plugin/hooks/scribe_prior_art.sh

@@ -258,14 +258,22 @@ fi
 # the sync nudge when the recorded file itself is edited later.
 state_dir="${TMPDIR:-/tmp}/scribe-priorart"
 mkdir -p "$state_dir" 2>/dev/null || true
+#
+# A THIRD channel (#2900): the ledger's derive arm names a duplicate family
+# (a derive group id) or a canon elsewhere (`canon:<snippet_id>`) for the
+# shapes being written. Keyed by that token, not a note id, so it dedups on
+# its own file and a family is named once per session, not at every edit.
 idfile=""
 syncfile=""
+derivefile=""
 exclude_q=""
 sync_exclude_q=""
+derive_exclude_q=""
 if [ -n "$session_id" ]; then
   safe_sid=$(printf '%s' "$session_id" | tr -c 'A-Za-z0-9._-' '_')
   idfile="$state_dir/${safe_sid}.ids"
   syncfile="$state_dir/${safe_sid}.sync.ids"
+  derivefile="$state_dir/${safe_sid}.derive.ids"
   if [ -f "$idfile" ]; then
     seen=$(tr '\n' ',' < "$idfile" 2>/dev/null | sed 's/,$//')
     [ -n "$seen" ] && exclude_q="&exclude_ids=${seen}"
@@ -274,13 +282,17 @@ if [ -n "$session_id" ]; then
     sync_seen=$(tr '\n' ',' < "$syncfile" 2>/dev/null | sed 's/,$//')
     [ -n "$sync_seen" ] && sync_exclude_q="&exclude_sync_ids=${sync_seen}"
   fi
+  if [ -f "$derivefile" ]; then
+    derive_seen=$(tr '\n' ',' < "$derivefile" 2>/dev/null | sed 's/,$//' | jq -sRr '@uri' 2>/dev/null) || derive_seen=""
+    [ -n "$derive_seen" ] && derive_exclude_q="&exclude_derive=${derive_seen}"
+  fi
 fi
 
 # `|| true`, not `|| exit 0`: an unreachable instance must not discard a local
 # finding that needed no instance to produce.
 body=$(curl -fsS --max-time 5 \
   -H "Authorization: Bearer ${token}" \
-  "${url%/}/api/plugin/prior-art?path=${path_enc}&code=${code_enc}${repo_q}${exclude_q}${sync_exclude_q}${shapes_q}" 2>/dev/null) || body=""
+  "${url%/}/api/plugin/prior-art?path=${path_enc}&code=${code_enc}${repo_q}${exclude_q}${sync_exclude_q}${derive_exclude_q}${shapes_q}" 2>/dev/null) || body=""
 
 context=""
 if [ -n "$body" ]; then
@@ -295,6 +307,9 @@ if [ -n "$body" ]; then
     if [ -n "$syncfile" ]; then
       printf '%s' "$body" | jq -r '(.sync_note_ids // [])[]?' 2>/dev/null >> "$syncfile" || true
     fi
+    if [ -n "$derivefile" ]; then
+      printf '%s' "$body" | jq -r '(.derive_keys // [])[]?' 2>/dev/null >> "$derivefile" || true
+    fi
   fi
 fi
 

src/scribe/routes/plugin.py

@@ -129,6 +129,10 @@ async def write_path_prior_art():
                              surfaced. A separate channel on purpose: a reuse
                              hint shown early must not suppress the record-sync
                              nudge when the recorded file is edited later.
+        exclude_derive (opt) — comma-separated derive keys (a derive group id
+                             or `canon:<snippet_id>`) already named this
+                             session by the ledger arm (#2900); its own
+                             channel, like the two above.
         shapes (opt)       — comma-separated `kind:name` definitions the hook
                              found in (or enclosing) the payload, kind being
                              css|sym. The shape ledger's write-path feed
@@ -144,6 +148,9 @@ async def write_path_prior_art():
     project_id, repo, _unbound = await _project_scope()
     exclude_ids = _int_list(request.args.get("exclude_ids"))
     exclude_sync_ids = _int_list(request.args.get("exclude_sync_ids"))
+    exclude_derive = [
+        p.strip() for p in (request.args.get("exclude_derive") or "").split(",") if p.strip()
+    ]
     shapes = _parse_shapes(request.args.get("shapes") or "")
     api_key = getattr(g, "api_key", None)
     may_stamp = api_key is None or getattr(api_key, "scope", "") == "write"
@@ -153,6 +160,7 @@ async def write_path_prior_art():
         exclude_ids=exclude_ids, exclude_sync_ids=exclude_sync_ids,
         stamp_shapes=shapes if may_stamp else None,
         repo_key=repo_bindings_svc.normalize_repo_key(repo) if repo else "",
+        exclude_derive=exclude_derive,
     )
     return jsonify(result)
 

