feat(ledger): write-path stamping — a pulled canon the session then instantiates lands as a hook instance row (#2791, milestone 294 step 5)

The prior-art hook now names the shapes being written (shapes=kind:name —
every definition in the payload, or the one enclosing an Edit found by
walking the file upward) and the server stamps them as instance rows when
the session PULLED a snippet inside PULL_WINDOW that the payload references
by symbol or that the semantic arm scored for this very payload.
classified_by=hook, evidence in reason; never overrides a judgment or a
canonical row, overridable by classify_shapes. Offered-but-unopened stamps
nothing. Pulled-and-already-seen snippets stay in the semantic query as
evidence without re-entering the deduped menu. A brand-new shape gets a
provisional row the next sync confirms or vanishes. Read-scoped keys get
the hint, never the stamp. Plugin 0.1.34.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_integration_shape_classify.py

@@ -219,3 +219,133 @@ async def test_sync_refiles_rows_whose_snippet_was_purged(seeded):
         ))).scalar_one()
     assert row.status == "unclassified"
     assert row.snippet_id is None
+
+
+# --- #2791: the write-path feed lands hook evidence as rows -------------------
+
+
+@pytest.mark.integration
+async def test_write_path_stamp_is_evidence_that_yields_to_judgment(seeded):
+    """Pulled + referenced → every named shape of the snippet's kind becomes
+    an instance row, classified_by=hook, carrying the evidence as reason. A
+    later agent judgment on one of them stands against a re-stamp; the hook
+    may only overwrite nobody's judgment or its own. The outsider stamps
+    nothing (write-gated like every other ledger write)."""
+    from datetime import datetime, timezone
+
+    from scribe.services.shape_ledger import stamp_write_path_instances
+
+    owner, other, pid, sid = (
+        seeded["owner"], seeded["other"], seeded["pid"], seeded["snippet"]
+    )
+    pulled = {sid: datetime.now(timezone.utc)}
+    code = "app = factory()\nreturn app\n"          # references the snippet's symbol
+
+    assert await stamp_write_path_instances(
+        other, pid, path="src/app.py", shapes=[("sym", "make_app")],
+        code=code, pulled=pulled,
+    ) == []
+
+    stamped = await stamp_write_path_instances(
+        owner, pid, path="src/app.py",
+        shapes=[("sym", "make_app"), ("sym", "Config"), ("css", "nope")],
+        code=code, pulled=pulled,
+    )
+    assert {s["symbol"] for s in stamped} == {"make_app", "Config"}   # css skipped: no css canon
+    rows, _ = await list_project_shapes(owner, pid, snippet_id=sid)
+    by_symbol = {r.symbol: r for r in rows}
+    assert by_symbol["make_app"].status == "instance"
+    assert by_symbol["make_app"].classified_by == "hook"
+    assert by_symbol["make_app"].reason == f"hook: pulled #{sid}; payload references `factory`"
+
+    # A judgment lands; the next stamp must leave it alone but may re-stamp
+    # its own earlier row.
+    await classify_shapes(owner, pid, [
+        {"path": "src/app.py", "symbol": "make_app", "status": "exempt",
+         "reason": "the app factory is its own thing"},
+    ])
+    again = await stamp_write_path_instances(
+        owner, pid, path="src/app.py",
+        shapes=[("sym", "make_app"), ("sym", "Config")], code=code, pulled=pulled,
+    )
+    assert {s["symbol"] for s in again} == {"Config"}
+    rows, _ = await list_project_shapes(owner, pid, path="src/app.py")
+    by_symbol = {r.symbol: r for r in rows}
+    assert by_symbol["make_app"].status == "exempt"
+    assert by_symbol["Config"].status == "instance"
+
+    # Neither pulled nor in play → nothing, even with shapes named.
+    assert await stamp_write_path_instances(
+        owner, pid, path="src/util.py", shapes=[("sym", "helper")],
+        code="print('unrelated')", pulled=pulled,
+    ) == []
+
+
+@pytest.mark.integration
+async def test_a_brand_new_shape_gets_a_provisional_row_the_sync_settles(seeded):
+    """The shape being written right now has no ledger row yet. With the
+    hook's repo key it gets a provisional one — seen markers unset — so the
+    stamp survives until the next sync, which confirms it (sets the marker)
+    or stamps it vanished. Without a repo key only existing rows are touched."""
+    from datetime import datetime, timezone
+
+    from scribe.services.shape_ledger import stamp_write_path_instances
+
+    owner, pid, sid = seeded["owner"], seeded["pid"], seeded["snippet"]
+    pulled = {sid: datetime.now(timezone.utc)}
+    code = "def build():\n    return factory()\n"
+
+    assert await stamp_write_path_instances(
+        owner, pid, path="src/new.py", shapes=[("sym", "build")],
+        code=code, pulled=pulled,                              # no repo_key
+    ) == []
+    stamped = await stamp_write_path_instances(
+        owner, pid, path="src/new.py", shapes=[("sym", "build")],
+        code=code, pulled=pulled, repo_key=REPO,
+    )
+    assert [s["symbol"] for s in stamped] == ["build"]
+    async with async_session() as s:
+        row = (await s.execute(select(CodeShape).where(
+            CodeShape.project_id == pid, CodeShape.path == "src/new.py",
+        ))).scalar_one()
+        assert row.status == "instance" and row.classified_by == "hook"
+        assert row.first_seen_commit is None and row.last_seen_commit is None
+
+    # The sync sees the shape in the tree → confirmed, stamp intact.
+    await sync_repo_shapes(
+        pid, REPO, SHAPES + [("src/new.py", "sym", "build")], seen_marker="abc123",
+    )
+    rows, _ = await list_project_shapes(owner, pid, path="src/new.py")
+    assert rows[0].status == "instance" and rows[0].last_seen_commit == "abc123"
+
+    # The sync no longer sees it → vanished, out of the live accounting.
+    await sync_repo_shapes(pid, REPO, SHAPES, seen_marker="def456")
+    rows, _ = await list_project_shapes(owner, pid, path="src/new.py")
+    assert rows == []
+    rows, _ = await list_project_shapes(owner, pid, path="src/new.py", include_vanished=True)
+    assert rows[0].vanished_at is not None
+
+
+@pytest.mark.integration
+async def test_recent_pulls_reads_the_usage_stream(seeded):
+    """The "actually pulled it" half is the PULLED usage event, inside the
+    window; a surfacing alone is not a pull."""
+    from datetime import datetime, timedelta, timezone
+
+    from scribe.models.note_usage import PULLED, SURFACED, NoteUsageEvent
+    from scribe.services.shape_ledger import recent_pulls
+
+    owner, sid = seeded["owner"], seeded["snippet"]
+    now = datetime.now(timezone.utc)
+    async with async_session() as s:
+        s.add_all([
+            NoteUsageEvent(user_id=owner, note_id=sid, event=PULLED, source="mcp_get_snippet"),
+            NoteUsageEvent(user_id=owner, note_id=sid + 1000, event=SURFACED, source="auto_inject"),
+            NoteUsageEvent(user_id=owner, note_id=sid + 2000, event=PULLED,
+                           source="mcp_get_snippet", created_at=now - timedelta(days=2)),
+        ])
+        await s.commit()
+    pulls = await recent_pulls(owner)
+    assert sid in pulls
+    assert sid + 1000 not in pulls
+    assert sid + 2000 not in pulls

