merge: T116 CannedQueue test fixture builder

tests/fixtures.py

@@ -0,0 +1,383 @@
+"""Structured test-fixture builder for ``MockLLMClient`` canned queues.
+
+Phase 4.5 (T116) carry-over from Phase 3. The turn-flow tests in
+``test_turn_flow.py``, ``test_meanwhile_turn_flow.py``,
+``test_phase3_integration.py``, and ``test_phase4_integration.py`` used
+to construct ``MockLLMClient`` canned-response queues as raw positional
+lists of pre-encoded JSON strings. That worked, but every time a new
+classifier call landed in a code path the tests had to be patched in
+many places at the right index — easy to mis-position, hard to read.
+
+This module ships :class:`CannedQueue`, a fluent builder that lets a
+test declare its classifier expectations by **name** and **order** of
+call, not by index into a brittle list. Each method appends one item
+to the queue and returns ``self`` for chaining; ``build()`` JSON-encodes
+the items and produces the flat ``list[str]`` that
+``MockLLMClient(canned=...)`` expects.
+
+Usage
+-----
+
+>>> from tests.fixtures import CannedQueue
+>>> from chat.llm.mock import MockLLMClient
+>>> canned = (
+...     CannedQueue()
+...         .parse_turn(segments=[{"kind": "dialogue", "text": "hello"}])
+...         .narrative("Hi there.")
+...         .state_update()
+...         .state_update()
+...         .build()
+... )
+>>> mock = MockLLMClient(canned=canned)
+
+Each method maps to a single classifier (or stream) call that the turn
+flow makes, in the order the production code makes them. Picking the
+right method for the slot you need keeps the test readable and lets the
+builder pin sensible defaults for the fields tests don't care about.
+
+Migration template
+------------------
+
+To migrate a positional canned-array test:
+
+1. Identify each slot in the existing array and what classifier it
+   feeds. Comments above the array often spell this out — start there.
+2. Replace each slot with the matching :class:`CannedQueue` method:
+
+   - ``json.dumps({"segments": [...]})`` → ``.parse_turn(segments=...)``
+   - bare narrative string → ``.narrative("...")``
+   - zero-state JSON  → ``.state_update()`` (defaults are zeros)
+   - ``json.dumps({"addressee_id": ...})`` → ``.detect_addressee(...)``
+   - ``json.dumps({"should_interject": ...})`` → ``.detect_interjection(...)``
+   - ``json.dumps({"should_close": ...})`` → ``.detect_scene_close(...)``
+   - ``json.dumps({"transitions": [...]})`` → ``.detect_event_transitions(...)``
+   - per-POV summary JSON → ``.summarize_scene_pov(summary=...)``
+3. End with ``.build()`` and pass that to
+   ``MockLLMClient(canned=...)``. The mock's contract is unchanged.
+
+Notes on streams
+----------------
+
+``MockLLMClient.stream`` and ``MockLLMClient.generate`` share one queue
+— each pop is one entry, regardless of whether the production code
+streams the response or generates it whole. The narrative service
+streams; classifier services generate. The builder treats both the same:
+``narrative()`` appends a raw string, the classifier methods append
+JSON-encoded dicts. Both end up in the same flat ``list[str]`` that the
+mock pops from in order.
+
+The remaining tests in the suite (about 30 across the four files
+mentioned above) still use positional arrays — Phase 5 work to migrate
+the rest. New tests should prefer this builder.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+
+class CannedQueue:
+    """Fluent builder for ``MockLLMClient`` canned-response queues.
+
+    Each method appends one item to an internal queue and returns
+    ``self`` for chaining. ``build()`` returns the flat ``list[str]``
+    suitable for ``MockLLMClient(canned=...)``.
+
+    The queue holds either ``dict`` (JSON-encoded at ``build()`` time)
+    or ``str`` (passed through verbatim — used for narrative streams).
+    """
+
+    def __init__(self) -> None:
+        self._queue: list[Any] = []
+
+    # ------------------------------------------------------------------
+    # Narrative stream — bare string, no JSON wrapping.
+    # ------------------------------------------------------------------
+
+    def narrative(self, text: str) -> "CannedQueue":
+        """Append one streaming narrative response.
+
+        ``MockLLMClient.stream`` pops the next entry from the same queue
+        as ``generate`` — a bare string is what the streaming bot beat
+        consumes. Use one ``narrative()`` per assistant beat (primary,