src/scribe/services/plugin_context.py

@@ -706,6 +706,7 @@ async def build_write_path_hint(
     exclude_sync_ids: list[int] | None = None,
     stamp_shapes: list[tuple[str, str]] | None = None,
     repo_key: str = "",
+    exclude_derive: list[str] | None = None,
 ) -> dict:
     """Prior-art hint for the plugin's PreToolUse hook on Write/Edit.
 
@@ -765,7 +766,7 @@ async def build_write_path_hint(
     """
     cfg = await get_writepath_config(user_id)
     empty = {"context": "", "note_ids": [], "sync_note_ids": [], "config": cfg,
-             "stamped": [], "divergence": []}
+             "stamped": [], "divergence": [], "derive": [], "derive_keys": []}
     path = (path or "").strip()
     if not cfg["enabled"] or not path:
         return empty
@@ -935,7 +936,20 @@ async def build_write_path_hint(
             )
         except Exception:
             logger.warning("write-time divergence check failed", exc_info=True)
-    if not synced and not menu and not stamped and not divergence:
+    # The in-band DERIVE check (#2900): the ledger's own knowledge of the
+    # names being written — a duplicate family with no canon, or a canon
+    # recorded elsewhere. This is the arm the by-name local grep could not
+    # be: it knows whether the other copies are canon or stray. Keyed per
+    # session (`exclude_derive`) so a family is named once, not per edit.
+    derive: list[dict] = []
+    if stamp_shapes and project_id:
+        try:
+            found = await shape_ledger_svc.write_time_derive(project_id, path, stamp_shapes)
+            skip = set(exclude_derive or [])
+            derive = [d for d in found if d.get("key") not in skip]
+        except Exception:
+            logger.warning("write-time derive check failed", exc_info=True)
+    if not synced and not menu and not stamped and not divergence and not derive:
         return empty
 
     owners = await owner_names_for({
@@ -1003,6 +1017,8 @@ async def build_write_path_hint(
         lines.append(_stamp_line(path, stamped))
     if divergence:
         lines.append(_divergence_line(path, divergence))
+    if derive:
+        lines.append(_derive_line(path, derive))
 
     # Split by arm, which is the whole reason this table exists. The place arm
     # carries no score and so has no home in retrieval_logs; before #2085 a
@@ -1027,9 +1043,40 @@ async def build_write_path_hint(
         "config": cfg,
         "stamped": stamped,
         "divergence": divergence,
+        "derive": derive,
+        "derive_keys": [d["key"] for d in derive],
     }
 
 
+def _derive_line(path: str, derive: list[dict]) -> str:
+    """The ledger's word on the names being written (#2900): a duplicate
+    family to derive, or a canon to reuse — said at the write."""
+    parts = []
+    for d in derive:
+        if d.get("canon"):
+            c = d["canon"]
+            parts.append(
+                f"`{c['label']}` is canon — snippet #{c['snippet_id']} at `{c['path']}`; "
+                "pull it and reuse, don't redefine"
+            )
+            continue
+        f = d["family"]
+        how = "identical body" if f.get("identical") else "same name defined"
+        files = ", ".join(f"`{x}`" for x in f.get("files") or [])
+        more = f.get("file_count", 0) - len(f.get("files") or [])
+        if more > 0:
+            files += f" +{more} more"
+        parts.append(
+            f"`{f['label']}` is a duplicate family with no canon — {how} in "
+            f"{f.get('file_count', 0)} other file(s): {files}; derive it now: "
+            "record the canon (create_snippet) and make the copies instances "
+            "(classify_shapes) — or, if these are convention not copies, "
+            "`classify_shapes(..., status=\"exempt\", reason_code=\"convention-plumbing\")` "
+            "dismisses the family — rather than adding another copy"
+        )
+    return f"> Shape ledger at `{path}`: " + "; ".join(parts) + "."
+
+
 def _divergence_line(path: str, divergence: list[dict]) -> str:
     """Button B where button A is canon — named at the write (#2793)."""
     parts = [