tests/test_shape_ledger.py

@@ -82,3 +82,56 @@ def test_classify_and_list_are_mounted_as_mcp_tools():
     mcp = build_mcp_server()
     for name in ("classify_shapes", "list_shapes", "refresh_pattern_coverage"):
         assert mcp._tool_manager.get_tool(name) is not None
+
+
+# --- step 5: the write-path feed's evidence tests (pure) ---------------------
+
+
+def test_symbol_reference_is_word_bounded_and_kind_aware():
+    from scribe.services.shape_ledger import references_symbol as ref
+
+    code = "const ok = await confirmed({ title: 'x' });\nif (!ok) return;"
+    assert ref(code, "confirmed", "sym")
+    assert not ref(code, "confirm", "sym")          # prefix never claims the call
+    assert not ref("", "confirmed", "sym")
+    assert not ref(code, "", "sym")
+    # CSS: the class as a selector or inside a class attribute; dashes are part
+    # of the name, so `btn` must not claim `btn-primary`.
+    html = '<button class="btn btn-primary">Go</button>'
+    assert ref(html, ".btn-primary", "css")
+    assert ref(html, "btn-primary", "css")
+    assert ref(".btn-primary { color: red }", ".btn-primary", "css")
+    assert not ref('<button class="btn-primary">', ".btn", "css")
+    assert ref('<button class="btn-primary btn">', ".btn", "css")
+
+
+def test_snippet_kind_reads_the_symbol_then_the_language():
+    from scribe.services.shape_ledger import snippet_kind
+
+    assert snippet_kind(".btn-primary", "css") == "css"
+    assert snippet_kind(".btn-primary", "") == "css"
+    assert snippet_kind("confirmed", "typescript") == "sym"
+    assert snippet_kind("", "scss") == "css"      # whole-stylesheet record
+    assert snippet_kind("", "python") == "sym"
+
+
+def test_route_shapes_param_parses_capped_and_deduped():
+    from scribe.routes.plugin import _SHAPES_CAP, _parse_shapes
+
+    assert _parse_shapes("css:btn-primary,sym:onTrash") == [
+        ("css", "btn-primary"), ("sym", "onTrash"),
+    ]
+    assert _parse_shapes(" sym:a , sym:a ,bogus:x,sym:,:,") == [("sym", "a")]
+    assert _parse_shapes("") == []
+    many = ",".join(f"sym:f{i}" for i in range(40))
+    assert len(_parse_shapes(many)) == _SHAPES_CAP
+
+
+def test_hook_is_a_server_internal_classifier():
+    """`hook` is in the status vocabulary but NOT a via a caller may claim —
+    a classify_shapes call saying via="hook" would launder judgment as
+    evidence (the reverse of the stamping rule's point)."""
+    from scribe.services.shape_ledger import _CALLER_VIAS
+
+    assert "hook" in SHAPE_CLASSIFIERS
+    assert "hook" not in _CALLER_VIAS

