name.
+
+VOICE
+- Calm. Concise. Human. Short sentences.
+- Use **bold** sparingly for task titles, project names, and people's names.
+- No bullet lists. Flow as 2-4 sentences of prose.
+
+LENGTH
+2-4 sentences total. Hard cap 4. If the day is truly empty, one sentence.
+
+Respond in the user's language ({language}). Today is {today}.\
+"""
+
+_PROJECT_BRIEF_FALLBACK = """\
+You are the project assistant producing a short status brief for ONE project.
+
+ROLE
+A senior project manager summarising state-of-play for the owner. Factual,
+sharp, forward-looking. Never reassuring filler, never emojis.
+
+SCOPE
+Work only with project_id = {project_id}. Do not mention or pull data from
+other projects. Use tools to fetch fresh data:
+- get_project — current status, dates, description
+- list_tasks(project_id) — open work, split by status
+- list_timelines(project_id) — milestones hit, upcoming, overdue
+- list_notes(project_id) — any recent decisions or blockers
+- memory_get — relevant context about the client, collaborators, constraints
+
+STRUCTURE — follow exactly, one short paragraph per section, no headers
+1. **State.** One sentence: current phase, health (on track / at risk / blocked),
+   and why. Cite the concrete signal (overdue milestone, stalled tasks, recent
+   blocker note).
+2. **What's moving.** What was completed or progressed recently. Name specific
+   tasks or milestones.
+3. **Next steps.** The 1-3 most important things the user should do next, in
+   priority order. Be concrete — task name, who owns it, when due if known.
+   If waiting on someone else, name them and what the ask is.
+4. **Risks / memory-flagged items.** One line max. Only include when there is
+   a real risk or a relevant memory (e.g. late-paying client, tight deadline,
+   scope change). Omit the section entirely if nothing to say.
+
+WHAT TO OMIT
+- Zero-counts ("no overdue tasks").
+- Generic advice ("keep up the good work").
+- Greetings, headers, bullet lists, emojis, sign-offs, meta-phrases.
+- XML/HTML tags or bracketed id lists. Plain prose only.
+
+VOICE
+- Direct. Factual. No fluff.
+- Use **bold** sparingly for task titles, milestone names, and the owner's name.
+- Short sentences. Prefer verbs over nouns ("Client review is blocking release"
+  not "There is a blocker which is the client review").
+
+LENGTH
+4-8 sentences total across the 3-4 sections. Hard cap 8.
+
+Respond in the user's language ({language}). Today is {today}.\
+"""
+
+
+def _resolve_language(context: dict[str, Any]) -> str:
+    core = context.get("core_memory") or {}
+    raw = (core.get("language") or "en").strip().lower()
+    return _LANGUAGE_NAMES.get(raw, raw.title()) or "English"
+
+
+def _build_read_tools(user_id: str, trace_id: str | None) -> list[Any]:
+    return [
+        *TASK_READ_TOOLS,
+        *PROJECT_READ_TOOLS,
+        *TIMELINE_READ_TOOLS,
+        *NOTE_READ_TOOLS,
+        *_read_only_memory_tools(user_id, trace_id),
+    ]
+
+
+async def run_home_brief(
+    user_id: str,
+    context: dict[str, Any],
+) -> AsyncGenerator[tuple[str, Any], None]:
+    """Stream a plain-text daily home brief.
+
+    Yields (event_type, data) tuples identical to _run_single_agent_stream.
+    Do NOT post-process output through _normalize_tagged_list_lines.
+    """
+    trace_id = _trace_id_from_context(context)
+    today = date.today().isoformat()
+    language = _resolve_language(context)
+
+    raw_template, langfuse_prompt = get_prompt_or_fallback("home_brief", _HOME_BRIEF_FALLBACK)
+    system_prompt = compile_prompt(raw_template, langfuse_prompt, language=language, today=today)
+    system_prompt += _relational_memory_injection(context)
+    system_prompt += _proactive_hints_injection(context)
+    system_prompt += _language_instruction(context)
+    if today not in system_prompt:
+        system_prompt += f"\nToday is {today}."
+
+    tools = _build_read_tools(user_id, trace_id)
+    async for event in _run_single_agent_stream(
+        user_id=user_id,
+        system_prompt=system_prompt,
+        message="Generate the daily brief.",
+        context=context,
+        langfuse_prompt=langfuse_prompt,
+        agent_name="brief-agent",
+        tools=tools,
+    ):
+        yield event
+
+
+async def run_project_brief(
+    user_id: str,
+    project_id: str,
+    context: dict[str, Any],
+) -> AsyncGenerator[tuple[str, Any], None]:
+    """Stream a plain-text project status brief for project_id.
+
+    Yields (event_type, data) tuples identical to _run_single_agent_stream.
+    Do NOT post-process output through _normalize_tagged_list_lines.
+    """
+    trace_id = _trace_id_from_context(context)
+    today = date.today().isoformat()
+    language = _resolve_language(context)
+
+    raw_template, langfuse_prompt = get_prompt_or_fallback("project_brief", _PROJECT_BRIEF_FALLBACK)
+    system_prompt = compile_prompt(
+        raw_template, langfuse_prompt,
+        language=language, today=today, project_id=project_id,
+    )
+    system_prompt += _relational_memory_injection(context)
+    system_prompt += _proactive_hints_injection(context)
+    system_prompt += _language_instruction(context)
+    if today not in system_prompt:
+        system_prompt += f"\nToday is {today}."
+
+    tools = _build_read_tools(user_id, trace_id)
+    async for event in _run_single_agent_stream(
+        user_id=user_id,
+        system_prompt=system_prompt,
+        message=f"Generate the project status brief for project {project_id}.",
+        context=context,
+        langfuse_prompt=langfuse_prompt,
+        agent_name="brief-agent",
+        tools=tools,
+    ):
+        yield event

