feat: give the curator continuous context and durable idea history

tests/test_api.py

@@ -82,9 +82,10 @@ def test_login_isolation_roles_and_debug_privacy(
             headers=WRITE_HEADERS,
         )
         assert member_fragment.status_code == 201
-        assert [item["content"] for item in client.get("/api/fragments").json()["items"]] == [
-            "用户二的记录"
-        ]
+        assert [
+            item["content"]
+            for item in client.get("/api/fragments").json()["items"]
+        ] == ["用户二的记录"]
         assert client.get("/api/admin/overview").status_code == 403
 
         run_id = database.start_agent_run(
@@ -105,9 +106,10 @@ def test_login_isolation_roles_and_debug_privacy(
         )
 
         client.cookies.set(COOKIE_NAME, admin_cookie)
-        assert [item["content"] for item in client.get("/api/fragments").json()["items"]] == [
-            "管理员的记录"
-        ]
+        assert [
+            item["content"]
+            for item in client.get("/api/fragments").json()["items"]
+        ] == ["管理员的记录"]
         redacted = client.get(f"/api/admin/runs/{run_id}").json()
         assert redacted["fragment"]["content_visible"] is False
         assert redacted["events"][-1]["payload"] == {
@@ -127,3 +129,44 @@ def test_login_isolation_roles_and_debug_privacy(
         visible = client.get(f"/api/admin/runs/{run_id}").json()
         assert visible["fragment"]["content_visible"] is True
         assert visible["fragment"]["content"] == "用户二的记录"
+
+        retry_error = RuntimeError("tool loop exceeded")
+        database.finish_agent_run(
+            run_id,
+            status="error",
+            duration_ms=100,
+            attempt_count=1,
+            model_rounds=4,
+            tool_calls=4,
+            search_calls=3,
+            inspection_calls=1,
+            input_tokens=400,
+            output_tokens=80,
+            reasoning_tokens=60,
+            cached_tokens=0,
+            error=retry_error,
+        )
+        database.set_fragment_status(
+            member_fragment.json()["id"], "error", str(retry_error)
+        )
+        queued: list[str] = []
+        monkeypatch.setattr(main.curator, "enqueue", queued.append)
+
+        client.cookies.set(COOKIE_NAME, member_cookie)
+        assert client.post(
+            f"/api/admin/runs/{run_id}/retry",
+            headers=WRITE_HEADERS,
+        ).status_code == 403
+
+        client.cookies.set(COOKIE_NAME, admin_cookie)
+        retried = client.post(
+            f"/api/admin/runs/{run_id}/retry",
+            headers=WRITE_HEADERS,
+        )
+        assert retried.status_code == 202
+        assert retried.json() == {"queued": True}
+        assert queued == [member_fragment.json()["id"]]
+        assert client.post(
+            f"/api/admin/runs/{run_id}/retry",
+            headers=WRITE_HEADERS,
+        ).status_code == 409

tests/test_curator.py

@@ -0,0 +1,66 @@
+import asyncio
+from pathlib import Path
+from types import SimpleNamespace
+
+from agents.exceptions import MaxTurnsExceeded
+
+from app.config import Settings, UserSeed
+from app.curator import Curator, Runner
+from app.db import Database
+
+
+def test_tool_loop_uses_no_tool_convergence_repair(
+    tmp_path: Path, monkeypatch
+):
+    admin = UserSeed(
+        id="admin",
+        label="管理员",
+        role="admin",
+        access_key_hash="unused",
+    )
+    database = Database(tmp_path / "repair.sqlite3")
+    database.initialize([admin])
+    fragment = database.create_fragment("admin", "一个需要收敛的念头")
+    settings = Settings(
+        data_dir=tmp_path,
+        database_path=tmp_path / "repair.sqlite3",
+        users=(admin,),
+        session_secret="unused",
+        deepseek_api_key="test-key",
+        deepseek_base_url="https://api.deepseek.com",
+        deepseek_model="deepseek-v4-pro",
+        cookie_secure=False,
+        auth_disabled=True,
+    )
+    calls = 0
+
+    async def fake_run(*args, **kwargs):
+        nonlocal calls
+        calls += 1
+        if calls == 1:
+            raise MaxTurnsExceeded("Max turns (6) exceeded")
+        assert kwargs["max_turns"] == 2
+        assert args[0].tools == []
+        return SimpleNamespace(
+            final_output=(
+                '{"standalone":true,"reasoning_note":"暂时独立保留",'
+                '"assessments":[]}'
+            )
+        )
+
+    monkeypatch.setattr(Runner, "run", fake_run)
+    curator = Curator(database, settings)
+
+    asyncio.run(curator.analyze(fragment["id"]))
+
+    assert calls == 2
+    assert database.get_fragment(fragment["id"], "admin")[
+        "analysis_status"
+    ] == "done"
+    run = database.list_agent_runs(1)[0]
+    events = database.list_agent_events(run["id"])
+    assert run["status"] == "success"
+    assert run["attempt_count"] == 2
+    assert "convergence_repair_started" in [
+        event["event_type"] for event in events
+    ]

tests/test_db.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 
 from app.config import UserSeed
+from app.curator import _rank_ideas, build_curator_prompt
 from app.db import Database
 
 
@@ -97,6 +98,105 @@ def test_apply_assessment_builds_trajectory(tmp_path: Path):
     assert idea["maturity"] == 46
 