tests/test_write_path_trigger.py

@@ -778,11 +778,13 @@ def test_route_reads_every_arg_the_hook_sends():
 
     from scribe.routes import plugin as routes
     src = inspect.getsource(routes.write_path_prior_art)
-    for arg in ("path", "code", "repo", "project_id", "exclude_ids", "exclude_sync_ids"):
+    for arg in ("path", "code", "repo", "project_id", "exclude_ids",
+                "exclude_sync_ids", "shapes"):
         assert f'request.args.get("{arg}"' in src, f"route ignores {arg}"
 
     hook = HOOK.read_text()
-    for arg in ("path=", "code=", "repo=", "exclude_ids=", "exclude_sync_ids="):
+    for arg in ("path=", "code=", "repo=", "exclude_ids=", "exclude_sync_ids=",
+                "shapes="):
         assert arg in hook, f"hook never sends {arg}"
 
 
@@ -1009,3 +1011,240 @@ def test_local_arm_finds_duplicates_in_every_language_family(
     ctx = json.loads(out.stdout)["hookSpecificOutput"]["additionalContext"]
     assert "already defined" in ctx
     assert "create_snippet" in ctx
+
+
+# --- #2791: the write-path feed — hook evidence lands as ledger rows ----------
+
+
+def _ts():
+    from datetime import datetime, timezone
+    return datetime.now(timezone.utc)
+
+
+@pytest.mark.asyncio
+async def test_stamping_needs_named_shapes_and_a_recent_pull():
+    """Offered-but-ignored stamps nothing: without a PULLED event there is no
+    evidence, and without the hook naming shapes there is nothing to stamp.
+    Neither case may even read the pull stream."""
+    from scribe.services import plugin_context as pc
+    pulls = AsyncMock(return_value={})
+    stamp = AsyncMock(return_value=[])
+    with patch.object(pc, "get_writepath_config", AsyncMock(return_value=_cfg())), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc, "semantic_search_notes", AsyncMock(return_value=[])), \
+         patch.object(pc, "record_retrieval", MagicMock()), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", pulls), \
+         patch.object(pc.shape_ledger_svc, "stamp_write_path_instances", stamp):
+        out = await pc.build_write_path_hint(1, "src/x.py", code=REAL_CODE, project_id=4)
+        assert out["stamped"] == []
+        pulls.assert_not_awaited()                       # no shapes → no read
+        out = await pc.build_write_path_hint(
+            1, "src/x.py", code=REAL_CODE, project_id=4,
+            stamp_shapes=[("sym", "debounce")],
+        )
+    pulls.assert_awaited_once()
+    stamp.assert_not_awaited()                           # shapes, but no pull
+    assert out["stamped"] == []
+
+
+@pytest.mark.asyncio
+async def test_a_pulled_snippet_already_seen_is_evidence_not_menu():
+    """The pulled-then-written flow IS the dedup-excluded flow: the hint offered
+    #7 earlier (so it sits in exclude_ids), the session pulled it, and now
+    writes code resembling it. #7 must be scored for this payload — and handed
+    to the stamp as resemblance — without being re-listed in the menu."""
+    from scribe.services import plugin_context as pc
+    search = AsyncMock(return_value=[(0.91, _note(7, "pulled")), (0.80, _note(8, "fresh"))])
+    stamp = AsyncMock(return_value=[{
+        "path": "src/x.py", "symbol": "debounce", "kind": "sym",
+        "snippet_id": 7, "reason": "hook: pulled #7; payload resembles it (0.91)",
+    }])
+    with patch.object(pc, "get_writepath_config", AsyncMock(return_value=_cfg(top_k=3))), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc, "semantic_search_notes", search), \
+         patch.object(pc, "record_retrieval", MagicMock()), \
+         patch.object(pc, "owner_names_for", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={7: _ts()})), \
+         patch.object(pc.shape_ledger_svc, "stamp_write_path_instances", stamp):
+        out = await pc.build_write_path_hint(
+            1, "src/x.py", code=REAL_CODE, project_id=4, exclude_ids=[7],