src/scribe/services/shape_ledger.py

@@ -1594,6 +1594,75 @@ async def write_time_divergence(
     return out
 
 
+# How many other files a family line names before "…" — enough to go look,
+# not a wall.
+_DERIVE_FILES_SHOWN = 4
+
+
+async def write_time_derive(
+    project_id: int, path: str, shapes: list[tuple[str, str]]
+) -> list[dict]:
+    """The in-band DERIVE check (#2900): for each (kind, name) the hook
+    named at ``path``, what the ledger already knows about that name
+    elsewhere in the project —
+
+      family  the name sits in a derive-first group (identical body in N
+              files, or the same name in ≥3): "this is a known duplicate
+              family with no canon — derive it now, don't add a copy";
+      canon   a `canonical` row of that name at another path: "this is
+              canon #N at <path> — reuse, don't redefine".
+
+    Only for shapes not yet judged at ``path`` (a judged shape is not
+    re-litigated at every edit), never for the canon's own file. Returns
+    [{symbol, kind, key, family?|canon?}] — `key` is the dedup token the
+    hook keeps per session (the group id, or canon:<snippet_id>)."""
+    wanted = {(k, _norm_symbol(n)): n for k, n in shapes if n}
+    if not wanted:
+        return []
+    async with async_session() as session:
+        rows = (
+            await session.execute(
+                select(CodeShape).where(
+                    CodeShape.project_id == project_id,
+                    CodeShape.vanished_at.is_(None),
+                    CodeShape.symbol.in_({norm for (_k, norm) in wanted}),
+                )
+            )
+        ).scalars().all()
+    out: list[dict] = []
+    for (kind, norm), name in wanted.items():
+        same = [r for r in rows if r.kind == kind and _norm_symbol(r.symbol) == norm]
+        here = next((r for r in same if r.path == path), None)
+        if here is not None and here.status not in _MECHANICAL_TODO:
+            continue  # judged here (or this IS the canon): nothing to say
+        others = [r for r in same if r.path != path]
+        label = ("." if kind == "css" else "") + name
+        canon = next((r for r in others if r.status == "canonical" and r.snippet_id), None)
+        if canon is not None:
+            out.append({"symbol": name, "kind": kind, "key": f"canon:{canon.snippet_id}",
+                        "canon": {"snippet_id": canon.snippet_id, "path": canon.path,
+                                  "label": label}})
+            continue
+        grouped = [r for r in others if r.proposal_group and r.status in _MECHANICAL_TODO]
+        if here is not None and here.proposal_group:
+            grouped = [r for r in grouped if r.proposal_group == here.proposal_group] or grouped
+        if not grouped:
+            continue
+        group = grouped[0].proposal_group
+        members = [r for r in grouped if r.proposal_group == group]
+        files = sorted({r.path for r in members})
+        out.append({
+            "symbol": name, "kind": kind, "key": group,
+            "family": {
+                "group": group, "label": label,
+                "identical": not group.startswith("name:"),
+                "files": files[:_DERIVE_FILES_SHOWN], "file_count": len(files),
+                "size": len(members) + (1 if here is not None else 0),
+            },
+        })
+    return out
+
+
 async def flag_divergence(project_id: int, *, since: datetime | None) -> int:
     """Flag shapes created after ``since`` (the previous refresh) that sit
     where a canon dominates and were not proposed as that canon. With no

tests/test_integration_shape_classify.py

@@ -597,6 +597,49 @@ async def test_derive_groups_land_on_rows_and_in_the_summary(seeded):
     assert {r.symbol for r in rows} == {"slug"}                   # 2 files < the name floor
 
