fix: complete B-03/B-08/B-09 and add OMBRE_*_MODEL env vars

- decay_engine: keep activation_count as float (B-03); refresh local meta after auto_resolve so resolved_factor applies in the same cycle (B-08) - server.hold(): user-supplied valence/arousal now takes priority over analyze() output (B-09) - utils.load_config: support OMBRE_DEHYDRATION_MODEL (with OMBRE_MODEL alias) and OMBRE_EMBEDDING_MODEL - ENV_VARS.md: document new model env vars - tests/conftest.py: align fixture with spec-correct weights (time_proximity=1.5, content_weight=1.0) and feel subdir layout
2026-04-21 19:05:08 +08:00
parent d2d4b89715
commit b318e557b0
5 changed files with 158 additions and 12 deletions
--- a/ENV_VARS.md
+++ b/ENV_VARS.md
@@ -9,6 +9,9 @@
 | `OMBRE_HOOK_URL` | 否 | — | Breath/Dream Webhook 回调地址，留空则不推送 |
 | `OMBRE_HOOK_SKIP` | 否 | `false` | 设为 `true` 跳过 Webhook 推送 |
 | `OMBRE_DASHBOARD_PASSWORD` | 否 | — | 预设 Dashboard 访问密码；设置后覆盖文件存储的密码，首次访问不弹设置向导 |
+| `OMBRE_DEHYDRATION_MODEL` | 否 | `deepseek-chat` | 脱水/打标/合并/拆分用的 LLM 模型名（覆盖 `dehydration.model`） |
+| `OMBRE_MODEL` | 否 | — | `OMBRE_DEHYDRATION_MODEL` 的别名（前者优先） |
+| `OMBRE_EMBEDDING_MODEL` | 否 | `gemini-embedding-001` | 向量嵌入模型名（覆盖 `embedding.model`） |

 ## 说明

--- a/decay_engine.py
+++ b/decay_engine.py
@@ -112,7 +112,7 @@ class DecayEngine:
            return 50.0

        importance = max(1, min(10, int(metadata.get("importance", 5))))
-        activation_count = max(1, int(metadata.get("activation_count", 1)))
+        activation_count = max(1.0, float(metadata.get("activation_count", 1)))

        # --- Days since last activation ---
        last_active_str = metadata.get("last_active", metadata.get("created", ""))
@@ -215,6 +215,7 @@ class DecayEngine:
                if imp <= 4 and days_since > 30:
                    try:
                        await self.bucket_mgr.update(bucket["id"], resolved=True)
+                        meta["resolved"] = True  # refresh local meta so resolved_factor applies this cycle
                        auto_resolved += 1
                        logger.info(
                            f"Auto-resolved / 自动结案: "
--- a/server.py
+++ b/server.py
@@ -790,11 +790,16 @@ async def hold(
        }

    domain = analysis["domain"]
-    valence = analysis["valence"]
-    arousal = analysis["arousal"]
+    auto_valence = analysis["valence"]
+    auto_arousal = analysis["arousal"]
    auto_tags = analysis["tags"]
    suggested_name = analysis.get("suggested_name", "")

+    # --- User-supplied valence/arousal takes priority over analyze() result ---
+    # --- 用户显式传入的 valence/arousal 优先，analyze() 结果作为 fallback ---
+    final_valence = valence if 0 <= valence <= 1 else auto_valence
+    final_arousal = arousal if 0 <= arousal <= 1 else auto_arousal
+
    all_tags = list(dict.fromkeys(auto_tags + extra_tags))

    # --- Pinned buckets bypass merge and are created directly in permanent dir ---
@@ -805,8 +810,8 @@ async def hold(
            tags=all_tags,
            importance=10,
            domain=domain,
-            valence=valence,
-            arousal=arousal,
+            valence=final_valence,
+            arousal=final_arousal,
            name=suggested_name or None,
            bucket_type="permanent",
            pinned=True,
@@ -823,8 +828,8 @@ async def hold(
        tags=all_tags,
        importance=importance,
        domain=domain,
-        valence=valence,
-        arousal=arousal,
+        valence=final_valence,
+        arousal=final_arousal,
        name=suggested_name,
    )