+            stamp_shapes=[("sym", "debounce")], repo_key="git.example.com/a/b",
+        )
+    # The query kept #7 eligible (and widened the budget by one for it)...
+    kw = search.call_args.kwargs
+    assert 7 not in kw["exclude_ids"]
+    assert kw["limit"] == 4
+    # ...but the menu still honours the session dedup.
+    assert out["note_ids"] == [8]
+    assert "#7" not in "\n".join(
+        line for line in out["context"].splitlines() if "[similar" in line
+    )
+    # The stamp saw the pull and the resemblance score for this payload.
+    skw = stamp.call_args.kwargs
+    assert skw["pulled"] == {7: skw["pulled"][7]}
+    assert skw["resembles"] == {7: 0.91}
+    assert skw["shapes"] == [("sym", "debounce")]
+    assert skw["repo_key"] == "git.example.com/a/b"
+    assert out["stamped"][0]["snippet_id"] == 7
+    # And the session is told what landed, with the way to correct it.
+    assert "Shape accounting" in out["context"]
+    assert "`debounce` → instance of #7" in out["context"]
+    assert "classify_shapes" in out["context"]
+
+
+@pytest.mark.asyncio
+async def test_a_stamp_renders_even_when_the_hint_is_otherwise_silent():
+    """After dedup the common case is an empty hint; the stamp must still run
+    and still be reported — silence about accounting is how hook rows would
+    become invisible."""
+    from scribe.services import plugin_context as pc
+    stamped = [{"path": "web/b.css", "symbol": "btn-primary", "kind": "css",
+                "snippet_id": 5, "reason": "hook: pulled #5; payload references `btn-primary`"}]
+    with patch.object(pc, "get_writepath_config", AsyncMock(return_value=_cfg())), \
+         patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))), \
+         patch.object(pc, "semantic_search_notes", AsyncMock(return_value=[])), \
+         patch.object(pc, "record_retrieval", MagicMock()), \
+         patch.object(pc, "owner_names_for", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={5: _ts()})), \
+         patch.object(pc.shape_ledger_svc, "stamp_write_path_instances",
+                      AsyncMock(return_value=stamped)):
+        out = await pc.build_write_path_hint(
+            1, "web/b.css", code=".btn-primary { color: red; }" * 4, project_id=4,
+            stamp_shapes=[("css", "btn-primary")],
+        )
+    assert out["note_ids"] == []
+    assert out["stamped"] == stamped
+    assert "`.btn-primary` → instance of #5" in out["context"]
+
+
+@pytest.mark.asyncio
+async def test_a_failing_stamp_does_not_sink_the_hint():
+    from scribe.services import plugin_context as pc
+    with patch.object(pc, "get_writepath_config", AsyncMock(return_value=_cfg())), \
+         patch.object(pc.snippets_svc, "list_snippets",
+                      AsyncMock(return_value=([_snippet_item(12, "records me")], 1))), \
+         patch.object(pc, "semantic_search_notes", AsyncMock(return_value=[])), \
+         patch.object(pc, "record_retrieval", MagicMock()), \
+         patch.object(pc, "owner_names_for", AsyncMock(return_value={})), \
+         patch.object(pc.shape_ledger_svc, "recent_pulls", AsyncMock(return_value={12: _ts()})), \
+         patch.object(pc.shape_ledger_svc, "stamp_write_path_instances",
+                      AsyncMock(side_effect=RuntimeError("ledger down"))):
+        out = await pc.build_write_path_hint(
+            1, "src/x.py", code=REAL_CODE, project_id=4, stamp_shapes=[("sym", "f")],
+        )
+    assert out["sync_note_ids"] == [12]
+    assert out["stamped"] == []
+
+
+def test_route_stamps_only_for_a_caller_allowed_to_write():
+    """A read-scoped key gets the hint — every plugin hook works on a read key
+    — but a GET must never change accounting for it. The route passes the
+    shapes through only when the key is write-scoped (or it's a session)."""
+    import inspect
+
+    from scribe.routes import plugin as routes
+    src = inspect.getsource(routes.write_path_prior_art)