app/core/deep_agent.py

@@ -489,6 +489,13 @@ def _memory_tools(user_id: str, trace_id: str | None) -> list[Any]:
     ]
 
 
+def _read_only_memory_tools(user_id: str, trace_id: str | None) -> list[Any]:
+    """Return memory tools that only read — safe for the read-only brief-agent subset."""
+    all_mem = _memory_tools(user_id, trace_id)
+    _read_names = {"memory_list_blocks", "memory_get", "archival_memory_search", "conversation_search"}
+    return [t for t in all_mem if t.name in _read_names]
+
+
 def _all_tools_for_user(user_id: str, trace_id: str | None) -> list[Any]:
     return [*_all_tools(), *_memory_tools(user_id, trace_id)]
 
@@ -792,12 +799,14 @@ async def _run_single_agent_stream(
     max_steps: int = 6,
     langfuse_prompt: Any = None,
     agent_name: str = "agent",
+    tools: list[Any] | None = None,
 ) -> AsyncGenerator[tuple[str, Any], None]:
     trace_id = _trace_id_from_context(context)
     session_id = _session_id_from_context(context)
     lf = get_langfuse()
     llm = get_agent_llm(agent_name)
-    tools = _all_tools_for_user(user_id, trace_id)
+    if tools is None:
+        tools = _all_tools_for_user(user_id, trace_id)
     model_context = _context_for_model(context)
     logger.info("deep_agent: run_single_agent_stream_start trace=%s user=%s", trace_id or "-", user_id)
     llm_with_tools = llm.bind_tools(tools)

app/core/llm.py

@@ -102,6 +102,7 @@ _AGENT_MODEL_SETTINGS: dict[str, Callable[[], str]] = {
     "floating-agent":      lambda: settings.LLM_MODEL_FLOATING_AGENT or settings.LLM_MODEL,
     "unified-processor":   lambda: settings.LLM_MODEL_UNIFIED_PROCESSOR or settings.LLM_MODEL,
     "cloud-processor":     lambda: settings.LLM_MODEL_CLOUD_PROCESSOR or settings.LLM_MODEL,
+    "brief-agent":         lambda: settings.LLM_MODEL_BRIEF_AGENT or settings.LLM_MODEL,
     "setup":               lambda: settings.LLM_MODEL_SETUP_AGENT or settings.LLM_MODEL,
     "memory-extractor":    lambda: settings.LLM_MODEL_MEMORY_EXTRACTOR or "gpt-4o-mini",
     "memory-miner":        lambda: settings.LLM_MODEL_MEMORY_MINER or "gpt-4o-mini",