--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -14,6 +14,7 @@ import pytest
 import asyncio
 from datetime import datetime, timedelta
 from pathlib import Path
+from unittest.mock import AsyncMock, MagicMock, patch

 # Ensure project root importable
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
@@ -21,23 +22,28 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

@pytest.fixture
 def test_config(tmp_path):
-    """Minimal config pointing to a temp directory."""
+    """
+    Minimal config pointing to a temp directory.
+    Uses spec-correct scoring weights (after B-05, B-06, B-07 fixes).
+    """
    buckets_dir = str(tmp_path / "buckets")
    os.makedirs(os.path.join(buckets_dir, "permanent"), exist_ok=True)
    os.makedirs(os.path.join(buckets_dir, "dynamic"), exist_ok=True)
    os.makedirs(os.path.join(buckets_dir, "archive"), exist_ok=True)
-    os.makedirs(os.path.join(buckets_dir, "dynamic", "feel"), exist_ok=True)
+    os.makedirs(os.path.join(buckets_dir, "feel"), exist_ok=True)

    return {
        "buckets_dir": buckets_dir,
+        "merge_threshold": 75,
        "matching": {"fuzzy_threshold": 50, "max_results": 10},
        "wikilink": {"enabled": False},
+        # Spec-correct weights (post B-05/B-06/B-07 fix)
        "scoring_weights": {
            "topic_relevance": 4.0,
            "emotion_resonance": 2.0,
-            "time_proximity": 2.5,
+            "time_proximity": 1.5,   # spec: 1.5 (was 2.5 in buggy code)
            "importance": 1.0,
-            "content_weight": 3.0,
+            "content_weight": 1.0,   # spec: 1.0 (was 3.0 in buggy code)
        },
        "decay": {
            "lambda": 0.05,
@@ -46,7 +52,7 @@ def test_config(tmp_path):
            "emotion_weights": {"base": 1.0, "arousal_boost": 0.8},
        },
        "dehydration": {
-            "api_key": os.environ.get("OMBRE_API_KEY", ""),
+            "api_key": os.environ.get("OMBRE_API_KEY", "test-key"),
            "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
            "model": "gemini-2.5-flash-lite",
        },
@@ -54,10 +60,49 @@ def test_config(tmp_path):
            "api_key": os.environ.get("OMBRE_API_KEY", ""),
            "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
            "model": "gemini-embedding-001",
+            "enabled": False,
        },
    }