 
+def test_curator_prompt_contains_recent_continuity_and_idea_catalog(
+    tmp_path: Path,
+):
+    db = database(tmp_path)
+    first = db.create_fragment(
+        ADMIN.id,
+        "我先让 AI 完成综述，接下来会抽取几个感兴趣的地方。",
+    )
+    db.apply_assessments(ADMIN.id, first["id"], [assessment()])
+    current = db.create_fragment(
+        ADMIN.id,
+        "我识别出了两个新的认知，第一点让我耳目一新。",
+    )
+    ideas, fragments = db.curator_context(ADMIN.id)
+
+    prompt = build_curator_prompt(current, ideas, fragments)
+
+    assert "我先让 AI 完成综述" in prompt
+    assert "我识别出了两个新的认知" in prompt
+    assert "无分类的笔记入口" in prompt
+    assert "不要要求用户显式建立会话" in prompt
+
+
+def test_delayed_reanalysis_keeps_later_input_out_of_prior_context(
+    tmp_path: Path,
+):
+    db = database(tmp_path)
+    previous = db.create_fragment(ADMIN.id, "当时真正的上文")
+    target = db.create_fragment(ADMIN.id, "后来需要重新整理的这一条")
+    future = db.create_fragment(ADMIN.id, "这句话发生在目标片段之后")
+    timeline = (
+        (previous, "2026-07-28T10:00:00.000+00:00"),
+        (target, "2026-07-28T10:10:00.000+00:00"),
+        (future, "2026-07-28T10:20:00.000+00:00"),
+    )
+    with db.connect() as connection:
+        for fragment, created_at in timeline:
+            fragment["created_at"] = created_at
+            connection.execute(
+                "UPDATE fragments SET created_at = ? WHERE id = ?",
+                (created_at, fragment["id"]),
+            )
+    ideas, fragments = db.curator_context(ADMIN.id)
+
+    prompt = build_curator_prompt(target, ideas, fragments)
+    recent_section = prompt.split("<recent_context>", 1)[1].split(
+        "</recent_context>", 1
+    )[0]
+    later_section = prompt.split("<later_context>", 1)[1].split(
+        "</later_context>", 1
+    )[0]
+
+    assert previous["content"] in recent_section
+    assert future["content"] not in recent_section
+    assert future["content"] in later_section
+    assert "延迟重整" in prompt
+
+
+def test_idea_search_falls_back_to_recent_catalog():
+    idea = {
+        "id": "idea-one",
+        "title": "先综述再深入",
+        "summary": "一种理解策略",
+        "position": "正在实践",
+        "tension": "可靠性",
+        "trajectory": "从原则走向实践",
+        "updated_at": "2026-07-28",
+        "recent_fragments": [],
+    }
+
+    candidates, fallback = _rank_ideas(
+        [idea], "agent architecture long task reliability"
+    )
+
+    assert fallback is True
+    assert candidates == [idea]
+
+
+def test_idea_versions_preserve_complete_state(tmp_path: Path):
+    db = database(tmp_path)
+    first = db.create_fragment(ADMIN.id, "第一条原始证据")
+    db.apply_assessments(ADMIN.id, first["id"], [assessment(maturity=30)])
+    idea = db.list_ideas(ADMIN.id)[0]
+    first_version = db.get_idea(ADMIN.id, idea["id"])["snapshots"][-1]
+
+    assert first_version["title"] == "无分类的笔记入口"
+    assert first_version["summary"] == "先保留念头，再让结构在后台形成。"
+    assert first_version["confidence"] == 0.76
+    assert first_version["change_kind"] == "analysis"
+    assert first_version["fragment_ids"] == [first["id"]]
+
+    db.update_idea_override(ADMIN.id, idea["id"], 61)
+    versions = db.get_idea(ADMIN.id, idea["id"])["snapshots"]
+
+    assert versions[-1]["change_kind"] == "manual_calibration"
+    assert versions[-1]["maturity_override"] == 61
+    assert versions[-1]["fragment_ids"] == [first["id"]]
+
+
 def test_manual_position_is_authoritative(tmp_path: Path):
     db = database(tmp_path)
     fragment = db.create_fragment(ADMIN.id, "一个想法")
@@ -188,3 +288,41 @@ def test_agent_run_records_metrics_and_events(tmp_path: Path):
         "tool_search_ideas",
     ]
     assert overview["last_24h"]["success_rate"] == 100
+
+
+def test_failed_agent_run_can_be_safely_requeued(tmp_path: Path):
+    db = database(tmp_path)
+    fragment = db.create_fragment(ADMIN.id, "需要重新整理")
+    run_id = db.start_agent_run(
+        ADMIN.id,
+        fragment["id"],
+        "deepseek-v4-pro",
+        "prompt.v2",
+        "high",
+    )
+    error = RuntimeError("temporary failure")
+    db.finish_agent_run(
+        run_id,
+        status="error",
+        duration_ms=100,
+        attempt_count=1,
+        model_rounds=1,
+        tool_calls=0,
+        search_calls=0,
+        inspection_calls=0,
+        input_tokens=10,
+        output_tokens=2,
+        reasoning_tokens=1,
+        cached_tokens=0,
+        error=error,
+    )
+    db.set_fragment_status(fragment["id"], "error", str(error))
+
+    retry = db.prepare_agent_retry(run_id)
+
+    assert retry == {
+        "user_id": ADMIN.id,
+        "fragment_id": fragment["id"],
+    }
+    assert db.get_fragment(fragment["id"], ADMIN.id)["analysis_status"] == "pending"
+    assert db.prepare_agent_retry(run_id) is None