fix tools calls

2026-04-27 09:15:08 +02:00
parent cb8f56d909
commit 6787e690ba
4 changed files with 659 additions and 120 deletions
--- a/tests/test_deep_agent.py
+++ b/tests/test_deep_agent.py
@@ -10,8 +10,11 @@ import pytest
 from langchain_core.messages import AIMessage, ToolMessage

 from app.core.deep_agent import (
+    _build_system_prompt,
+    _datetime_context_injection,
    _infer_floating_domain,
    _normalize_tagged_list_lines,
+    _request_context_block,
    run_floating,
    run_floating_stream,
    run_home,
@@ -91,8 +94,12 @@ async def test_run_floating_stream_emits_domain_then_tokens_with_mocked_tool_res
        "floating_domain",
        {"type": "timeline", "id": "tl-1", "section": None},
    )
-    assert ("token", "stream-") in events
-    assert ("token", "ok") in events
+    # _run_single_agent_stream uses ainvoke (not astream); the final token is
+    # the second LLM response which echoes the tool result.
+    token_events = [e for e in events if e[0] == "token"]
+    assert token_events, "Expected at least one token event"
+    combined = "".join(str(e[1]) for e in token_events)
+    assert "Mock Task" in combined


@pytest.mark.asyncio
@@ -286,3 +293,213 @@ async def test_run_floating_stream_returns_fallback_when_sanitization_would_empt
            events.append(event)