+        and optionally an interjection / second beat).
+        """
+        self._queue.append(text)
+        return self
+
+    def raw(self, value: str) -> "CannedQueue":
+        """Append a raw string (escape hatch for non-classifier calls).
+
+        Most tests should reach for the named helpers — this is here
+        for one-offs the builder doesn't model yet.
+        """
+        self._queue.append(value)
+        return self
+
+    # ------------------------------------------------------------------
+    # Turn parser — splits user prose into segments.
+    # ------------------------------------------------------------------
+
+    def parse_turn(
+        self,
+        *,
+        segments: list[dict] | None = None,
+        intent: str = "narrative",
+        landing_state_hint: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one ``parse_turn`` classifier response.
+
+        ``intent`` defaults to ``"narrative"``; pass ``"skip_elision"``
+        or ``"skip_jump"`` to exercise the natural-language skip paths.
+        ``landing_state_hint`` carries the residual descriptor for
+        elision skips and is otherwise ignored.
+        """
+        payload: dict[str, Any] = {
+            "segments": segments if segments is not None else [],
+            "intent": intent,
+            "landing_state_hint": landing_state_hint,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Multi-entity addressee classifier (T74.1).
+    # ------------------------------------------------------------------
+
+    def detect_addressee(
+        self,
+        *,
+        addressee_id: str,
+        confidence: str = "medium",
+        reason: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one ``detect_addressee`` classifier response."""
+        payload: dict[str, Any] = {
+            "addressee_id": addressee_id,
+            "confidence": confidence,
+            "reason": reason,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # State-update — one per directed edge per turn.
+    # ------------------------------------------------------------------
+
+    def state_update(
+        self,
+        *,
+        affinity_delta: int = 0,
+        trust_delta: int = 0,
+        knowledge_facts: list | None = None,
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one ``apply_state_update`` classifier response.
+
+        Defaults to a benign zero-delta payload — tests that don't care
+        about state mutations can call this without arguments. One call
+        is required per directed edge that fires after the assistant
+        beat (e.g. single-bot non-guest turn = 2 calls; multi-bot guest
+        turn = 6 calls).
+        """
+        payload: dict[str, Any] = {
+            "affinity_delta": affinity_delta,
+            "trust_delta": trust_delta,
+            "knowledge_facts": (
+                knowledge_facts if knowledge_facts is not None else []
+            ),
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    def zero_state(self) -> "CannedQueue":
+        """Alias for ``state_update()`` with all defaults — matches the
+        ``_zero_state()`` helper in existing tests.
+        """
+        return self.state_update()
+
+    # ------------------------------------------------------------------
+    # Interjection (T74.2) — silent witness chimes in.
+    # ------------------------------------------------------------------
+
+    def detect_interjection(
+        self,
+        *,
+        should_interject: bool,
+        reason: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one ``detect_interjection`` classifier response."""
+        payload: dict[str, Any] = {
+            "should_interject": should_interject,
+            "reason": reason,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    def detect_interjection_targeted(
+        self,
+        *,
+        targeted: bool,
+        target_id: str | None = None,
+        reason: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one targeted-interjection classifier response."""
+        payload: dict[str, Any] = {
+            "targeted": targeted,
+            "target_id": target_id,
+            "reason": reason,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Scene-close detector (T26).
+    # ------------------------------------------------------------------
+
+    def detect_scene_close(
+        self,
+        *,
+        should_close: bool,