+@pytest.fixture
+def buggy_config(tmp_path):
+    """
+    Config using the PRE-FIX (buggy) scoring weights.
+    Used in regression tests to document the old broken behaviour.
+    """
+    buckets_dir = str(tmp_path / "buckets")
+    for d in ["permanent", "dynamic", "archive", "feel"]:
+        os.makedirs(os.path.join(buckets_dir, d), exist_ok=True)
+
+    return {
+        "buckets_dir": buckets_dir,
+        "merge_threshold": 75,
+        "matching": {"fuzzy_threshold": 50, "max_results": 10},
+        "wikilink": {"enabled": False},
+        # Buggy weights (before B-05/B-06/B-07 fixes)
+        "scoring_weights": {
+            "topic_relevance": 4.0,
+            "emotion_resonance": 2.0,
+            "time_proximity": 2.5,   # B-06: was too high
+            "importance": 1.0,
+            "content_weight": 3.0,   # B-07: was too high
+        },
+        "decay": {
+            "lambda": 0.05,
+            "threshold": 0.3,
+            "check_interval_hours": 24,
+            "emotion_weights": {"base": 1.0, "arousal_boost": 0.8},
+        },
+        "dehydration": {
+            "api_key": "",
+            "base_url": "https://example.com",
+            "model": "test-model",
+        },
+        "embedding": {"enabled": False, "api_key": ""},
+    }
+
+
@pytest.fixture
 def bucket_mgr(test_config):
    from bucket_manager import BucketManager
@@ -68,3 +113,85 @@ def bucket_mgr(test_config):
 def decay_eng(test_config, bucket_mgr):
    from decay_engine import DecayEngine
    return DecayEngine(test_config, bucket_mgr)
+
+
+@pytest.fixture
+def mock_dehydrator():
+    """
+    Mock Dehydrator that returns deterministic results without any API calls.
+    Suitable for integration tests that do not test LLM behaviour.
+    """
+    dh = MagicMock()
+
+    async def fake_dehydrate(content, meta=None):
+        return f"[摘要] {content[:60]}"
+
+    async def fake_analyze(content):
+        return {
+            "domain": ["学习"],
+            "valence": 0.7,
+            "arousal": 0.5,
+            "tags": ["测试"],
+            "suggested_name": "测试记忆",
+        }
+
+    async def fake_merge(old, new):
+        return old + "\n---合并---\n" + new
+
+    async def fake_digest(content):
+        return [
+            {
+                "name": "条目一",
+                "content": content[:100],
+                "domain": ["日常"],
+                "valence": 0.6,
+                "arousal": 0.4,
+                "tags": ["测试"],
+                "importance": 5,
+            }
+        ]
+
+    dh.dehydrate = AsyncMock(side_effect=fake_dehydrate)
+    dh.analyze = AsyncMock(side_effect=fake_analyze)
+    dh.merge = AsyncMock(side_effect=fake_merge)
+    dh.digest = AsyncMock(side_effect=fake_digest)
+    dh.api_available = True
+    return dh
+
+
+@pytest.fixture
+def mock_embedding_engine():
+    """Mock EmbeddingEngine that returns empty results — no network calls."""
+    ee = MagicMock()
+    ee.enabled = False
+    ee.generate_and_store = AsyncMock(return_value=None)
+    ee.search_similar = AsyncMock(return_value=[])
+    ee.delete_embedding = AsyncMock(return_value=True)
+    ee.get_embedding = AsyncMock(return_value=None)
+    return ee
+
+
+async def _write_bucket_file(bucket_mgr, content, **kwargs):
+    """
+    Helper: create a bucket and optionally patch its frontmatter fields.
+    Accepts extra kwargs like created/last_active/resolved/digested/pinned.
+    Returns bucket_id.
+    """
+    import frontmatter as fm
+
+    direct_fields = {
+        k: kwargs.pop(k) for k in list(kwargs.keys())
+        if k in ("created", "last_active", "resolved", "digested", "activation_count")
+    }
+
+    bid = await bucket_mgr.create(content=content, **kwargs)
+
+    if direct_fields:
+        fpath = bucket_mgr._find_bucket_file(bid)
+        post = fm.load(fpath)
+        for k, v in direct_fields.items():
+            post[k] = v
+        with open(fpath, "w", encoding="utf-8") as f:
+            f.write(fm.dumps(post))
+
+    return bid
--- a/utils.py
+++ b/utils.py
@@ -98,6 +98,16 @@ def load_config(config_path: str = None) -> dict:
    if env_buckets_dir:
        config["buckets_dir"] = env_buckets_dir

+    # OMBRE_DEHYDRATION_MODEL (with OMBRE_MODEL alias) overrides dehydration.model
+    env_dehy_model = os.environ.get("OMBRE_DEHYDRATION_MODEL", "") or os.environ.get("OMBRE_MODEL", "")
+    if env_dehy_model:
+        config.setdefault("dehydration", {})["model"] = env_dehy_model
+
+    # OMBRE_EMBEDDING_MODEL overrides embedding.model
+    env_embed_model = os.environ.get("OMBRE_EMBEDDING_MODEL", "")
+    if env_embed_model:
+        config.setdefault("embedding", {})["model"] = env_embed_model
+
    # --- Ensure bucket storage directories exist ---
    # --- 确保记忆桶存储目录存在 ---
    buckets_dir = config["buckets_dir"]