+    assert 'request.args.get("shapes"' in src
+    assert '== "write"' in src
+    assert "stamp_shapes=shapes if may_stamp else None" in src
+    assert "normalize_repo_key(repo)" in src
+    hook = HOOK.read_text()
+    assert "&shapes=" in hook
+
+
+def test_hook_names_the_shapes_being_written():
+    """The feed's two inputs: every definition in the payload, or — for an Edit
+    that changes a body, not a signature — the definition enclosing the edit,
+    found by walking the target file upward from the edited lines."""
+    src = HOOK.read_text()
+    assert "scribe_defs()" in src                      # one extractor, two consumers
+    assert ".tool_input.old_string" in src             # the Edit's anchor
+    assert "| tac | scribe_defs | head -1" in src      # nearest definition above
+    # The ledger feed sends NAMES, never bodies, and stays on the one GET.
+    assert src.count("/api/plugin/prior-art?") == 1
+
+
+def _run_hook_against_sink(tmp_path, payload):
+    """Run the hook with SCRIBE_URL pointed at a throwaway local listener and
+    return the query the hook sent. Lets the shell be tested end to end —
+    the extraction, the encoding, the URL — without a Scribe instance."""
+    import http.server
+    import threading
+    import urllib.parse
+
+    seen: dict = {}
+
+    class _Sink(http.server.BaseHTTPRequestHandler):
+        def do_GET(self):
+            seen.update(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":"","note_ids":[]}')
+
+        def log_message(self, *a):
+            pass
+
+    server = http.server.HTTPServer(("127.0.0.1", 0), _Sink)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    try:
+        env = dict(_hook_runtime_env(), SCRIBE_URL=f"http://127.0.0.1:{server.server_port}")
+        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()
+        server.server_close()
+    return seen
+
+
+def test_hook_sends_every_definition_in_a_write(tmp_path):
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    env = _hook_runtime_env()
+    subprocess.run(["git", "init", "-q"], cwd=repo, check=True, env=env)
+    seen = _run_hook_against_sink(tmp_path, {
+        "session_id": "s-feed-w", "cwd": str(repo), "tool_name": "Write",
+        "tool_input": {
+            "file_path": str(repo / "new.ts"),
+            "content": "export async function onDelete(): Promise<void> {\n"
+                       "  const ok = await confirmed({ title: 'x' });\n}\n"
+                       ".btn-primary {\n  color: red;\n}\n",
+        },
+    })
+    assert seen["path"] == ["new.ts"]
+    assert seen["shapes"] == ["css:btn-primary,sym:onDelete"]
+
+
+def test_hook_sends_the_enclosing_definition_for_a_body_edit(tmp_path):
+    """An Edit to the inside of onTrash names no definition itself; the hook
+    must walk the file upward from the edited line and send onTrash."""
+    import shutil
+    if shutil.which("tac") is None:
+        pytest.skip("the enclosing-definition walk needs tac")
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    env = _hook_runtime_env()
+    subprocess.run(["git", "init", "-q"], cwd=repo, check=True, env=env)
+    target = repo / "comp.vue"
+    target.write_text(
+        "<script setup lang=\"ts\">\n"
+        "async function onTrash(): Promise<void> {\n"
+        "  const ok = await confirmed({ title: 'Move to the trash?' });\n"
+        "  if (!ok) return;\n"
+        "}\n"
+        "const other = () => {\n  return 1;\n};\n"
+        "</script>\n"
+    )
+    seen = _run_hook_against_sink(tmp_path, {
+        "session_id": "s-feed-e", "cwd": str(repo), "tool_name": "Edit",
+        "tool_input": {
+            "file_path": str(target),
+            "old_string": "  if (!ok) return;",
+            "new_string": "  if (!ok) return;\n  await guarded(() => store.trashNode(id));",
+        },
+    })
+    assert seen["shapes"] == ["sym:onTrash"]