+        reason: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one ``detect_scene_close`` classifier response."""
+        payload: dict[str, Any] = {
+            "should_close": should_close,
+            "reason": reason,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Event lifecycle (T52, T61) — per-turn transitions.
+    # ------------------------------------------------------------------
+
+    def detect_event_transitions(
+        self,
+        transitions: list[dict] | None = None,
+    ) -> "CannedQueue":
+        """Append one ``detect_event_transitions`` classifier response.
+
+        ``transitions`` is a list of ``{"event_id": ..., "new_status":
+        "active"|"completed"|"cancelled", "reason": ...}`` dicts. Pass
+        an empty list (or omit the argument) to assert that the call
+        ran but produced no transitions; pass ``None`` for an empty
+        list with the same shape.
+
+        Note: when no events are seeded, ``detect_event_transitions``
+        short-circuits without an LLM call — in that case do NOT append
+        this slot.
+        """
+        payload = {"transitions": transitions if transitions is not None else []}
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Per-POV scene summary (used after scene close).
+    # ------------------------------------------------------------------
+
+    def summarize_scene_pov(
+        self,
+        *,
+        summary: str,
+        knowledge_facts: list | None = None,
+        relationship_summary: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one per-POV scene-summary response.
+
+        Used by ``apply_scene_close_summary`` — one call per witness
+        once a scene closes.
+        """
+        payload: dict[str, Any] = {
+            "summary": summary,
+            "knowledge_facts": (
+                knowledge_facts if knowledge_facts is not None else []
+            ),
+            "relationship_summary": relationship_summary,
+        }
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Thread detection (Phase 3 §3.3).
+    # ------------------------------------------------------------------
+
+    def detect_threads(
+        self,
+        candidates: list[dict] | None = None,
+    ) -> "CannedQueue":
+        """Append one ``detect_threads`` classifier response.
+
+        ``candidates`` is a list of ``{"action": "open"|"update",
+        "title": ..., "summary": ..., "existing_thread_id": ...}`` dicts.
+        """
+        payload = {"candidates": candidates if candidates is not None else []}
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Meanwhile digest — narrative summary of what happened off-screen.
+    # ------------------------------------------------------------------
+
+    def meanwhile_digest(self, summary: str) -> "CannedQueue":
+        """Append one meanwhile-digest narrative response.
+
+        The digest service streams the digest as plain text (not JSON)
+        so this is a thin wrapper over ``narrative``/``raw`` for
+        readability at the call site.
+        """
+        self._queue.append(summary)
+        return self
+
+    # ------------------------------------------------------------------
+    # Significance scorer (background worker; rarely hit in unit tests
+    # but available for completeness).
+    # ------------------------------------------------------------------
+
+    def score_significance(
+        self,
+        *,
+        score: float = 0.0,
+        reason: str = "",
+        **rest: Any,
+    ) -> "CannedQueue":
+        """Append one significance-scoring classifier response."""
+        payload: dict[str, Any] = {"score": score, "reason": reason}
+        payload.update(rest)
+        self._queue.append(payload)
+        return self
+
+    # ------------------------------------------------------------------
+    # Build / introspection.
+    # ------------------------------------------------------------------
+
+    def build(self) -> list[str]:
+        """Return the flat ``list[str]`` queue for ``MockLLMClient``.
+
+        Dict items are JSON-encoded; string items are passed through
+        verbatim (so streaming responses retain their raw form).
+        """
+        out: list[str] = []
+        for item in self._queue:
+            if isinstance(item, str):
+                out.append(item)
+            else:
+                out.append(json.dumps(item))
+        return out
+
+    def __len__(self) -> int:
+        return len(self._queue)