    assert ("token", "No results found.") in events
+
+
+# ── _datetime_context_injection ────────────────────────────────────────────────
+
+def _fp(tz: str, now_iso: str) -> dict:
+    return {"timezone": tz, "now_iso": now_iso, "date_format": "dd/MM/yyyy", "time_format": "24h"}
+
+
+def _parse_ms(block: str, key: str) -> tuple[int, int]:
+    """Extract [start, end] from a 'key  [start, end]' line in the DATE CONTEXT block."""
+    import re
+    m = re.search(rf"^{key}\s+\[(\d+),\s*(\d+)\]", block, re.MULTILINE)
+    assert m, f"Key '{key}' not found in block:\n{block}"
+    return int(m.group(1)), int(m.group(2))
+
+
+def test_datetime_context_injection_europe_rome_late_evening():
+    """22:16 CEST on 2026-04-26 — 'tomorrow' must be 2026-04-27 00:00→23:59:59.999 CEST."""
+    from zoneinfo import ZoneInfo
+    from datetime import datetime, timezone
+
+    block = _datetime_context_injection({"format_prefs": _fp("Europe/Rome", "2026-04-26T20:16:02.155Z")})
+    assert "DATE CONTEXT" in block
+    assert "Europe/Rome" in block
+
+    tz = ZoneInfo("Europe/Rome")
+    today_start = int(datetime(2026, 4, 26, tzinfo=tz).timestamp() * 1000)
+    today_end = int(datetime(2026, 4, 27, tzinfo=tz).timestamp() * 1000) - 1
+    tomorrow_start = today_end + 1
+    tomorrow_end = int(datetime(2026, 4, 28, tzinfo=tz).timestamp() * 1000) - 1
+
+    t_s, t_e = _parse_ms(block, "today")
+    assert t_s == today_start
+    assert t_e == today_end
+
+    tm_s, tm_e = _parse_ms(block, "tomorrow")
+    assert tm_s == tomorrow_start
+    assert tm_e == tomorrow_end
+
+    # Sanity: window is exactly 86 400 000 ms (1 day, CEST has no DST jump on this date)
+    assert today_end - today_start + 1 == 86_400_000
+    assert tomorrow_end - tomorrow_start + 1 == 86_400_000
+
+
+def test_datetime_context_injection_utc():
+    """UTC timezone: boundaries are clean UTC midnights."""
+    from datetime import datetime, timezone
+
+    block = _datetime_context_injection({"format_prefs": _fp("UTC", "2026-01-15T10:00:00Z")})
+    t_s, t_e = _parse_ms(block, "today")
+    expected_start = int(datetime(2026, 1, 15, tzinfo=timezone.utc).timestamp() * 1000)
+    assert t_s == expected_start
+    assert t_e == expected_start + 86_400_000 - 1
+
+
+def test_datetime_context_injection_dst_spring_forward():
+    """Europe/Rome DST spring-forward 2026-03-29: that day is 23h, not 24h."""
+    from zoneinfo import ZoneInfo
+    from datetime import datetime
+
+    block = _datetime_context_injection({"format_prefs": _fp("Europe/Rome", "2026-03-29T08:00:00Z")})
+    tz = ZoneInfo("Europe/Rome")
+    day_start = int(datetime(2026, 3, 29, tzinfo=tz).timestamp() * 1000)
+    day_end = int(datetime(2026, 3, 30, tzinfo=tz).timestamp() * 1000) - 1
+
+    t_s, t_e = _parse_ms(block, "today")
+    assert t_s == day_start
+    assert t_e == day_end
+    assert t_e - t_s + 1 == 23 * 3_600_000  # 23-hour day
+
+
+def test_datetime_context_injection_dst_fall_back():
+    """Europe/Rome DST fall-back 2026-10-25: that day is 25h."""
+    from zoneinfo import ZoneInfo
+    from datetime import datetime
+
+    block = _datetime_context_injection({"format_prefs": _fp("Europe/Rome", "2026-10-25T08:00:00Z")})
+    tz = ZoneInfo("Europe/Rome")
+    day_start = int(datetime(2026, 10, 25, tzinfo=tz).timestamp() * 1000)
+    day_end = int(datetime(2026, 10, 26, tzinfo=tz).timestamp() * 1000) - 1
+
+    t_s, t_e = _parse_ms(block, "today")
+    assert t_s == day_start
+    assert t_e == day_end
+    assert t_e - t_s + 1 == 25 * 3_600_000  # 25-hour day
+
+
+def test_datetime_context_injection_year_boundary():
+    """Dec 31 → Jan 1: last_year, this_year, next_month cross year boundary correctly."""
+    from zoneinfo import ZoneInfo
+    from datetime import datetime
+
+    block = _datetime_context_injection({"format_prefs": _fp("UTC", "2026-12-31T23:00:00Z")})
+    tz = ZoneInfo("UTC")
+
+    yr_s, yr_e = _parse_ms(block, "this_year")
+    assert yr_s == int(datetime(2026, 1, 1, tzinfo=tz).timestamp() * 1000)
+    assert yr_e == int(datetime(2027, 1, 1, tzinfo=tz).timestamp() * 1000) - 1
+
+    ly_s, ly_e = _parse_ms(block, "last_year")
+    assert ly_s == int(datetime(2025, 1, 1, tzinfo=tz).timestamp() * 1000)
+    assert ly_e == yr_s - 1
+
+    nm_s, _ = _parse_ms(block, "next_month")
+    assert nm_s == int(datetime(2027, 1, 1, tzinfo=tz).timestamp() * 1000)
+
+
+def test_datetime_context_injection_missing_format_prefs():
+    assert _datetime_context_injection({}) == ""
+    assert _datetime_context_injection({"format_prefs": None}) == ""
+    assert _datetime_context_injection({"format_prefs": "bad"}) == ""
+
+
+# ── _request_context_block ─────────────────────────────────────────────────────
+
+def test_request_context_block_scope_and_project():
+    ctx = {"scope": {"type": "task", "id": "t-1"}, "resolved_project_id": "proj-uuid"}
+    block = _request_context_block(ctx)
+    assert "scope" in block
+    assert "resolved_project_id: proj-uuid" in block
+
+
+def test_request_context_block_empty():
+    assert _request_context_block({}) == ""
+    assert _request_context_block({"scope": None}) == ""
+
+
+# ── _build_system_prompt ───────────────────────────────────────────────────────
+
+def test_build_system_prompt_substitutes_all_slots(monkeypatch):
+    """All five slots must appear in the compiled output; no raw placeholder remains."""
+    # Patch get_prompt_or_fallback to return None prompt_obj so we use fallback .format() path
+    import app.core.deep_agent as da
+    monkeypatch.setattr(da, "get_prompt_or_fallback", lambda name, fallback: (fallback, None))
+
+    ctx = {
+        "format_prefs": _fp("Europe/Rome", "2026-04-26T20:16:02.155Z"),
+        "core_memory": {"language": "it"},
+        "relational_memory": ["Alice — client"],
+        "proactive_hints": ["User prefers morning meetings"],
+        "scope": {"type": "task"},
+        "resolved_project_id": "proj-1",
+    }
+    from app.core.deep_agent import _HOME_SYSTEM_PROMPT
+    text, _ = _build_system_prompt("home_system", _HOME_SYSTEM_PROMPT, ctx)
+
+    # No unresolved placeholders
+    assert "{date_context}" not in text
+    assert "{language_instruction}" not in text
+    assert "{relational_memory}" not in text
+    assert "{proactive_hints}" not in text
+    assert "{request_context}" not in text
+
+    # Content was injected
+    assert "DATE CONTEXT" in text
+    assert "Italian" in text
+    assert "Alice" in text
+    assert "morning meetings" in text
+    assert "proj-1" in text
+
+
+def test_build_system_prompt_empty_format_prefs(monkeypatch):
+    """Missing format_prefs must not raise — date_context slot renders empty string."""
+    import app.core.deep_agent as da
+    monkeypatch.setattr(da, "get_prompt_or_fallback", lambda name, fallback: (fallback, None))
+
+    from app.core.deep_agent import _HOME_SYSTEM_PROMPT
+    text, _ = _build_system_prompt("home_system", _HOME_SYSTEM_PROMPT, {})
+    # Prompt renders without error; date section is empty but structure holds
+    assert "# Date filtering" in text
+    assert "{date_context}" not in text
+
+
+def test_human_message_is_bare_message(monkeypatch):
+    """After the refactor HumanMessage content must equal the raw user message exactly."""
+    import app.core.deep_agent as da
+    from langchain_core.messages import HumanMessage as LCHumanMessage
+
+    captured: list[list] = []
+
+    class _CaptureLLM:
+        def bind_tools(self, _):
+            return self
+
+        async def ainvoke(self, messages):
+            captured.append(list(messages))
+            return AIMessage(content="risposta")
+
+    monkeypatch.setattr(da, "get_prompt_or_fallback", lambda n, f: (f, None))
+    monkeypatch.setattr(da, "get_agent_llm", lambda _: _CaptureLLM())
+    monkeypatch.setattr(da, "_all_tools_for_user", lambda *_: [])
+    monkeypatch.setattr(da, "get_langfuse", lambda: None)
+    monkeypatch.setattr(da, "set_tool_result_collector", lambda _: None)
+    monkeypatch.setattr(da, "clear_tool_result_collector", lambda: None)
+
+    import asyncio
+
+    async def _run():
+        chunks = []
+        ctx = {"format_prefs": _fp("UTC", "2026-04-27T10:00:00Z")}
+        async for ev in da.run_home_stream("u1", "Cosa devo fare domani?", ctx):
+            chunks.append(ev)
+
+    asyncio.get_event_loop().run_until_complete(_run())
+
+    assert captured, "LLM was never called"
+    messages = captured[0]
+    human = next(m for m in messages if isinstance(m, LCHumanMessage))
+    assert human.content == "Cosa devo fare domani?"
+    assert "Context:" not in human.content