feat: auto-project-detection + project stages

Three changes:

1. ABB-Space registered as a lead project with stage=lead in
   Trusted Project State. Projects now have lifecycle awareness
   (lead/proposition vs active contract vs completed).

2. Extraction no longer drops unregistered project tags. When the
   LLM extractor sees a conversation about a project not in the
   registry, it keeps the model's tag on the candidate instead of
   falling back to empty. This enables auto-detection of new
   projects/leads from organic conversations. The nightly pipeline
   surfaces these candidates for triage, where the operator sees
   "hey, there's a new project called X" and can decide whether
   to register it.

3. Extraction prompt updated to tell the model: "If the conversation
   discusses a project NOT in the known list, still tag it — the
   system will auto-detect it." This removes the artificial ceiling
   that prevented new project discovery.

Updated Case D test: unregistered + unscoped now keeps the model's
tag instead of dropping to empty.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/batch_llm_extract_live.py

@@ -35,7 +35,7 @@ SYSTEM_PROMPT = """You extract durable memory candidates from LLM conversation t
 
 AtoCore stores two kinds of knowledge:
 
-A. PROJECT-SPECIFIC: applied decisions, constraints, and architecture for a named project (p04-gigabit, p05-interferometer, p06-polisher, atomizer-v2, atocore). These stay scoped to one project.
+A. PROJECT-SPECIFIC: applied decisions, constraints, and architecture for a named project. Known projects include p04-gigabit, p05-interferometer, p06-polisher, atomizer-v2, atocore, abb-space. If the conversation discusses a project NOT in this list, still tag it with the project name you identify — the system will auto-detect it as a new project or lead.
 
 B. DOMAIN KNOWLEDGE: generalizable engineering insight that was EARNED through project work and is reusable across projects. Tag these with a domain instead of a project.
 
@@ -213,9 +213,11 @@ def parse_candidates(raw, interaction_project):
         model_project = str(item.get("project") or "").strip()
         domain = str(item.get("domain") or "").strip().lower()
         # R9 trust hierarchy: interaction scope always wins when set.
+        # For unscoped interactions, keep model's project tag even if
+        # unregistered — the system will detect new projects/leads.
         if interaction_project:
             project = interaction_project
-        elif model_project and model_project in _known_projects:
+        elif model_project:
             project = model_project
         else:
             project = ""

src/atocore/memory/extractor_llm.py

@@ -74,7 +74,7 @@ _SYSTEM_PROMPT = """You extract durable memory candidates from LLM conversation
 
 AtoCore stores two kinds of knowledge:
 
-A. PROJECT-SPECIFIC: applied decisions, constraints, and architecture for a named project (p04-gigabit, p05-interferometer, p06-polisher, atomizer-v2, atocore). These stay scoped to one project.
+A. PROJECT-SPECIFIC: applied decisions, constraints, and architecture for a named project. Known projects include p04-gigabit, p05-interferometer, p06-polisher, atomizer-v2, atocore, abb-space. If the conversation discusses a project NOT in this list, still tag it with the project name you identify — the system will auto-detect it as a new project or lead.
 
 B. DOMAIN KNOWLEDGE: generalizable engineering insight that was EARNED through project work and is reusable across projects. Tag these with a domain instead of a project.
 
@@ -291,9 +291,20 @@ def _parse_candidates(raw_output: str, interaction: Interaction) -> list[MemoryC
 
                 registered_ids = {p.project_id for p in load_project_registry()}
                 resolved = resolve_project_name(model_project)
-                project = resolved if resolved in registered_ids else ""
+                if resolved in registered_ids:
+                    project = resolved
+                else:
+                    # Unregistered project — keep the model's tag so
+                    # auto-triage / the operator can see it and decide
+                    # whether to register it as a new project or lead.
+                    project = model_project
+                    log.info(
+                        "unregistered_project_detected",
+                        model_project=model_project,
+                        interaction_id=interaction.id,
+                    )
             except Exception:
-                project = ""
+                project = model_project if model_project else ""
         else:
             project = ""
         domain = str(item.get("domain") or "").strip().lower()

tests/test_extractor_llm.py

@@ -130,17 +130,17 @@ def test_case_c_unregistered_model_scoped_interaction(tmp_data_dir, project_regi
     assert result[0].project == "p06-polisher"
 
 
-def test_case_d_unregistered_model_unscoped_interaction(tmp_data_dir, project_registry):
+def test_case_d_unregistered_model_unscoped_keeps_tag(tmp_data_dir, project_registry):
     """Case D: model returns unregistered project, interaction is unscoped.
-    Falls to empty (not the hallucinated name)."""
+    Keeps the model's tag for auto-project-detection (new behavior)."""
     from atocore.models.database import init_db
     init_db()
     project_registry(("p06-polisher", ["p06"]))
-    raw = '[{"type": "project", "content": "x", "project": "fake-project-99"}]'
+    raw = '[{"type": "project", "content": "x", "project": "new-lead-project"}]'
     interaction = _make_interaction()
     interaction.project = ""
     result = _parse_candidates(raw, interaction)
-    assert result[0].project == ""
+    assert result[0].project == "new-lead-project"
 
 
 def test_case_e_matching_model_and_interaction(tmp_data_dir, project_registry):