tests/test_fixtures.py

@@ -0,0 +1,140 @@
+"""Sanity tests for :mod:`tests.fixtures` — the structured CannedQueue
+builder for ``MockLLMClient`` (T116).
+
+The builder is a thin shaping layer over JSON dicts; these tests pin
+the JSON shapes and the ``MockLLMClient`` round-trip so nothing
+silently regresses if a default field name or shape gets renamed.
+"""
+
+from __future__ import annotations
+
+import json
+
+import pytest
+
+from chat.llm.mock import MockLLMClient
+from tests.fixtures import CannedQueue
+
+
+def test_canned_queue_build_emits_expected_shapes():
+    """Each builder method emits the JSON shape its classifier consumer
+    expects. The narrative slot is a bare string (stream).
+    """
+    canned = (
+        CannedQueue()
+            .parse_turn(segments=[{"kind": "dialogue", "text": "hello"}])
+            .detect_addressee(addressee_id="bot_a", reason="host")
+            .narrative("Hi there.")
+            .state_update()
+            .state_update(affinity_delta=1, trust_delta=2)
+            .detect_interjection(should_interject=False, reason="calm")
+            .detect_event_transitions(
+                [{"event_id": "evt_1", "new_status": "active", "reason": "they arrived"}]
+            )
+            .detect_scene_close(should_close=False, reason="no signal")
+            .summarize_scene_pov(summary="BotA noticed the day winding down.")
+            .detect_threads(
+                [
+                    {
+                        "action": "open",
+                        "title": "Maya's job hunt",
+                        "summary": "Maya is looking for a new job",
+                        "existing_thread_id": None,
+                    }
+                ]
+            )
+            .build()
+    )
+
+    # All slots are strings (the MockLLMClient pops strings).
+    assert all(isinstance(slot, str) for slot in canned)
+    assert len(canned) == 10
+
+    # Slot 0: parse_turn — defaults intent="narrative".
+    parse = json.loads(canned[0])
+    assert parse["segments"] == [{"kind": "dialogue", "text": "hello"}]
+    assert parse["intent"] == "narrative"
+    assert parse["landing_state_hint"] == ""
+
+    # Slot 1: detect_addressee.
+    addr = json.loads(canned[1])
+    assert addr["addressee_id"] == "bot_a"
+    assert addr["confidence"] == "medium"
+    assert addr["reason"] == "host"
+
+    # Slot 2: narrative — bare string, NOT JSON.
+    assert canned[2] == "Hi there."
+    with pytest.raises(json.JSONDecodeError):
+        json.loads(canned[2])
+
+    # Slot 3: state_update with all defaults — zero deltas, no facts.
+    su0 = json.loads(canned[3])
+    assert su0 == {"affinity_delta": 0, "trust_delta": 0, "knowledge_facts": []}
+
+    # Slot 4: state_update with custom deltas.
+    su1 = json.loads(canned[4])
+    assert su1["affinity_delta"] == 1
+    assert su1["trust_delta"] == 2
+    assert su1["knowledge_facts"] == []
+
+    # Slot 5: detect_interjection.
+    interj = json.loads(canned[5])
+    assert interj == {"should_interject": False, "reason": "calm"}
+
+    # Slot 6: detect_event_transitions.
+    transitions = json.loads(canned[6])
+    assert transitions["transitions"][0]["event_id"] == "evt_1"
+    assert transitions["transitions"][0]["new_status"] == "active"
+
+    # Slot 7: detect_scene_close.
+    close = json.loads(canned[7])
+    assert close == {"should_close": False, "reason": "no signal"}
+
+    # Slot 8: summarize_scene_pov.
+    pov = json.loads(canned[8])
+    assert pov["summary"] == "BotA noticed the day winding down."
+    assert pov["knowledge_facts"] == []
+    assert pov["relationship_summary"] == ""
+
+    # Slot 9: detect_threads.
+    threads = json.loads(canned[9])
+    assert threads["candidates"][0]["action"] == "open"
+    assert threads["candidates"][0]["title"] == "Maya's job hunt"
+
+
+@pytest.mark.asyncio
+async def test_canned_queue_round_trips_through_mock_llm_client():
+    """Building a queue and feeding it to ``MockLLMClient`` produces the
+    same items back via ``generate`` (in order). This is the contract
+    every migrated test relies on.
+    """
+    canned = (
+        CannedQueue()
+            .parse_turn(segments=[{"kind": "dialogue", "text": "hi"}])
+            .narrative("Hello back.")
+            .state_update()
+            .build()
+    )
+    mock = MockLLMClient(canned=canned)
+
+    # generate() pops from the front.
+    parse_str = await mock.generate([], model="x")
+    assert json.loads(parse_str)["segments"] == [
+        {"kind": "dialogue", "text": "hi"}
+    ]
+
+    # The narrative slot is a raw string — generate returns it as-is.
+    narr_str = await mock.generate([], model="x")
+    assert narr_str == "Hello back."
+
+    # The state_update slot has zero-delta defaults.
+    su_str = await mock.generate([], model="x")
+    assert json.loads(su_str) == {
+        "affinity_delta": 0,
+        "trust_delta": 0,
+        "knowledge_facts": [],
+    }
+
+    # Queue fully drained.
+    with pytest.raises(IndexError):
+        await mock.generate([], model="x")

tests/test_turn_flow.py

@@ -22,6 +22,7 @@ from chat.db.connection import open_db
 from chat.eventlog.log import append_and_apply, append_event
 from chat.eventlog.projector import project
 from chat.llm.mock import MockLLMClient
+from tests.fixtures import CannedQueue
 