 
+@pytest.mark.integration
+async def test_write_time_derive_names_the_family_or_the_canon_for_a_name(seeded):
+    """#2900: against real rows — a name in a dup family → the family (other
+    files, count); a name whose canonical row lives elsewhere → that canon;
+    a judged row at the path, the canon's own file, or an unknown name →
+    silence."""
+    from scribe.services.shape_ledger import apply_derive_groups, write_time_derive
+
+    owner, pid, sid = seeded["owner"], seeded["pid"], seeded["snippet"]
+    defs = _defs(
+        ("v/A.vue", "css", "log-empty", ".log-empty {", ".log-empty { color: red }"),
+        ("v/B.vue", "css", "log-empty", ".log-empty {", ".log-empty { color: red }"),
+        ("v/C.vue", "css", "log-empty", ".log-empty {", ".log-empty { color: red }"),
+        ("src/factory.py", "sym", "factory", "def factory():", "def factory():\n    return 1"),
+    )
+    await sync_repo_shapes(pid, REPO, defs, seen_marker="m1")
+    await classify_shapes(owner, pid, [
+        {"path": "src/factory.py", "symbol": "factory", "status": "canonical", "snippet_id": sid},
+    ])
+    assert await apply_derive_groups(pid) >= 3
+
+    # A 4th copy about to be written → the family, naming the other files.
+    out = await write_time_derive(pid, "v/D.vue", [("css", "log-empty"), ("css", "unknown")])
+    assert len(out) == 1 and out[0]["symbol"] == "log-empty" and out[0]["kind"] == "css"
+    fam = out[0]["family"]
+    assert fam["identical"] is True and fam["label"] == ".log-empty"
+    assert fam["files"] == ["v/A.vue", "v/B.vue", "v/C.vue"] and fam["file_count"] == 3
+    assert out[0]["key"] == fam["group"] and fam["group"].startswith("dup:")
+    # Editing one existing member still names the OTHER members.
+    out = await write_time_derive(pid, "v/A.vue", [("css", "log-empty")])
+    assert out[0]["family"]["files"] == ["v/B.vue", "v/C.vue"] and out[0]["family"]["size"] == 3
+    # The canon's name elsewhere → the canon; in the canon's own file → silence.
+    out = await write_time_derive(pid, "src/other.py", [("sym", "factory")])
+    assert out == [{"symbol": "factory", "kind": "sym", "key": f"canon:{sid}",
+                    "canon": {"snippet_id": sid, "path": "src/factory.py", "label": "factory"}}]
+    assert await write_time_derive(pid, "src/factory.py", [("sym", "factory")]) == []
+    # A judged row at the path is not re-litigated.
+    await classify_shapes(owner, pid, [
+        {"path": "v/B.vue", "symbol": "log-empty", "status": "exempt", "reason": "print sheet"},
+    ])
+    assert await write_time_derive(pid, "v/B.vue", [("css", "log-empty")]) == []
+
+
 @pytest.mark.integration
 async def test_derive_new_names_the_copy_that_joined_a_family_since_the_stamp(seeded):
     """#2899: the first sync seeds one `slug`; a later sync adds an identical

tests/test_write_path_trigger.py

@@ -1243,6 +1243,116 @@ def test_hook_sends_the_enclosing_definition_for_a_body_edit(tmp_path):
     assert seen["shapes"] == ["sym:onTrash"]
 