 
 @pytest.fixture
@@ -362,14 +363,20 @@ def test_single_bot_turn_no_guest_regression(app_state_setup, tmp_path):
     the chat has no guest, so ``detect_interjection`` is NOT invoked.
     Ends with one user_turn, one assistant_turn, two edge_updates, and a
     single ``memory_written``.
+
+    T116: migrated to :class:`tests.fixtures.CannedQueue` as a proof of
+    concept for the structured canned-queue builder.
     """
     _seed(tmp_path / "test.db")
-    canned_parse = json.dumps(
-        {"segments": [{"kind": "dialogue", "text": "hello"}]}
-    )
-    mock = _override_llm(
-        [canned_parse, "Hi there.", _zero_state(), _zero_state()]
+    canned = (
+        CannedQueue()
+            .parse_turn(segments=[{"kind": "dialogue", "text": "hello"}])
+            .narrative("Hi there.")
+            .state_update()
+            .state_update()
+            .build()
     )
+    mock = _override_llm(canned)
     try:
         response = app_state_setup.post(
             "/chats/chat_bot_a/turns", data={"prose": "hello"}
@@ -979,29 +986,25 @@ def test_turn_with_event_transition_appends_started_event(
             },
         )
 
-    canned_parse = json.dumps(
-        {"segments": [{"kind": "dialogue", "text": "they arrived"}]}
-    )
-    canned_event_decision = json.dumps(
-        {
-            "transitions": [
-                {
-                    "event_id": "evt_1",
-                    "new_status": "active",
-                    "reason": "they arrived",
-                }
-            ]
-        }
-    )
-    mock = _override_llm(
-        [
-            canned_parse,
-            "They walk in.",
-            _zero_state(),
-            _zero_state(),
-            canned_event_decision,
-        ]
+    # T116: migrated to :class:`tests.fixtures.CannedQueue`.
+    canned = (
+        CannedQueue()
+            .parse_turn(segments=[{"kind": "dialogue", "text": "they arrived"}])
+            .narrative("They walk in.")
+            .state_update()
+            .state_update()
+            .detect_event_transitions(
+                [
+                    {
+                        "event_id": "evt_1",
+                        "new_status": "active",
+                        "reason": "they arrived",
+                    }
+                ]
+            )
+            .build()
     )
+    mock = _override_llm(canned)
     try:
         response = app_state_setup.post(
             "/chats/chat_bot_a/turns", data={"prose": "they arrived"}
@@ -1155,18 +1158,23 @@ def test_turn_with_no_active_events_skips_classifier(app_state_setup, tmp_path):
     short-circuits without an LLM call (per T52). The canned queue must
     therefore have ZERO event-detection slots — same shape as the
     Phase 2 no-guest baseline.
+
+    T116: migrated to :class:`tests.fixtures.CannedQueue`.
     """
     _seed(tmp_path / "test.db")
 
-    canned_parse = json.dumps(
-        {"segments": [{"kind": "dialogue", "text": "hello"}]}
-    )
     # Only 4 slots: parse + narrative + 2 state-updates. NO extra slot for
     # event-detection — non-existent active_events causes the helper to
     # short-circuit before pulling from the queue.
-    mock = _override_llm(
-        [canned_parse, "Hi there.", _zero_state(), _zero_state()]
+    canned = (
+        CannedQueue()
+            .parse_turn(segments=[{"kind": "dialogue", "text": "hello"}])
+            .narrative("Hi there.")
+            .state_update()
+            .state_update()
+            .build()
     )
+    mock = _override_llm(canned)
     try:
         response = app_state_setup.post(
             "/chats/chat_bot_a/turns", data={"prose": "hello"}