 
+@pytest.mark.asyncio
+async def test_the_write_time_derive_check_names_a_family_or_a_canon_in_band():
+    """#2900: the ledger's own word on the names being written — a duplicate
+    family with no canon, or a canon recorded elsewhere — rendered at the
+    write even when nothing else does; keyed so the session's exclude
+    channel silences a family already named."""
+    from scribe.services import plugin_context as pc
+    found = [
+        {"symbol": "log-empty", "kind": "css", "key": "dup:483a",
+         "family": {"group": "dup:483a", "label": ".log-empty", "identical": True,
+                    "files": ["a/TaskLogSection.vue", "a/WorkspaceTaskPanel.vue"],
+                    "file_count": 5, "size": 6}},
+        {"symbol": "btn-primary", "kind": "css", "key": "canon:2855",
+         "canon": {"snippet_id": 2855, "path": "frontend/src/assets/components.css",
+                   "label": ".btn-primary"}},
+        {"symbol": "load", "kind": "sym", "key": "name:sym:load",
+         "family": {"group": "name:sym:load", "label": "load", "identical": False,
+                    "files": ["a/X.vue", "a/Y.vue", "a/Z.vue"], "file_count": 3, "size": 4}},
+    ]
+    check = AsyncMock(return_value=found)
+    patches = dict(
+        get_writepath_config=AsyncMock(return_value=_cfg()),
+        semantic_search_notes=AsyncMock(return_value=[]),
+        record_retrieval=MagicMock(), owner_names_for=AsyncMock(return_value={}),
+    )
+    with patch.multiple(pc, **patches), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "write_time_divergence", AsyncMock(return_value=[])), \
+         patch.object(pc.shape_ledger_svc, "write_time_derive", check):
+        out = await pc.build_write_path_hint(
+            1, "frontend/src/components/New.vue", code=REAL_CODE, project_id=24,
+            stamp_shapes=[("css", "log-empty"), ("css", "btn-primary"), ("sym", "load")],
+            exclude_derive=["name:sym:load"],
+        )
+    check.assert_awaited_once_with(24, "frontend/src/components/New.vue",
+                                   [("css", "log-empty"), ("css", "btn-primary"), ("sym", "load")])
+    # The excluded family is gone; the other two render and are keyed.
+    assert [d["key"] for d in out["derive"]] == ["dup:483a", "canon:2855"]
+    assert out["derive_keys"] == ["dup:483a", "canon:2855"]
+    ctx = out["context"]
+    assert "Shape ledger at `frontend/src/components/New.vue`" in ctx
+    assert "`.log-empty` is a duplicate family with no canon — identical body in 5 other file(s): " \
+           "`a/TaskLogSection.vue`, `a/WorkspaceTaskPanel.vue` +3 more; derive it now" in ctx
+    assert "`.btn-primary` is canon — snippet #2855 at `frontend/src/assets/components.css`" in ctx
+    assert "convention-plumbing" in ctx
+    assert "`load`" not in ctx
+    # No project → no check; a failing check never sinks the hint.
+    check.reset_mock()
+    with patch.multiple(pc, **patches), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "write_time_divergence", AsyncMock(return_value=[])), \
+         patch.object(pc.shape_ledger_svc, "write_time_derive", check):
+        out = await pc.build_write_path_hint(1, "x.py", code=REAL_CODE, stamp_shapes=[("sym", "f")])
+    check.assert_not_awaited()
+    assert out["derive"] == [] and out["derive_keys"] == []
+    boom = AsyncMock(side_effect=RuntimeError("ledger down"))
+    with patch.multiple(pc, **patches), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "write_time_divergence", AsyncMock(return_value=[])), \
+         patch.object(pc.shape_ledger_svc, "write_time_derive", boom):
+        out = await pc.build_write_path_hint(1, "x.py", code=REAL_CODE, project_id=24,
+                                             stamp_shapes=[("sym", "f")])
+    assert out["context"] == "" and out["derive"] == []
+
+
+def test_the_hook_keeps_a_derive_channel_and_sends_it_back(tmp_path):
+    """#2900: derive keys the server returns land in the session's own
+    `.derive.ids` file and go back as `exclude_derive` on the next write —
+    a family is named once per session, not at every edit."""
+    import http.server
+    import threading
+    import urllib.parse
+
+    seen: list[dict] = []
+
+    class _Sink(http.server.BaseHTTPRequestHandler):
+        def do_GET(self):
+            seen.append(urllib.parse.parse_qs(urllib.parse.urlparse(self.path).query))
+            self.send_response(200)
+            self.send_header("Content-Type", "application/json")
+            self.end_headers()
+            self.wfile.write(b'{"context":"> family","note_ids":[],"sync_note_ids":[],'
+                             b'"derive_keys":["dup:483a","canon:2855"]}')
+
+        def log_message(self, *a):
+            pass
+
+    server = http.server.HTTPServer(("127.0.0.1", 0), _Sink)
+    threading.Thread(target=server.serve_forever, daemon=True).start()
+    try:
+        env = dict(_hook_runtime_env(), SCRIBE_URL=f"http://127.0.0.1:{server.server_port}",
+                   TMPDIR=str(tmp_path))
+        payload = {"session_id": "s-derive-1", "cwd": str(tmp_path), "tool_name": "Write",
+                   "tool_input": {"file_path": str(tmp_path / "a.css"),
+                                  "content": ".log-empty {\n  color: red;\n}\n"}}
+        for _ in range(2):
+            out = subprocess.run(["bash", str(HOOK)], input=json.dumps(payload),
+                                 capture_output=True, text=True, env=env)
+            assert out.returncode == 0, out.stderr
+    finally:
+        server.shutdown()
+    assert "exclude_derive" not in seen[0]
+    assert seen[1]["exclude_derive"] == ["dup:483a,canon:2855"]
+    state = tmp_path / "scribe-priorart" / "s-derive-1.derive.ids"
+    assert state.read_text().split() == ["dup:483a", "canon:2855", "dup:483a", "canon:2855"]
+
+
 @pytest.mark.asyncio
 async def test_the_write_time_divergence_check_is_named_in_band():
     """#2793: the hook named a shape at a path whose directory a canon